[llvm] [ISel] Introduce llvm.clmul[rh] intrinsics (PR #168731)
Ramkumar Ramachandra via llvm-commits
llvm-commits at lists.llvm.org
Wed Nov 19 08:15:50 PST 2025
https://github.com/artagnon created https://github.com/llvm/llvm-project/pull/168731
In line with a std proposal to introduce the llvm.clmul[rh] family of intrinsics corresponding to carry-less multiply operations. This work builds upon 727ee7e ([APInt] Introduce carry-less multiply primitives), and follow-up patches will introduce custom-lowering on supported targets, replacing target-specific clmul intrinsics.
Testing is done on the RISC-V target, which should be sufficient to prove that the intrinsic works, since no RISC-V specific lowering has been added.
Ref: https://isocpp.org/files/papers/P3642R3.html
>From 72c0e768071d66439d3f8511391ed5a9c4785197 Mon Sep 17 00:00:00 2001
From: Ramkumar Ramachandra <ramkumar.ramachandra at codasip.com>
Date: Wed, 19 Nov 2025 15:43:42 +0000
Subject: [PATCH] [ISel] Introduce llvm.clmul[rh] intrinsics
In line with a std proposal to introduce the llvm.clmul[rh] family of
intrinsics corresponding to carry-less multiply operations. This work
builds upon 727ee7e ([APInt] Introduce carry-less multiply primitives),
and follow-up patches will introduce custom-lowering on supported
targets, replacing target-specific clmul intrinsics.
Testing is done on the RISC-V target, which should be sufficient to
prove that the intrinsic works, since no RISC-V specific lowering has
been added.
Ref: https://isocpp.org/files/papers/P3642R3.html
Co-authored-by: Oscar Smith <oscardssmith at gmail.com>
---
llvm/docs/LangRef.rst | 149 +-
llvm/include/llvm/CodeGen/ISDOpcodes.h | 5 +
llvm/include/llvm/CodeGen/TargetLowering.h | 5 +
llvm/include/llvm/IR/Intrinsics.td | 6 +
.../include/llvm/Target/TargetSelectionDAG.td | 6 +
llvm/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp | 6 +
.../SelectionDAG/LegalizeIntegerTypes.cpp | 16 +-
llvm/lib/CodeGen/SelectionDAG/LegalizeTypes.h | 2 +
.../SelectionDAG/LegalizeVectorTypes.cpp | 63 +-
.../lib/CodeGen/SelectionDAG/SelectionDAG.cpp | 28 +
.../SelectionDAG/SelectionDAGBuilder.cpp | 20 +
.../SelectionDAG/SelectionDAGDumper.cpp | 3 +
.../CodeGen/SelectionDAG/TargetLowering.cpp | 40 +
llvm/lib/CodeGen/TargetLoweringBase.cpp | 3 +
llvm/test/CodeGen/RISCV/clmul.ll | 11952 +++++
llvm/test/CodeGen/RISCV/rvv/clmul-sdnode.ll | 42843 ++++++++++++++++
.../CodeGen/RISCV/rvv/fixed-vectors-clmul.ll | 34118 ++++++++++++
17 files changed, 89246 insertions(+), 19 deletions(-)
create mode 100644 llvm/test/CodeGen/RISCV/clmul.ll
create mode 100644 llvm/test/CodeGen/RISCV/rvv/clmul-sdnode.ll
create mode 100644 llvm/test/CodeGen/RISCV/rvv/fixed-vectors-clmul.ll
diff --git a/llvm/docs/LangRef.rst b/llvm/docs/LangRef.rst
index 734778f73af5f..03eacbc3f0730 100644
--- a/llvm/docs/LangRef.rst
+++ b/llvm/docs/LangRef.rst
@@ -18291,8 +18291,6 @@ then the result is the size in bits of the type of ``src`` if
``is_zero_poison == 0`` and ``poison`` otherwise. For example,
``llvm.cttz(2) = 1``.
-.. _int_overflow:
-
.. _int_fshl:
'``llvm.fshl.*``' Intrinsic
@@ -18389,6 +18387,153 @@ Example:
%r = call i8 @llvm.fshr.i8(i8 15, i8 15, i8 11) ; %r = i8: 225 (0b11100001)
%r = call i8 @llvm.fshr.i8(i8 0, i8 255, i8 8) ; %r = i8: 255 (0b11111111)
+.. _int_clmul:
+
+'``llvm.clmul.*``' Intrinsic
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Syntax:
+"""""""
+
+This is an overloaded intrinsic. You can use ``llvm.clmul`` on any integer
+or vectors of integer elements.
+
+::
+
+ declare i16 @llvm.clmul.i16(i16 %a, i16 %b)
+ declare i32 @llvm.clmul.i32(i32 %a, i32 %b)
+ declare i64 @llvm.clmul.i64(i64 %a, i64 %b)
+ declare <4 x i32> @llvm.clmul.v4i32(<4 x i32> %a, <4 x i32> %b)
+
+Overview:
+"""""""""
+
+The '``llvm.clmul``' family of intrinsic functions performs carry-less
+multiplication, or XOR multiplication, on the two arguments, and returns
+the low-bits.
+
+Arguments:
+""""""""""
+
+The arguments may be any integer type or vector of integer type. Both arguments
+and result must have the same type.
+
+Semantics:
+""""""""""
+
+The '``llvm.clmul``' intrinsic computes carry-less multiply of its arguments,
+which is the result of applying the standard Eucledian multiplication algorithm,
+where all of the additions are replaced with XORs, and returns the low-bits.
+The vector variants operate lane-wise.
+
+Example:
+""""""""
+
+.. code-block:: llvm
+
+ %r = call i4 @llvm.clmul.i4(i4 1, i4 2) ; %r = 2
+ %r = call i4 @llvm.clmul.i4(i4 5, i4 6) ; %r = 14
+ %r = call i4 @llvm.clmul.i4(i4 -4, i4 2) ; %r = -8
+ %r = call i4 @llvm.clmul.i4(i4 -4, i4 -5) ; %r = 4
+
+'``llvm.clmulr.*``' Intrinsic
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Syntax:
+"""""""
+
+This is an overloaded intrinsic. You can use ``llvm.clmulr`` on any integer
+or vectors of integer elements.
+
+::
+
+ declare i16 @llvm.clmulr.i16(i16 %a, i16 %b)
+ declare i32 @llvm.clmulr.i32(i32 %a, i32 %b)
+ declare i64 @llvm.clmulr.i64(i64 %a, i64 %b)
+ declare <4 x i32> @llvm.clmulr.v4i32(<4 x i32> %a, <4 x i32> %b)
+
+Overview:
+"""""""""
+
+The '``llvm.clmulr``' family of intrinsic functions performs reversed
+carry-less multiplication on the two arguments.
+
+Arguments:
+""""""""""
+
+The arguments may be any integer type or vector of integer type. Both arguments
+and result must have the same type.
+
+Semantics:
+""""""""""
+
+The '``llvm.clmulr``' intrinsic computes reversed carry-less multiply of its
+arguments. The vector variants operate lane-wise.
+
+.. codeblock:: text
+
+ clmulr(%a, %b) = bitreverse(clmul(bitreverse(%a), bitreverse(%b)))
+
+Example:
+""""""""
+
+.. code-block:: llvm
+
+ %r = call i4 @llvm.clmulr.i4(i4 1, i4 2) ; %r = 0
+ %r = call i4 @llvm.clmulr.i4(i4 5, i4 6) ; %r = 3
+ %r = call i4 @llvm.clmulr.i4(i4 -4, i4 2) ; %r = 3
+ %r = call i4 @llvm.clmulr.i4(i4 -4, i4 -5) ; %r = -2
+
+'``llvm.clmulh.*``' Intrinsic
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Syntax:
+"""""""
+
+This is an overloaded intrinsic. You can use ``llvm.clmulh`` on any integer
+or vectors of integer elements.
+
+::
+
+ declare i16 @llvm.clmulh.i16(i16 %a, i16 %b)
+ declare i32 @llvm.clmulh.i32(i32 %a, i32 %b)
+ declare i64 @llvm.clmulh.i64(i64 %a, i64 %b)
+ declare <4 x i32> @llvm.clmulh.v4i32(<4 x i32> %a, <4 x i32> %b)
+
+Overview:
+"""""""""
+
+The '``llvm.clmulh``' family of intrinsic functions performs carry-less
+multiplication on the two arguments, and returns the high-bits.
+
+Arguments:
+""""""""""
+
+The arguments may be any integer type or vector of integer type. Both arguments
+and result must have the same type.
+
+Semantics:
+""""""""""
+
+The '``llvm.clmulh``' intrinsic computes carry-less multiply of its arguments,
+and returns the high-bits. The vector variants operate lane-wise.
+
+.. codeblock:: text
+
+ clmulh(%a, %b) = clmulr(%a, %b) >> 1
+
+Example:
+""""""""
+
+.. code-block:: llvm
+
+ %r = call i4 @llvm.clmulh.i4(i4 1, i4 2) ; %r = 0
+ %r = call i4 @llvm.clmulh.i4(i4 5, i4 6) ; %r = 1
+ %r = call i4 @llvm.clmulh.i4(i4 -4, i4 2) ; %r = 1
+ %r = call i4 @llvm.clmulh.i4(i4 -4, i4 -5) ; %r = 7
+
+.. _int_overflow:
+
Arithmetic with Overflow Intrinsics
-----------------------------------
diff --git a/llvm/include/llvm/CodeGen/ISDOpcodes.h b/llvm/include/llvm/CodeGen/ISDOpcodes.h
index cdaa916548c25..08d87f7e7b266 100644
--- a/llvm/include/llvm/CodeGen/ISDOpcodes.h
+++ b/llvm/include/llvm/CodeGen/ISDOpcodes.h
@@ -767,6 +767,11 @@ enum NodeType {
FSHL,
FSHR,
+ /// Carry-less multiplication operations.
+ CLMUL,
+ CLMULR,
+ CLMULH,
+
/// Byte Swap and Counting operators.
BSWAP,
CTTZ,
diff --git a/llvm/include/llvm/CodeGen/TargetLowering.h b/llvm/include/llvm/CodeGen/TargetLowering.h
index 4c932c523e423..b38bd6729f34d 100644
--- a/llvm/include/llvm/CodeGen/TargetLowering.h
+++ b/llvm/include/llvm/CodeGen/TargetLowering.h
@@ -5455,6 +5455,11 @@ class LLVM_ABI TargetLowering : public TargetLoweringBase {
/// \returns The expansion if successful, SDValue() otherwise
SDValue expandFunnelShift(SDNode *N, SelectionDAG &DAG) const;
+ /// Expand carryless multiply.
+ /// \param N Node to expand
+ /// \returns The expansion if successful, SDValue() otherwise
+ SDValue expandCLMUL(SDNode *N, SelectionDAG &DAG) const;
+
/// Expand rotations.
/// \param N Node to expand
/// \param AllowVectorOps expand vector rotate, this should only be performed
diff --git a/llvm/include/llvm/IR/Intrinsics.td b/llvm/include/llvm/IR/Intrinsics.td
index 8f3cc54747074..11fc73829b026 100644
--- a/llvm/include/llvm/IR/Intrinsics.td
+++ b/llvm/include/llvm/IR/Intrinsics.td
@@ -1465,6 +1465,12 @@ let IntrProperties = [IntrNoMem, IntrSpeculatable, IntrNoCreateUndefOrPoison] in
[LLVMMatchType<0>, LLVMMatchType<0>, LLVMMatchType<0>]>;
def int_fshr : DefaultAttrsIntrinsic<[llvm_anyint_ty],
[LLVMMatchType<0>, LLVMMatchType<0>, LLVMMatchType<0>]>;
+ def int_clmul : DefaultAttrsIntrinsic<[llvm_anyint_ty],
+ [LLVMMatchType<0>, LLVMMatchType<0>]>;
+ def int_clmulr : DefaultAttrsIntrinsic<[llvm_anyint_ty],
+ [LLVMMatchType<0>, LLVMMatchType<0>]>;
+ def int_clmulh : DefaultAttrsIntrinsic<[llvm_anyint_ty],
+ [LLVMMatchType<0>, LLVMMatchType<0>]>;
}
let IntrProperties = [IntrNoMem, IntrSpeculatable,
diff --git a/llvm/include/llvm/Target/TargetSelectionDAG.td b/llvm/include/llvm/Target/TargetSelectionDAG.td
index a9750a5ab03f9..c50afe3bfe4bb 100644
--- a/llvm/include/llvm/Target/TargetSelectionDAG.td
+++ b/llvm/include/llvm/Target/TargetSelectionDAG.td
@@ -441,6 +441,12 @@ def sra_parts : SDNode<"ISD::SRA_PARTS" , SDTIntShiftPairOp>;
def srl_parts : SDNode<"ISD::SRL_PARTS" , SDTIntShiftPairOp>;
def fshl : SDNode<"ISD::FSHL" , SDTIntShiftDOp>;
def fshr : SDNode<"ISD::FSHR" , SDTIntShiftDOp>;
+def clmul : SDNode<"ISD::CLMUL" , SDTIntBinOp,
+ [SDNPCommutative, SDNPAssociative]>;
+def clmulr : SDNode<"ISD::CLMULR" , SDTIntBinOp,
+ [SDNPCommutative, SDNPAssociative]>;
+def clmulh : SDNode<"ISD::CLMULH" , SDTIntBinOp,
+ [SDNPCommutative, SDNPAssociative]>;
def and : SDNode<"ISD::AND" , SDTIntBinOp,
[SDNPCommutative, SDNPAssociative]>;
def or : SDNode<"ISD::OR" , SDTIntBinOp,
diff --git a/llvm/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp b/llvm/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp
index 99d14a60c6ed1..4e9cbbb85c129 100644
--- a/llvm/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp
@@ -4095,6 +4095,12 @@ bool SelectionDAGLegalize::ExpandNode(SDNode *Node) {
if (SDValue Expanded = TLI.expandFunnelShift(Node, DAG))
Results.push_back(Expanded);
break;
+ case ISD::CLMUL:
+ case ISD::CLMULR:
+ case ISD::CLMULH:
+ if (SDValue Expanded = TLI.expandCLMUL(Node, DAG))
+ Results.push_back(Expanded);
+ break;
case ISD::ROTL:
case ISD::ROTR:
if (SDValue Expanded = TLI.expandROT(Node, true /*AllowVectorOps*/, DAG))
diff --git a/llvm/lib/CodeGen/SelectionDAG/LegalizeIntegerTypes.cpp b/llvm/lib/CodeGen/SelectionDAG/LegalizeIntegerTypes.cpp
index 44e5a187c4281..3fb58ca52bf30 100644
--- a/llvm/lib/CodeGen/SelectionDAG/LegalizeIntegerTypes.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/LegalizeIntegerTypes.cpp
@@ -204,6 +204,9 @@ void DAGTypeLegalizer::PromoteIntegerResult(SDNode *N, unsigned ResNo) {
case ISD::ADD:
case ISD::SUB:
case ISD::MUL:
+ case ISD::CLMUL:
+ case ISD::CLMULR:
+ case ISD::CLMULH:
case ISD::VP_AND:
case ISD::VP_OR:
case ISD::VP_XOR:
@@ -3128,7 +3131,7 @@ void DAGTypeLegalizer::ExpandIntegerResult(SDNode *N, unsigned ResNo) {
case ISD::USHLSAT: ExpandIntRes_SHLSAT(N, Lo, Hi); break;
case ISD::AVGCEILS:
- case ISD::AVGCEILU:
+ case ISD::AVGCEILU:
case ISD::AVGFLOORS:
case ISD::AVGFLOORU: ExpandIntRes_AVG(N, Lo, Hi); break;
@@ -3162,6 +3165,12 @@ void DAGTypeLegalizer::ExpandIntegerResult(SDNode *N, unsigned ResNo) {
ExpandIntRes_FunnelShift(N, Lo, Hi);
break;
+ case ISD::CLMUL:
+ case ISD::CLMULR:
+ case ISD::CLMULH:
+ ExpandIntRes_CLMUL(N, Lo, Hi);
+ break;
+
case ISD::VSCALE:
ExpandIntRes_VSCALE(N, Lo, Hi);
break;
@@ -5492,6 +5501,11 @@ void DAGTypeLegalizer::ExpandIntRes_FunnelShift(SDNode *N, SDValue &Lo,
Hi = DAG.getNode(Opc, DL, HalfVT, Select3, Select2, NewShAmt);
}
+void DAGTypeLegalizer::ExpandIntRes_CLMUL(SDNode *N, SDValue &Lo, SDValue &Hi) {
+ SDValue Res = TLI.expandCLMUL(N, DAG);
+ SplitInteger(Res, Lo, Hi);
+}
+
void DAGTypeLegalizer::ExpandIntRes_VSCALE(SDNode *N, SDValue &Lo,
SDValue &Hi) {
EVT VT = N->getValueType(0);
diff --git a/llvm/lib/CodeGen/SelectionDAG/LegalizeTypes.h b/llvm/lib/CodeGen/SelectionDAG/LegalizeTypes.h
index ede522eff6df3..5ebda11cc189e 100644
--- a/llvm/lib/CodeGen/SelectionDAG/LegalizeTypes.h
+++ b/llvm/lib/CodeGen/SelectionDAG/LegalizeTypes.h
@@ -513,6 +513,7 @@ class LLVM_LIBRARY_VISIBILITY DAGTypeLegalizer {
void ExpandIntRes_Rotate (SDNode *N, SDValue &Lo, SDValue &Hi);
void ExpandIntRes_FunnelShift (SDNode *N, SDValue &Lo, SDValue &Hi);
+ void ExpandIntRes_CLMUL(SDNode *N, SDValue &Lo, SDValue &Hi);
void ExpandIntRes_VSCALE (SDNode *N, SDValue &Lo, SDValue &Hi);
void ExpandIntRes_READ_REGISTER(SDNode *N, SDValue &Lo, SDValue &Hi);
@@ -912,6 +913,7 @@ class LLVM_LIBRARY_VISIBILITY DAGTypeLegalizer {
SDValue ScalarizeVecOp_UnaryOp(SDNode *N);
SDValue ScalarizeVecOp_UnaryOpWithExtraInput(SDNode *N);
SDValue ScalarizeVecOp_UnaryOp_StrictFP(SDNode *N);
+ SDValue ScalarizeVecOp_BinOp(SDNode *N);
SDValue ScalarizeVecOp_CONCAT_VECTORS(SDNode *N);
SDValue ScalarizeVecOp_INSERT_SUBVECTOR(SDNode *N, unsigned OpNo);
SDValue ScalarizeVecOp_EXTRACT_VECTOR_ELT(SDNode *N);
diff --git a/llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp b/llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp
index 71eeee78bd868..a7b408f88e1d5 100644
--- a/llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp
@@ -173,6 +173,9 @@ void DAGTypeLegalizer::ScalarizeVectorResult(SDNode *N, unsigned ResNo) {
case ISD::SMAX:
case ISD::UMIN:
case ISD::UMAX:
+ case ISD::CLMUL:
+ case ISD::CLMULR:
+ case ISD::CLMULH:
case ISD::SADDSAT:
case ISD::UADDSAT:
@@ -799,6 +802,11 @@ bool DAGTypeLegalizer::ScalarizeVectorOperand(SDNode *N, unsigned OpNo) {
case ISD::LLRINT:
Res = ScalarizeVecOp_UnaryOp(N);
break;
+ case ISD::CLMUL:
+ case ISD::CLMULR:
+ case ISD::CLMULH:
+ Res = ScalarizeVecOp_BinOp(N);
+ break;
case ISD::FP_TO_SINT_SAT:
case ISD::FP_TO_UINT_SAT:
Res = ScalarizeVecOp_UnaryOpWithExtraInput(N);
@@ -950,6 +958,20 @@ SDValue DAGTypeLegalizer::ScalarizeVecOp_UnaryOp_StrictFP(SDNode *N) {
return SDValue();
}
+/// If the input is a vector that needs to be scalarized, it must be <1 x ty>.
+/// Do the operation on the element instead.
+SDValue DAGTypeLegalizer::ScalarizeVecOp_BinOp(SDNode *N) {
+ assert(N->getValueType(0).getVectorNumElements() == 2 &&
+ "Unexpected vector type!");
+ SDValue L = GetScalarizedVector(N->getOperand(0));
+ SDValue R = GetScalarizedVector(N->getOperand(1));
+ SDValue Op = DAG.getNode(N->getOpcode(), SDLoc(N),
+ N->getValueType(0).getScalarType(), L, R);
+ // Revectorize the result so the types line up with what the uses of this
+ // expression expect.
+ return DAG.getNode(ISD::SCALAR_TO_VECTOR, SDLoc(N), N->getValueType(0), Op);
+}
+
/// The vectors to concatenate have length one - use a BUILD_VECTOR instead.
SDValue DAGTypeLegalizer::ScalarizeVecOp_CONCAT_VECTORS(SDNode *N) {
SmallVector<SDValue, 8> Ops(N->getNumOperands());
@@ -1091,14 +1113,14 @@ SDValue DAGTypeLegalizer::ScalarizeVecOp_FP_ROUND(SDNode *N, unsigned OpNo) {
return DAG.getNode(ISD::SCALAR_TO_VECTOR, SDLoc(N), N->getValueType(0), Res);
}
-SDValue DAGTypeLegalizer::ScalarizeVecOp_STRICT_FP_ROUND(SDNode *N,
+SDValue DAGTypeLegalizer::ScalarizeVecOp_STRICT_FP_ROUND(SDNode *N,
unsigned OpNo) {
assert(OpNo == 1 && "Wrong operand for scalarization!");
SDValue Elt = GetScalarizedVector(N->getOperand(1));
- SDValue Res = DAG.getNode(ISD::STRICT_FP_ROUND, SDLoc(N),
- { N->getValueType(0).getVectorElementType(),
- MVT::Other },
- { N->getOperand(0), Elt, N->getOperand(2) });
+ SDValue Res =
+ DAG.getNode(ISD::STRICT_FP_ROUND, SDLoc(N),
+ {N->getValueType(0).getVectorElementType(), MVT::Other},
+ {N->getOperand(0), Elt, N->getOperand(2)});
// Legalize the chain result - switch anything that used the old chain to
// use the new one.
ReplaceValueWith(SDValue(N, 1), Res.getValue(1));
@@ -1372,6 +1394,9 @@ void DAGTypeLegalizer::SplitVectorResult(SDNode *N, unsigned ResNo) {
case ISD::ADD: case ISD::VP_ADD:
case ISD::SUB: case ISD::VP_SUB:
case ISD::MUL: case ISD::VP_MUL:
+ case ISD::CLMUL:
+ case ISD::CLMULR:
+ case ISD::CLMULH:
case ISD::MULHS:
case ISD::MULHU:
case ISD::ABDS:
@@ -3842,16 +3867,16 @@ SDValue DAGTypeLegalizer::SplitVecOp_UnaryOp(SDNode *N) {
InVT.getVectorElementCount());
if (N->isStrictFPOpcode()) {
- Lo = DAG.getNode(N->getOpcode(), dl, { OutVT, MVT::Other },
- { N->getOperand(0), Lo });
- Hi = DAG.getNode(N->getOpcode(), dl, { OutVT, MVT::Other },
- { N->getOperand(0), Hi });
+ Lo = DAG.getNode(N->getOpcode(), dl, {OutVT, MVT::Other},
+ {N->getOperand(0), Lo});
+ Hi = DAG.getNode(N->getOpcode(), dl, {OutVT, MVT::Other},
+ {N->getOperand(0), Hi});
// Build a factor node to remember that this operation is independent
// of the other one.
SDValue Ch = DAG.getNode(ISD::TokenFactor, dl, MVT::Other, Lo.getValue(1),
Hi.getValue(1));
-
+
// Legalize the chain result - switch anything that used the old chain to
// use the new one.
ReplaceValueWith(SDValue(N, 1), Ch);
@@ -4638,13 +4663,13 @@ SDValue DAGTypeLegalizer::SplitVecOp_FP_ROUND(SDNode *N) {
InVT.getVectorElementCount());
if (N->isStrictFPOpcode()) {
- Lo = DAG.getNode(N->getOpcode(), DL, { OutVT, MVT::Other },
- { N->getOperand(0), Lo, N->getOperand(2) });
- Hi = DAG.getNode(N->getOpcode(), DL, { OutVT, MVT::Other },
- { N->getOperand(0), Hi, N->getOperand(2) });
+ Lo = DAG.getNode(N->getOpcode(), DL, {OutVT, MVT::Other},
+ {N->getOperand(0), Lo, N->getOperand(2)});
+ Hi = DAG.getNode(N->getOpcode(), DL, {OutVT, MVT::Other},
+ {N->getOperand(0), Hi, N->getOperand(2)});
// Legalize the chain result - switch anything that used the old chain to
// use the new one.
- SDValue NewChain = DAG.getNode(ISD::TokenFactor, DL, MVT::Other,
+ SDValue NewChain = DAG.getNode(ISD::TokenFactor, DL, MVT::Other,
Lo.getValue(1), Hi.getValue(1));
ReplaceValueWith(SDValue(N, 1), NewChain);
} else if (N->getOpcode() == ISD::VP_FP_ROUND) {
@@ -4924,6 +4949,9 @@ void DAGTypeLegalizer::WidenVectorResult(SDNode *N, unsigned ResNo) {
case ISD::SHL: case ISD::VP_SHL:
case ISD::SRA: case ISD::VP_SRA:
case ISD::SRL: case ISD::VP_SRL:
+ case ISD::CLMUL:
+ case ISD::CLMULR:
+ case ISD::CLMULH:
case ISD::FMINNUM:
case ISD::FMINNUM_IEEE:
case ISD::VP_FMINNUM:
@@ -5517,7 +5545,7 @@ SDValue DAGTypeLegalizer::WidenVecRes_StrictFP(SDNode *N) {
EOps.push_back(Op);
}
- EVT WidenVT[] = {WidenEltVT, MVT::Other};
+ EVT WidenVT[] = {WidenEltVT, MVT::Other};
SDValue Oper = DAG.getNode(Opcode, dl, WidenVT, EOps);
ConcatOps[ConcatEnd++] = Oper;
Chains.push_back(Oper.getValue(1));
@@ -7064,6 +7092,9 @@ bool DAGTypeLegalizer::WidenVectorOperand(SDNode *N, unsigned OpNo) {
case ISD::LLROUND:
case ISD::LRINT:
case ISD::LLRINT:
+ case ISD::CLMUL:
+ case ISD::CLMULR:
+ case ISD::CLMULH:
Res = WidenVecOp_UnrollVectorOp(N);
break;
case ISD::IS_FPCLASS: Res = WidenVecOp_IS_FPCLASS(N); break;
diff --git a/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp b/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
index 8827bff111c22..d587b581e0e8a 100644
--- a/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
@@ -7121,6 +7121,34 @@ SDValue SelectionDAG::FoldConstantArithmetic(unsigned Opcode, const SDLoc &DL,
}
}
+ // Handle clmul special cases.
+ if (Opcode == ISD::CLMUL || Opcode == ISD::CLMULR || Opcode == ISD::CLMULH) {
+ assert(VT.isInteger() && "This operator only applies to integer types!");
+ assert(Ops[0].getValueType() == VT && Ops[1].getValueType() == VT &&
+ "CLMUL types must match!");
+
+ auto *C1 = dyn_cast<ConstantSDNode>(Ops[0]);
+ auto *C2 = dyn_cast<ConstantSDNode>(Ops[1]);
+
+ if (C1 && C2) {
+ const APInt &V1 = C1->getAPIntValue();
+ const APInt &V2 = C2->getAPIntValue();
+ APInt Res;
+ switch (Opcode) {
+ case ISD::CLMUL:
+ Res = APIntOps::clmul(V1, V2);
+ break;
+ case ISD::CLMULR:
+ Res = APIntOps::clmulr(V1, V2);
+ break;
+ case ISD::CLMULH:
+ Res = APIntOps::clmulh(V1, V2);
+ break;
+ }
+ return getConstant(Res, DL, VT);
+ }
+ }
+
// Handle fma/fmad special cases.
if (Opcode == ISD::FMA || Opcode == ISD::FMAD || Opcode == ISD::FMULADD) {
assert(VT.isFloatingPoint() && "This operator only applies to FP types!");
diff --git a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
index 4f13f3b128ea4..155f014acbbdc 100644
--- a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
@@ -7283,6 +7283,26 @@ void SelectionDAGBuilder::visitIntrinsicCall(const CallInst &I,
}
return;
}
+ case Intrinsic::clmul:
+ case Intrinsic::clmulr:
+ case Intrinsic::clmulh: {
+ SDValue Op1 = getValue(I.getArgOperand(0));
+ SDValue Op2 = getValue(I.getArgOperand(1));
+ unsigned Opcode;
+ switch (Intrinsic) {
+ case Intrinsic::clmul:
+ Opcode = ISD::CLMUL;
+ break;
+ case Intrinsic::clmulr:
+ Opcode = ISD::CLMULR;
+ break;
+ case Intrinsic::clmulh:
+ Opcode = ISD::CLMULH;
+ break;
+ }
+ setValue(&I, DAG.getNode(Opcode, sdl, Op1.getValueType(), Op1, Op2));
+ return;
+ }
case Intrinsic::sadd_sat: {
SDValue Op1 = getValue(I.getArgOperand(0));
SDValue Op2 = getValue(I.getArgOperand(1));
diff --git a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGDumper.cpp b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGDumper.cpp
index ec5edd5f13978..d537236afb41c 100644
--- a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGDumper.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGDumper.cpp
@@ -299,6 +299,9 @@ std::string SDNode::getOperationName(const SelectionDAG *G) const {
case ISD::ROTR: return "rotr";
case ISD::FSHL: return "fshl";
case ISD::FSHR: return "fshr";
+ case ISD::CLMUL: return "clmul";
+ case ISD::CLMULR: return "clmulr";
+ case ISD::CLMULH: return "clmulh";
case ISD::FADD: return "fadd";
case ISD::STRICT_FADD: return "strict_fadd";
case ISD::FSUB: return "fsub";
diff --git a/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp b/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp
index bb64f4ee70280..a0d1a6b41e90b 100644
--- a/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp
@@ -8301,6 +8301,46 @@ SDValue TargetLowering::expandFunnelShift(SDNode *Node,
return DAG.getNode(ISD::OR, DL, VT, ShX, ShY);
}
+SDValue TargetLowering::expandCLMUL(SDNode *Node, SelectionDAG &DAG) const {
+ SDLoc DL(Node);
+ EVT VT = Node->getValueType(0);
+ SDValue X = Node->getOperand(0);
+ SDValue Y = Node->getOperand(1);
+ unsigned BW = VT.getScalarSizeInBits();
+
+ if (VT.isVector() && (isOperationLegalOrCustomOrPromote(
+ Node->getOpcode(), VT.getVectorElementType()) ||
+ !isOperationLegalOrCustom(ISD::VSELECT, VT)))
+ return DAG.UnrollVectorOp(Node);
+
+ SDValue Res = DAG.getConstant(0, DL, VT);
+ switch (Node->getOpcode()) {
+ case ISD::CLMUL: {
+ for (unsigned I = 0; I < BW; ++I) {
+ SDValue SignMask = DAG.getConstant(APInt::getOneBitSet(BW, I), DL, VT);
+ SDValue YMasked = DAG.getNode(ISD::AND, DL, VT, Y, SignMask);
+ SDValue Mul = DAG.getNode(ISD::MUL, DL, VT, X, YMasked);
+ Res = DAG.getNode(ISD::XOR, DL, VT, Res, Mul);
+ }
+ break;
+ }
+ case ISD::CLMULR: {
+ SDValue XRev = DAG.getNode(ISD::BITREVERSE, DL, VT, X);
+ SDValue YRev = DAG.getNode(ISD::BITREVERSE, DL, VT, X);
+ SDValue ResR = DAG.getNode(ISD::CLMUL, DL, VT, XRev, YRev);
+ Res = DAG.getNode(ISD::BITREVERSE, DL, VT, ResR);
+ break;
+ }
+ case ISD::CLMULH: {
+ SDValue ResR = DAG.getNode(ISD::CLMULR, DL, VT, X, Y);
+ Res = DAG.getNode(ISD::SRL, DL, VT, ResR,
+ DAG.getShiftAmountConstant(1, VT, DL));
+ break;
+ }
+ }
+ return Res;
+}
+
// TODO: Merge with expandFunnelShift.
SDValue TargetLowering::expandROT(SDNode *Node, bool AllowVectorOps,
SelectionDAG &DAG) const {
diff --git a/llvm/lib/CodeGen/TargetLoweringBase.cpp b/llvm/lib/CodeGen/TargetLoweringBase.cpp
index 0562fd8c08ba8..6614014d74548 100644
--- a/llvm/lib/CodeGen/TargetLoweringBase.cpp
+++ b/llvm/lib/CodeGen/TargetLoweringBase.cpp
@@ -912,6 +912,9 @@ void TargetLoweringBase::initActions() {
// Absolute difference
setOperationAction({ISD::ABDS, ISD::ABDU}, VT, Expand);
+ // Carry-less multiply
+ setOperationAction({ISD::CLMUL, ISD::CLMULR, ISD::CLMULH}, VT, Expand);
+
// Saturated trunc
setOperationAction(ISD::TRUNCATE_SSAT_S, VT, Expand);
setOperationAction(ISD::TRUNCATE_SSAT_U, VT, Expand);
diff --git a/llvm/test/CodeGen/RISCV/clmul.ll b/llvm/test/CodeGen/RISCV/clmul.ll
new file mode 100644
index 0000000000000..7429b89817533
--- /dev/null
+++ b/llvm/test/CodeGen/RISCV/clmul.ll
@@ -0,0 +1,11952 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=riscv32 -mattr=+m -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK,RV32IM
+; RUN: llc -mtriple=riscv64 -mattr=+m -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK,RV64IM
+
+define i4 @clmul_i4(i4 %a, i4 %b) nounwind {
+; RV32IM-LABEL: clmul_i4:
+; RV32IM: # %bb.0:
+; RV32IM-NEXT: addi sp, sp, -48
+; RV32IM-NEXT: sw s0, 44(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s1, 40(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s2, 36(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s3, 32(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s4, 28(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s5, 24(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s6, 20(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s7, 16(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s8, 12(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s9, 8(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s10, 4(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi t6, a1, 2
+; RV32IM-NEXT: andi s1, a1, 1
+; RV32IM-NEXT: andi a7, a1, 4
+; RV32IM-NEXT: andi t2, a1, 8
+; RV32IM-NEXT: andi t0, a1, 16
+; RV32IM-NEXT: andi t3, a1, 32
+; RV32IM-NEXT: andi a2, a1, 64
+; RV32IM-NEXT: andi t4, a1, 128
+; RV32IM-NEXT: andi s0, a1, 256
+; RV32IM-NEXT: andi a3, a1, 512
+; RV32IM-NEXT: li a4, 1
+; RV32IM-NEXT: lui a5, 1
+; RV32IM-NEXT: lui a6, 2
+; RV32IM-NEXT: lui t1, 4
+; RV32IM-NEXT: lui t5, 8
+; RV32IM-NEXT: lui s2, 16
+; RV32IM-NEXT: lui s3, 32
+; RV32IM-NEXT: lui s4, 64
+; RV32IM-NEXT: lui s5, 128
+; RV32IM-NEXT: lui s6, 256
+; RV32IM-NEXT: lui s7, 512
+; RV32IM-NEXT: lui s8, 1024
+; RV32IM-NEXT: lui s9, 2048
+; RV32IM-NEXT: lui s10, 4096
+; RV32IM-NEXT: mul t6, a0, t6
+; RV32IM-NEXT: mul s1, a0, s1
+; RV32IM-NEXT: xor t6, s1, t6
+; RV32IM-NEXT: lui s1, 8192
+; RV32IM-NEXT: mul a7, a0, a7
+; RV32IM-NEXT: mul t2, a0, t2
+; RV32IM-NEXT: xor a7, a7, t2
+; RV32IM-NEXT: lui t2, 16384
+; RV32IM-NEXT: mul t0, a0, t0
+; RV32IM-NEXT: mul t3, a0, t3
+; RV32IM-NEXT: xor t0, t0, t3
+; RV32IM-NEXT: lui t3, 32768
+; RV32IM-NEXT: mul t4, a0, t4
+; RV32IM-NEXT: mul s0, a0, s0
+; RV32IM-NEXT: xor t4, t4, s0
+; RV32IM-NEXT: lui s0, 65536
+; RV32IM-NEXT: xor a7, t6, a7
+; RV32IM-NEXT: lui t6, 131072
+; RV32IM-NEXT: mul a2, a0, a2
+; RV32IM-NEXT: xor a2, t0, a2
+; RV32IM-NEXT: lui t0, 262144
+; RV32IM-NEXT: mul a3, a0, a3
+; RV32IM-NEXT: xor a3, t4, a3
+; RV32IM-NEXT: lui t4, 524288
+; RV32IM-NEXT: slli a4, a4, 11
+; RV32IM-NEXT: and a5, a1, a5
+; RV32IM-NEXT: and a6, a1, a6
+; RV32IM-NEXT: and t1, a1, t1
+; RV32IM-NEXT: and t5, a1, t5
+; RV32IM-NEXT: and s2, a1, s2
+; RV32IM-NEXT: and s3, a1, s3
+; RV32IM-NEXT: and s4, a1, s4
+; RV32IM-NEXT: and s5, a1, s5
+; RV32IM-NEXT: and s6, a1, s6
+; RV32IM-NEXT: and s7, a1, s7
+; RV32IM-NEXT: and s8, a1, s8
+; RV32IM-NEXT: and s9, a1, s9
+; RV32IM-NEXT: and s10, a1, s10
+; RV32IM-NEXT: and s1, a1, s1
+; RV32IM-NEXT: and t2, a1, t2
+; RV32IM-NEXT: and t3, a1, t3
+; RV32IM-NEXT: and s0, a1, s0
+; RV32IM-NEXT: and t6, a1, t6
+; RV32IM-NEXT: and t0, a1, t0
+; RV32IM-NEXT: and t4, a1, t4
+; RV32IM-NEXT: and a4, a1, a4
+; RV32IM-NEXT: andi a1, a1, 1024
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: mul a5, a0, a5
+; RV32IM-NEXT: mul a6, a0, a6
+; RV32IM-NEXT: mul t1, a0, t1
+; RV32IM-NEXT: mul t5, a0, t5
+; RV32IM-NEXT: mul s2, a0, s2
+; RV32IM-NEXT: mul s3, a0, s3
+; RV32IM-NEXT: mul s4, a0, s4
+; RV32IM-NEXT: mul s5, a0, s5
+; RV32IM-NEXT: mul s6, a0, s6
+; RV32IM-NEXT: mul s7, a0, s7
+; RV32IM-NEXT: mul s8, a0, s8
+; RV32IM-NEXT: mul s9, a0, s9
+; RV32IM-NEXT: mul s10, a0, s10
+; RV32IM-NEXT: mul s1, a0, s1
+; RV32IM-NEXT: mul t2, a0, t2
+; RV32IM-NEXT: mul t3, a0, t3
+; RV32IM-NEXT: mul s0, a0, s0
+; RV32IM-NEXT: mul t6, a0, t6
+; RV32IM-NEXT: mul t0, a0, t0
+; RV32IM-NEXT: mul t4, a0, t4
+; RV32IM-NEXT: mul a0, a0, a4
+; RV32IM-NEXT: xor a4, t1, t5
+; RV32IM-NEXT: xor t1, s5, s6
+; RV32IM-NEXT: xor t2, s1, t2
+; RV32IM-NEXT: xor a2, a7, a2
+; RV32IM-NEXT: xor a1, a3, a1
+; RV32IM-NEXT: xor a0, a0, a5
+; RV32IM-NEXT: xor a3, a4, s2
+; RV32IM-NEXT: xor a4, t1, s7
+; RV32IM-NEXT: xor a5, t2, t3
+; RV32IM-NEXT: xor a1, a2, a1
+; RV32IM-NEXT: xor a0, a0, a6
+; RV32IM-NEXT: xor a2, a3, s3
+; RV32IM-NEXT: xor a3, a4, s8
+; RV32IM-NEXT: xor a5, a5, s0
+; RV32IM-NEXT: xor a0, a1, a0
+; RV32IM-NEXT: xor a1, a2, s4
+; RV32IM-NEXT: xor a2, a3, s9
+; RV32IM-NEXT: xor a3, a5, t6
+; RV32IM-NEXT: xor a0, a0, a1
+; RV32IM-NEXT: xor a1, a2, s10
+; RV32IM-NEXT: xor a2, a3, t0
+; RV32IM-NEXT: xor a0, a0, a1
+; RV32IM-NEXT: xor a1, a2, t4
+; RV32IM-NEXT: xor a0, a0, a1
+; RV32IM-NEXT: lw s0, 44(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s1, 40(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s2, 36(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s3, 32(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s4, 28(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s5, 24(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s6, 20(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s7, 16(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s8, 12(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s9, 8(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s10, 4(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: addi sp, sp, 48
+; RV32IM-NEXT: ret
+;
+; RV64IM-LABEL: clmul_i4:
+; RV64IM: # %bb.0:
+; RV64IM-NEXT: addi sp, sp, -448
+; RV64IM-NEXT: sd ra, 440(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s0, 432(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s1, 424(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s2, 416(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s3, 408(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s4, 400(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s5, 392(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s6, 384(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s7, 376(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s8, 368(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s9, 360(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s10, 352(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s11, 344(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi t2, a1, 2
+; RV64IM-NEXT: andi t4, a1, 1
+; RV64IM-NEXT: andi a6, a1, 4
+; RV64IM-NEXT: andi t0, a1, 8
+; RV64IM-NEXT: andi a5, a1, 16
+; RV64IM-NEXT: andi a7, a1, 32
+; RV64IM-NEXT: andi a3, a1, 64
+; RV64IM-NEXT: andi t1, a1, 128
+; RV64IM-NEXT: andi t3, a1, 256
+; RV64IM-NEXT: andi a4, a1, 512
+; RV64IM-NEXT: li a2, 1
+; RV64IM-NEXT: lui s7, 1
+; RV64IM-NEXT: lui t6, 2
+; RV64IM-NEXT: lui s0, 4
+; RV64IM-NEXT: lui s1, 8
+; RV64IM-NEXT: lui s2, 16
+; RV64IM-NEXT: lui s3, 32
+; RV64IM-NEXT: lui s4, 64
+; RV64IM-NEXT: lui s5, 128
+; RV64IM-NEXT: lui s6, 256
+; RV64IM-NEXT: lui s8, 512
+; RV64IM-NEXT: lui s9, 1024
+; RV64IM-NEXT: lui s10, 2048
+; RV64IM-NEXT: lui s11, 4096
+; RV64IM-NEXT: lui ra, 8192
+; RV64IM-NEXT: lui t5, 16384
+; RV64IM-NEXT: mul t2, a0, t2
+; RV64IM-NEXT: mul t4, a0, t4
+; RV64IM-NEXT: xor t2, t4, t2
+; RV64IM-NEXT: lui t4, 32768
+; RV64IM-NEXT: mul a6, a0, a6
+; RV64IM-NEXT: mul t0, a0, t0
+; RV64IM-NEXT: xor a6, a6, t0
+; RV64IM-NEXT: lui t0, 65536
+; RV64IM-NEXT: mul a5, a0, a5
+; RV64IM-NEXT: mul a7, a0, a7
+; RV64IM-NEXT: xor a5, a5, a7
+; RV64IM-NEXT: lui a7, 131072
+; RV64IM-NEXT: mul t1, a0, t1
+; RV64IM-NEXT: mul t3, a0, t3
+; RV64IM-NEXT: xor t1, t1, t3
+; RV64IM-NEXT: lui t3, 262144
+; RV64IM-NEXT: mul a3, a0, a3
+; RV64IM-NEXT: mul a4, a0, a4
+; RV64IM-NEXT: xor a6, t2, a6
+; RV64IM-NEXT: sd a6, 336(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a6, a2, 11
+; RV64IM-NEXT: sd a6, 216(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and s7, a1, s7
+; RV64IM-NEXT: and a6, a1, t6
+; RV64IM-NEXT: sd a6, 288(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and s0, a1, s0
+; RV64IM-NEXT: and s1, a1, s1
+; RV64IM-NEXT: and s2, a1, s2
+; RV64IM-NEXT: and s3, a1, s3
+; RV64IM-NEXT: and a6, a1, s4
+; RV64IM-NEXT: sd a6, 280(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a6, a1, s5
+; RV64IM-NEXT: and t2, a1, s6
+; RV64IM-NEXT: and s8, a1, s8
+; RV64IM-NEXT: and t6, a1, s9
+; RV64IM-NEXT: sd t6, 272(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and t6, a1, s10
+; RV64IM-NEXT: sd t6, 264(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and t6, a1, s11
+; RV64IM-NEXT: sd t6, 256(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and t6, a1, ra
+; RV64IM-NEXT: and t5, a1, t5
+; RV64IM-NEXT: and t4, a1, t4
+; RV64IM-NEXT: sd t4, 248(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and t0, a1, t0
+; RV64IM-NEXT: sd t0, 240(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a7, a1, a7
+; RV64IM-NEXT: sd a7, 232(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a7, a1, t3
+; RV64IM-NEXT: sd a7, 224(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: xor a3, a5, a3
+; RV64IM-NEXT: sd a3, 328(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli t4, a2, 32
+; RV64IM-NEXT: xor a3, t1, a4
+; RV64IM-NEXT: sd a3, 320(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli s4, a2, 33
+; RV64IM-NEXT: mul a3, a0, s0
+; RV64IM-NEXT: mul a4, a0, s1
+; RV64IM-NEXT: xor a3, a3, a4
+; RV64IM-NEXT: sd a3, 312(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli s0, a2, 34
+; RV64IM-NEXT: mul a3, a0, a6
+; RV64IM-NEXT: mul a4, a0, t2
+; RV64IM-NEXT: xor a3, a3, a4
+; RV64IM-NEXT: sd a3, 304(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli s1, a2, 35
+; RV64IM-NEXT: mul a3, a0, t6
+; RV64IM-NEXT: mul a4, a0, t5
+; RV64IM-NEXT: xor a3, a3, a4
+; RV64IM-NEXT: sd a3, 296(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli t5, a2, 36
+; RV64IM-NEXT: slli t6, a2, 37
+; RV64IM-NEXT: slli s5, a2, 38
+; RV64IM-NEXT: slli s6, a2, 39
+; RV64IM-NEXT: slli s9, a2, 40
+; RV64IM-NEXT: slli s10, a2, 41
+; RV64IM-NEXT: slli s11, a2, 42
+; RV64IM-NEXT: slli ra, a2, 43
+; RV64IM-NEXT: slli a3, a2, 44
+; RV64IM-NEXT: sd a3, 208(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a2, 45
+; RV64IM-NEXT: sd a3, 200(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a2, 46
+; RV64IM-NEXT: sd a3, 192(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a2, 47
+; RV64IM-NEXT: sd a3, 184(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a2, 48
+; RV64IM-NEXT: sd a3, 176(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a2, 49
+; RV64IM-NEXT: sd a3, 168(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a2, 50
+; RV64IM-NEXT: sd a3, 160(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a2, 51
+; RV64IM-NEXT: sd a3, 152(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a2, 52
+; RV64IM-NEXT: sd a3, 144(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a2, 53
+; RV64IM-NEXT: sd a3, 136(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a2, 54
+; RV64IM-NEXT: sd a3, 128(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli t1, a2, 55
+; RV64IM-NEXT: slli t0, a2, 56
+; RV64IM-NEXT: slli a7, a2, 57
+; RV64IM-NEXT: slli a6, a2, 58
+; RV64IM-NEXT: slli a5, a2, 59
+; RV64IM-NEXT: slli a4, a2, 60
+; RV64IM-NEXT: slli a3, a2, 61
+; RV64IM-NEXT: slli a2, a2, 62
+; RV64IM-NEXT: ld t2, 216(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and t3, a1, t2
+; RV64IM-NEXT: and t2, a1, t4
+; RV64IM-NEXT: sd t2, 120(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and t4, a1, s4
+; RV64IM-NEXT: and s0, a1, s0
+; RV64IM-NEXT: sd s0, 112(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and s1, a1, s1
+; RV64IM-NEXT: sd s1, 104(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and t2, a1, t5
+; RV64IM-NEXT: sd t2, 96(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and s1, a1, t6
+; RV64IM-NEXT: and t2, a1, s5
+; RV64IM-NEXT: sd t2, 88(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and t2, a1, s6
+; RV64IM-NEXT: sd t2, 80(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and s4, a1, s9
+; RV64IM-NEXT: and s5, a1, s10
+; RV64IM-NEXT: and s6, a1, s11
+; RV64IM-NEXT: and t6, a1, ra
+; RV64IM-NEXT: ld t2, 208(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and t2, a1, t2
+; RV64IM-NEXT: sd t2, 72(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld t2, 200(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and t2, a1, t2
+; RV64IM-NEXT: sd t2, 64(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld t2, 192(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s10, a1, t2
+; RV64IM-NEXT: ld t2, 184(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s11, a1, t2
+; RV64IM-NEXT: ld t2, 176(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and ra, a1, t2
+; RV64IM-NEXT: ld t2, 168(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and t2, a1, t2
+; RV64IM-NEXT: sd t2, 184(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld t2, 160(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and t2, a1, t2
+; RV64IM-NEXT: sd t2, 160(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld t2, 152(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and t2, a1, t2
+; RV64IM-NEXT: sd t2, 152(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld t2, 144(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and t2, a1, t2
+; RV64IM-NEXT: sd t2, 144(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld t2, 136(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and t2, a1, t2
+; RV64IM-NEXT: sd t2, 136(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld t2, 128(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and t2, a1, t2
+; RV64IM-NEXT: sd t2, 128(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and t1, a1, t1
+; RV64IM-NEXT: and t0, a1, t0
+; RV64IM-NEXT: sd t0, 56(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a7, a1, a7
+; RV64IM-NEXT: sd a7, 48(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a6, a1, a6
+; RV64IM-NEXT: and a5, a1, a5
+; RV64IM-NEXT: sd a5, 40(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a4, a1, a4
+; RV64IM-NEXT: sd a4, 32(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a3, a1, a3
+; RV64IM-NEXT: sd a3, 24(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a2, a1, a2
+; RV64IM-NEXT: sd a2, 16(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi a2, a1, 1024
+; RV64IM-NEXT: srliw a3, a1, 31
+; RV64IM-NEXT: srli a1, a1, 63
+; RV64IM-NEXT: mul s9, a0, a2
+; RV64IM-NEXT: slli a3, a3, 31
+; RV64IM-NEXT: slli a1, a1, 63
+; RV64IM-NEXT: mul s7, a0, s7
+; RV64IM-NEXT: ld a2, 288(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, a0, a2
+; RV64IM-NEXT: sd a2, 192(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul s2, a0, s2
+; RV64IM-NEXT: mul a2, a0, s3
+; RV64IM-NEXT: sd a2, 176(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 280(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, a0, a2
+; RV64IM-NEXT: sd a2, 216(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul s0, a0, s8
+; RV64IM-NEXT: ld a2, 272(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, a0, a2
+; RV64IM-NEXT: sd a2, 8(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 264(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, a0, a2
+; RV64IM-NEXT: sd a2, 208(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 256(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, a0, a2
+; RV64IM-NEXT: sd a2, 272(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 248(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul t2, a0, a2
+; RV64IM-NEXT: ld a2, 240(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, a0, a2
+; RV64IM-NEXT: sd a2, 0(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 232(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, a0, a2
+; RV64IM-NEXT: sd a2, 200(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 224(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, a0, a2
+; RV64IM-NEXT: sd a2, 256(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a2, a0, a3
+; RV64IM-NEXT: sd a2, 280(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a1, a0, a1
+; RV64IM-NEXT: sd a1, 288(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a5, a0, t3
+; RV64IM-NEXT: ld a1, 120(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a7, a0, a1
+; RV64IM-NEXT: mul t4, a0, t4
+; RV64IM-NEXT: ld a1, 112(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul t5, a0, a1
+; RV64IM-NEXT: ld a1, 104(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a1, a0, a1
+; RV64IM-NEXT: sd a1, 120(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a1, 96(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a1, a0, a1
+; RV64IM-NEXT: sd a1, 224(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a1, a0, s1
+; RV64IM-NEXT: sd a1, 240(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a1, 88(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a1, a0, a1
+; RV64IM-NEXT: sd a1, 264(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a1, 80(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul s1, a0, a1
+; RV64IM-NEXT: mul s4, a0, s4
+; RV64IM-NEXT: mul s5, a0, s5
+; RV64IM-NEXT: mul s6, a0, s6
+; RV64IM-NEXT: mul a1, a0, t6
+; RV64IM-NEXT: sd a1, 112(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a1, 72(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a1, a0, a1
+; RV64IM-NEXT: sd a1, 168(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a1, 64(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a1, a0, a1
+; RV64IM-NEXT: sd a1, 232(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a1, a0, s10
+; RV64IM-NEXT: sd a1, 248(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul s10, a0, s11
+; RV64IM-NEXT: mul s11, a0, ra
+; RV64IM-NEXT: ld a1, 184(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul ra, a0, a1
+; RV64IM-NEXT: ld a1, 160(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul t0, a0, a1
+; RV64IM-NEXT: ld a1, 152(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul t3, a0, a1
+; RV64IM-NEXT: ld a1, 144(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul s3, a0, a1
+; RV64IM-NEXT: ld a1, 136(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a1, a0, a1
+; RV64IM-NEXT: sd a1, 152(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a1, 128(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a1, a0, a1
+; RV64IM-NEXT: sd a1, 160(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a1, a0, t1
+; RV64IM-NEXT: sd a1, 184(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a1, 56(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, a0, a1
+; RV64IM-NEXT: ld a1, 48(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a1, a0, a1
+; RV64IM-NEXT: mul a3, a0, a6
+; RV64IM-NEXT: ld a4, 40(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a4, a0, a4
+; RV64IM-NEXT: ld a6, 32(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a6, a0, a6
+; RV64IM-NEXT: ld t1, 24(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul t1, a0, t1
+; RV64IM-NEXT: ld t6, 16(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul t6, a0, t6
+; RV64IM-NEXT: ld a0, 336(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s8, 328(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a0, a0, s8
+; RV64IM-NEXT: ld s8, 320(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s9, s8, s9
+; RV64IM-NEXT: xor a5, a5, s7
+; RV64IM-NEXT: ld s7, 312(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s2, s7, s2
+; RV64IM-NEXT: ld s7, 304(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s0, s7, s0
+; RV64IM-NEXT: ld s7, 296(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor t2, s7, t2
+; RV64IM-NEXT: xor a7, a7, t4
+; RV64IM-NEXT: xor t4, s1, s4
+; RV64IM-NEXT: xor s1, s10, s11
+; RV64IM-NEXT: xor a1, a2, a1
+; RV64IM-NEXT: xor a0, a0, s9
+; RV64IM-NEXT: ld a2, 192(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a5, a2
+; RV64IM-NEXT: ld a5, 176(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a5, s2, a5
+; RV64IM-NEXT: ld s2, 8(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s0, s0, s2
+; RV64IM-NEXT: ld s2, 0(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor t2, t2, s2
+; RV64IM-NEXT: xor a7, a7, t5
+; RV64IM-NEXT: xor t4, t4, s5
+; RV64IM-NEXT: xor t5, s1, ra
+; RV64IM-NEXT: xor a1, a1, a3
+; RV64IM-NEXT: xor a0, a0, a2
+; RV64IM-NEXT: ld a2, 216(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a5, a2
+; RV64IM-NEXT: ld a3, 208(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, s0, a3
+; RV64IM-NEXT: ld a5, 200(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a5, t2, a5
+; RV64IM-NEXT: ld t2, 120(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a7, a7, t2
+; RV64IM-NEXT: xor t2, t4, s6
+; RV64IM-NEXT: xor t0, t5, t0
+; RV64IM-NEXT: xor a1, a1, a4
+; RV64IM-NEXT: xor a0, a0, a2
+; RV64IM-NEXT: ld a2, 272(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a3, a2
+; RV64IM-NEXT: ld a3, 256(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a5, a3
+; RV64IM-NEXT: ld a4, 224(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, a7, a4
+; RV64IM-NEXT: ld a5, 112(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a5, t2, a5
+; RV64IM-NEXT: xor a7, t0, t3
+; RV64IM-NEXT: xor a1, a1, a6
+; RV64IM-NEXT: xor a0, a0, a2
+; RV64IM-NEXT: ld a2, 280(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a3, a2
+; RV64IM-NEXT: ld a3, 240(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a4, a3
+; RV64IM-NEXT: ld a4, 168(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, a5, a4
+; RV64IM-NEXT: xor a5, a7, s3
+; RV64IM-NEXT: xor a1, a1, t1
+; RV64IM-NEXT: xor a0, a0, a2
+; RV64IM-NEXT: ld a2, 264(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a3, a2
+; RV64IM-NEXT: ld a3, 232(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a4, a3
+; RV64IM-NEXT: ld a4, 152(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, a5, a4
+; RV64IM-NEXT: xor a1, a1, t6
+; RV64IM-NEXT: xor a0, a0, a2
+; RV64IM-NEXT: ld a2, 248(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a3, a2
+; RV64IM-NEXT: ld a3, 160(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a4, a3
+; RV64IM-NEXT: xor a0, a0, a2
+; RV64IM-NEXT: ld a2, 184(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a3, a2
+; RV64IM-NEXT: xor a0, a0, a2
+; RV64IM-NEXT: ld a2, 288(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a1, a1, a2
+; RV64IM-NEXT: xor a0, a0, a1
+; RV64IM-NEXT: ld ra, 440(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s0, 432(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s1, 424(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s2, 416(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s3, 408(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s4, 400(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s5, 392(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s6, 384(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s7, 376(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s8, 368(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s9, 360(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s10, 352(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s11, 344(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: addi sp, sp, 448
+; RV64IM-NEXT: ret
+ %res = call i4 @llvm.clmul.i4(i4 %a, i4 %b)
+ ret i4 %res
+}
+
+define i8 @clmul_i8(i8 %a, i8 %b) nounwind {
+; RV32IM-LABEL: clmul_i8:
+; RV32IM: # %bb.0:
+; RV32IM-NEXT: addi sp, sp, -48
+; RV32IM-NEXT: sw s0, 44(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s1, 40(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s2, 36(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s3, 32(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s4, 28(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s5, 24(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s6, 20(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s7, 16(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s8, 12(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s9, 8(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s10, 4(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi t6, a1, 2
+; RV32IM-NEXT: andi s1, a1, 1
+; RV32IM-NEXT: andi a7, a1, 4
+; RV32IM-NEXT: andi t2, a1, 8
+; RV32IM-NEXT: andi t0, a1, 16
+; RV32IM-NEXT: andi t3, a1, 32
+; RV32IM-NEXT: andi a2, a1, 64
+; RV32IM-NEXT: andi t4, a1, 128
+; RV32IM-NEXT: andi s0, a1, 256
+; RV32IM-NEXT: andi a3, a1, 512
+; RV32IM-NEXT: li a4, 1
+; RV32IM-NEXT: lui a5, 1
+; RV32IM-NEXT: lui a6, 2
+; RV32IM-NEXT: lui t1, 4
+; RV32IM-NEXT: lui t5, 8
+; RV32IM-NEXT: lui s2, 16
+; RV32IM-NEXT: lui s3, 32
+; RV32IM-NEXT: lui s4, 64
+; RV32IM-NEXT: lui s5, 128
+; RV32IM-NEXT: lui s6, 256
+; RV32IM-NEXT: lui s7, 512
+; RV32IM-NEXT: lui s8, 1024
+; RV32IM-NEXT: lui s9, 2048
+; RV32IM-NEXT: lui s10, 4096
+; RV32IM-NEXT: mul t6, a0, t6
+; RV32IM-NEXT: mul s1, a0, s1
+; RV32IM-NEXT: xor t6, s1, t6
+; RV32IM-NEXT: lui s1, 8192
+; RV32IM-NEXT: mul a7, a0, a7
+; RV32IM-NEXT: mul t2, a0, t2
+; RV32IM-NEXT: xor a7, a7, t2
+; RV32IM-NEXT: lui t2, 16384
+; RV32IM-NEXT: mul t0, a0, t0
+; RV32IM-NEXT: mul t3, a0, t3
+; RV32IM-NEXT: xor t0, t0, t3
+; RV32IM-NEXT: lui t3, 32768
+; RV32IM-NEXT: mul t4, a0, t4
+; RV32IM-NEXT: mul s0, a0, s0
+; RV32IM-NEXT: xor t4, t4, s0
+; RV32IM-NEXT: lui s0, 65536
+; RV32IM-NEXT: xor a7, t6, a7
+; RV32IM-NEXT: lui t6, 131072
+; RV32IM-NEXT: mul a2, a0, a2
+; RV32IM-NEXT: xor a2, t0, a2
+; RV32IM-NEXT: lui t0, 262144
+; RV32IM-NEXT: mul a3, a0, a3
+; RV32IM-NEXT: xor a3, t4, a3
+; RV32IM-NEXT: lui t4, 524288
+; RV32IM-NEXT: slli a4, a4, 11
+; RV32IM-NEXT: and a5, a1, a5
+; RV32IM-NEXT: and a6, a1, a6
+; RV32IM-NEXT: and t1, a1, t1
+; RV32IM-NEXT: and t5, a1, t5
+; RV32IM-NEXT: and s2, a1, s2
+; RV32IM-NEXT: and s3, a1, s3
+; RV32IM-NEXT: and s4, a1, s4
+; RV32IM-NEXT: and s5, a1, s5
+; RV32IM-NEXT: and s6, a1, s6
+; RV32IM-NEXT: and s7, a1, s7
+; RV32IM-NEXT: and s8, a1, s8
+; RV32IM-NEXT: and s9, a1, s9
+; RV32IM-NEXT: and s10, a1, s10
+; RV32IM-NEXT: and s1, a1, s1
+; RV32IM-NEXT: and t2, a1, t2
+; RV32IM-NEXT: and t3, a1, t3
+; RV32IM-NEXT: and s0, a1, s0
+; RV32IM-NEXT: and t6, a1, t6
+; RV32IM-NEXT: and t0, a1, t0
+; RV32IM-NEXT: and t4, a1, t4
+; RV32IM-NEXT: and a4, a1, a4
+; RV32IM-NEXT: andi a1, a1, 1024
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: mul a5, a0, a5
+; RV32IM-NEXT: mul a6, a0, a6
+; RV32IM-NEXT: mul t1, a0, t1
+; RV32IM-NEXT: mul t5, a0, t5
+; RV32IM-NEXT: mul s2, a0, s2
+; RV32IM-NEXT: mul s3, a0, s3
+; RV32IM-NEXT: mul s4, a0, s4
+; RV32IM-NEXT: mul s5, a0, s5
+; RV32IM-NEXT: mul s6, a0, s6
+; RV32IM-NEXT: mul s7, a0, s7
+; RV32IM-NEXT: mul s8, a0, s8
+; RV32IM-NEXT: mul s9, a0, s9
+; RV32IM-NEXT: mul s10, a0, s10
+; RV32IM-NEXT: mul s1, a0, s1
+; RV32IM-NEXT: mul t2, a0, t2
+; RV32IM-NEXT: mul t3, a0, t3
+; RV32IM-NEXT: mul s0, a0, s0
+; RV32IM-NEXT: mul t6, a0, t6
+; RV32IM-NEXT: mul t0, a0, t0
+; RV32IM-NEXT: mul t4, a0, t4
+; RV32IM-NEXT: mul a0, a0, a4
+; RV32IM-NEXT: xor a4, t1, t5
+; RV32IM-NEXT: xor t1, s5, s6
+; RV32IM-NEXT: xor t2, s1, t2
+; RV32IM-NEXT: xor a2, a7, a2
+; RV32IM-NEXT: xor a1, a3, a1
+; RV32IM-NEXT: xor a0, a0, a5
+; RV32IM-NEXT: xor a3, a4, s2
+; RV32IM-NEXT: xor a4, t1, s7
+; RV32IM-NEXT: xor a5, t2, t3
+; RV32IM-NEXT: xor a1, a2, a1
+; RV32IM-NEXT: xor a0, a0, a6
+; RV32IM-NEXT: xor a2, a3, s3
+; RV32IM-NEXT: xor a3, a4, s8
+; RV32IM-NEXT: xor a5, a5, s0
+; RV32IM-NEXT: xor a0, a1, a0
+; RV32IM-NEXT: xor a1, a2, s4
+; RV32IM-NEXT: xor a2, a3, s9
+; RV32IM-NEXT: xor a3, a5, t6
+; RV32IM-NEXT: xor a0, a0, a1
+; RV32IM-NEXT: xor a1, a2, s10
+; RV32IM-NEXT: xor a2, a3, t0
+; RV32IM-NEXT: xor a0, a0, a1
+; RV32IM-NEXT: xor a1, a2, t4
+; RV32IM-NEXT: xor a0, a0, a1
+; RV32IM-NEXT: lw s0, 44(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s1, 40(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s2, 36(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s3, 32(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s4, 28(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s5, 24(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s6, 20(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s7, 16(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s8, 12(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s9, 8(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s10, 4(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: addi sp, sp, 48
+; RV32IM-NEXT: ret
+;
+; RV64IM-LABEL: clmul_i8:
+; RV64IM: # %bb.0:
+; RV64IM-NEXT: addi sp, sp, -448
+; RV64IM-NEXT: sd ra, 440(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s0, 432(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s1, 424(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s2, 416(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s3, 408(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s4, 400(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s5, 392(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s6, 384(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s7, 376(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s8, 368(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s9, 360(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s10, 352(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s11, 344(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi t2, a1, 2
+; RV64IM-NEXT: andi t4, a1, 1
+; RV64IM-NEXT: andi a6, a1, 4
+; RV64IM-NEXT: andi t0, a1, 8
+; RV64IM-NEXT: andi a5, a1, 16
+; RV64IM-NEXT: andi a7, a1, 32
+; RV64IM-NEXT: andi a3, a1, 64
+; RV64IM-NEXT: andi t1, a1, 128
+; RV64IM-NEXT: andi t3, a1, 256
+; RV64IM-NEXT: andi a4, a1, 512
+; RV64IM-NEXT: li a2, 1
+; RV64IM-NEXT: lui s7, 1
+; RV64IM-NEXT: lui t6, 2
+; RV64IM-NEXT: lui s0, 4
+; RV64IM-NEXT: lui s1, 8
+; RV64IM-NEXT: lui s2, 16
+; RV64IM-NEXT: lui s3, 32
+; RV64IM-NEXT: lui s4, 64
+; RV64IM-NEXT: lui s5, 128
+; RV64IM-NEXT: lui s6, 256
+; RV64IM-NEXT: lui s8, 512
+; RV64IM-NEXT: lui s9, 1024
+; RV64IM-NEXT: lui s10, 2048
+; RV64IM-NEXT: lui s11, 4096
+; RV64IM-NEXT: lui ra, 8192
+; RV64IM-NEXT: lui t5, 16384
+; RV64IM-NEXT: mul t2, a0, t2
+; RV64IM-NEXT: mul t4, a0, t4
+; RV64IM-NEXT: xor t2, t4, t2
+; RV64IM-NEXT: lui t4, 32768
+; RV64IM-NEXT: mul a6, a0, a6
+; RV64IM-NEXT: mul t0, a0, t0
+; RV64IM-NEXT: xor a6, a6, t0
+; RV64IM-NEXT: lui t0, 65536
+; RV64IM-NEXT: mul a5, a0, a5
+; RV64IM-NEXT: mul a7, a0, a7
+; RV64IM-NEXT: xor a5, a5, a7
+; RV64IM-NEXT: lui a7, 131072
+; RV64IM-NEXT: mul t1, a0, t1
+; RV64IM-NEXT: mul t3, a0, t3
+; RV64IM-NEXT: xor t1, t1, t3
+; RV64IM-NEXT: lui t3, 262144
+; RV64IM-NEXT: mul a3, a0, a3
+; RV64IM-NEXT: mul a4, a0, a4
+; RV64IM-NEXT: xor a6, t2, a6
+; RV64IM-NEXT: sd a6, 336(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a6, a2, 11
+; RV64IM-NEXT: sd a6, 216(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and s7, a1, s7
+; RV64IM-NEXT: and a6, a1, t6
+; RV64IM-NEXT: sd a6, 288(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and s0, a1, s0
+; RV64IM-NEXT: and s1, a1, s1
+; RV64IM-NEXT: and s2, a1, s2
+; RV64IM-NEXT: and s3, a1, s3
+; RV64IM-NEXT: and a6, a1, s4
+; RV64IM-NEXT: sd a6, 280(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a6, a1, s5
+; RV64IM-NEXT: and t2, a1, s6
+; RV64IM-NEXT: and s8, a1, s8
+; RV64IM-NEXT: and t6, a1, s9
+; RV64IM-NEXT: sd t6, 272(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and t6, a1, s10
+; RV64IM-NEXT: sd t6, 264(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and t6, a1, s11
+; RV64IM-NEXT: sd t6, 256(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and t6, a1, ra
+; RV64IM-NEXT: and t5, a1, t5
+; RV64IM-NEXT: and t4, a1, t4
+; RV64IM-NEXT: sd t4, 248(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and t0, a1, t0
+; RV64IM-NEXT: sd t0, 240(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a7, a1, a7
+; RV64IM-NEXT: sd a7, 232(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a7, a1, t3
+; RV64IM-NEXT: sd a7, 224(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: xor a3, a5, a3
+; RV64IM-NEXT: sd a3, 328(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli t4, a2, 32
+; RV64IM-NEXT: xor a3, t1, a4
+; RV64IM-NEXT: sd a3, 320(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli s4, a2, 33
+; RV64IM-NEXT: mul a3, a0, s0
+; RV64IM-NEXT: mul a4, a0, s1
+; RV64IM-NEXT: xor a3, a3, a4
+; RV64IM-NEXT: sd a3, 312(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli s0, a2, 34
+; RV64IM-NEXT: mul a3, a0, a6
+; RV64IM-NEXT: mul a4, a0, t2
+; RV64IM-NEXT: xor a3, a3, a4
+; RV64IM-NEXT: sd a3, 304(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli s1, a2, 35
+; RV64IM-NEXT: mul a3, a0, t6
+; RV64IM-NEXT: mul a4, a0, t5
+; RV64IM-NEXT: xor a3, a3, a4
+; RV64IM-NEXT: sd a3, 296(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli t5, a2, 36
+; RV64IM-NEXT: slli t6, a2, 37
+; RV64IM-NEXT: slli s5, a2, 38
+; RV64IM-NEXT: slli s6, a2, 39
+; RV64IM-NEXT: slli s9, a2, 40
+; RV64IM-NEXT: slli s10, a2, 41
+; RV64IM-NEXT: slli s11, a2, 42
+; RV64IM-NEXT: slli ra, a2, 43
+; RV64IM-NEXT: slli a3, a2, 44
+; RV64IM-NEXT: sd a3, 208(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a2, 45
+; RV64IM-NEXT: sd a3, 200(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a2, 46
+; RV64IM-NEXT: sd a3, 192(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a2, 47
+; RV64IM-NEXT: sd a3, 184(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a2, 48
+; RV64IM-NEXT: sd a3, 176(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a2, 49
+; RV64IM-NEXT: sd a3, 168(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a2, 50
+; RV64IM-NEXT: sd a3, 160(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a2, 51
+; RV64IM-NEXT: sd a3, 152(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a2, 52
+; RV64IM-NEXT: sd a3, 144(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a2, 53
+; RV64IM-NEXT: sd a3, 136(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a2, 54
+; RV64IM-NEXT: sd a3, 128(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli t1, a2, 55
+; RV64IM-NEXT: slli t0, a2, 56
+; RV64IM-NEXT: slli a7, a2, 57
+; RV64IM-NEXT: slli a6, a2, 58
+; RV64IM-NEXT: slli a5, a2, 59
+; RV64IM-NEXT: slli a4, a2, 60
+; RV64IM-NEXT: slli a3, a2, 61
+; RV64IM-NEXT: slli a2, a2, 62
+; RV64IM-NEXT: ld t2, 216(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and t3, a1, t2
+; RV64IM-NEXT: and t2, a1, t4
+; RV64IM-NEXT: sd t2, 120(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and t4, a1, s4
+; RV64IM-NEXT: and s0, a1, s0
+; RV64IM-NEXT: sd s0, 112(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and s1, a1, s1
+; RV64IM-NEXT: sd s1, 104(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and t2, a1, t5
+; RV64IM-NEXT: sd t2, 96(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and s1, a1, t6
+; RV64IM-NEXT: and t2, a1, s5
+; RV64IM-NEXT: sd t2, 88(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and t2, a1, s6
+; RV64IM-NEXT: sd t2, 80(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and s4, a1, s9
+; RV64IM-NEXT: and s5, a1, s10
+; RV64IM-NEXT: and s6, a1, s11
+; RV64IM-NEXT: and t6, a1, ra
+; RV64IM-NEXT: ld t2, 208(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and t2, a1, t2
+; RV64IM-NEXT: sd t2, 72(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld t2, 200(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and t2, a1, t2
+; RV64IM-NEXT: sd t2, 64(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld t2, 192(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s10, a1, t2
+; RV64IM-NEXT: ld t2, 184(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s11, a1, t2
+; RV64IM-NEXT: ld t2, 176(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and ra, a1, t2
+; RV64IM-NEXT: ld t2, 168(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and t2, a1, t2
+; RV64IM-NEXT: sd t2, 184(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld t2, 160(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and t2, a1, t2
+; RV64IM-NEXT: sd t2, 160(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld t2, 152(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and t2, a1, t2
+; RV64IM-NEXT: sd t2, 152(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld t2, 144(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and t2, a1, t2
+; RV64IM-NEXT: sd t2, 144(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld t2, 136(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and t2, a1, t2
+; RV64IM-NEXT: sd t2, 136(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld t2, 128(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and t2, a1, t2
+; RV64IM-NEXT: sd t2, 128(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and t1, a1, t1
+; RV64IM-NEXT: and t0, a1, t0
+; RV64IM-NEXT: sd t0, 56(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a7, a1, a7
+; RV64IM-NEXT: sd a7, 48(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a6, a1, a6
+; RV64IM-NEXT: and a5, a1, a5
+; RV64IM-NEXT: sd a5, 40(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a4, a1, a4
+; RV64IM-NEXT: sd a4, 32(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a3, a1, a3
+; RV64IM-NEXT: sd a3, 24(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a2, a1, a2
+; RV64IM-NEXT: sd a2, 16(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi a2, a1, 1024
+; RV64IM-NEXT: srliw a3, a1, 31
+; RV64IM-NEXT: srli a1, a1, 63
+; RV64IM-NEXT: mul s9, a0, a2
+; RV64IM-NEXT: slli a3, a3, 31
+; RV64IM-NEXT: slli a1, a1, 63
+; RV64IM-NEXT: mul s7, a0, s7
+; RV64IM-NEXT: ld a2, 288(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, a0, a2
+; RV64IM-NEXT: sd a2, 192(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul s2, a0, s2
+; RV64IM-NEXT: mul a2, a0, s3
+; RV64IM-NEXT: sd a2, 176(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 280(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, a0, a2
+; RV64IM-NEXT: sd a2, 216(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul s0, a0, s8
+; RV64IM-NEXT: ld a2, 272(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, a0, a2
+; RV64IM-NEXT: sd a2, 8(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 264(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, a0, a2
+; RV64IM-NEXT: sd a2, 208(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 256(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, a0, a2
+; RV64IM-NEXT: sd a2, 272(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 248(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul t2, a0, a2
+; RV64IM-NEXT: ld a2, 240(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, a0, a2
+; RV64IM-NEXT: sd a2, 0(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 232(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, a0, a2
+; RV64IM-NEXT: sd a2, 200(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 224(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, a0, a2
+; RV64IM-NEXT: sd a2, 256(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a2, a0, a3
+; RV64IM-NEXT: sd a2, 280(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a1, a0, a1
+; RV64IM-NEXT: sd a1, 288(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a5, a0, t3
+; RV64IM-NEXT: ld a1, 120(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a7, a0, a1
+; RV64IM-NEXT: mul t4, a0, t4
+; RV64IM-NEXT: ld a1, 112(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul t5, a0, a1
+; RV64IM-NEXT: ld a1, 104(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a1, a0, a1
+; RV64IM-NEXT: sd a1, 120(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a1, 96(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a1, a0, a1
+; RV64IM-NEXT: sd a1, 224(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a1, a0, s1
+; RV64IM-NEXT: sd a1, 240(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a1, 88(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a1, a0, a1
+; RV64IM-NEXT: sd a1, 264(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a1, 80(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul s1, a0, a1
+; RV64IM-NEXT: mul s4, a0, s4
+; RV64IM-NEXT: mul s5, a0, s5
+; RV64IM-NEXT: mul s6, a0, s6
+; RV64IM-NEXT: mul a1, a0, t6
+; RV64IM-NEXT: sd a1, 112(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a1, 72(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a1, a0, a1
+; RV64IM-NEXT: sd a1, 168(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a1, 64(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a1, a0, a1
+; RV64IM-NEXT: sd a1, 232(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a1, a0, s10
+; RV64IM-NEXT: sd a1, 248(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul s10, a0, s11
+; RV64IM-NEXT: mul s11, a0, ra
+; RV64IM-NEXT: ld a1, 184(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul ra, a0, a1
+; RV64IM-NEXT: ld a1, 160(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul t0, a0, a1
+; RV64IM-NEXT: ld a1, 152(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul t3, a0, a1
+; RV64IM-NEXT: ld a1, 144(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul s3, a0, a1
+; RV64IM-NEXT: ld a1, 136(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a1, a0, a1
+; RV64IM-NEXT: sd a1, 152(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a1, 128(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a1, a0, a1
+; RV64IM-NEXT: sd a1, 160(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a1, a0, t1
+; RV64IM-NEXT: sd a1, 184(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a1, 56(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, a0, a1
+; RV64IM-NEXT: ld a1, 48(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a1, a0, a1
+; RV64IM-NEXT: mul a3, a0, a6
+; RV64IM-NEXT: ld a4, 40(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a4, a0, a4
+; RV64IM-NEXT: ld a6, 32(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a6, a0, a6
+; RV64IM-NEXT: ld t1, 24(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul t1, a0, t1
+; RV64IM-NEXT: ld t6, 16(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul t6, a0, t6
+; RV64IM-NEXT: ld a0, 336(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s8, 328(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a0, a0, s8
+; RV64IM-NEXT: ld s8, 320(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s9, s8, s9
+; RV64IM-NEXT: xor a5, a5, s7
+; RV64IM-NEXT: ld s7, 312(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s2, s7, s2
+; RV64IM-NEXT: ld s7, 304(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s0, s7, s0
+; RV64IM-NEXT: ld s7, 296(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor t2, s7, t2
+; RV64IM-NEXT: xor a7, a7, t4
+; RV64IM-NEXT: xor t4, s1, s4
+; RV64IM-NEXT: xor s1, s10, s11
+; RV64IM-NEXT: xor a1, a2, a1
+; RV64IM-NEXT: xor a0, a0, s9
+; RV64IM-NEXT: ld a2, 192(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a5, a2
+; RV64IM-NEXT: ld a5, 176(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a5, s2, a5
+; RV64IM-NEXT: ld s2, 8(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s0, s0, s2
+; RV64IM-NEXT: ld s2, 0(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor t2, t2, s2
+; RV64IM-NEXT: xor a7, a7, t5
+; RV64IM-NEXT: xor t4, t4, s5
+; RV64IM-NEXT: xor t5, s1, ra
+; RV64IM-NEXT: xor a1, a1, a3
+; RV64IM-NEXT: xor a0, a0, a2
+; RV64IM-NEXT: ld a2, 216(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a5, a2
+; RV64IM-NEXT: ld a3, 208(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, s0, a3
+; RV64IM-NEXT: ld a5, 200(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a5, t2, a5
+; RV64IM-NEXT: ld t2, 120(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a7, a7, t2
+; RV64IM-NEXT: xor t2, t4, s6
+; RV64IM-NEXT: xor t0, t5, t0
+; RV64IM-NEXT: xor a1, a1, a4
+; RV64IM-NEXT: xor a0, a0, a2
+; RV64IM-NEXT: ld a2, 272(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a3, a2
+; RV64IM-NEXT: ld a3, 256(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a5, a3
+; RV64IM-NEXT: ld a4, 224(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, a7, a4
+; RV64IM-NEXT: ld a5, 112(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a5, t2, a5
+; RV64IM-NEXT: xor a7, t0, t3
+; RV64IM-NEXT: xor a1, a1, a6
+; RV64IM-NEXT: xor a0, a0, a2
+; RV64IM-NEXT: ld a2, 280(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a3, a2
+; RV64IM-NEXT: ld a3, 240(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a4, a3
+; RV64IM-NEXT: ld a4, 168(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, a5, a4
+; RV64IM-NEXT: xor a5, a7, s3
+; RV64IM-NEXT: xor a1, a1, t1
+; RV64IM-NEXT: xor a0, a0, a2
+; RV64IM-NEXT: ld a2, 264(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a3, a2
+; RV64IM-NEXT: ld a3, 232(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a4, a3
+; RV64IM-NEXT: ld a4, 152(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, a5, a4
+; RV64IM-NEXT: xor a1, a1, t6
+; RV64IM-NEXT: xor a0, a0, a2
+; RV64IM-NEXT: ld a2, 248(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a3, a2
+; RV64IM-NEXT: ld a3, 160(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a4, a3
+; RV64IM-NEXT: xor a0, a0, a2
+; RV64IM-NEXT: ld a2, 184(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a3, a2
+; RV64IM-NEXT: xor a0, a0, a2
+; RV64IM-NEXT: ld a2, 288(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a1, a1, a2
+; RV64IM-NEXT: xor a0, a0, a1
+; RV64IM-NEXT: ld ra, 440(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s0, 432(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s1, 424(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s2, 416(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s3, 408(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s4, 400(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s5, 392(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s6, 384(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s7, 376(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s8, 368(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s9, 360(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s10, 352(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s11, 344(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: addi sp, sp, 448
+; RV64IM-NEXT: ret
+ %res = call i8 @llvm.clmul.i8(i8 %a, i8 %b)
+ ret i8 %res
+}
+
+define i16 @clmul_i16(i16 %a, i16 %b) nounwind {
+; RV32IM-LABEL: clmul_i16:
+; RV32IM: # %bb.0:
+; RV32IM-NEXT: addi sp, sp, -48
+; RV32IM-NEXT: sw s0, 44(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s1, 40(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s2, 36(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s3, 32(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s4, 28(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s5, 24(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s6, 20(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s7, 16(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s8, 12(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s9, 8(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s10, 4(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi t6, a1, 2
+; RV32IM-NEXT: andi s1, a1, 1
+; RV32IM-NEXT: andi a7, a1, 4
+; RV32IM-NEXT: andi t2, a1, 8
+; RV32IM-NEXT: andi t0, a1, 16
+; RV32IM-NEXT: andi t3, a1, 32
+; RV32IM-NEXT: andi a2, a1, 64
+; RV32IM-NEXT: andi t4, a1, 128
+; RV32IM-NEXT: andi s0, a1, 256
+; RV32IM-NEXT: andi a3, a1, 512
+; RV32IM-NEXT: li a4, 1
+; RV32IM-NEXT: lui a5, 1
+; RV32IM-NEXT: lui a6, 2
+; RV32IM-NEXT: lui t1, 4
+; RV32IM-NEXT: lui t5, 8
+; RV32IM-NEXT: lui s2, 16
+; RV32IM-NEXT: lui s3, 32
+; RV32IM-NEXT: lui s4, 64
+; RV32IM-NEXT: lui s5, 128
+; RV32IM-NEXT: lui s6, 256
+; RV32IM-NEXT: lui s7, 512
+; RV32IM-NEXT: lui s8, 1024
+; RV32IM-NEXT: lui s9, 2048
+; RV32IM-NEXT: lui s10, 4096
+; RV32IM-NEXT: mul t6, a0, t6
+; RV32IM-NEXT: mul s1, a0, s1
+; RV32IM-NEXT: xor t6, s1, t6
+; RV32IM-NEXT: lui s1, 8192
+; RV32IM-NEXT: mul a7, a0, a7
+; RV32IM-NEXT: mul t2, a0, t2
+; RV32IM-NEXT: xor a7, a7, t2
+; RV32IM-NEXT: lui t2, 16384
+; RV32IM-NEXT: mul t0, a0, t0
+; RV32IM-NEXT: mul t3, a0, t3
+; RV32IM-NEXT: xor t0, t0, t3
+; RV32IM-NEXT: lui t3, 32768
+; RV32IM-NEXT: mul t4, a0, t4
+; RV32IM-NEXT: mul s0, a0, s0
+; RV32IM-NEXT: xor t4, t4, s0
+; RV32IM-NEXT: lui s0, 65536
+; RV32IM-NEXT: xor a7, t6, a7
+; RV32IM-NEXT: lui t6, 131072
+; RV32IM-NEXT: mul a2, a0, a2
+; RV32IM-NEXT: xor a2, t0, a2
+; RV32IM-NEXT: lui t0, 262144
+; RV32IM-NEXT: mul a3, a0, a3
+; RV32IM-NEXT: xor a3, t4, a3
+; RV32IM-NEXT: lui t4, 524288
+; RV32IM-NEXT: slli a4, a4, 11
+; RV32IM-NEXT: and a5, a1, a5
+; RV32IM-NEXT: and a6, a1, a6
+; RV32IM-NEXT: and t1, a1, t1
+; RV32IM-NEXT: and t5, a1, t5
+; RV32IM-NEXT: and s2, a1, s2
+; RV32IM-NEXT: and s3, a1, s3
+; RV32IM-NEXT: and s4, a1, s4
+; RV32IM-NEXT: and s5, a1, s5
+; RV32IM-NEXT: and s6, a1, s6
+; RV32IM-NEXT: and s7, a1, s7
+; RV32IM-NEXT: and s8, a1, s8
+; RV32IM-NEXT: and s9, a1, s9
+; RV32IM-NEXT: and s10, a1, s10
+; RV32IM-NEXT: and s1, a1, s1
+; RV32IM-NEXT: and t2, a1, t2
+; RV32IM-NEXT: and t3, a1, t3
+; RV32IM-NEXT: and s0, a1, s0
+; RV32IM-NEXT: and t6, a1, t6
+; RV32IM-NEXT: and t0, a1, t0
+; RV32IM-NEXT: and t4, a1, t4
+; RV32IM-NEXT: and a4, a1, a4
+; RV32IM-NEXT: andi a1, a1, 1024
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: mul a5, a0, a5
+; RV32IM-NEXT: mul a6, a0, a6
+; RV32IM-NEXT: mul t1, a0, t1
+; RV32IM-NEXT: mul t5, a0, t5
+; RV32IM-NEXT: mul s2, a0, s2
+; RV32IM-NEXT: mul s3, a0, s3
+; RV32IM-NEXT: mul s4, a0, s4
+; RV32IM-NEXT: mul s5, a0, s5
+; RV32IM-NEXT: mul s6, a0, s6
+; RV32IM-NEXT: mul s7, a0, s7
+; RV32IM-NEXT: mul s8, a0, s8
+; RV32IM-NEXT: mul s9, a0, s9
+; RV32IM-NEXT: mul s10, a0, s10
+; RV32IM-NEXT: mul s1, a0, s1
+; RV32IM-NEXT: mul t2, a0, t2
+; RV32IM-NEXT: mul t3, a0, t3
+; RV32IM-NEXT: mul s0, a0, s0
+; RV32IM-NEXT: mul t6, a0, t6
+; RV32IM-NEXT: mul t0, a0, t0
+; RV32IM-NEXT: mul t4, a0, t4
+; RV32IM-NEXT: mul a0, a0, a4
+; RV32IM-NEXT: xor a4, t1, t5
+; RV32IM-NEXT: xor t1, s5, s6
+; RV32IM-NEXT: xor t2, s1, t2
+; RV32IM-NEXT: xor a2, a7, a2
+; RV32IM-NEXT: xor a1, a3, a1
+; RV32IM-NEXT: xor a0, a0, a5
+; RV32IM-NEXT: xor a3, a4, s2
+; RV32IM-NEXT: xor a4, t1, s7
+; RV32IM-NEXT: xor a5, t2, t3
+; RV32IM-NEXT: xor a1, a2, a1
+; RV32IM-NEXT: xor a0, a0, a6
+; RV32IM-NEXT: xor a2, a3, s3
+; RV32IM-NEXT: xor a3, a4, s8
+; RV32IM-NEXT: xor a5, a5, s0
+; RV32IM-NEXT: xor a0, a1, a0
+; RV32IM-NEXT: xor a1, a2, s4
+; RV32IM-NEXT: xor a2, a3, s9
+; RV32IM-NEXT: xor a3, a5, t6
+; RV32IM-NEXT: xor a0, a0, a1
+; RV32IM-NEXT: xor a1, a2, s10
+; RV32IM-NEXT: xor a2, a3, t0
+; RV32IM-NEXT: xor a0, a0, a1
+; RV32IM-NEXT: xor a1, a2, t4
+; RV32IM-NEXT: xor a0, a0, a1
+; RV32IM-NEXT: lw s0, 44(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s1, 40(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s2, 36(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s3, 32(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s4, 28(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s5, 24(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s6, 20(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s7, 16(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s8, 12(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s9, 8(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s10, 4(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: addi sp, sp, 48
+; RV32IM-NEXT: ret
+;
+; RV64IM-LABEL: clmul_i16:
+; RV64IM: # %bb.0:
+; RV64IM-NEXT: addi sp, sp, -448
+; RV64IM-NEXT: sd ra, 440(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s0, 432(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s1, 424(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s2, 416(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s3, 408(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s4, 400(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s5, 392(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s6, 384(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s7, 376(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s8, 368(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s9, 360(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s10, 352(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s11, 344(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi t2, a1, 2
+; RV64IM-NEXT: andi t4, a1, 1
+; RV64IM-NEXT: andi a6, a1, 4
+; RV64IM-NEXT: andi t0, a1, 8
+; RV64IM-NEXT: andi a5, a1, 16
+; RV64IM-NEXT: andi a7, a1, 32
+; RV64IM-NEXT: andi a3, a1, 64
+; RV64IM-NEXT: andi t1, a1, 128
+; RV64IM-NEXT: andi t3, a1, 256
+; RV64IM-NEXT: andi a4, a1, 512
+; RV64IM-NEXT: li a2, 1
+; RV64IM-NEXT: lui s7, 1
+; RV64IM-NEXT: lui t6, 2
+; RV64IM-NEXT: lui s0, 4
+; RV64IM-NEXT: lui s1, 8
+; RV64IM-NEXT: lui s2, 16
+; RV64IM-NEXT: lui s3, 32
+; RV64IM-NEXT: lui s4, 64
+; RV64IM-NEXT: lui s5, 128
+; RV64IM-NEXT: lui s6, 256
+; RV64IM-NEXT: lui s8, 512
+; RV64IM-NEXT: lui s9, 1024
+; RV64IM-NEXT: lui s10, 2048
+; RV64IM-NEXT: lui s11, 4096
+; RV64IM-NEXT: lui ra, 8192
+; RV64IM-NEXT: lui t5, 16384
+; RV64IM-NEXT: mul t2, a0, t2
+; RV64IM-NEXT: mul t4, a0, t4
+; RV64IM-NEXT: xor t2, t4, t2
+; RV64IM-NEXT: lui t4, 32768
+; RV64IM-NEXT: mul a6, a0, a6
+; RV64IM-NEXT: mul t0, a0, t0
+; RV64IM-NEXT: xor a6, a6, t0
+; RV64IM-NEXT: lui t0, 65536
+; RV64IM-NEXT: mul a5, a0, a5
+; RV64IM-NEXT: mul a7, a0, a7
+; RV64IM-NEXT: xor a5, a5, a7
+; RV64IM-NEXT: lui a7, 131072
+; RV64IM-NEXT: mul t1, a0, t1
+; RV64IM-NEXT: mul t3, a0, t3
+; RV64IM-NEXT: xor t1, t1, t3
+; RV64IM-NEXT: lui t3, 262144
+; RV64IM-NEXT: mul a3, a0, a3
+; RV64IM-NEXT: mul a4, a0, a4
+; RV64IM-NEXT: xor a6, t2, a6
+; RV64IM-NEXT: sd a6, 336(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a6, a2, 11
+; RV64IM-NEXT: sd a6, 216(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and s7, a1, s7
+; RV64IM-NEXT: and a6, a1, t6
+; RV64IM-NEXT: sd a6, 288(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and s0, a1, s0
+; RV64IM-NEXT: and s1, a1, s1
+; RV64IM-NEXT: and s2, a1, s2
+; RV64IM-NEXT: and s3, a1, s3
+; RV64IM-NEXT: and a6, a1, s4
+; RV64IM-NEXT: sd a6, 280(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a6, a1, s5
+; RV64IM-NEXT: and t2, a1, s6
+; RV64IM-NEXT: and s8, a1, s8
+; RV64IM-NEXT: and t6, a1, s9
+; RV64IM-NEXT: sd t6, 272(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and t6, a1, s10
+; RV64IM-NEXT: sd t6, 264(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and t6, a1, s11
+; RV64IM-NEXT: sd t6, 256(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and t6, a1, ra
+; RV64IM-NEXT: and t5, a1, t5
+; RV64IM-NEXT: and t4, a1, t4
+; RV64IM-NEXT: sd t4, 248(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and t0, a1, t0
+; RV64IM-NEXT: sd t0, 240(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a7, a1, a7
+; RV64IM-NEXT: sd a7, 232(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a7, a1, t3
+; RV64IM-NEXT: sd a7, 224(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: xor a3, a5, a3
+; RV64IM-NEXT: sd a3, 328(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli t4, a2, 32
+; RV64IM-NEXT: xor a3, t1, a4
+; RV64IM-NEXT: sd a3, 320(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli s4, a2, 33
+; RV64IM-NEXT: mul a3, a0, s0
+; RV64IM-NEXT: mul a4, a0, s1
+; RV64IM-NEXT: xor a3, a3, a4
+; RV64IM-NEXT: sd a3, 312(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli s0, a2, 34
+; RV64IM-NEXT: mul a3, a0, a6
+; RV64IM-NEXT: mul a4, a0, t2
+; RV64IM-NEXT: xor a3, a3, a4
+; RV64IM-NEXT: sd a3, 304(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli s1, a2, 35
+; RV64IM-NEXT: mul a3, a0, t6
+; RV64IM-NEXT: mul a4, a0, t5
+; RV64IM-NEXT: xor a3, a3, a4
+; RV64IM-NEXT: sd a3, 296(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli t5, a2, 36
+; RV64IM-NEXT: slli t6, a2, 37
+; RV64IM-NEXT: slli s5, a2, 38
+; RV64IM-NEXT: slli s6, a2, 39
+; RV64IM-NEXT: slli s9, a2, 40
+; RV64IM-NEXT: slli s10, a2, 41
+; RV64IM-NEXT: slli s11, a2, 42
+; RV64IM-NEXT: slli ra, a2, 43
+; RV64IM-NEXT: slli a3, a2, 44
+; RV64IM-NEXT: sd a3, 208(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a2, 45
+; RV64IM-NEXT: sd a3, 200(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a2, 46
+; RV64IM-NEXT: sd a3, 192(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a2, 47
+; RV64IM-NEXT: sd a3, 184(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a2, 48
+; RV64IM-NEXT: sd a3, 176(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a2, 49
+; RV64IM-NEXT: sd a3, 168(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a2, 50
+; RV64IM-NEXT: sd a3, 160(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a2, 51
+; RV64IM-NEXT: sd a3, 152(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a2, 52
+; RV64IM-NEXT: sd a3, 144(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a2, 53
+; RV64IM-NEXT: sd a3, 136(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a2, 54
+; RV64IM-NEXT: sd a3, 128(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli t1, a2, 55
+; RV64IM-NEXT: slli t0, a2, 56
+; RV64IM-NEXT: slli a7, a2, 57
+; RV64IM-NEXT: slli a6, a2, 58
+; RV64IM-NEXT: slli a5, a2, 59
+; RV64IM-NEXT: slli a4, a2, 60
+; RV64IM-NEXT: slli a3, a2, 61
+; RV64IM-NEXT: slli a2, a2, 62
+; RV64IM-NEXT: ld t2, 216(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and t3, a1, t2
+; RV64IM-NEXT: and t2, a1, t4
+; RV64IM-NEXT: sd t2, 120(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and t4, a1, s4
+; RV64IM-NEXT: and s0, a1, s0
+; RV64IM-NEXT: sd s0, 112(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and s1, a1, s1
+; RV64IM-NEXT: sd s1, 104(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and t2, a1, t5
+; RV64IM-NEXT: sd t2, 96(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and s1, a1, t6
+; RV64IM-NEXT: and t2, a1, s5
+; RV64IM-NEXT: sd t2, 88(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and t2, a1, s6
+; RV64IM-NEXT: sd t2, 80(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and s4, a1, s9
+; RV64IM-NEXT: and s5, a1, s10
+; RV64IM-NEXT: and s6, a1, s11
+; RV64IM-NEXT: and t6, a1, ra
+; RV64IM-NEXT: ld t2, 208(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and t2, a1, t2
+; RV64IM-NEXT: sd t2, 72(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld t2, 200(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and t2, a1, t2
+; RV64IM-NEXT: sd t2, 64(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld t2, 192(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s10, a1, t2
+; RV64IM-NEXT: ld t2, 184(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s11, a1, t2
+; RV64IM-NEXT: ld t2, 176(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and ra, a1, t2
+; RV64IM-NEXT: ld t2, 168(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and t2, a1, t2
+; RV64IM-NEXT: sd t2, 184(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld t2, 160(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and t2, a1, t2
+; RV64IM-NEXT: sd t2, 160(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld t2, 152(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and t2, a1, t2
+; RV64IM-NEXT: sd t2, 152(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld t2, 144(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and t2, a1, t2
+; RV64IM-NEXT: sd t2, 144(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld t2, 136(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and t2, a1, t2
+; RV64IM-NEXT: sd t2, 136(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld t2, 128(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and t2, a1, t2
+; RV64IM-NEXT: sd t2, 128(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and t1, a1, t1
+; RV64IM-NEXT: and t0, a1, t0
+; RV64IM-NEXT: sd t0, 56(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a7, a1, a7
+; RV64IM-NEXT: sd a7, 48(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a6, a1, a6
+; RV64IM-NEXT: and a5, a1, a5
+; RV64IM-NEXT: sd a5, 40(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a4, a1, a4
+; RV64IM-NEXT: sd a4, 32(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a3, a1, a3
+; RV64IM-NEXT: sd a3, 24(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a2, a1, a2
+; RV64IM-NEXT: sd a2, 16(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi a2, a1, 1024
+; RV64IM-NEXT: srliw a3, a1, 31
+; RV64IM-NEXT: srli a1, a1, 63
+; RV64IM-NEXT: mul s9, a0, a2
+; RV64IM-NEXT: slli a3, a3, 31
+; RV64IM-NEXT: slli a1, a1, 63
+; RV64IM-NEXT: mul s7, a0, s7
+; RV64IM-NEXT: ld a2, 288(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, a0, a2
+; RV64IM-NEXT: sd a2, 192(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul s2, a0, s2
+; RV64IM-NEXT: mul a2, a0, s3
+; RV64IM-NEXT: sd a2, 176(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 280(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, a0, a2
+; RV64IM-NEXT: sd a2, 216(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul s0, a0, s8
+; RV64IM-NEXT: ld a2, 272(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, a0, a2
+; RV64IM-NEXT: sd a2, 8(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 264(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, a0, a2
+; RV64IM-NEXT: sd a2, 208(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 256(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, a0, a2
+; RV64IM-NEXT: sd a2, 272(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 248(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul t2, a0, a2
+; RV64IM-NEXT: ld a2, 240(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, a0, a2
+; RV64IM-NEXT: sd a2, 0(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 232(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, a0, a2
+; RV64IM-NEXT: sd a2, 200(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 224(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, a0, a2
+; RV64IM-NEXT: sd a2, 256(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a2, a0, a3
+; RV64IM-NEXT: sd a2, 280(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a1, a0, a1
+; RV64IM-NEXT: sd a1, 288(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a5, a0, t3
+; RV64IM-NEXT: ld a1, 120(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a7, a0, a1
+; RV64IM-NEXT: mul t4, a0, t4
+; RV64IM-NEXT: ld a1, 112(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul t5, a0, a1
+; RV64IM-NEXT: ld a1, 104(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a1, a0, a1
+; RV64IM-NEXT: sd a1, 120(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a1, 96(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a1, a0, a1
+; RV64IM-NEXT: sd a1, 224(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a1, a0, s1
+; RV64IM-NEXT: sd a1, 240(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a1, 88(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a1, a0, a1
+; RV64IM-NEXT: sd a1, 264(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a1, 80(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul s1, a0, a1
+; RV64IM-NEXT: mul s4, a0, s4
+; RV64IM-NEXT: mul s5, a0, s5
+; RV64IM-NEXT: mul s6, a0, s6
+; RV64IM-NEXT: mul a1, a0, t6
+; RV64IM-NEXT: sd a1, 112(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a1, 72(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a1, a0, a1
+; RV64IM-NEXT: sd a1, 168(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a1, 64(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a1, a0, a1
+; RV64IM-NEXT: sd a1, 232(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a1, a0, s10
+; RV64IM-NEXT: sd a1, 248(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul s10, a0, s11
+; RV64IM-NEXT: mul s11, a0, ra
+; RV64IM-NEXT: ld a1, 184(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul ra, a0, a1
+; RV64IM-NEXT: ld a1, 160(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul t0, a0, a1
+; RV64IM-NEXT: ld a1, 152(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul t3, a0, a1
+; RV64IM-NEXT: ld a1, 144(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul s3, a0, a1
+; RV64IM-NEXT: ld a1, 136(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a1, a0, a1
+; RV64IM-NEXT: sd a1, 152(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a1, 128(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a1, a0, a1
+; RV64IM-NEXT: sd a1, 160(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a1, a0, t1
+; RV64IM-NEXT: sd a1, 184(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a1, 56(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, a0, a1
+; RV64IM-NEXT: ld a1, 48(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a1, a0, a1
+; RV64IM-NEXT: mul a3, a0, a6
+; RV64IM-NEXT: ld a4, 40(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a4, a0, a4
+; RV64IM-NEXT: ld a6, 32(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a6, a0, a6
+; RV64IM-NEXT: ld t1, 24(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul t1, a0, t1
+; RV64IM-NEXT: ld t6, 16(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul t6, a0, t6
+; RV64IM-NEXT: ld a0, 336(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s8, 328(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a0, a0, s8
+; RV64IM-NEXT: ld s8, 320(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s9, s8, s9
+; RV64IM-NEXT: xor a5, a5, s7
+; RV64IM-NEXT: ld s7, 312(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s2, s7, s2
+; RV64IM-NEXT: ld s7, 304(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s0, s7, s0
+; RV64IM-NEXT: ld s7, 296(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor t2, s7, t2
+; RV64IM-NEXT: xor a7, a7, t4
+; RV64IM-NEXT: xor t4, s1, s4
+; RV64IM-NEXT: xor s1, s10, s11
+; RV64IM-NEXT: xor a1, a2, a1
+; RV64IM-NEXT: xor a0, a0, s9
+; RV64IM-NEXT: ld a2, 192(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a5, a2
+; RV64IM-NEXT: ld a5, 176(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a5, s2, a5
+; RV64IM-NEXT: ld s2, 8(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s0, s0, s2
+; RV64IM-NEXT: ld s2, 0(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor t2, t2, s2
+; RV64IM-NEXT: xor a7, a7, t5
+; RV64IM-NEXT: xor t4, t4, s5
+; RV64IM-NEXT: xor t5, s1, ra
+; RV64IM-NEXT: xor a1, a1, a3
+; RV64IM-NEXT: xor a0, a0, a2
+; RV64IM-NEXT: ld a2, 216(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a5, a2
+; RV64IM-NEXT: ld a3, 208(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, s0, a3
+; RV64IM-NEXT: ld a5, 200(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a5, t2, a5
+; RV64IM-NEXT: ld t2, 120(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a7, a7, t2
+; RV64IM-NEXT: xor t2, t4, s6
+; RV64IM-NEXT: xor t0, t5, t0
+; RV64IM-NEXT: xor a1, a1, a4
+; RV64IM-NEXT: xor a0, a0, a2
+; RV64IM-NEXT: ld a2, 272(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a3, a2
+; RV64IM-NEXT: ld a3, 256(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a5, a3
+; RV64IM-NEXT: ld a4, 224(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, a7, a4
+; RV64IM-NEXT: ld a5, 112(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a5, t2, a5
+; RV64IM-NEXT: xor a7, t0, t3
+; RV64IM-NEXT: xor a1, a1, a6
+; RV64IM-NEXT: xor a0, a0, a2
+; RV64IM-NEXT: ld a2, 280(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a3, a2
+; RV64IM-NEXT: ld a3, 240(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a4, a3
+; RV64IM-NEXT: ld a4, 168(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, a5, a4
+; RV64IM-NEXT: xor a5, a7, s3
+; RV64IM-NEXT: xor a1, a1, t1
+; RV64IM-NEXT: xor a0, a0, a2
+; RV64IM-NEXT: ld a2, 264(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a3, a2
+; RV64IM-NEXT: ld a3, 232(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a4, a3
+; RV64IM-NEXT: ld a4, 152(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, a5, a4
+; RV64IM-NEXT: xor a1, a1, t6
+; RV64IM-NEXT: xor a0, a0, a2
+; RV64IM-NEXT: ld a2, 248(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a3, a2
+; RV64IM-NEXT: ld a3, 160(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a4, a3
+; RV64IM-NEXT: xor a0, a0, a2
+; RV64IM-NEXT: ld a2, 184(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a3, a2
+; RV64IM-NEXT: xor a0, a0, a2
+; RV64IM-NEXT: ld a2, 288(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a1, a1, a2
+; RV64IM-NEXT: xor a0, a0, a1
+; RV64IM-NEXT: ld ra, 440(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s0, 432(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s1, 424(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s2, 416(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s3, 408(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s4, 400(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s5, 392(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s6, 384(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s7, 376(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s8, 368(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s9, 360(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s10, 352(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s11, 344(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: addi sp, sp, 448
+; RV64IM-NEXT: ret
+ %res = call i16 @llvm.clmul.i16(i16 %a, i16 %b)
+ ret i16 %res
+}
+
+define i32 @clmul_i32(i32 %a, i32 %b) nounwind {
+; RV32IM-LABEL: clmul_i32:
+; RV32IM: # %bb.0:
+; RV32IM-NEXT: addi sp, sp, -48
+; RV32IM-NEXT: sw s0, 44(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s1, 40(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s2, 36(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s3, 32(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s4, 28(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s5, 24(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s6, 20(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s7, 16(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s8, 12(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s9, 8(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s10, 4(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi t6, a1, 2
+; RV32IM-NEXT: andi s1, a1, 1
+; RV32IM-NEXT: andi a7, a1, 4
+; RV32IM-NEXT: andi t2, a1, 8
+; RV32IM-NEXT: andi t0, a1, 16
+; RV32IM-NEXT: andi t3, a1, 32
+; RV32IM-NEXT: andi a2, a1, 64
+; RV32IM-NEXT: andi t4, a1, 128
+; RV32IM-NEXT: andi s0, a1, 256
+; RV32IM-NEXT: andi a3, a1, 512
+; RV32IM-NEXT: li a4, 1
+; RV32IM-NEXT: lui a5, 1
+; RV32IM-NEXT: lui a6, 2
+; RV32IM-NEXT: lui t1, 4
+; RV32IM-NEXT: lui t5, 8
+; RV32IM-NEXT: lui s2, 16
+; RV32IM-NEXT: lui s3, 32
+; RV32IM-NEXT: lui s4, 64
+; RV32IM-NEXT: lui s5, 128
+; RV32IM-NEXT: lui s6, 256
+; RV32IM-NEXT: lui s7, 512
+; RV32IM-NEXT: lui s8, 1024
+; RV32IM-NEXT: lui s9, 2048
+; RV32IM-NEXT: lui s10, 4096
+; RV32IM-NEXT: mul t6, a0, t6
+; RV32IM-NEXT: mul s1, a0, s1
+; RV32IM-NEXT: xor t6, s1, t6
+; RV32IM-NEXT: lui s1, 8192
+; RV32IM-NEXT: mul a7, a0, a7
+; RV32IM-NEXT: mul t2, a0, t2
+; RV32IM-NEXT: xor a7, a7, t2
+; RV32IM-NEXT: lui t2, 16384
+; RV32IM-NEXT: mul t0, a0, t0
+; RV32IM-NEXT: mul t3, a0, t3
+; RV32IM-NEXT: xor t0, t0, t3
+; RV32IM-NEXT: lui t3, 32768
+; RV32IM-NEXT: mul t4, a0, t4
+; RV32IM-NEXT: mul s0, a0, s0
+; RV32IM-NEXT: xor t4, t4, s0
+; RV32IM-NEXT: lui s0, 65536
+; RV32IM-NEXT: xor a7, t6, a7
+; RV32IM-NEXT: lui t6, 131072
+; RV32IM-NEXT: mul a2, a0, a2
+; RV32IM-NEXT: xor a2, t0, a2
+; RV32IM-NEXT: lui t0, 262144
+; RV32IM-NEXT: mul a3, a0, a3
+; RV32IM-NEXT: xor a3, t4, a3
+; RV32IM-NEXT: lui t4, 524288
+; RV32IM-NEXT: slli a4, a4, 11
+; RV32IM-NEXT: and a5, a1, a5
+; RV32IM-NEXT: and a6, a1, a6
+; RV32IM-NEXT: and t1, a1, t1
+; RV32IM-NEXT: and t5, a1, t5
+; RV32IM-NEXT: and s2, a1, s2
+; RV32IM-NEXT: and s3, a1, s3
+; RV32IM-NEXT: and s4, a1, s4
+; RV32IM-NEXT: and s5, a1, s5
+; RV32IM-NEXT: and s6, a1, s6
+; RV32IM-NEXT: and s7, a1, s7
+; RV32IM-NEXT: and s8, a1, s8
+; RV32IM-NEXT: and s9, a1, s9
+; RV32IM-NEXT: and s10, a1, s10
+; RV32IM-NEXT: and s1, a1, s1
+; RV32IM-NEXT: and t2, a1, t2
+; RV32IM-NEXT: and t3, a1, t3
+; RV32IM-NEXT: and s0, a1, s0
+; RV32IM-NEXT: and t6, a1, t6
+; RV32IM-NEXT: and t0, a1, t0
+; RV32IM-NEXT: and t4, a1, t4
+; RV32IM-NEXT: and a4, a1, a4
+; RV32IM-NEXT: andi a1, a1, 1024
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: mul a5, a0, a5
+; RV32IM-NEXT: mul a6, a0, a6
+; RV32IM-NEXT: mul t1, a0, t1
+; RV32IM-NEXT: mul t5, a0, t5
+; RV32IM-NEXT: mul s2, a0, s2
+; RV32IM-NEXT: mul s3, a0, s3
+; RV32IM-NEXT: mul s4, a0, s4
+; RV32IM-NEXT: mul s5, a0, s5
+; RV32IM-NEXT: mul s6, a0, s6
+; RV32IM-NEXT: mul s7, a0, s7
+; RV32IM-NEXT: mul s8, a0, s8
+; RV32IM-NEXT: mul s9, a0, s9
+; RV32IM-NEXT: mul s10, a0, s10
+; RV32IM-NEXT: mul s1, a0, s1
+; RV32IM-NEXT: mul t2, a0, t2
+; RV32IM-NEXT: mul t3, a0, t3
+; RV32IM-NEXT: mul s0, a0, s0
+; RV32IM-NEXT: mul t6, a0, t6
+; RV32IM-NEXT: mul t0, a0, t0
+; RV32IM-NEXT: mul t4, a0, t4
+; RV32IM-NEXT: mul a0, a0, a4
+; RV32IM-NEXT: xor a4, t1, t5
+; RV32IM-NEXT: xor t1, s5, s6
+; RV32IM-NEXT: xor t2, s1, t2
+; RV32IM-NEXT: xor a2, a7, a2
+; RV32IM-NEXT: xor a1, a3, a1
+; RV32IM-NEXT: xor a0, a0, a5
+; RV32IM-NEXT: xor a3, a4, s2
+; RV32IM-NEXT: xor a4, t1, s7
+; RV32IM-NEXT: xor a5, t2, t3
+; RV32IM-NEXT: xor a1, a2, a1
+; RV32IM-NEXT: xor a0, a0, a6
+; RV32IM-NEXT: xor a2, a3, s3
+; RV32IM-NEXT: xor a3, a4, s8
+; RV32IM-NEXT: xor a5, a5, s0
+; RV32IM-NEXT: xor a0, a1, a0
+; RV32IM-NEXT: xor a1, a2, s4
+; RV32IM-NEXT: xor a2, a3, s9
+; RV32IM-NEXT: xor a3, a5, t6
+; RV32IM-NEXT: xor a0, a0, a1
+; RV32IM-NEXT: xor a1, a2, s10
+; RV32IM-NEXT: xor a2, a3, t0
+; RV32IM-NEXT: xor a0, a0, a1
+; RV32IM-NEXT: xor a1, a2, t4
+; RV32IM-NEXT: xor a0, a0, a1
+; RV32IM-NEXT: lw s0, 44(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s1, 40(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s2, 36(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s3, 32(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s4, 28(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s5, 24(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s6, 20(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s7, 16(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s8, 12(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s9, 8(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s10, 4(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: addi sp, sp, 48
+; RV32IM-NEXT: ret
+;
+; RV64IM-LABEL: clmul_i32:
+; RV64IM: # %bb.0:
+; RV64IM-NEXT: addi sp, sp, -448
+; RV64IM-NEXT: sd ra, 440(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s0, 432(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s1, 424(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s2, 416(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s3, 408(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s4, 400(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s5, 392(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s6, 384(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s7, 376(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s8, 368(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s9, 360(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s10, 352(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s11, 344(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi t2, a1, 2
+; RV64IM-NEXT: andi t4, a1, 1
+; RV64IM-NEXT: andi a6, a1, 4
+; RV64IM-NEXT: andi t0, a1, 8
+; RV64IM-NEXT: andi a5, a1, 16
+; RV64IM-NEXT: andi a7, a1, 32
+; RV64IM-NEXT: andi a3, a1, 64
+; RV64IM-NEXT: andi t1, a1, 128
+; RV64IM-NEXT: andi t3, a1, 256
+; RV64IM-NEXT: andi a4, a1, 512
+; RV64IM-NEXT: li a2, 1
+; RV64IM-NEXT: lui s7, 1
+; RV64IM-NEXT: lui t6, 2
+; RV64IM-NEXT: lui s0, 4
+; RV64IM-NEXT: lui s1, 8
+; RV64IM-NEXT: lui s2, 16
+; RV64IM-NEXT: lui s3, 32
+; RV64IM-NEXT: lui s4, 64
+; RV64IM-NEXT: lui s5, 128
+; RV64IM-NEXT: lui s6, 256
+; RV64IM-NEXT: lui s8, 512
+; RV64IM-NEXT: lui s9, 1024
+; RV64IM-NEXT: lui s10, 2048
+; RV64IM-NEXT: lui s11, 4096
+; RV64IM-NEXT: lui ra, 8192
+; RV64IM-NEXT: lui t5, 16384
+; RV64IM-NEXT: mul t2, a0, t2
+; RV64IM-NEXT: mul t4, a0, t4
+; RV64IM-NEXT: xor t2, t4, t2
+; RV64IM-NEXT: lui t4, 32768
+; RV64IM-NEXT: mul a6, a0, a6
+; RV64IM-NEXT: mul t0, a0, t0
+; RV64IM-NEXT: xor a6, a6, t0
+; RV64IM-NEXT: lui t0, 65536
+; RV64IM-NEXT: mul a5, a0, a5
+; RV64IM-NEXT: mul a7, a0, a7
+; RV64IM-NEXT: xor a5, a5, a7
+; RV64IM-NEXT: lui a7, 131072
+; RV64IM-NEXT: mul t1, a0, t1
+; RV64IM-NEXT: mul t3, a0, t3
+; RV64IM-NEXT: xor t1, t1, t3
+; RV64IM-NEXT: lui t3, 262144
+; RV64IM-NEXT: mul a3, a0, a3
+; RV64IM-NEXT: mul a4, a0, a4
+; RV64IM-NEXT: xor a6, t2, a6
+; RV64IM-NEXT: sd a6, 336(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a6, a2, 11
+; RV64IM-NEXT: sd a6, 216(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and s7, a1, s7
+; RV64IM-NEXT: and a6, a1, t6
+; RV64IM-NEXT: sd a6, 288(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and s0, a1, s0
+; RV64IM-NEXT: and s1, a1, s1
+; RV64IM-NEXT: and s2, a1, s2
+; RV64IM-NEXT: and s3, a1, s3
+; RV64IM-NEXT: and a6, a1, s4
+; RV64IM-NEXT: sd a6, 280(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a6, a1, s5
+; RV64IM-NEXT: and t2, a1, s6
+; RV64IM-NEXT: and s8, a1, s8
+; RV64IM-NEXT: and t6, a1, s9
+; RV64IM-NEXT: sd t6, 272(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and t6, a1, s10
+; RV64IM-NEXT: sd t6, 264(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and t6, a1, s11
+; RV64IM-NEXT: sd t6, 256(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and t6, a1, ra
+; RV64IM-NEXT: and t5, a1, t5
+; RV64IM-NEXT: and t4, a1, t4
+; RV64IM-NEXT: sd t4, 248(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and t0, a1, t0
+; RV64IM-NEXT: sd t0, 240(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a7, a1, a7
+; RV64IM-NEXT: sd a7, 232(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a7, a1, t3
+; RV64IM-NEXT: sd a7, 224(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: xor a3, a5, a3
+; RV64IM-NEXT: sd a3, 328(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli t4, a2, 32
+; RV64IM-NEXT: xor a3, t1, a4
+; RV64IM-NEXT: sd a3, 320(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli s4, a2, 33
+; RV64IM-NEXT: mul a3, a0, s0
+; RV64IM-NEXT: mul a4, a0, s1
+; RV64IM-NEXT: xor a3, a3, a4
+; RV64IM-NEXT: sd a3, 312(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli s0, a2, 34
+; RV64IM-NEXT: mul a3, a0, a6
+; RV64IM-NEXT: mul a4, a0, t2
+; RV64IM-NEXT: xor a3, a3, a4
+; RV64IM-NEXT: sd a3, 304(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli s1, a2, 35
+; RV64IM-NEXT: mul a3, a0, t6
+; RV64IM-NEXT: mul a4, a0, t5
+; RV64IM-NEXT: xor a3, a3, a4
+; RV64IM-NEXT: sd a3, 296(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli t5, a2, 36
+; RV64IM-NEXT: slli t6, a2, 37
+; RV64IM-NEXT: slli s5, a2, 38
+; RV64IM-NEXT: slli s6, a2, 39
+; RV64IM-NEXT: slli s9, a2, 40
+; RV64IM-NEXT: slli s10, a2, 41
+; RV64IM-NEXT: slli s11, a2, 42
+; RV64IM-NEXT: slli ra, a2, 43
+; RV64IM-NEXT: slli a3, a2, 44
+; RV64IM-NEXT: sd a3, 208(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a2, 45
+; RV64IM-NEXT: sd a3, 200(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a2, 46
+; RV64IM-NEXT: sd a3, 192(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a2, 47
+; RV64IM-NEXT: sd a3, 184(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a2, 48
+; RV64IM-NEXT: sd a3, 176(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a2, 49
+; RV64IM-NEXT: sd a3, 168(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a2, 50
+; RV64IM-NEXT: sd a3, 160(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a2, 51
+; RV64IM-NEXT: sd a3, 152(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a2, 52
+; RV64IM-NEXT: sd a3, 144(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a2, 53
+; RV64IM-NEXT: sd a3, 136(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a2, 54
+; RV64IM-NEXT: sd a3, 128(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli t1, a2, 55
+; RV64IM-NEXT: slli t0, a2, 56
+; RV64IM-NEXT: slli a7, a2, 57
+; RV64IM-NEXT: slli a6, a2, 58
+; RV64IM-NEXT: slli a5, a2, 59
+; RV64IM-NEXT: slli a4, a2, 60
+; RV64IM-NEXT: slli a3, a2, 61
+; RV64IM-NEXT: slli a2, a2, 62
+; RV64IM-NEXT: ld t2, 216(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and t3, a1, t2
+; RV64IM-NEXT: and t2, a1, t4
+; RV64IM-NEXT: sd t2, 120(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and t4, a1, s4
+; RV64IM-NEXT: and s0, a1, s0
+; RV64IM-NEXT: sd s0, 112(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and s1, a1, s1
+; RV64IM-NEXT: sd s1, 104(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and t2, a1, t5
+; RV64IM-NEXT: sd t2, 96(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and s1, a1, t6
+; RV64IM-NEXT: and t2, a1, s5
+; RV64IM-NEXT: sd t2, 88(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and t2, a1, s6
+; RV64IM-NEXT: sd t2, 80(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and s4, a1, s9
+; RV64IM-NEXT: and s5, a1, s10
+; RV64IM-NEXT: and s6, a1, s11
+; RV64IM-NEXT: and t6, a1, ra
+; RV64IM-NEXT: ld t2, 208(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and t2, a1, t2
+; RV64IM-NEXT: sd t2, 72(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld t2, 200(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and t2, a1, t2
+; RV64IM-NEXT: sd t2, 64(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld t2, 192(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s10, a1, t2
+; RV64IM-NEXT: ld t2, 184(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s11, a1, t2
+; RV64IM-NEXT: ld t2, 176(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and ra, a1, t2
+; RV64IM-NEXT: ld t2, 168(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and t2, a1, t2
+; RV64IM-NEXT: sd t2, 184(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld t2, 160(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and t2, a1, t2
+; RV64IM-NEXT: sd t2, 160(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld t2, 152(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and t2, a1, t2
+; RV64IM-NEXT: sd t2, 152(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld t2, 144(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and t2, a1, t2
+; RV64IM-NEXT: sd t2, 144(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld t2, 136(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and t2, a1, t2
+; RV64IM-NEXT: sd t2, 136(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld t2, 128(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and t2, a1, t2
+; RV64IM-NEXT: sd t2, 128(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and t1, a1, t1
+; RV64IM-NEXT: and t0, a1, t0
+; RV64IM-NEXT: sd t0, 56(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a7, a1, a7
+; RV64IM-NEXT: sd a7, 48(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a6, a1, a6
+; RV64IM-NEXT: and a5, a1, a5
+; RV64IM-NEXT: sd a5, 40(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a4, a1, a4
+; RV64IM-NEXT: sd a4, 32(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a3, a1, a3
+; RV64IM-NEXT: sd a3, 24(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a2, a1, a2
+; RV64IM-NEXT: sd a2, 16(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi a2, a1, 1024
+; RV64IM-NEXT: srliw a3, a1, 31
+; RV64IM-NEXT: srli a1, a1, 63
+; RV64IM-NEXT: mul s9, a0, a2
+; RV64IM-NEXT: slli a3, a3, 31
+; RV64IM-NEXT: slli a1, a1, 63
+; RV64IM-NEXT: mul s7, a0, s7
+; RV64IM-NEXT: ld a2, 288(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, a0, a2
+; RV64IM-NEXT: sd a2, 192(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul s2, a0, s2
+; RV64IM-NEXT: mul a2, a0, s3
+; RV64IM-NEXT: sd a2, 176(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 280(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, a0, a2
+; RV64IM-NEXT: sd a2, 216(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul s0, a0, s8
+; RV64IM-NEXT: ld a2, 272(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, a0, a2
+; RV64IM-NEXT: sd a2, 8(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 264(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, a0, a2
+; RV64IM-NEXT: sd a2, 208(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 256(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, a0, a2
+; RV64IM-NEXT: sd a2, 272(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 248(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul t2, a0, a2
+; RV64IM-NEXT: ld a2, 240(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, a0, a2
+; RV64IM-NEXT: sd a2, 0(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 232(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, a0, a2
+; RV64IM-NEXT: sd a2, 200(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 224(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, a0, a2
+; RV64IM-NEXT: sd a2, 256(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a2, a0, a3
+; RV64IM-NEXT: sd a2, 280(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a1, a0, a1
+; RV64IM-NEXT: sd a1, 288(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a5, a0, t3
+; RV64IM-NEXT: ld a1, 120(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a7, a0, a1
+; RV64IM-NEXT: mul t4, a0, t4
+; RV64IM-NEXT: ld a1, 112(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul t5, a0, a1
+; RV64IM-NEXT: ld a1, 104(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a1, a0, a1
+; RV64IM-NEXT: sd a1, 120(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a1, 96(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a1, a0, a1
+; RV64IM-NEXT: sd a1, 224(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a1, a0, s1
+; RV64IM-NEXT: sd a1, 240(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a1, 88(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a1, a0, a1
+; RV64IM-NEXT: sd a1, 264(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a1, 80(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul s1, a0, a1
+; RV64IM-NEXT: mul s4, a0, s4
+; RV64IM-NEXT: mul s5, a0, s5
+; RV64IM-NEXT: mul s6, a0, s6
+; RV64IM-NEXT: mul a1, a0, t6
+; RV64IM-NEXT: sd a1, 112(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a1, 72(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a1, a0, a1
+; RV64IM-NEXT: sd a1, 168(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a1, 64(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a1, a0, a1
+; RV64IM-NEXT: sd a1, 232(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a1, a0, s10
+; RV64IM-NEXT: sd a1, 248(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul s10, a0, s11
+; RV64IM-NEXT: mul s11, a0, ra
+; RV64IM-NEXT: ld a1, 184(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul ra, a0, a1
+; RV64IM-NEXT: ld a1, 160(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul t0, a0, a1
+; RV64IM-NEXT: ld a1, 152(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul t3, a0, a1
+; RV64IM-NEXT: ld a1, 144(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul s3, a0, a1
+; RV64IM-NEXT: ld a1, 136(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a1, a0, a1
+; RV64IM-NEXT: sd a1, 152(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a1, 128(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a1, a0, a1
+; RV64IM-NEXT: sd a1, 160(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a1, a0, t1
+; RV64IM-NEXT: sd a1, 184(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a1, 56(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, a0, a1
+; RV64IM-NEXT: ld a1, 48(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a1, a0, a1
+; RV64IM-NEXT: mul a3, a0, a6
+; RV64IM-NEXT: ld a4, 40(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a4, a0, a4
+; RV64IM-NEXT: ld a6, 32(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a6, a0, a6
+; RV64IM-NEXT: ld t1, 24(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul t1, a0, t1
+; RV64IM-NEXT: ld t6, 16(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul t6, a0, t6
+; RV64IM-NEXT: ld a0, 336(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s8, 328(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a0, a0, s8
+; RV64IM-NEXT: ld s8, 320(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s9, s8, s9
+; RV64IM-NEXT: xor a5, a5, s7
+; RV64IM-NEXT: ld s7, 312(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s2, s7, s2
+; RV64IM-NEXT: ld s7, 304(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s0, s7, s0
+; RV64IM-NEXT: ld s7, 296(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor t2, s7, t2
+; RV64IM-NEXT: xor a7, a7, t4
+; RV64IM-NEXT: xor t4, s1, s4
+; RV64IM-NEXT: xor s1, s10, s11
+; RV64IM-NEXT: xor a1, a2, a1
+; RV64IM-NEXT: xor a0, a0, s9
+; RV64IM-NEXT: ld a2, 192(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a5, a2
+; RV64IM-NEXT: ld a5, 176(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a5, s2, a5
+; RV64IM-NEXT: ld s2, 8(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s0, s0, s2
+; RV64IM-NEXT: ld s2, 0(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor t2, t2, s2
+; RV64IM-NEXT: xor a7, a7, t5
+; RV64IM-NEXT: xor t4, t4, s5
+; RV64IM-NEXT: xor t5, s1, ra
+; RV64IM-NEXT: xor a1, a1, a3
+; RV64IM-NEXT: xor a0, a0, a2
+; RV64IM-NEXT: ld a2, 216(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a5, a2
+; RV64IM-NEXT: ld a3, 208(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, s0, a3
+; RV64IM-NEXT: ld a5, 200(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a5, t2, a5
+; RV64IM-NEXT: ld t2, 120(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a7, a7, t2
+; RV64IM-NEXT: xor t2, t4, s6
+; RV64IM-NEXT: xor t0, t5, t0
+; RV64IM-NEXT: xor a1, a1, a4
+; RV64IM-NEXT: xor a0, a0, a2
+; RV64IM-NEXT: ld a2, 272(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a3, a2
+; RV64IM-NEXT: ld a3, 256(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a5, a3
+; RV64IM-NEXT: ld a4, 224(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, a7, a4
+; RV64IM-NEXT: ld a5, 112(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a5, t2, a5
+; RV64IM-NEXT: xor a7, t0, t3
+; RV64IM-NEXT: xor a1, a1, a6
+; RV64IM-NEXT: xor a0, a0, a2
+; RV64IM-NEXT: ld a2, 280(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a3, a2
+; RV64IM-NEXT: ld a3, 240(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a4, a3
+; RV64IM-NEXT: ld a4, 168(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, a5, a4
+; RV64IM-NEXT: xor a5, a7, s3
+; RV64IM-NEXT: xor a1, a1, t1
+; RV64IM-NEXT: xor a0, a0, a2
+; RV64IM-NEXT: ld a2, 264(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a3, a2
+; RV64IM-NEXT: ld a3, 232(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a4, a3
+; RV64IM-NEXT: ld a4, 152(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, a5, a4
+; RV64IM-NEXT: xor a1, a1, t6
+; RV64IM-NEXT: xor a0, a0, a2
+; RV64IM-NEXT: ld a2, 248(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a3, a2
+; RV64IM-NEXT: ld a3, 160(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a4, a3
+; RV64IM-NEXT: xor a0, a0, a2
+; RV64IM-NEXT: ld a2, 184(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a3, a2
+; RV64IM-NEXT: xor a0, a0, a2
+; RV64IM-NEXT: ld a2, 288(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a1, a1, a2
+; RV64IM-NEXT: xor a0, a0, a1
+; RV64IM-NEXT: ld ra, 440(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s0, 432(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s1, 424(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s2, 416(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s3, 408(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s4, 400(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s5, 392(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s6, 384(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s7, 376(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s8, 368(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s9, 360(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s10, 352(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s11, 344(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: addi sp, sp, 448
+; RV64IM-NEXT: ret
+ %res = call i32 @llvm.clmul.i32(i32 %a, i32 %b)
+ ret i32 %res
+}
+
+define i64 @clmul_i64(i64 %a, i64 %b) nounwind {
+; RV32IM-LABEL: clmul_i64:
+; RV32IM: # %bb.0:
+; RV32IM-NEXT: addi sp, sp, -368
+; RV32IM-NEXT: sw ra, 364(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s0, 360(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s1, 356(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s2, 352(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s3, 348(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s4, 344(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s5, 340(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s6, 336(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s7, 332(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s8, 328(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s9, 324(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s10, 320(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s11, 316(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mv t0, a1
+; RV32IM-NEXT: andi t3, a2, 4
+; RV32IM-NEXT: andi t5, a2, 2
+; RV32IM-NEXT: andi a4, a2, 1
+; RV32IM-NEXT: andi t6, a2, 8
+; RV32IM-NEXT: andi s0, a2, 16
+; RV32IM-NEXT: andi s1, a2, 32
+; RV32IM-NEXT: andi s9, a2, 64
+; RV32IM-NEXT: andi t1, a2, 128
+; RV32IM-NEXT: andi s2, a2, 256
+; RV32IM-NEXT: andi ra, a2, 512
+; RV32IM-NEXT: andi s11, a2, 1024
+; RV32IM-NEXT: andi s4, a3, 1
+; RV32IM-NEXT: mul a5, a1, t3
+; RV32IM-NEXT: mulhu a6, a0, t3
+; RV32IM-NEXT: mul a1, a1, t5
+; RV32IM-NEXT: mulhu a7, a0, t5
+; RV32IM-NEXT: mul t2, t0, t6
+; RV32IM-NEXT: mulhu t4, a0, t6
+; RV32IM-NEXT: mul s3, t0, s0
+; RV32IM-NEXT: mulhu s5, a0, s0
+; RV32IM-NEXT: mul s6, t0, s1
+; RV32IM-NEXT: mulhu s7, a0, s1
+; RV32IM-NEXT: sw s9, 296(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul s8, t0, s9
+; RV32IM-NEXT: or a5, a6, a5
+; RV32IM-NEXT: mulhu s9, a0, s9
+; RV32IM-NEXT: or a6, a7, a1
+; RV32IM-NEXT: mul s10, t0, t1
+; RV32IM-NEXT: or a1, t4, t2
+; RV32IM-NEXT: mulhu t4, a0, t1
+; RV32IM-NEXT: or a7, s5, s3
+; RV32IM-NEXT: mul s3, t0, s2
+; RV32IM-NEXT: or t2, s7, s6
+; RV32IM-NEXT: mulhu s5, a0, s2
+; RV32IM-NEXT: or s6, s9, s8
+; RV32IM-NEXT: sw s6, 308(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw ra, 136(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul s6, t0, ra
+; RV32IM-NEXT: or t4, t4, s10
+; RV32IM-NEXT: mulhu s7, a0, ra
+; RV32IM-NEXT: or s3, s5, s3
+; RV32IM-NEXT: sw s11, 300(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul s5, t0, s11
+; RV32IM-NEXT: or s6, s7, s6
+; RV32IM-NEXT: sw s6, 304(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mulhu s6, a0, s11
+; RV32IM-NEXT: or s5, s6, s5
+; RV32IM-NEXT: sw s5, 312(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi s5, a3, 2
+; RV32IM-NEXT: mul s4, a0, s4
+; RV32IM-NEXT: mul s5, a0, s5
+; RV32IM-NEXT: mul t5, a0, t5
+; RV32IM-NEXT: xor s9, s4, s5
+; RV32IM-NEXT: mul s4, a0, a4
+; RV32IM-NEXT: xor s6, s4, t5
+; RV32IM-NEXT: lui s4, 2
+; RV32IM-NEXT: mul t3, a0, t3
+; RV32IM-NEXT: mul t5, a0, t6
+; RV32IM-NEXT: xor s7, t3, t5
+; RV32IM-NEXT: lui s10, 4
+; RV32IM-NEXT: mul a4, t0, a4
+; RV32IM-NEXT: mul t3, a0, s0
+; RV32IM-NEXT: mul t5, a0, s1
+; RV32IM-NEXT: xor s0, t3, t5
+; RV32IM-NEXT: lui s5, 1
+; RV32IM-NEXT: and t6, a2, s5
+; RV32IM-NEXT: mul t1, a0, t1
+; RV32IM-NEXT: mul t3, a0, s2
+; RV32IM-NEXT: xor s1, t1, t3
+; RV32IM-NEXT: and t3, a2, s4
+; RV32IM-NEXT: xor a4, a4, a6
+; RV32IM-NEXT: sw a4, 276(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and t1, a2, s10
+; RV32IM-NEXT: xor a1, a5, a1
+; RV32IM-NEXT: sw a1, 272(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw t6, 204(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a4, t0, t6
+; RV32IM-NEXT: xor a1, a7, t2
+; RV32IM-NEXT: sw a1, 268(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mulhu a5, a0, t6
+; RV32IM-NEXT: xor a1, t4, s3
+; RV32IM-NEXT: sw a1, 260(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw t3, 196(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a6, t0, t3
+; RV32IM-NEXT: or a4, a5, a4
+; RV32IM-NEXT: sw a4, 288(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mulhu a4, a0, t3
+; RV32IM-NEXT: or a1, a4, a6
+; RV32IM-NEXT: sw a1, 292(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw t1, 200(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a4, t0, t1
+; RV32IM-NEXT: mulhu a5, a0, t1
+; RV32IM-NEXT: or a4, a5, a4
+; RV32IM-NEXT: sw a4, 256(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lui a1, 8
+; RV32IM-NEXT: and a1, a2, a1
+; RV32IM-NEXT: sw a1, 188(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a4, t0, a1
+; RV32IM-NEXT: mulhu a5, a0, a1
+; RV32IM-NEXT: or a4, a5, a4
+; RV32IM-NEXT: sw a4, 248(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lui a1, 16
+; RV32IM-NEXT: and a1, a2, a1
+; RV32IM-NEXT: lui s8, 16
+; RV32IM-NEXT: sw a1, 184(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a4, t0, a1
+; RV32IM-NEXT: mulhu a5, a0, a1
+; RV32IM-NEXT: or a4, a5, a4
+; RV32IM-NEXT: sw a4, 264(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lui a1, 32
+; RV32IM-NEXT: and a1, a2, a1
+; RV32IM-NEXT: sw a1, 176(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a4, t0, a1
+; RV32IM-NEXT: mulhu a5, a0, a1
+; RV32IM-NEXT: or a4, a5, a4
+; RV32IM-NEXT: sw a4, 280(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lui t2, 64
+; RV32IM-NEXT: and a1, a2, t2
+; RV32IM-NEXT: sw a1, 172(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a4, t0, a1
+; RV32IM-NEXT: mulhu a5, a0, a1
+; RV32IM-NEXT: or a4, a5, a4
+; RV32IM-NEXT: sw a4, 284(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lui s3, 128
+; RV32IM-NEXT: and a1, a2, s3
+; RV32IM-NEXT: sw a1, 164(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a4, t0, a1
+; RV32IM-NEXT: mulhu a5, a0, a1
+; RV32IM-NEXT: or a4, a5, a4
+; RV32IM-NEXT: sw a4, 232(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lui a1, 256
+; RV32IM-NEXT: and a1, a2, a1
+; RV32IM-NEXT: lui t5, 256
+; RV32IM-NEXT: sw a1, 160(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a4, t0, a1
+; RV32IM-NEXT: mulhu a5, a0, a1
+; RV32IM-NEXT: or a4, a5, a4
+; RV32IM-NEXT: sw a4, 220(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lui t3, 512
+; RV32IM-NEXT: and a1, a2, t3
+; RV32IM-NEXT: sw a1, 156(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a4, t0, a1
+; RV32IM-NEXT: mulhu a5, a0, a1
+; RV32IM-NEXT: or a4, a5, a4
+; RV32IM-NEXT: sw a4, 236(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lui t4, 1024
+; RV32IM-NEXT: and a1, a2, t4
+; RV32IM-NEXT: sw a1, 152(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a4, t0, a1
+; RV32IM-NEXT: mulhu a5, a0, a1
+; RV32IM-NEXT: or a4, a5, a4
+; RV32IM-NEXT: sw a4, 240(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lui t6, 2048
+; RV32IM-NEXT: and a1, a2, t6
+; RV32IM-NEXT: sw a1, 148(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a4, t0, a1
+; RV32IM-NEXT: mulhu a5, a0, a1
+; RV32IM-NEXT: or a4, a5, a4
+; RV32IM-NEXT: sw a4, 244(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lui s2, 4096
+; RV32IM-NEXT: and a1, a2, s2
+; RV32IM-NEXT: sw a1, 144(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a4, t0, a1
+; RV32IM-NEXT: mulhu a5, a0, a1
+; RV32IM-NEXT: or a4, a5, a4
+; RV32IM-NEXT: sw a4, 252(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lui a1, 8192
+; RV32IM-NEXT: and a1, a2, a1
+; RV32IM-NEXT: sw a1, 140(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a4, t0, a1
+; RV32IM-NEXT: mulhu a5, a0, a1
+; RV32IM-NEXT: or a4, a5, a4
+; RV32IM-NEXT: sw a4, 180(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lui a1, 16384
+; RV32IM-NEXT: and a1, a2, a1
+; RV32IM-NEXT: lui s4, 16384
+; RV32IM-NEXT: sw a1, 132(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a4, t0, a1
+; RV32IM-NEXT: mulhu a5, a0, a1
+; RV32IM-NEXT: or a4, a5, a4
+; RV32IM-NEXT: sw a4, 168(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lui a1, 32768
+; RV32IM-NEXT: and a1, a2, a1
+; RV32IM-NEXT: lui t1, 32768
+; RV32IM-NEXT: sw a1, 124(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a4, t0, a1
+; RV32IM-NEXT: mulhu a5, a0, a1
+; RV32IM-NEXT: or a4, a5, a4
+; RV32IM-NEXT: sw a4, 192(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lui a1, 65536
+; RV32IM-NEXT: and a1, a2, a1
+; RV32IM-NEXT: lui a7, 65536
+; RV32IM-NEXT: sw a1, 104(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a4, t0, a1
+; RV32IM-NEXT: mulhu a5, a0, a1
+; RV32IM-NEXT: or a4, a5, a4
+; RV32IM-NEXT: sw a4, 208(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lui a1, 131072
+; RV32IM-NEXT: and a1, a2, a1
+; RV32IM-NEXT: lui a6, 131072
+; RV32IM-NEXT: sw a1, 88(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a4, t0, a1
+; RV32IM-NEXT: mulhu a5, a0, a1
+; RV32IM-NEXT: or a4, a5, a4
+; RV32IM-NEXT: sw a4, 212(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lui a5, 262144
+; RV32IM-NEXT: and a1, a2, a5
+; RV32IM-NEXT: sw a1, 68(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a4, t0, a1
+; RV32IM-NEXT: mulhu ra, a0, a1
+; RV32IM-NEXT: or a1, ra, a4
+; RV32IM-NEXT: sw a1, 216(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lui ra, 524288
+; RV32IM-NEXT: and s10, a2, ra
+; RV32IM-NEXT: mul a1, t0, s10
+; RV32IM-NEXT: mulhu s11, a0, s10
+; RV32IM-NEXT: or a1, s11, a1
+; RV32IM-NEXT: sw a1, 224(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi a1, a3, 4
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: xor a1, s9, a1
+; RV32IM-NEXT: sw a1, 116(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a1, a3, s3
+; RV32IM-NEXT: and s11, a3, t5
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: mul s11, a0, s11
+; RV32IM-NEXT: xor a1, a1, s11
+; RV32IM-NEXT: sw a1, 96(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a5, a3, a5
+; RV32IM-NEXT: and a1, a3, ra
+; RV32IM-NEXT: mul a5, a0, a5
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: xor a1, a5, a1
+; RV32IM-NEXT: sw a1, 228(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: xor a1, s6, s7
+; RV32IM-NEXT: sw a1, 72(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 296(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: xor a1, s0, a1
+; RV32IM-NEXT: sw a1, 64(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 136(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: xor a1, s1, a1
+; RV32IM-NEXT: sw a1, 60(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: li a1, 1
+; RV32IM-NEXT: slli a1, a1, 11
+; RV32IM-NEXT: and s6, a3, s5
+; RV32IM-NEXT: lui a4, 2
+; RV32IM-NEXT: and s11, a3, a4
+; RV32IM-NEXT: lui a4, 4
+; RV32IM-NEXT: and s5, a3, a4
+; RV32IM-NEXT: lui a4, 8
+; RV32IM-NEXT: and s7, a3, a4
+; RV32IM-NEXT: and s8, a3, s8
+; RV32IM-NEXT: lui a4, 32
+; RV32IM-NEXT: and s9, a3, a4
+; RV32IM-NEXT: and t2, a3, t2
+; RV32IM-NEXT: and t3, a3, t3
+; RV32IM-NEXT: and t4, a3, t4
+; RV32IM-NEXT: and t5, a3, t6
+; RV32IM-NEXT: and t6, a3, s2
+; RV32IM-NEXT: lui s0, 8192
+; RV32IM-NEXT: and s0, a3, s0
+; RV32IM-NEXT: and s1, a3, s4
+; RV32IM-NEXT: and s2, a3, t1
+; RV32IM-NEXT: and s3, a3, a7
+; RV32IM-NEXT: and s4, a3, a6
+; RV32IM-NEXT: and t1, a2, a1
+; RV32IM-NEXT: and a1, a3, a1
+; RV32IM-NEXT: sw a1, 16(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi a1, a3, 8
+; RV32IM-NEXT: andi ra, a3, 16
+; RV32IM-NEXT: andi a2, a3, 32
+; RV32IM-NEXT: andi a4, a3, 64
+; RV32IM-NEXT: andi a5, a3, 128
+; RV32IM-NEXT: andi a6, a3, 256
+; RV32IM-NEXT: andi a7, a3, 512
+; RV32IM-NEXT: andi a3, a3, 1024
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 24(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a1, a0, ra
+; RV32IM-NEXT: sw a1, 36(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a1, a0, a2
+; RV32IM-NEXT: sw a1, 48(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a1, a0, a4
+; RV32IM-NEXT: sw a1, 80(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a1, a0, a5
+; RV32IM-NEXT: sw a1, 120(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a1, a0, a6
+; RV32IM-NEXT: sw a1, 136(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a1, a0, a7
+; RV32IM-NEXT: sw a1, 296(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul ra, a0, a3
+; RV32IM-NEXT: lw a1, 300(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 12(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a1, a0, s6
+; RV32IM-NEXT: sw a1, 28(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a1, a0, s11
+; RV32IM-NEXT: sw a1, 40(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a1, a0, s5
+; RV32IM-NEXT: sw a1, 52(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a1, a0, s7
+; RV32IM-NEXT: sw a1, 84(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a1, a0, s8
+; RV32IM-NEXT: sw a1, 112(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a1, a0, s9
+; RV32IM-NEXT: sw a1, 128(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a1, a0, t2
+; RV32IM-NEXT: sw a1, 300(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a3, a0, t3
+; RV32IM-NEXT: mul a1, a0, t4
+; RV32IM-NEXT: sw a1, 20(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a1, a0, t5
+; RV32IM-NEXT: sw a1, 32(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a1, a0, t6
+; RV32IM-NEXT: sw a1, 44(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a1, a0, s0
+; RV32IM-NEXT: sw a1, 56(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a1, a0, s1
+; RV32IM-NEXT: sw a1, 76(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a1, a0, s2
+; RV32IM-NEXT: sw a1, 92(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a1, a0, s3
+; RV32IM-NEXT: sw a1, 100(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a1, a0, s4
+; RV32IM-NEXT: sw a1, 108(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 204(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s11, a0, a1
+; RV32IM-NEXT: lw a1, 196(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 196(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 200(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul t3, a0, a1
+; RV32IM-NEXT: lw a1, 188(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul t4, a0, a1
+; RV32IM-NEXT: lw a1, 184(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul t5, a0, a1
+; RV32IM-NEXT: lw a1, 176(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul t2, a0, a1
+; RV32IM-NEXT: lw a1, 172(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 204(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 164(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul t6, a0, a1
+; RV32IM-NEXT: lw a1, 160(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s0, a0, a1
+; RV32IM-NEXT: lw a1, 156(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s1, a0, a1
+; RV32IM-NEXT: lw a1, 152(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s2, a0, a1
+; RV32IM-NEXT: lw a1, 148(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a7, a0, a1
+; RV32IM-NEXT: lw a1, 144(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 200(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 140(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s3, a0, a1
+; RV32IM-NEXT: lw a1, 132(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s4, a0, a1
+; RV32IM-NEXT: lw a1, 124(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s5, a0, a1
+; RV32IM-NEXT: lw a1, 104(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s6, a0, a1
+; RV32IM-NEXT: lw a1, 88(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s7, a0, a1
+; RV32IM-NEXT: lw a1, 68(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a5, a0, a1
+; RV32IM-NEXT: mul a6, a0, s10
+; RV32IM-NEXT: mul t0, t0, t1
+; RV32IM-NEXT: lw a1, 16(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s8, a0, a1
+; RV32IM-NEXT: mulhu s9, a0, t1
+; RV32IM-NEXT: mul a4, a0, t1
+; RV32IM-NEXT: xor t1, t3, t4
+; RV32IM-NEXT: xor t3, t6, s0
+; RV32IM-NEXT: xor t4, s3, s4
+; RV32IM-NEXT: lw a0, 276(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw a1, 272(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t6, a0, a1
+; RV32IM-NEXT: lw a0, 308(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s0, 268(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor s0, s0, a0
+; RV32IM-NEXT: lw a0, 304(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw a1, 260(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor s3, a1, a0
+; RV32IM-NEXT: or t0, s9, t0
+; RV32IM-NEXT: lw a0, 256(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw a1, 248(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor s4, a0, a1
+; RV32IM-NEXT: lw a0, 232(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw a1, 220(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor s9, a0, a1
+; RV32IM-NEXT: lw a0, 180(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw a1, 168(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor s10, a0, a1
+; RV32IM-NEXT: lw a0, 116(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw a2, 24(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a2, a0, a2
+; RV32IM-NEXT: xor s8, ra, s8
+; RV32IM-NEXT: lw a0, 96(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a3, a0, a3
+; RV32IM-NEXT: lw a0, 72(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw a1, 64(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a1, a0, a1
+; RV32IM-NEXT: lw a0, 60(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a0, a0, ra
+; RV32IM-NEXT: xor a4, a4, s11
+; RV32IM-NEXT: xor t1, t1, t5
+; RV32IM-NEXT: xor t3, t3, s1
+; RV32IM-NEXT: xor t4, t4, s5
+; RV32IM-NEXT: xor t5, t6, s0
+; RV32IM-NEXT: lw t6, 312(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t6, s3, t6
+; RV32IM-NEXT: lw s0, 288(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t0, t0, s0
+; RV32IM-NEXT: lw s0, 264(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor s0, s4, s0
+; RV32IM-NEXT: lw s1, 236(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor s1, s9, s1
+; RV32IM-NEXT: lw s3, 192(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor s3, s10, s3
+; RV32IM-NEXT: lw s4, 36(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a2, a2, s4
+; RV32IM-NEXT: lw s4, 28(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor s4, s8, s4
+; RV32IM-NEXT: lw s5, 20(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a3, a3, s5
+; RV32IM-NEXT: xor a0, a1, a0
+; RV32IM-NEXT: lw a1, 196(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a1, a4, a1
+; RV32IM-NEXT: xor a4, t1, t2
+; RV32IM-NEXT: xor t1, t3, s2
+; RV32IM-NEXT: xor t2, t4, s6
+; RV32IM-NEXT: xor t3, t5, t6
+; RV32IM-NEXT: lw t4, 292(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t0, t0, t4
+; RV32IM-NEXT: lw t4, 280(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t4, s0, t4
+; RV32IM-NEXT: lw t5, 240(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t5, s1, t5
+; RV32IM-NEXT: lw t6, 208(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t6, s3, t6
+; RV32IM-NEXT: lw s0, 48(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a2, a2, s0
+; RV32IM-NEXT: lw s0, 40(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor s0, s4, s0
+; RV32IM-NEXT: lw s1, 32(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a3, a3, s1
+; RV32IM-NEXT: xor a0, a0, a1
+; RV32IM-NEXT: lw a1, 204(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a1, a4, a1
+; RV32IM-NEXT: xor a4, t1, a7
+; RV32IM-NEXT: xor a7, t2, s7
+; RV32IM-NEXT: xor t0, t3, t0
+; RV32IM-NEXT: lw t1, 284(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t1, t4, t1
+; RV32IM-NEXT: lw t2, 244(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t2, t5, t2
+; RV32IM-NEXT: lw t3, 212(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t3, t6, t3
+; RV32IM-NEXT: lw t4, 80(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a2, a2, t4
+; RV32IM-NEXT: lw t4, 52(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t4, s0, t4
+; RV32IM-NEXT: lw t5, 44(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a3, a3, t5
+; RV32IM-NEXT: xor a0, a0, a1
+; RV32IM-NEXT: lw a1, 200(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a1, a4, a1
+; RV32IM-NEXT: xor a4, a7, a5
+; RV32IM-NEXT: xor a5, t0, t1
+; RV32IM-NEXT: lw a7, 252(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a7, t2, a7
+; RV32IM-NEXT: lw t0, 216(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t0, t3, t0
+; RV32IM-NEXT: lw t1, 120(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a2, a2, t1
+; RV32IM-NEXT: lw t1, 84(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t1, t4, t1
+; RV32IM-NEXT: lw t2, 56(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a3, a3, t2
+; RV32IM-NEXT: xor a0, a0, a1
+; RV32IM-NEXT: xor a4, a4, a6
+; RV32IM-NEXT: xor a1, a5, a7
+; RV32IM-NEXT: lw a5, 224(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a5, t0, a5
+; RV32IM-NEXT: lw a6, 136(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a2, a2, a6
+; RV32IM-NEXT: lw a6, 112(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a6, t1, a6
+; RV32IM-NEXT: lw a7, 76(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a3, a3, a7
+; RV32IM-NEXT: xor a1, a1, a5
+; RV32IM-NEXT: lw a5, 296(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a2, a2, a5
+; RV32IM-NEXT: lw a5, 128(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a5, a6, a5
+; RV32IM-NEXT: lw a6, 92(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a3, a3, a6
+; RV32IM-NEXT: xor a1, a1, a2
+; RV32IM-NEXT: lw a2, 300(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a2, a5, a2
+; RV32IM-NEXT: lw a5, 100(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a3, a3, a5
+; RV32IM-NEXT: xor a1, a1, a2
+; RV32IM-NEXT: lw a2, 108(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a2, a3, a2
+; RV32IM-NEXT: xor a1, a1, a2
+; RV32IM-NEXT: lw a2, 228(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a1, a1, a2
+; RV32IM-NEXT: xor a0, a0, a4
+; RV32IM-NEXT: lw ra, 364(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s0, 360(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s1, 356(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s2, 352(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s3, 348(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s4, 344(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s5, 340(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s6, 336(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s7, 332(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s8, 328(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s9, 324(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s10, 320(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s11, 316(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: addi sp, sp, 368
+; RV32IM-NEXT: ret
+;
+; RV64IM-LABEL: clmul_i64:
+; RV64IM: # %bb.0:
+; RV64IM-NEXT: addi sp, sp, -448
+; RV64IM-NEXT: sd ra, 440(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s0, 432(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s1, 424(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s2, 416(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s3, 408(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s4, 400(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s5, 392(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s6, 384(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s7, 376(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s8, 368(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s9, 360(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s10, 352(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s11, 344(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi t2, a1, 2
+; RV64IM-NEXT: andi t4, a1, 1
+; RV64IM-NEXT: andi a6, a1, 4
+; RV64IM-NEXT: andi t0, a1, 8
+; RV64IM-NEXT: andi a5, a1, 16
+; RV64IM-NEXT: andi a7, a1, 32
+; RV64IM-NEXT: andi a3, a1, 64
+; RV64IM-NEXT: andi t1, a1, 128
+; RV64IM-NEXT: andi t3, a1, 256
+; RV64IM-NEXT: andi a4, a1, 512
+; RV64IM-NEXT: li a2, 1
+; RV64IM-NEXT: lui s7, 1
+; RV64IM-NEXT: lui t6, 2
+; RV64IM-NEXT: lui s0, 4
+; RV64IM-NEXT: lui s1, 8
+; RV64IM-NEXT: lui s2, 16
+; RV64IM-NEXT: lui s3, 32
+; RV64IM-NEXT: lui s4, 64
+; RV64IM-NEXT: lui s5, 128
+; RV64IM-NEXT: lui s6, 256
+; RV64IM-NEXT: lui s8, 512
+; RV64IM-NEXT: lui s9, 1024
+; RV64IM-NEXT: lui s10, 2048
+; RV64IM-NEXT: lui s11, 4096
+; RV64IM-NEXT: lui ra, 8192
+; RV64IM-NEXT: lui t5, 16384
+; RV64IM-NEXT: mul t2, a0, t2
+; RV64IM-NEXT: mul t4, a0, t4
+; RV64IM-NEXT: xor t2, t4, t2
+; RV64IM-NEXT: lui t4, 32768
+; RV64IM-NEXT: mul a6, a0, a6
+; RV64IM-NEXT: mul t0, a0, t0
+; RV64IM-NEXT: xor a6, a6, t0
+; RV64IM-NEXT: lui t0, 65536
+; RV64IM-NEXT: mul a5, a0, a5
+; RV64IM-NEXT: mul a7, a0, a7
+; RV64IM-NEXT: xor a5, a5, a7
+; RV64IM-NEXT: lui a7, 131072
+; RV64IM-NEXT: mul t1, a0, t1
+; RV64IM-NEXT: mul t3, a0, t3
+; RV64IM-NEXT: xor t1, t1, t3
+; RV64IM-NEXT: lui t3, 262144
+; RV64IM-NEXT: mul a3, a0, a3
+; RV64IM-NEXT: mul a4, a0, a4
+; RV64IM-NEXT: xor a6, t2, a6
+; RV64IM-NEXT: sd a6, 336(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a6, a2, 11
+; RV64IM-NEXT: sd a6, 216(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and s7, a1, s7
+; RV64IM-NEXT: and a6, a1, t6
+; RV64IM-NEXT: sd a6, 288(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and s0, a1, s0
+; RV64IM-NEXT: and s1, a1, s1
+; RV64IM-NEXT: and s2, a1, s2
+; RV64IM-NEXT: and s3, a1, s3
+; RV64IM-NEXT: and a6, a1, s4
+; RV64IM-NEXT: sd a6, 280(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a6, a1, s5
+; RV64IM-NEXT: and t2, a1, s6
+; RV64IM-NEXT: and s8, a1, s8
+; RV64IM-NEXT: and t6, a1, s9
+; RV64IM-NEXT: sd t6, 272(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and t6, a1, s10
+; RV64IM-NEXT: sd t6, 264(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and t6, a1, s11
+; RV64IM-NEXT: sd t6, 256(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and t6, a1, ra
+; RV64IM-NEXT: and t5, a1, t5
+; RV64IM-NEXT: and t4, a1, t4
+; RV64IM-NEXT: sd t4, 248(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and t0, a1, t0
+; RV64IM-NEXT: sd t0, 240(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a7, a1, a7
+; RV64IM-NEXT: sd a7, 232(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a7, a1, t3
+; RV64IM-NEXT: sd a7, 224(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: xor a3, a5, a3
+; RV64IM-NEXT: sd a3, 328(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli t4, a2, 32
+; RV64IM-NEXT: xor a3, t1, a4
+; RV64IM-NEXT: sd a3, 320(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli s4, a2, 33
+; RV64IM-NEXT: mul a3, a0, s0
+; RV64IM-NEXT: mul a4, a0, s1
+; RV64IM-NEXT: xor a3, a3, a4
+; RV64IM-NEXT: sd a3, 312(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli s0, a2, 34
+; RV64IM-NEXT: mul a3, a0, a6
+; RV64IM-NEXT: mul a4, a0, t2
+; RV64IM-NEXT: xor a3, a3, a4
+; RV64IM-NEXT: sd a3, 304(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli s1, a2, 35
+; RV64IM-NEXT: mul a3, a0, t6
+; RV64IM-NEXT: mul a4, a0, t5
+; RV64IM-NEXT: xor a3, a3, a4
+; RV64IM-NEXT: sd a3, 296(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli t5, a2, 36
+; RV64IM-NEXT: slli t6, a2, 37
+; RV64IM-NEXT: slli s5, a2, 38
+; RV64IM-NEXT: slli s6, a2, 39
+; RV64IM-NEXT: slli s9, a2, 40
+; RV64IM-NEXT: slli s10, a2, 41
+; RV64IM-NEXT: slli s11, a2, 42
+; RV64IM-NEXT: slli ra, a2, 43
+; RV64IM-NEXT: slli a3, a2, 44
+; RV64IM-NEXT: sd a3, 208(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a2, 45
+; RV64IM-NEXT: sd a3, 200(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a2, 46
+; RV64IM-NEXT: sd a3, 192(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a2, 47
+; RV64IM-NEXT: sd a3, 184(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a2, 48
+; RV64IM-NEXT: sd a3, 176(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a2, 49
+; RV64IM-NEXT: sd a3, 168(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a2, 50
+; RV64IM-NEXT: sd a3, 160(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a2, 51
+; RV64IM-NEXT: sd a3, 152(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a2, 52
+; RV64IM-NEXT: sd a3, 144(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a2, 53
+; RV64IM-NEXT: sd a3, 136(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a2, 54
+; RV64IM-NEXT: sd a3, 128(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli t1, a2, 55
+; RV64IM-NEXT: slli t0, a2, 56
+; RV64IM-NEXT: slli a7, a2, 57
+; RV64IM-NEXT: slli a6, a2, 58
+; RV64IM-NEXT: slli a5, a2, 59
+; RV64IM-NEXT: slli a4, a2, 60
+; RV64IM-NEXT: slli a3, a2, 61
+; RV64IM-NEXT: slli a2, a2, 62
+; RV64IM-NEXT: ld t2, 216(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and t3, a1, t2
+; RV64IM-NEXT: and t2, a1, t4
+; RV64IM-NEXT: sd t2, 120(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and t4, a1, s4
+; RV64IM-NEXT: and s0, a1, s0
+; RV64IM-NEXT: sd s0, 112(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and s1, a1, s1
+; RV64IM-NEXT: sd s1, 104(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and t2, a1, t5
+; RV64IM-NEXT: sd t2, 96(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and s1, a1, t6
+; RV64IM-NEXT: and t2, a1, s5
+; RV64IM-NEXT: sd t2, 88(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and t2, a1, s6
+; RV64IM-NEXT: sd t2, 80(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and s4, a1, s9
+; RV64IM-NEXT: and s5, a1, s10
+; RV64IM-NEXT: and s6, a1, s11
+; RV64IM-NEXT: and t6, a1, ra
+; RV64IM-NEXT: ld t2, 208(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and t2, a1, t2
+; RV64IM-NEXT: sd t2, 72(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld t2, 200(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and t2, a1, t2
+; RV64IM-NEXT: sd t2, 64(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld t2, 192(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s10, a1, t2
+; RV64IM-NEXT: ld t2, 184(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s11, a1, t2
+; RV64IM-NEXT: ld t2, 176(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and ra, a1, t2
+; RV64IM-NEXT: ld t2, 168(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and t2, a1, t2
+; RV64IM-NEXT: sd t2, 184(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld t2, 160(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and t2, a1, t2
+; RV64IM-NEXT: sd t2, 160(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld t2, 152(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and t2, a1, t2
+; RV64IM-NEXT: sd t2, 152(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld t2, 144(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and t2, a1, t2
+; RV64IM-NEXT: sd t2, 144(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld t2, 136(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and t2, a1, t2
+; RV64IM-NEXT: sd t2, 136(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld t2, 128(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and t2, a1, t2
+; RV64IM-NEXT: sd t2, 128(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and t1, a1, t1
+; RV64IM-NEXT: and t0, a1, t0
+; RV64IM-NEXT: sd t0, 56(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a7, a1, a7
+; RV64IM-NEXT: sd a7, 48(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a6, a1, a6
+; RV64IM-NEXT: and a5, a1, a5
+; RV64IM-NEXT: sd a5, 40(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a4, a1, a4
+; RV64IM-NEXT: sd a4, 32(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a3, a1, a3
+; RV64IM-NEXT: sd a3, 24(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a2, a1, a2
+; RV64IM-NEXT: sd a2, 16(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi a2, a1, 1024
+; RV64IM-NEXT: srliw a3, a1, 31
+; RV64IM-NEXT: srli a1, a1, 63
+; RV64IM-NEXT: mul s9, a0, a2
+; RV64IM-NEXT: slli a3, a3, 31
+; RV64IM-NEXT: slli a1, a1, 63
+; RV64IM-NEXT: mul s7, a0, s7
+; RV64IM-NEXT: ld a2, 288(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, a0, a2
+; RV64IM-NEXT: sd a2, 192(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul s2, a0, s2
+; RV64IM-NEXT: mul a2, a0, s3
+; RV64IM-NEXT: sd a2, 176(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 280(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, a0, a2
+; RV64IM-NEXT: sd a2, 216(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul s0, a0, s8
+; RV64IM-NEXT: ld a2, 272(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, a0, a2
+; RV64IM-NEXT: sd a2, 8(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 264(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, a0, a2
+; RV64IM-NEXT: sd a2, 208(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 256(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, a0, a2
+; RV64IM-NEXT: sd a2, 272(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 248(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul t2, a0, a2
+; RV64IM-NEXT: ld a2, 240(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, a0, a2
+; RV64IM-NEXT: sd a2, 0(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 232(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, a0, a2
+; RV64IM-NEXT: sd a2, 200(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 224(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, a0, a2
+; RV64IM-NEXT: sd a2, 256(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a2, a0, a3
+; RV64IM-NEXT: sd a2, 280(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a1, a0, a1
+; RV64IM-NEXT: sd a1, 288(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a5, a0, t3
+; RV64IM-NEXT: ld a1, 120(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a7, a0, a1
+; RV64IM-NEXT: mul t4, a0, t4
+; RV64IM-NEXT: ld a1, 112(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul t5, a0, a1
+; RV64IM-NEXT: ld a1, 104(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a1, a0, a1
+; RV64IM-NEXT: sd a1, 120(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a1, 96(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a1, a0, a1
+; RV64IM-NEXT: sd a1, 224(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a1, a0, s1
+; RV64IM-NEXT: sd a1, 240(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a1, 88(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a1, a0, a1
+; RV64IM-NEXT: sd a1, 264(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a1, 80(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul s1, a0, a1
+; RV64IM-NEXT: mul s4, a0, s4
+; RV64IM-NEXT: mul s5, a0, s5
+; RV64IM-NEXT: mul s6, a0, s6
+; RV64IM-NEXT: mul a1, a0, t6
+; RV64IM-NEXT: sd a1, 112(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a1, 72(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a1, a0, a1
+; RV64IM-NEXT: sd a1, 168(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a1, 64(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a1, a0, a1
+; RV64IM-NEXT: sd a1, 232(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a1, a0, s10
+; RV64IM-NEXT: sd a1, 248(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul s10, a0, s11
+; RV64IM-NEXT: mul s11, a0, ra
+; RV64IM-NEXT: ld a1, 184(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul ra, a0, a1
+; RV64IM-NEXT: ld a1, 160(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul t0, a0, a1
+; RV64IM-NEXT: ld a1, 152(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul t3, a0, a1
+; RV64IM-NEXT: ld a1, 144(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul s3, a0, a1
+; RV64IM-NEXT: ld a1, 136(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a1, a0, a1
+; RV64IM-NEXT: sd a1, 152(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a1, 128(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a1, a0, a1
+; RV64IM-NEXT: sd a1, 160(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a1, a0, t1
+; RV64IM-NEXT: sd a1, 184(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a1, 56(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, a0, a1
+; RV64IM-NEXT: ld a1, 48(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a1, a0, a1
+; RV64IM-NEXT: mul a3, a0, a6
+; RV64IM-NEXT: ld a4, 40(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a4, a0, a4
+; RV64IM-NEXT: ld a6, 32(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a6, a0, a6
+; RV64IM-NEXT: ld t1, 24(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul t1, a0, t1
+; RV64IM-NEXT: ld t6, 16(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul t6, a0, t6
+; RV64IM-NEXT: ld a0, 336(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s8, 328(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a0, a0, s8
+; RV64IM-NEXT: ld s8, 320(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s9, s8, s9
+; RV64IM-NEXT: xor a5, a5, s7
+; RV64IM-NEXT: ld s7, 312(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s2, s7, s2
+; RV64IM-NEXT: ld s7, 304(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s0, s7, s0
+; RV64IM-NEXT: ld s7, 296(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor t2, s7, t2
+; RV64IM-NEXT: xor a7, a7, t4
+; RV64IM-NEXT: xor t4, s1, s4
+; RV64IM-NEXT: xor s1, s10, s11
+; RV64IM-NEXT: xor a1, a2, a1
+; RV64IM-NEXT: xor a0, a0, s9
+; RV64IM-NEXT: ld a2, 192(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a5, a2
+; RV64IM-NEXT: ld a5, 176(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a5, s2, a5
+; RV64IM-NEXT: ld s2, 8(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s0, s0, s2
+; RV64IM-NEXT: ld s2, 0(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor t2, t2, s2
+; RV64IM-NEXT: xor a7, a7, t5
+; RV64IM-NEXT: xor t4, t4, s5
+; RV64IM-NEXT: xor t5, s1, ra
+; RV64IM-NEXT: xor a1, a1, a3
+; RV64IM-NEXT: xor a0, a0, a2
+; RV64IM-NEXT: ld a2, 216(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a5, a2
+; RV64IM-NEXT: ld a3, 208(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, s0, a3
+; RV64IM-NEXT: ld a5, 200(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a5, t2, a5
+; RV64IM-NEXT: ld t2, 120(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a7, a7, t2
+; RV64IM-NEXT: xor t2, t4, s6
+; RV64IM-NEXT: xor t0, t5, t0
+; RV64IM-NEXT: xor a1, a1, a4
+; RV64IM-NEXT: xor a0, a0, a2
+; RV64IM-NEXT: ld a2, 272(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a3, a2
+; RV64IM-NEXT: ld a3, 256(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a5, a3
+; RV64IM-NEXT: ld a4, 224(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, a7, a4
+; RV64IM-NEXT: ld a5, 112(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a5, t2, a5
+; RV64IM-NEXT: xor a7, t0, t3
+; RV64IM-NEXT: xor a1, a1, a6
+; RV64IM-NEXT: xor a0, a0, a2
+; RV64IM-NEXT: ld a2, 280(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a3, a2
+; RV64IM-NEXT: ld a3, 240(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a4, a3
+; RV64IM-NEXT: ld a4, 168(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, a5, a4
+; RV64IM-NEXT: xor a5, a7, s3
+; RV64IM-NEXT: xor a1, a1, t1
+; RV64IM-NEXT: xor a0, a0, a2
+; RV64IM-NEXT: ld a2, 264(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a3, a2
+; RV64IM-NEXT: ld a3, 232(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a4, a3
+; RV64IM-NEXT: ld a4, 152(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, a5, a4
+; RV64IM-NEXT: xor a1, a1, t6
+; RV64IM-NEXT: xor a0, a0, a2
+; RV64IM-NEXT: ld a2, 248(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a3, a2
+; RV64IM-NEXT: ld a3, 160(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a4, a3
+; RV64IM-NEXT: xor a0, a0, a2
+; RV64IM-NEXT: ld a2, 184(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a3, a2
+; RV64IM-NEXT: xor a0, a0, a2
+; RV64IM-NEXT: ld a2, 288(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a1, a1, a2
+; RV64IM-NEXT: xor a0, a0, a1
+; RV64IM-NEXT: ld ra, 440(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s0, 432(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s1, 424(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s2, 416(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s3, 408(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s4, 400(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s5, 392(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s6, 384(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s7, 376(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s8, 368(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s9, 360(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s10, 352(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s11, 344(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: addi sp, sp, 448
+; RV64IM-NEXT: ret
+ %res = call i64 @llvm.clmul.i64(i64 %a, i64 %b)
+ ret i64 %res
+}
+
+define i4 @clmul_constfold_i4() nounwind {
+; CHECK-LABEL: clmul_constfold_i4:
+; CHECK: # %bb.0:
+; CHECK-NEXT: li a0, 2
+; CHECK-NEXT: ret
+ %res = call i4 @llvm.clmul.i4(i4 1, i4 2)
+ ret i4 %res
+}
+
+define i16 @clmul_constfold_i16() nounwind {
+; RV32IM-LABEL: clmul_constfold_i16:
+; RV32IM: # %bb.0:
+; RV32IM-NEXT: lui a0, 699051
+; RV32IM-NEXT: addi a0, a0, -1366
+; RV32IM-NEXT: ret
+;
+; RV64IM-LABEL: clmul_constfold_i16:
+; RV64IM: # %bb.0:
+; RV64IM-NEXT: lui a0, %hi(.LCPI6_0)
+; RV64IM-NEXT: ld a0, %lo(.LCPI6_0)(a0)
+; RV64IM-NEXT: ret
+ %res = call i16 @llvm.clmul.i16(i16 -2, i16 -1)
+ ret i16 %res
+}
+
+define i4 @clmulr_i4(i4 %a, i4 %b) nounwind {
+; RV32IM-LABEL: clmulr_i4:
+; RV32IM: # %bb.0:
+; RV32IM-NEXT: addi sp, sp, -144
+; RV32IM-NEXT: sw ra, 140(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s0, 136(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s1, 132(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s2, 128(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s3, 124(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s4, 120(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s5, 116(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s6, 112(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s7, 108(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s8, 104(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s9, 100(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s10, 96(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s11, 92(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: srli a3, a0, 8
+; RV32IM-NEXT: lui s9, 16
+; RV32IM-NEXT: srli a4, a0, 24
+; RV32IM-NEXT: slli a2, a0, 24
+; RV32IM-NEXT: lui a7, 61681
+; RV32IM-NEXT: lui ra, 209715
+; RV32IM-NEXT: lui a1, 349525
+; RV32IM-NEXT: li s0, 1
+; RV32IM-NEXT: lui t1, 1
+; RV32IM-NEXT: lui t2, 2
+; RV32IM-NEXT: lui t3, 4
+; RV32IM-NEXT: lui t4, 8
+; RV32IM-NEXT: lui t0, 32
+; RV32IM-NEXT: lui a6, 64
+; RV32IM-NEXT: lui a5, 128
+; RV32IM-NEXT: lui s1, 256
+; RV32IM-NEXT: lui t5, 512
+; RV32IM-NEXT: lui t6, 1024
+; RV32IM-NEXT: lui s4, 2048
+; RV32IM-NEXT: lui s2, 4096
+; RV32IM-NEXT: lui s3, 8192
+; RV32IM-NEXT: lui s7, 16384
+; RV32IM-NEXT: lui s5, 32768
+; RV32IM-NEXT: lui s6, 65536
+; RV32IM-NEXT: lui s11, 131072
+; RV32IM-NEXT: lui s8, 262144
+; RV32IM-NEXT: addi s10, s9, -256
+; RV32IM-NEXT: and a3, a3, s10
+; RV32IM-NEXT: or a3, a3, a4
+; RV32IM-NEXT: addi a7, a7, -241
+; RV32IM-NEXT: sw a7, 80(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: addi a4, ra, 819
+; RV32IM-NEXT: sw a4, 84(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: addi a1, a1, 1365
+; RV32IM-NEXT: sw a1, 88(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: slli s0, s0, 11
+; RV32IM-NEXT: and a0, a0, s10
+; RV32IM-NEXT: slli a0, a0, 8
+; RV32IM-NEXT: or a0, a2, a0
+; RV32IM-NEXT: or a0, a0, a3
+; RV32IM-NEXT: srli a2, a0, 4
+; RV32IM-NEXT: and a0, a0, a7
+; RV32IM-NEXT: and a2, a2, a7
+; RV32IM-NEXT: slli a0, a0, 4
+; RV32IM-NEXT: or a0, a2, a0
+; RV32IM-NEXT: srli a2, a0, 2
+; RV32IM-NEXT: and a0, a0, a4
+; RV32IM-NEXT: and a2, a2, a4
+; RV32IM-NEXT: slli a0, a0, 2
+; RV32IM-NEXT: or a0, a2, a0
+; RV32IM-NEXT: srli a2, a0, 1
+; RV32IM-NEXT: and a0, a0, a1
+; RV32IM-NEXT: and a2, a2, a1
+; RV32IM-NEXT: slli a0, a0, 1
+; RV32IM-NEXT: or a3, a2, a0
+; RV32IM-NEXT: andi a0, a3, 2
+; RV32IM-NEXT: andi a1, a3, 1
+; RV32IM-NEXT: and a4, a3, s0
+; RV32IM-NEXT: and a7, a3, t1
+; RV32IM-NEXT: and s0, a3, t2
+; RV32IM-NEXT: and ra, a3, t3
+; RV32IM-NEXT: and a2, a3, t4
+; RV32IM-NEXT: sw a2, 68(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a2, a3, s9
+; RV32IM-NEXT: sw a2, 64(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a2, a3, t0
+; RV32IM-NEXT: sw a2, 60(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a6, a3, a6
+; RV32IM-NEXT: and a5, a3, a5
+; RV32IM-NEXT: and s1, a3, s1
+; RV32IM-NEXT: sw s1, 56(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a2, a3, t5
+; RV32IM-NEXT: sw a2, 52(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and t6, a3, t6
+; RV32IM-NEXT: and a2, a3, s4
+; RV32IM-NEXT: sw a2, 48(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and s2, a3, s2
+; RV32IM-NEXT: and a2, a3, s3
+; RV32IM-NEXT: sw a2, 44(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a2, a3, s7
+; RV32IM-NEXT: sw a2, 40(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a2, a3, s5
+; RV32IM-NEXT: sw a2, 36(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a2, a3, s6
+; RV32IM-NEXT: sw a2, 32(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a2, a3, s11
+; RV32IM-NEXT: sw a2, 28(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a2, a3, s8
+; RV32IM-NEXT: sw a2, 24(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lui a2, 524288
+; RV32IM-NEXT: and a2, a3, a2
+; RV32IM-NEXT: sw a2, 20(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a0, a3, a0
+; RV32IM-NEXT: sw a0, 72(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a0, a3, a1
+; RV32IM-NEXT: sw a0, 16(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi a0, a3, 4
+; RV32IM-NEXT: mul a0, a3, a0
+; RV32IM-NEXT: sw a0, 12(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi a1, a3, 8
+; RV32IM-NEXT: mul a0, a3, a1
+; RV32IM-NEXT: sw a0, 0(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi a2, a3, 16
+; RV32IM-NEXT: mul s9, a3, a2
+; RV32IM-NEXT: andi t0, a3, 32
+; RV32IM-NEXT: mul s6, a3, t0
+; RV32IM-NEXT: andi t1, a3, 64
+; RV32IM-NEXT: mul a0, a3, t1
+; RV32IM-NEXT: sw a0, 4(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi t2, a3, 128
+; RV32IM-NEXT: mul a0, a3, t2
+; RV32IM-NEXT: sw a0, 76(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi t2, a3, 256
+; RV32IM-NEXT: mul s1, a3, t2
+; RV32IM-NEXT: andi t3, a3, 512
+; RV32IM-NEXT: mul t5, a3, t3
+; RV32IM-NEXT: andi t4, a3, 1024
+; RV32IM-NEXT: mul s5, a3, t4
+; RV32IM-NEXT: mul s8, a3, a4
+; RV32IM-NEXT: mul a0, a3, a7
+; RV32IM-NEXT: sw a0, 8(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul t2, a3, s0
+; RV32IM-NEXT: mul a7, a3, ra
+; RV32IM-NEXT: lw a0, 68(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s0, a3, a0
+; RV32IM-NEXT: lw a0, 64(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s4, a3, a0
+; RV32IM-NEXT: lw a0, 60(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s7, a3, a0
+; RV32IM-NEXT: mul a0, a3, a6
+; RV32IM-NEXT: sw a0, 68(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a6, a3, a5
+; RV32IM-NEXT: lw a0, 56(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a4, a3, a0
+; RV32IM-NEXT: lw a0, 52(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul t1, a3, a0
+; RV32IM-NEXT: mul t4, a3, t6
+; RV32IM-NEXT: lw a0, 48(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s3, a3, a0
+; RV32IM-NEXT: mul a2, a3, s2
+; RV32IM-NEXT: lw a0, 44(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a1, a3, a0
+; RV32IM-NEXT: lw a0, 40(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a5, a3, a0
+; RV32IM-NEXT: lw a0, 36(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul t0, a3, a0
+; RV32IM-NEXT: lw a0, 32(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul t3, a3, a0
+; RV32IM-NEXT: lw a0, 28(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul t6, a3, a0
+; RV32IM-NEXT: lw a0, 24(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s2, a3, a0
+; RV32IM-NEXT: lw a0, 20(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a3, a3, a0
+; RV32IM-NEXT: lw a0, 72(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s11, 16(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a0, s11, a0
+; RV32IM-NEXT: lw s11, 12(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw ra, 0(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor s11, s11, ra
+; RV32IM-NEXT: xor s6, s9, s6
+; RV32IM-NEXT: xor t5, s1, t5
+; RV32IM-NEXT: xor a7, t2, a7
+; RV32IM-NEXT: xor a4, a6, a4
+; RV32IM-NEXT: xor a1, a2, a1
+; RV32IM-NEXT: xor a0, a0, s11
+; RV32IM-NEXT: lw a2, 4(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a2, s6, a2
+; RV32IM-NEXT: xor a6, t5, s5
+; RV32IM-NEXT: xor a7, a7, s0
+; RV32IM-NEXT: xor a4, a4, t1
+; RV32IM-NEXT: xor a1, a1, a5
+; RV32IM-NEXT: xor a0, a0, a2
+; RV32IM-NEXT: xor a2, a6, s8
+; RV32IM-NEXT: xor a5, a7, s4
+; RV32IM-NEXT: xor a4, a4, t4
+; RV32IM-NEXT: xor a1, a1, t0
+; RV32IM-NEXT: lw a6, 76(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a0, a0, a6
+; RV32IM-NEXT: lw a6, 8(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a2, a2, a6
+; RV32IM-NEXT: xor a5, a5, s7
+; RV32IM-NEXT: xor a4, a4, s3
+; RV32IM-NEXT: xor a1, a1, t3
+; RV32IM-NEXT: lw a6, 68(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a5, a5, a6
+; RV32IM-NEXT: xor a1, a1, t6
+; RV32IM-NEXT: xor a2, a0, a2
+; RV32IM-NEXT: xor a2, a2, a5
+; RV32IM-NEXT: slli a0, a0, 24
+; RV32IM-NEXT: xor a1, a1, s2
+; RV32IM-NEXT: xor a2, a2, a4
+; RV32IM-NEXT: xor a1, a1, a3
+; RV32IM-NEXT: and a3, a2, s10
+; RV32IM-NEXT: srli a4, a2, 8
+; RV32IM-NEXT: xor a1, a2, a1
+; RV32IM-NEXT: slli a3, a3, 8
+; RV32IM-NEXT: and a2, a4, s10
+; RV32IM-NEXT: srli a1, a1, 24
+; RV32IM-NEXT: or a0, a0, a3
+; RV32IM-NEXT: or a1, a2, a1
+; RV32IM-NEXT: or a0, a0, a1
+; RV32IM-NEXT: srli a1, a0, 4
+; RV32IM-NEXT: lw a2, 80(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: and a0, a0, a2
+; RV32IM-NEXT: and a1, a1, a2
+; RV32IM-NEXT: slli a0, a0, 4
+; RV32IM-NEXT: or a0, a1, a0
+; RV32IM-NEXT: srli a1, a0, 2
+; RV32IM-NEXT: lw a2, 84(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: and a0, a0, a2
+; RV32IM-NEXT: and a1, a1, a2
+; RV32IM-NEXT: slli a0, a0, 2
+; RV32IM-NEXT: or a0, a1, a0
+; RV32IM-NEXT: srli a1, a0, 1
+; RV32IM-NEXT: lw a2, 88(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: and a0, a0, a2
+; RV32IM-NEXT: and a1, a1, a2
+; RV32IM-NEXT: slli a0, a0, 1
+; RV32IM-NEXT: or a0, a1, a0
+; RV32IM-NEXT: lw ra, 140(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s0, 136(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s1, 132(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s2, 128(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s3, 124(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s4, 120(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s5, 116(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s6, 112(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s7, 108(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s8, 104(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s9, 100(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s10, 96(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s11, 92(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: addi sp, sp, 144
+; RV32IM-NEXT: ret
+;
+; RV64IM-LABEL: clmulr_i4:
+; RV64IM: # %bb.0:
+; RV64IM-NEXT: addi sp, sp, -448
+; RV64IM-NEXT: sd ra, 440(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s0, 432(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s1, 424(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s2, 416(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s3, 408(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s4, 400(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s5, 392(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s6, 384(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s7, 376(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s8, 368(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s9, 360(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s10, 352(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s11, 344(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: srli a2, a0, 24
+; RV64IM-NEXT: srli a6, a0, 8
+; RV64IM-NEXT: li a3, 255
+; RV64IM-NEXT: srli a5, a0, 40
+; RV64IM-NEXT: lui s3, 16
+; RV64IM-NEXT: srli s0, a0, 56
+; RV64IM-NEXT: srliw t2, a0, 24
+; RV64IM-NEXT: slli t0, a0, 56
+; RV64IM-NEXT: lui t3, 61681
+; RV64IM-NEXT: lui t4, 209715
+; RV64IM-NEXT: lui t6, 349525
+; RV64IM-NEXT: li a7, 1
+; RV64IM-NEXT: lui s5, 2
+; RV64IM-NEXT: lui t1, 4
+; RV64IM-NEXT: lui a4, 128
+; RV64IM-NEXT: lui s7, 256
+; RV64IM-NEXT: lui s8, 4096
+; RV64IM-NEXT: lui s10, 8192
+; RV64IM-NEXT: lui a1, 4080
+; RV64IM-NEXT: and a2, a2, a1
+; RV64IM-NEXT: slli a3, a3, 24
+; RV64IM-NEXT: sd a3, 336(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: addi s1, s3, -256
+; RV64IM-NEXT: and t5, a0, a1
+; RV64IM-NEXT: slli a1, t2, 32
+; RV64IM-NEXT: addi s9, t3, -241
+; RV64IM-NEXT: addi t4, t4, 819
+; RV64IM-NEXT: addi t2, t6, 1365
+; RV64IM-NEXT: slli t3, a7, 11
+; RV64IM-NEXT: slli s11, a7, 32
+; RV64IM-NEXT: slli ra, a7, 33
+; RV64IM-NEXT: slli t6, a7, 34
+; RV64IM-NEXT: slli s2, a7, 35
+; RV64IM-NEXT: slli s4, a7, 36
+; RV64IM-NEXT: sd s4, 256(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a3, a6, a3
+; RV64IM-NEXT: or a2, a3, a2
+; RV64IM-NEXT: slli a3, a7, 37
+; RV64IM-NEXT: sd a3, 248(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s1, 304(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a3, a5, s1
+; RV64IM-NEXT: or a3, a3, s0
+; RV64IM-NEXT: slli a5, a7, 38
+; RV64IM-NEXT: sd a5, 232(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli t5, t5, 24
+; RV64IM-NEXT: and a0, a0, s1
+; RV64IM-NEXT: or a1, t5, a1
+; RV64IM-NEXT: slli a5, s9, 32
+; RV64IM-NEXT: add a5, s9, a5
+; RV64IM-NEXT: slli s0, t4, 32
+; RV64IM-NEXT: add t4, t4, s0
+; RV64IM-NEXT: slli s4, t2, 32
+; RV64IM-NEXT: slli a0, a0, 40
+; RV64IM-NEXT: add t2, t2, s4
+; RV64IM-NEXT: or a2, a2, a3
+; RV64IM-NEXT: or a0, t0, a0
+; RV64IM-NEXT: or a0, a0, a1
+; RV64IM-NEXT: or a0, a0, a2
+; RV64IM-NEXT: srli a1, a0, 4
+; RV64IM-NEXT: sd a5, 312(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, a0, a5
+; RV64IM-NEXT: and a1, a1, a5
+; RV64IM-NEXT: slli a0, a0, 4
+; RV64IM-NEXT: or a0, a1, a0
+; RV64IM-NEXT: srli a1, a0, 2
+; RV64IM-NEXT: sd t4, 320(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, a0, t4
+; RV64IM-NEXT: and a1, a1, t4
+; RV64IM-NEXT: slli a0, a0, 2
+; RV64IM-NEXT: or a0, a1, a0
+; RV64IM-NEXT: srli a1, a0, 1
+; RV64IM-NEXT: sd t2, 328(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, a0, t2
+; RV64IM-NEXT: and a1, a1, t2
+; RV64IM-NEXT: slli a0, a0, 1
+; RV64IM-NEXT: or t0, a1, a0
+; RV64IM-NEXT: andi a0, t0, 2
+; RV64IM-NEXT: andi a1, t0, 1
+; RV64IM-NEXT: andi a2, t0, 4
+; RV64IM-NEXT: andi a3, t0, 8
+; RV64IM-NEXT: andi a5, t0, 16
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: xor a0, a1, a0
+; RV64IM-NEXT: sd a0, 296(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi a0, t0, 32
+; RV64IM-NEXT: mul a1, t0, a2
+; RV64IM-NEXT: mul a2, t0, a3
+; RV64IM-NEXT: xor a1, a1, a2
+; RV64IM-NEXT: sd a1, 288(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi a1, t0, 256
+; RV64IM-NEXT: mul a2, t0, a5
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: xor a0, a2, a0
+; RV64IM-NEXT: sd a0, 280(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi a0, t0, 512
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: xor a0, a1, a0
+; RV64IM-NEXT: sd a0, 272(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli t4, a7, 39
+; RV64IM-NEXT: and a0, t0, s5
+; RV64IM-NEXT: and a1, t0, t1
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: xor a0, a0, a1
+; RV64IM-NEXT: sd a0, 264(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 40
+; RV64IM-NEXT: and a1, t0, a4
+; RV64IM-NEXT: and a2, t0, s7
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: xor a1, a1, a2
+; RV64IM-NEXT: sd a1, 240(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a1, a7, 41
+; RV64IM-NEXT: and a2, t0, s8
+; RV64IM-NEXT: and a3, t0, s10
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: mul a3, t0, a3
+; RV64IM-NEXT: xor a2, a2, a3
+; RV64IM-NEXT: sd a2, 224(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a2, a7, 48
+; RV64IM-NEXT: and a3, t0, s11
+; RV64IM-NEXT: and a4, t0, ra
+; RV64IM-NEXT: mul a3, t0, a3
+; RV64IM-NEXT: mul a4, t0, a4
+; RV64IM-NEXT: xor a3, a3, a4
+; RV64IM-NEXT: sd a3, 216(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a7, 49
+; RV64IM-NEXT: and a0, t0, a0
+; RV64IM-NEXT: and a1, t0, a1
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: xor a0, a0, a1
+; RV64IM-NEXT: sd a0, 208(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 56
+; RV64IM-NEXT: and a1, t0, a2
+; RV64IM-NEXT: and a2, t0, a3
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: xor a1, a1, a2
+; RV64IM-NEXT: sd a1, 200(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a1, a7, 57
+; RV64IM-NEXT: and a0, t0, a0
+; RV64IM-NEXT: and a1, t0, a1
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: xor a0, a0, a1
+; RV64IM-NEXT: sd a0, 192(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a2, a7, 42
+; RV64IM-NEXT: slli ra, a7, 43
+; RV64IM-NEXT: slli a3, a7, 44
+; RV64IM-NEXT: slli a4, a7, 45
+; RV64IM-NEXT: slli t5, a7, 46
+; RV64IM-NEXT: slli s0, a7, 47
+; RV64IM-NEXT: slli s1, a7, 50
+; RV64IM-NEXT: slli a0, a7, 51
+; RV64IM-NEXT: sd a0, 184(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 52
+; RV64IM-NEXT: sd a0, 176(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 53
+; RV64IM-NEXT: sd a0, 168(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 54
+; RV64IM-NEXT: sd a0, 160(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 55
+; RV64IM-NEXT: sd a0, 152(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 58
+; RV64IM-NEXT: sd a0, 144(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 59
+; RV64IM-NEXT: sd a0, 136(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 60
+; RV64IM-NEXT: sd a0, 120(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 61
+; RV64IM-NEXT: sd a0, 80(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a7, a7, 62
+; RV64IM-NEXT: sd a7, 48(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, t0, t3
+; RV64IM-NEXT: sd a0, 128(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s7, 1
+; RV64IM-NEXT: and a0, t0, s7
+; RV64IM-NEXT: sd a0, 112(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s8, 8
+; RV64IM-NEXT: and a0, t0, s8
+; RV64IM-NEXT: sd a0, 104(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, t0, s3
+; RV64IM-NEXT: sd a0, 96(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s6, 32
+; RV64IM-NEXT: and a0, t0, s6
+; RV64IM-NEXT: sd a0, 88(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s10, 64
+; RV64IM-NEXT: and a0, t0, s10
+; RV64IM-NEXT: sd a0, 72(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s11, 512
+; RV64IM-NEXT: and a0, t0, s11
+; RV64IM-NEXT: sd a0, 64(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s4, 1024
+; RV64IM-NEXT: and a0, t0, s4
+; RV64IM-NEXT: sd a0, 56(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s5, 2048
+; RV64IM-NEXT: and a0, t0, s5
+; RV64IM-NEXT: sd a0, 40(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s9, 16384
+; RV64IM-NEXT: and a0, t0, s9
+; RV64IM-NEXT: sd a0, 32(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui a5, 32768
+; RV64IM-NEXT: and a5, t0, a5
+; RV64IM-NEXT: lui a6, 65536
+; RV64IM-NEXT: and a6, t0, a6
+; RV64IM-NEXT: lui t1, 131072
+; RV64IM-NEXT: and t1, t0, t1
+; RV64IM-NEXT: lui t2, 262144
+; RV64IM-NEXT: and t2, t0, t2
+; RV64IM-NEXT: and a0, t0, t6
+; RV64IM-NEXT: sd a0, 24(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, t0, s2
+; RV64IM-NEXT: sd a0, 16(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a0, 256(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, t0, a0
+; RV64IM-NEXT: sd a0, 8(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a0, 248(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, t0, a0
+; RV64IM-NEXT: sd a0, 0(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a0, 232(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, t0, a0
+; RV64IM-NEXT: and a1, t0, t4
+; RV64IM-NEXT: and a7, t0, a2
+; RV64IM-NEXT: and ra, t0, ra
+; RV64IM-NEXT: and t3, t0, a3
+; RV64IM-NEXT: and t4, t0, a4
+; RV64IM-NEXT: and t5, t0, t5
+; RV64IM-NEXT: and t6, t0, s0
+; RV64IM-NEXT: and s0, t0, s1
+; RV64IM-NEXT: ld a2, 184(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s1, t0, a2
+; RV64IM-NEXT: ld a2, 176(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s2, t0, a2
+; RV64IM-NEXT: ld a2, 168(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s3, t0, a2
+; RV64IM-NEXT: ld a2, 160(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s4, t0, a2
+; RV64IM-NEXT: ld a2, 152(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s5, t0, a2
+; RV64IM-NEXT: ld a2, 144(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s6, t0, a2
+; RV64IM-NEXT: ld a2, 136(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s7, t0, a2
+; RV64IM-NEXT: ld a2, 120(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s8, t0, a2
+; RV64IM-NEXT: ld a2, 80(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s9, t0, a2
+; RV64IM-NEXT: ld a2, 48(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s10, t0, a2
+; RV64IM-NEXT: andi s11, t0, 64
+; RV64IM-NEXT: mul a2, t0, s11
+; RV64IM-NEXT: sd a2, 80(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi s11, t0, 128
+; RV64IM-NEXT: mul a2, t0, s11
+; RV64IM-NEXT: sd a2, 232(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi s11, t0, 1024
+; RV64IM-NEXT: mul a2, t0, s11
+; RV64IM-NEXT: sd a2, 48(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 128(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 120(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 112(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 176(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 104(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul s11, t0, a2
+; RV64IM-NEXT: ld a2, 96(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 104(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 88(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 168(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 72(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 256(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 64(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a4, t0, a2
+; RV64IM-NEXT: ld a2, 56(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 96(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 40(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 136(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 32(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a3, t0, a2
+; RV64IM-NEXT: mul a2, t0, a5
+; RV64IM-NEXT: sd a2, 88(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a2, t0, a6
+; RV64IM-NEXT: sd a2, 128(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a2, t0, t1
+; RV64IM-NEXT: sd a2, 160(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a2, t0, t2
+; RV64IM-NEXT: sd a2, 248(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: srliw t2, t0, 31
+; RV64IM-NEXT: slli t2, t2, 31
+; RV64IM-NEXT: ld a2, 24(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: ld a5, 16(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a5, t0, a5
+; RV64IM-NEXT: ld a6, 8(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul t1, t0, a6
+; RV64IM-NEXT: ld a6, 0(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a6, t0, a6
+; RV64IM-NEXT: sd a6, 112(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: sd a0, 152(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a0, t0, a1
+; RV64IM-NEXT: sd a0, 184(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a7, t0, a7
+; RV64IM-NEXT: mul ra, t0, ra
+; RV64IM-NEXT: mul a6, t0, t3
+; RV64IM-NEXT: mul t4, t0, t4
+; RV64IM-NEXT: mul t5, t0, t5
+; RV64IM-NEXT: mul a0, t0, t6
+; RV64IM-NEXT: sd a0, 144(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul t6, t0, s0
+; RV64IM-NEXT: mul s0, t0, s1
+; RV64IM-NEXT: mul s1, t0, s2
+; RV64IM-NEXT: mul s2, t0, s3
+; RV64IM-NEXT: mul s3, t0, s4
+; RV64IM-NEXT: mul s4, t0, s5
+; RV64IM-NEXT: mul s5, t0, s6
+; RV64IM-NEXT: mul s6, t0, s7
+; RV64IM-NEXT: mul s7, t0, s8
+; RV64IM-NEXT: mul s8, t0, s9
+; RV64IM-NEXT: mul s9, t0, s10
+; RV64IM-NEXT: srli s10, t0, 63
+; RV64IM-NEXT: slli s10, s10, 63
+; RV64IM-NEXT: mul t2, t0, t2
+; RV64IM-NEXT: mul t0, t0, s10
+; RV64IM-NEXT: ld a0, 296(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld a1, 288(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s10, a0, a1
+; RV64IM-NEXT: ld a0, 280(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld a1, 80(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a0, a0, a1
+; RV64IM-NEXT: ld a1, 272(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld t3, 48(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a1, a1, t3
+; RV64IM-NEXT: ld t3, 264(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s11, t3, s11
+; RV64IM-NEXT: ld t3, 240(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, t3, a4
+; RV64IM-NEXT: ld t3, 224(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, t3, a3
+; RV64IM-NEXT: ld t3, 216(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, t3, a2
+; RV64IM-NEXT: ld t3, 208(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a7, t3, a7
+; RV64IM-NEXT: ld t3, 200(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor t6, t3, t6
+; RV64IM-NEXT: ld t3, 192(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s5, t3, s5
+; RV64IM-NEXT: xor a0, s10, a0
+; RV64IM-NEXT: ld t3, 120(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a1, a1, t3
+; RV64IM-NEXT: ld t3, 104(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s10, s11, t3
+; RV64IM-NEXT: ld t3, 96(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, a4, t3
+; RV64IM-NEXT: ld t3, 88(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a3, t3
+; RV64IM-NEXT: xor a2, a2, a5
+; RV64IM-NEXT: xor a5, a7, ra
+; RV64IM-NEXT: xor a7, t6, s0
+; RV64IM-NEXT: xor t6, s5, s6
+; RV64IM-NEXT: ld t3, 232(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a0, a0, t3
+; RV64IM-NEXT: ld t3, 176(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a1, a1, t3
+; RV64IM-NEXT: ld t3, 168(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s0, s10, t3
+; RV64IM-NEXT: ld t3, 136(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, a4, t3
+; RV64IM-NEXT: ld t3, 128(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a3, t3
+; RV64IM-NEXT: xor a2, a2, t1
+; RV64IM-NEXT: xor a5, a5, a6
+; RV64IM-NEXT: xor a6, a7, s1
+; RV64IM-NEXT: xor a7, t6, s7
+; RV64IM-NEXT: ld t1, 256(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor t1, s0, t1
+; RV64IM-NEXT: ld t3, 160(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a3, t3
+; RV64IM-NEXT: ld t3, 112(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a2, t3
+; RV64IM-NEXT: xor a5, a5, t4
+; RV64IM-NEXT: xor a6, a6, s2
+; RV64IM-NEXT: xor a7, a7, s8
+; RV64IM-NEXT: xor a1, a0, a1
+; RV64IM-NEXT: xor a1, a1, t1
+; RV64IM-NEXT: ld t1, 248(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a3, t1
+; RV64IM-NEXT: ld t1, 152(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a2, t1
+; RV64IM-NEXT: xor a5, a5, t5
+; RV64IM-NEXT: xor a6, a6, s3
+; RV64IM-NEXT: xor a7, a7, s9
+; RV64IM-NEXT: xor a1, a1, a4
+; RV64IM-NEXT: xor a3, a3, t2
+; RV64IM-NEXT: ld a4, 184(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a2, a4
+; RV64IM-NEXT: ld a4, 144(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, a5, a4
+; RV64IM-NEXT: xor a5, a6, s4
+; RV64IM-NEXT: slli a0, a0, 56
+; RV64IM-NEXT: xor a6, a7, t0
+; RV64IM-NEXT: ld t0, 304(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a7, a1, t0
+; RV64IM-NEXT: xor a1, a1, a3
+; RV64IM-NEXT: slli a7, a7, 40
+; RV64IM-NEXT: xor a1, a1, a2
+; RV64IM-NEXT: or a0, a0, a7
+; RV64IM-NEXT: lui a7, 4080
+; RV64IM-NEXT: and a2, a1, a7
+; RV64IM-NEXT: xor a4, a1, a4
+; RV64IM-NEXT: srli a1, a1, 8
+; RV64IM-NEXT: slli a2, a2, 24
+; RV64IM-NEXT: xor a5, a4, a5
+; RV64IM-NEXT: ld a3, 336(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a1, a1, a3
+; RV64IM-NEXT: srli a4, a4, 24
+; RV64IM-NEXT: srliw a3, a5, 24
+; RV64IM-NEXT: and a4, a4, a7
+; RV64IM-NEXT: srli a7, a5, 40
+; RV64IM-NEXT: xor a5, a5, a6
+; RV64IM-NEXT: slli a3, a3, 32
+; RV64IM-NEXT: or a1, a1, a4
+; RV64IM-NEXT: and a4, a7, t0
+; RV64IM-NEXT: srli a5, a5, 56
+; RV64IM-NEXT: or a2, a2, a3
+; RV64IM-NEXT: or a4, a4, a5
+; RV64IM-NEXT: or a0, a0, a2
+; RV64IM-NEXT: or a1, a1, a4
+; RV64IM-NEXT: or a0, a0, a1
+; RV64IM-NEXT: srli a1, a0, 4
+; RV64IM-NEXT: ld a2, 312(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, a0, a2
+; RV64IM-NEXT: and a1, a1, a2
+; RV64IM-NEXT: slli a0, a0, 4
+; RV64IM-NEXT: or a0, a1, a0
+; RV64IM-NEXT: srli a1, a0, 2
+; RV64IM-NEXT: ld a2, 320(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, a0, a2
+; RV64IM-NEXT: and a1, a1, a2
+; RV64IM-NEXT: slli a0, a0, 2
+; RV64IM-NEXT: or a0, a1, a0
+; RV64IM-NEXT: srli a1, a0, 1
+; RV64IM-NEXT: ld a2, 328(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, a0, a2
+; RV64IM-NEXT: and a1, a1, a2
+; RV64IM-NEXT: slli a0, a0, 1
+; RV64IM-NEXT: or a0, a1, a0
+; RV64IM-NEXT: ld ra, 440(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s0, 432(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s1, 424(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s2, 416(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s3, 408(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s4, 400(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s5, 392(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s6, 384(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s7, 376(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s8, 368(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s9, 360(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s10, 352(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s11, 344(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: addi sp, sp, 448
+; RV64IM-NEXT: ret
+ %res = call i4 @llvm.clmulr.i4(i4 %a, i4 %b)
+ ret i4 %res
+}
+
+define i8 @clmulr_i8(i8 %a, i8 %b) nounwind {
+; RV32IM-LABEL: clmulr_i8:
+; RV32IM: # %bb.0:
+; RV32IM-NEXT: addi sp, sp, -144
+; RV32IM-NEXT: sw ra, 140(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s0, 136(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s1, 132(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s2, 128(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s3, 124(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s4, 120(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s5, 116(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s6, 112(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s7, 108(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s8, 104(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s9, 100(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s10, 96(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s11, 92(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: srli a3, a0, 8
+; RV32IM-NEXT: lui s9, 16
+; RV32IM-NEXT: srli a4, a0, 24
+; RV32IM-NEXT: slli a2, a0, 24
+; RV32IM-NEXT: lui a7, 61681
+; RV32IM-NEXT: lui ra, 209715
+; RV32IM-NEXT: lui a1, 349525
+; RV32IM-NEXT: li s0, 1
+; RV32IM-NEXT: lui t1, 1
+; RV32IM-NEXT: lui t2, 2
+; RV32IM-NEXT: lui t3, 4
+; RV32IM-NEXT: lui t4, 8
+; RV32IM-NEXT: lui t0, 32
+; RV32IM-NEXT: lui a6, 64
+; RV32IM-NEXT: lui a5, 128
+; RV32IM-NEXT: lui s1, 256
+; RV32IM-NEXT: lui t5, 512
+; RV32IM-NEXT: lui t6, 1024
+; RV32IM-NEXT: lui s4, 2048
+; RV32IM-NEXT: lui s2, 4096
+; RV32IM-NEXT: lui s3, 8192
+; RV32IM-NEXT: lui s7, 16384
+; RV32IM-NEXT: lui s5, 32768
+; RV32IM-NEXT: lui s6, 65536
+; RV32IM-NEXT: lui s11, 131072
+; RV32IM-NEXT: lui s8, 262144
+; RV32IM-NEXT: addi s10, s9, -256
+; RV32IM-NEXT: and a3, a3, s10
+; RV32IM-NEXT: or a3, a3, a4
+; RV32IM-NEXT: addi a7, a7, -241
+; RV32IM-NEXT: sw a7, 80(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: addi a4, ra, 819
+; RV32IM-NEXT: sw a4, 84(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: addi a1, a1, 1365
+; RV32IM-NEXT: sw a1, 88(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: slli s0, s0, 11
+; RV32IM-NEXT: and a0, a0, s10
+; RV32IM-NEXT: slli a0, a0, 8
+; RV32IM-NEXT: or a0, a2, a0
+; RV32IM-NEXT: or a0, a0, a3
+; RV32IM-NEXT: srli a2, a0, 4
+; RV32IM-NEXT: and a0, a0, a7
+; RV32IM-NEXT: and a2, a2, a7
+; RV32IM-NEXT: slli a0, a0, 4
+; RV32IM-NEXT: or a0, a2, a0
+; RV32IM-NEXT: srli a2, a0, 2
+; RV32IM-NEXT: and a0, a0, a4
+; RV32IM-NEXT: and a2, a2, a4
+; RV32IM-NEXT: slli a0, a0, 2
+; RV32IM-NEXT: or a0, a2, a0
+; RV32IM-NEXT: srli a2, a0, 1
+; RV32IM-NEXT: and a0, a0, a1
+; RV32IM-NEXT: and a2, a2, a1
+; RV32IM-NEXT: slli a0, a0, 1
+; RV32IM-NEXT: or a3, a2, a0
+; RV32IM-NEXT: andi a0, a3, 2
+; RV32IM-NEXT: andi a1, a3, 1
+; RV32IM-NEXT: and a4, a3, s0
+; RV32IM-NEXT: and a7, a3, t1
+; RV32IM-NEXT: and s0, a3, t2
+; RV32IM-NEXT: and ra, a3, t3
+; RV32IM-NEXT: and a2, a3, t4
+; RV32IM-NEXT: sw a2, 68(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a2, a3, s9
+; RV32IM-NEXT: sw a2, 64(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a2, a3, t0
+; RV32IM-NEXT: sw a2, 60(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a6, a3, a6
+; RV32IM-NEXT: and a5, a3, a5
+; RV32IM-NEXT: and s1, a3, s1
+; RV32IM-NEXT: sw s1, 56(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a2, a3, t5
+; RV32IM-NEXT: sw a2, 52(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and t6, a3, t6
+; RV32IM-NEXT: and a2, a3, s4
+; RV32IM-NEXT: sw a2, 48(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and s2, a3, s2
+; RV32IM-NEXT: and a2, a3, s3
+; RV32IM-NEXT: sw a2, 44(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a2, a3, s7
+; RV32IM-NEXT: sw a2, 40(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a2, a3, s5
+; RV32IM-NEXT: sw a2, 36(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a2, a3, s6
+; RV32IM-NEXT: sw a2, 32(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a2, a3, s11
+; RV32IM-NEXT: sw a2, 28(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a2, a3, s8
+; RV32IM-NEXT: sw a2, 24(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lui a2, 524288
+; RV32IM-NEXT: and a2, a3, a2
+; RV32IM-NEXT: sw a2, 20(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a0, a3, a0
+; RV32IM-NEXT: sw a0, 72(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a0, a3, a1
+; RV32IM-NEXT: sw a0, 16(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi a0, a3, 4
+; RV32IM-NEXT: mul a0, a3, a0
+; RV32IM-NEXT: sw a0, 12(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi a1, a3, 8
+; RV32IM-NEXT: mul a0, a3, a1
+; RV32IM-NEXT: sw a0, 0(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi a2, a3, 16
+; RV32IM-NEXT: mul s9, a3, a2
+; RV32IM-NEXT: andi t0, a3, 32
+; RV32IM-NEXT: mul s6, a3, t0
+; RV32IM-NEXT: andi t1, a3, 64
+; RV32IM-NEXT: mul a0, a3, t1
+; RV32IM-NEXT: sw a0, 4(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi t2, a3, 128
+; RV32IM-NEXT: mul a0, a3, t2
+; RV32IM-NEXT: sw a0, 76(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi t2, a3, 256
+; RV32IM-NEXT: mul s1, a3, t2
+; RV32IM-NEXT: andi t3, a3, 512
+; RV32IM-NEXT: mul t5, a3, t3
+; RV32IM-NEXT: andi t4, a3, 1024
+; RV32IM-NEXT: mul s5, a3, t4
+; RV32IM-NEXT: mul s8, a3, a4
+; RV32IM-NEXT: mul a0, a3, a7
+; RV32IM-NEXT: sw a0, 8(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul t2, a3, s0
+; RV32IM-NEXT: mul a7, a3, ra
+; RV32IM-NEXT: lw a0, 68(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s0, a3, a0
+; RV32IM-NEXT: lw a0, 64(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s4, a3, a0
+; RV32IM-NEXT: lw a0, 60(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s7, a3, a0
+; RV32IM-NEXT: mul a0, a3, a6
+; RV32IM-NEXT: sw a0, 68(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a6, a3, a5
+; RV32IM-NEXT: lw a0, 56(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a4, a3, a0
+; RV32IM-NEXT: lw a0, 52(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul t1, a3, a0
+; RV32IM-NEXT: mul t4, a3, t6
+; RV32IM-NEXT: lw a0, 48(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s3, a3, a0
+; RV32IM-NEXT: mul a2, a3, s2
+; RV32IM-NEXT: lw a0, 44(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a1, a3, a0
+; RV32IM-NEXT: lw a0, 40(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a5, a3, a0
+; RV32IM-NEXT: lw a0, 36(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul t0, a3, a0
+; RV32IM-NEXT: lw a0, 32(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul t3, a3, a0
+; RV32IM-NEXT: lw a0, 28(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul t6, a3, a0
+; RV32IM-NEXT: lw a0, 24(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s2, a3, a0
+; RV32IM-NEXT: lw a0, 20(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a3, a3, a0
+; RV32IM-NEXT: lw a0, 72(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s11, 16(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a0, s11, a0
+; RV32IM-NEXT: lw s11, 12(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw ra, 0(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor s11, s11, ra
+; RV32IM-NEXT: xor s6, s9, s6
+; RV32IM-NEXT: xor t5, s1, t5
+; RV32IM-NEXT: xor a7, t2, a7
+; RV32IM-NEXT: xor a4, a6, a4
+; RV32IM-NEXT: xor a1, a2, a1
+; RV32IM-NEXT: xor a0, a0, s11
+; RV32IM-NEXT: lw a2, 4(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a2, s6, a2
+; RV32IM-NEXT: xor a6, t5, s5
+; RV32IM-NEXT: xor a7, a7, s0
+; RV32IM-NEXT: xor a4, a4, t1
+; RV32IM-NEXT: xor a1, a1, a5
+; RV32IM-NEXT: xor a0, a0, a2
+; RV32IM-NEXT: xor a2, a6, s8
+; RV32IM-NEXT: xor a5, a7, s4
+; RV32IM-NEXT: xor a4, a4, t4
+; RV32IM-NEXT: xor a1, a1, t0
+; RV32IM-NEXT: lw a6, 76(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a0, a0, a6
+; RV32IM-NEXT: lw a6, 8(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a2, a2, a6
+; RV32IM-NEXT: xor a5, a5, s7
+; RV32IM-NEXT: xor a4, a4, s3
+; RV32IM-NEXT: xor a1, a1, t3
+; RV32IM-NEXT: lw a6, 68(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a5, a5, a6
+; RV32IM-NEXT: xor a1, a1, t6
+; RV32IM-NEXT: xor a2, a0, a2
+; RV32IM-NEXT: xor a2, a2, a5
+; RV32IM-NEXT: slli a0, a0, 24
+; RV32IM-NEXT: xor a1, a1, s2
+; RV32IM-NEXT: xor a2, a2, a4
+; RV32IM-NEXT: xor a1, a1, a3
+; RV32IM-NEXT: and a3, a2, s10
+; RV32IM-NEXT: srli a4, a2, 8
+; RV32IM-NEXT: xor a1, a2, a1
+; RV32IM-NEXT: slli a3, a3, 8
+; RV32IM-NEXT: and a2, a4, s10
+; RV32IM-NEXT: srli a1, a1, 24
+; RV32IM-NEXT: or a0, a0, a3
+; RV32IM-NEXT: or a1, a2, a1
+; RV32IM-NEXT: or a0, a0, a1
+; RV32IM-NEXT: srli a1, a0, 4
+; RV32IM-NEXT: lw a2, 80(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: and a0, a0, a2
+; RV32IM-NEXT: and a1, a1, a2
+; RV32IM-NEXT: slli a0, a0, 4
+; RV32IM-NEXT: or a0, a1, a0
+; RV32IM-NEXT: srli a1, a0, 2
+; RV32IM-NEXT: lw a2, 84(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: and a0, a0, a2
+; RV32IM-NEXT: and a1, a1, a2
+; RV32IM-NEXT: slli a0, a0, 2
+; RV32IM-NEXT: or a0, a1, a0
+; RV32IM-NEXT: srli a1, a0, 1
+; RV32IM-NEXT: lw a2, 88(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: and a0, a0, a2
+; RV32IM-NEXT: and a1, a1, a2
+; RV32IM-NEXT: slli a0, a0, 1
+; RV32IM-NEXT: or a0, a1, a0
+; RV32IM-NEXT: lw ra, 140(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s0, 136(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s1, 132(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s2, 128(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s3, 124(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s4, 120(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s5, 116(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s6, 112(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s7, 108(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s8, 104(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s9, 100(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s10, 96(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s11, 92(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: addi sp, sp, 144
+; RV32IM-NEXT: ret
+;
+; RV64IM-LABEL: clmulr_i8:
+; RV64IM: # %bb.0:
+; RV64IM-NEXT: addi sp, sp, -448
+; RV64IM-NEXT: sd ra, 440(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s0, 432(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s1, 424(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s2, 416(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s3, 408(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s4, 400(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s5, 392(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s6, 384(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s7, 376(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s8, 368(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s9, 360(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s10, 352(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s11, 344(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: srli a2, a0, 24
+; RV64IM-NEXT: srli a6, a0, 8
+; RV64IM-NEXT: li a3, 255
+; RV64IM-NEXT: srli a5, a0, 40
+; RV64IM-NEXT: lui s3, 16
+; RV64IM-NEXT: srli s0, a0, 56
+; RV64IM-NEXT: srliw t2, a0, 24
+; RV64IM-NEXT: slli t0, a0, 56
+; RV64IM-NEXT: lui t3, 61681
+; RV64IM-NEXT: lui t4, 209715
+; RV64IM-NEXT: lui t6, 349525
+; RV64IM-NEXT: li a7, 1
+; RV64IM-NEXT: lui s5, 2
+; RV64IM-NEXT: lui t1, 4
+; RV64IM-NEXT: lui a4, 128
+; RV64IM-NEXT: lui s7, 256
+; RV64IM-NEXT: lui s8, 4096
+; RV64IM-NEXT: lui s10, 8192
+; RV64IM-NEXT: lui a1, 4080
+; RV64IM-NEXT: and a2, a2, a1
+; RV64IM-NEXT: slli a3, a3, 24
+; RV64IM-NEXT: sd a3, 336(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: addi s1, s3, -256
+; RV64IM-NEXT: and t5, a0, a1
+; RV64IM-NEXT: slli a1, t2, 32
+; RV64IM-NEXT: addi s9, t3, -241
+; RV64IM-NEXT: addi t4, t4, 819
+; RV64IM-NEXT: addi t2, t6, 1365
+; RV64IM-NEXT: slli t3, a7, 11
+; RV64IM-NEXT: slli s11, a7, 32
+; RV64IM-NEXT: slli ra, a7, 33
+; RV64IM-NEXT: slli t6, a7, 34
+; RV64IM-NEXT: slli s2, a7, 35
+; RV64IM-NEXT: slli s4, a7, 36
+; RV64IM-NEXT: sd s4, 256(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a3, a6, a3
+; RV64IM-NEXT: or a2, a3, a2
+; RV64IM-NEXT: slli a3, a7, 37
+; RV64IM-NEXT: sd a3, 248(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s1, 304(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a3, a5, s1
+; RV64IM-NEXT: or a3, a3, s0
+; RV64IM-NEXT: slli a5, a7, 38
+; RV64IM-NEXT: sd a5, 232(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli t5, t5, 24
+; RV64IM-NEXT: and a0, a0, s1
+; RV64IM-NEXT: or a1, t5, a1
+; RV64IM-NEXT: slli a5, s9, 32
+; RV64IM-NEXT: add a5, s9, a5
+; RV64IM-NEXT: slli s0, t4, 32
+; RV64IM-NEXT: add t4, t4, s0
+; RV64IM-NEXT: slli s4, t2, 32
+; RV64IM-NEXT: slli a0, a0, 40
+; RV64IM-NEXT: add t2, t2, s4
+; RV64IM-NEXT: or a2, a2, a3
+; RV64IM-NEXT: or a0, t0, a0
+; RV64IM-NEXT: or a0, a0, a1
+; RV64IM-NEXT: or a0, a0, a2
+; RV64IM-NEXT: srli a1, a0, 4
+; RV64IM-NEXT: sd a5, 312(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, a0, a5
+; RV64IM-NEXT: and a1, a1, a5
+; RV64IM-NEXT: slli a0, a0, 4
+; RV64IM-NEXT: or a0, a1, a0
+; RV64IM-NEXT: srli a1, a0, 2
+; RV64IM-NEXT: sd t4, 320(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, a0, t4
+; RV64IM-NEXT: and a1, a1, t4
+; RV64IM-NEXT: slli a0, a0, 2
+; RV64IM-NEXT: or a0, a1, a0
+; RV64IM-NEXT: srli a1, a0, 1
+; RV64IM-NEXT: sd t2, 328(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, a0, t2
+; RV64IM-NEXT: and a1, a1, t2
+; RV64IM-NEXT: slli a0, a0, 1
+; RV64IM-NEXT: or t0, a1, a0
+; RV64IM-NEXT: andi a0, t0, 2
+; RV64IM-NEXT: andi a1, t0, 1
+; RV64IM-NEXT: andi a2, t0, 4
+; RV64IM-NEXT: andi a3, t0, 8
+; RV64IM-NEXT: andi a5, t0, 16
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: xor a0, a1, a0
+; RV64IM-NEXT: sd a0, 296(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi a0, t0, 32
+; RV64IM-NEXT: mul a1, t0, a2
+; RV64IM-NEXT: mul a2, t0, a3
+; RV64IM-NEXT: xor a1, a1, a2
+; RV64IM-NEXT: sd a1, 288(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi a1, t0, 256
+; RV64IM-NEXT: mul a2, t0, a5
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: xor a0, a2, a0
+; RV64IM-NEXT: sd a0, 280(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi a0, t0, 512
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: xor a0, a1, a0
+; RV64IM-NEXT: sd a0, 272(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli t4, a7, 39
+; RV64IM-NEXT: and a0, t0, s5
+; RV64IM-NEXT: and a1, t0, t1
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: xor a0, a0, a1
+; RV64IM-NEXT: sd a0, 264(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 40
+; RV64IM-NEXT: and a1, t0, a4
+; RV64IM-NEXT: and a2, t0, s7
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: xor a1, a1, a2
+; RV64IM-NEXT: sd a1, 240(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a1, a7, 41
+; RV64IM-NEXT: and a2, t0, s8
+; RV64IM-NEXT: and a3, t0, s10
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: mul a3, t0, a3
+; RV64IM-NEXT: xor a2, a2, a3
+; RV64IM-NEXT: sd a2, 224(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a2, a7, 48
+; RV64IM-NEXT: and a3, t0, s11
+; RV64IM-NEXT: and a4, t0, ra
+; RV64IM-NEXT: mul a3, t0, a3
+; RV64IM-NEXT: mul a4, t0, a4
+; RV64IM-NEXT: xor a3, a3, a4
+; RV64IM-NEXT: sd a3, 216(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a7, 49
+; RV64IM-NEXT: and a0, t0, a0
+; RV64IM-NEXT: and a1, t0, a1
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: xor a0, a0, a1
+; RV64IM-NEXT: sd a0, 208(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 56
+; RV64IM-NEXT: and a1, t0, a2
+; RV64IM-NEXT: and a2, t0, a3
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: xor a1, a1, a2
+; RV64IM-NEXT: sd a1, 200(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a1, a7, 57
+; RV64IM-NEXT: and a0, t0, a0
+; RV64IM-NEXT: and a1, t0, a1
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: xor a0, a0, a1
+; RV64IM-NEXT: sd a0, 192(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a2, a7, 42
+; RV64IM-NEXT: slli ra, a7, 43
+; RV64IM-NEXT: slli a3, a7, 44
+; RV64IM-NEXT: slli a4, a7, 45
+; RV64IM-NEXT: slli t5, a7, 46
+; RV64IM-NEXT: slli s0, a7, 47
+; RV64IM-NEXT: slli s1, a7, 50
+; RV64IM-NEXT: slli a0, a7, 51
+; RV64IM-NEXT: sd a0, 184(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 52
+; RV64IM-NEXT: sd a0, 176(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 53
+; RV64IM-NEXT: sd a0, 168(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 54
+; RV64IM-NEXT: sd a0, 160(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 55
+; RV64IM-NEXT: sd a0, 152(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 58
+; RV64IM-NEXT: sd a0, 144(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 59
+; RV64IM-NEXT: sd a0, 136(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 60
+; RV64IM-NEXT: sd a0, 120(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 61
+; RV64IM-NEXT: sd a0, 80(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a7, a7, 62
+; RV64IM-NEXT: sd a7, 48(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, t0, t3
+; RV64IM-NEXT: sd a0, 128(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s7, 1
+; RV64IM-NEXT: and a0, t0, s7
+; RV64IM-NEXT: sd a0, 112(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s8, 8
+; RV64IM-NEXT: and a0, t0, s8
+; RV64IM-NEXT: sd a0, 104(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, t0, s3
+; RV64IM-NEXT: sd a0, 96(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s6, 32
+; RV64IM-NEXT: and a0, t0, s6
+; RV64IM-NEXT: sd a0, 88(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s10, 64
+; RV64IM-NEXT: and a0, t0, s10
+; RV64IM-NEXT: sd a0, 72(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s11, 512
+; RV64IM-NEXT: and a0, t0, s11
+; RV64IM-NEXT: sd a0, 64(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s4, 1024
+; RV64IM-NEXT: and a0, t0, s4
+; RV64IM-NEXT: sd a0, 56(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s5, 2048
+; RV64IM-NEXT: and a0, t0, s5
+; RV64IM-NEXT: sd a0, 40(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s9, 16384
+; RV64IM-NEXT: and a0, t0, s9
+; RV64IM-NEXT: sd a0, 32(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui a5, 32768
+; RV64IM-NEXT: and a5, t0, a5
+; RV64IM-NEXT: lui a6, 65536
+; RV64IM-NEXT: and a6, t0, a6
+; RV64IM-NEXT: lui t1, 131072
+; RV64IM-NEXT: and t1, t0, t1
+; RV64IM-NEXT: lui t2, 262144
+; RV64IM-NEXT: and t2, t0, t2
+; RV64IM-NEXT: and a0, t0, t6
+; RV64IM-NEXT: sd a0, 24(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, t0, s2
+; RV64IM-NEXT: sd a0, 16(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a0, 256(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, t0, a0
+; RV64IM-NEXT: sd a0, 8(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a0, 248(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, t0, a0
+; RV64IM-NEXT: sd a0, 0(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a0, 232(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, t0, a0
+; RV64IM-NEXT: and a1, t0, t4
+; RV64IM-NEXT: and a7, t0, a2
+; RV64IM-NEXT: and ra, t0, ra
+; RV64IM-NEXT: and t3, t0, a3
+; RV64IM-NEXT: and t4, t0, a4
+; RV64IM-NEXT: and t5, t0, t5
+; RV64IM-NEXT: and t6, t0, s0
+; RV64IM-NEXT: and s0, t0, s1
+; RV64IM-NEXT: ld a2, 184(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s1, t0, a2
+; RV64IM-NEXT: ld a2, 176(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s2, t0, a2
+; RV64IM-NEXT: ld a2, 168(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s3, t0, a2
+; RV64IM-NEXT: ld a2, 160(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s4, t0, a2
+; RV64IM-NEXT: ld a2, 152(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s5, t0, a2
+; RV64IM-NEXT: ld a2, 144(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s6, t0, a2
+; RV64IM-NEXT: ld a2, 136(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s7, t0, a2
+; RV64IM-NEXT: ld a2, 120(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s8, t0, a2
+; RV64IM-NEXT: ld a2, 80(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s9, t0, a2
+; RV64IM-NEXT: ld a2, 48(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s10, t0, a2
+; RV64IM-NEXT: andi s11, t0, 64
+; RV64IM-NEXT: mul a2, t0, s11
+; RV64IM-NEXT: sd a2, 80(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi s11, t0, 128
+; RV64IM-NEXT: mul a2, t0, s11
+; RV64IM-NEXT: sd a2, 232(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi s11, t0, 1024
+; RV64IM-NEXT: mul a2, t0, s11
+; RV64IM-NEXT: sd a2, 48(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 128(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 120(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 112(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 176(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 104(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul s11, t0, a2
+; RV64IM-NEXT: ld a2, 96(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 104(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 88(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 168(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 72(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 256(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 64(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a4, t0, a2
+; RV64IM-NEXT: ld a2, 56(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 96(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 40(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 136(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 32(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a3, t0, a2
+; RV64IM-NEXT: mul a2, t0, a5
+; RV64IM-NEXT: sd a2, 88(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a2, t0, a6
+; RV64IM-NEXT: sd a2, 128(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a2, t0, t1
+; RV64IM-NEXT: sd a2, 160(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a2, t0, t2
+; RV64IM-NEXT: sd a2, 248(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: srliw t2, t0, 31
+; RV64IM-NEXT: slli t2, t2, 31
+; RV64IM-NEXT: ld a2, 24(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: ld a5, 16(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a5, t0, a5
+; RV64IM-NEXT: ld a6, 8(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul t1, t0, a6
+; RV64IM-NEXT: ld a6, 0(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a6, t0, a6
+; RV64IM-NEXT: sd a6, 112(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: sd a0, 152(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a0, t0, a1
+; RV64IM-NEXT: sd a0, 184(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a7, t0, a7
+; RV64IM-NEXT: mul ra, t0, ra
+; RV64IM-NEXT: mul a6, t0, t3
+; RV64IM-NEXT: mul t4, t0, t4
+; RV64IM-NEXT: mul t5, t0, t5
+; RV64IM-NEXT: mul a0, t0, t6
+; RV64IM-NEXT: sd a0, 144(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul t6, t0, s0
+; RV64IM-NEXT: mul s0, t0, s1
+; RV64IM-NEXT: mul s1, t0, s2
+; RV64IM-NEXT: mul s2, t0, s3
+; RV64IM-NEXT: mul s3, t0, s4
+; RV64IM-NEXT: mul s4, t0, s5
+; RV64IM-NEXT: mul s5, t0, s6
+; RV64IM-NEXT: mul s6, t0, s7
+; RV64IM-NEXT: mul s7, t0, s8
+; RV64IM-NEXT: mul s8, t0, s9
+; RV64IM-NEXT: mul s9, t0, s10
+; RV64IM-NEXT: srli s10, t0, 63
+; RV64IM-NEXT: slli s10, s10, 63
+; RV64IM-NEXT: mul t2, t0, t2
+; RV64IM-NEXT: mul t0, t0, s10
+; RV64IM-NEXT: ld a0, 296(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld a1, 288(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s10, a0, a1
+; RV64IM-NEXT: ld a0, 280(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld a1, 80(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a0, a0, a1
+; RV64IM-NEXT: ld a1, 272(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld t3, 48(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a1, a1, t3
+; RV64IM-NEXT: ld t3, 264(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s11, t3, s11
+; RV64IM-NEXT: ld t3, 240(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, t3, a4
+; RV64IM-NEXT: ld t3, 224(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, t3, a3
+; RV64IM-NEXT: ld t3, 216(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, t3, a2
+; RV64IM-NEXT: ld t3, 208(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a7, t3, a7
+; RV64IM-NEXT: ld t3, 200(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor t6, t3, t6
+; RV64IM-NEXT: ld t3, 192(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s5, t3, s5
+; RV64IM-NEXT: xor a0, s10, a0
+; RV64IM-NEXT: ld t3, 120(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a1, a1, t3
+; RV64IM-NEXT: ld t3, 104(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s10, s11, t3
+; RV64IM-NEXT: ld t3, 96(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, a4, t3
+; RV64IM-NEXT: ld t3, 88(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a3, t3
+; RV64IM-NEXT: xor a2, a2, a5
+; RV64IM-NEXT: xor a5, a7, ra
+; RV64IM-NEXT: xor a7, t6, s0
+; RV64IM-NEXT: xor t6, s5, s6
+; RV64IM-NEXT: ld t3, 232(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a0, a0, t3
+; RV64IM-NEXT: ld t3, 176(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a1, a1, t3
+; RV64IM-NEXT: ld t3, 168(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s0, s10, t3
+; RV64IM-NEXT: ld t3, 136(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, a4, t3
+; RV64IM-NEXT: ld t3, 128(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a3, t3
+; RV64IM-NEXT: xor a2, a2, t1
+; RV64IM-NEXT: xor a5, a5, a6
+; RV64IM-NEXT: xor a6, a7, s1
+; RV64IM-NEXT: xor a7, t6, s7
+; RV64IM-NEXT: ld t1, 256(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor t1, s0, t1
+; RV64IM-NEXT: ld t3, 160(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a3, t3
+; RV64IM-NEXT: ld t3, 112(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a2, t3
+; RV64IM-NEXT: xor a5, a5, t4
+; RV64IM-NEXT: xor a6, a6, s2
+; RV64IM-NEXT: xor a7, a7, s8
+; RV64IM-NEXT: xor a1, a0, a1
+; RV64IM-NEXT: xor a1, a1, t1
+; RV64IM-NEXT: ld t1, 248(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a3, t1
+; RV64IM-NEXT: ld t1, 152(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a2, t1
+; RV64IM-NEXT: xor a5, a5, t5
+; RV64IM-NEXT: xor a6, a6, s3
+; RV64IM-NEXT: xor a7, a7, s9
+; RV64IM-NEXT: xor a1, a1, a4
+; RV64IM-NEXT: xor a3, a3, t2
+; RV64IM-NEXT: ld a4, 184(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a2, a4
+; RV64IM-NEXT: ld a4, 144(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, a5, a4
+; RV64IM-NEXT: xor a5, a6, s4
+; RV64IM-NEXT: slli a0, a0, 56
+; RV64IM-NEXT: xor a6, a7, t0
+; RV64IM-NEXT: ld t0, 304(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a7, a1, t0
+; RV64IM-NEXT: xor a1, a1, a3
+; RV64IM-NEXT: slli a7, a7, 40
+; RV64IM-NEXT: xor a1, a1, a2
+; RV64IM-NEXT: or a0, a0, a7
+; RV64IM-NEXT: lui a7, 4080
+; RV64IM-NEXT: and a2, a1, a7
+; RV64IM-NEXT: xor a4, a1, a4
+; RV64IM-NEXT: srli a1, a1, 8
+; RV64IM-NEXT: slli a2, a2, 24
+; RV64IM-NEXT: xor a5, a4, a5
+; RV64IM-NEXT: ld a3, 336(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a1, a1, a3
+; RV64IM-NEXT: srli a4, a4, 24
+; RV64IM-NEXT: srliw a3, a5, 24
+; RV64IM-NEXT: and a4, a4, a7
+; RV64IM-NEXT: srli a7, a5, 40
+; RV64IM-NEXT: xor a5, a5, a6
+; RV64IM-NEXT: slli a3, a3, 32
+; RV64IM-NEXT: or a1, a1, a4
+; RV64IM-NEXT: and a4, a7, t0
+; RV64IM-NEXT: srli a5, a5, 56
+; RV64IM-NEXT: or a2, a2, a3
+; RV64IM-NEXT: or a4, a4, a5
+; RV64IM-NEXT: or a0, a0, a2
+; RV64IM-NEXT: or a1, a1, a4
+; RV64IM-NEXT: or a0, a0, a1
+; RV64IM-NEXT: srli a1, a0, 4
+; RV64IM-NEXT: ld a2, 312(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, a0, a2
+; RV64IM-NEXT: and a1, a1, a2
+; RV64IM-NEXT: slli a0, a0, 4
+; RV64IM-NEXT: or a0, a1, a0
+; RV64IM-NEXT: srli a1, a0, 2
+; RV64IM-NEXT: ld a2, 320(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, a0, a2
+; RV64IM-NEXT: and a1, a1, a2
+; RV64IM-NEXT: slli a0, a0, 2
+; RV64IM-NEXT: or a0, a1, a0
+; RV64IM-NEXT: srli a1, a0, 1
+; RV64IM-NEXT: ld a2, 328(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, a0, a2
+; RV64IM-NEXT: and a1, a1, a2
+; RV64IM-NEXT: slli a0, a0, 1
+; RV64IM-NEXT: or a0, a1, a0
+; RV64IM-NEXT: ld ra, 440(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s0, 432(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s1, 424(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s2, 416(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s3, 408(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s4, 400(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s5, 392(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s6, 384(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s7, 376(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s8, 368(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s9, 360(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s10, 352(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s11, 344(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: addi sp, sp, 448
+; RV64IM-NEXT: ret
+ %res = call i8 @llvm.clmulr.i8(i8 %a, i8 %b)
+ ret i8 %res
+}
+
+define i16 @clmulr_i16(i16 %a, i16 %b) nounwind {
+; RV32IM-LABEL: clmulr_i16:
+; RV32IM: # %bb.0:
+; RV32IM-NEXT: addi sp, sp, -144
+; RV32IM-NEXT: sw ra, 140(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s0, 136(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s1, 132(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s2, 128(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s3, 124(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s4, 120(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s5, 116(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s6, 112(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s7, 108(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s8, 104(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s9, 100(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s10, 96(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s11, 92(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: srli a3, a0, 8
+; RV32IM-NEXT: lui s9, 16
+; RV32IM-NEXT: srli a4, a0, 24
+; RV32IM-NEXT: slli a2, a0, 24
+; RV32IM-NEXT: lui a7, 61681
+; RV32IM-NEXT: lui ra, 209715
+; RV32IM-NEXT: lui a1, 349525
+; RV32IM-NEXT: li s0, 1
+; RV32IM-NEXT: lui t1, 1
+; RV32IM-NEXT: lui t2, 2
+; RV32IM-NEXT: lui t3, 4
+; RV32IM-NEXT: lui t4, 8
+; RV32IM-NEXT: lui t0, 32
+; RV32IM-NEXT: lui a6, 64
+; RV32IM-NEXT: lui a5, 128
+; RV32IM-NEXT: lui s1, 256
+; RV32IM-NEXT: lui t5, 512
+; RV32IM-NEXT: lui t6, 1024
+; RV32IM-NEXT: lui s4, 2048
+; RV32IM-NEXT: lui s2, 4096
+; RV32IM-NEXT: lui s3, 8192
+; RV32IM-NEXT: lui s7, 16384
+; RV32IM-NEXT: lui s5, 32768
+; RV32IM-NEXT: lui s6, 65536
+; RV32IM-NEXT: lui s11, 131072
+; RV32IM-NEXT: lui s8, 262144
+; RV32IM-NEXT: addi s10, s9, -256
+; RV32IM-NEXT: and a3, a3, s10
+; RV32IM-NEXT: or a3, a3, a4
+; RV32IM-NEXT: addi a7, a7, -241
+; RV32IM-NEXT: sw a7, 80(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: addi a4, ra, 819
+; RV32IM-NEXT: sw a4, 84(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: addi a1, a1, 1365
+; RV32IM-NEXT: sw a1, 88(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: slli s0, s0, 11
+; RV32IM-NEXT: and a0, a0, s10
+; RV32IM-NEXT: slli a0, a0, 8
+; RV32IM-NEXT: or a0, a2, a0
+; RV32IM-NEXT: or a0, a0, a3
+; RV32IM-NEXT: srli a2, a0, 4
+; RV32IM-NEXT: and a0, a0, a7
+; RV32IM-NEXT: and a2, a2, a7
+; RV32IM-NEXT: slli a0, a0, 4
+; RV32IM-NEXT: or a0, a2, a0
+; RV32IM-NEXT: srli a2, a0, 2
+; RV32IM-NEXT: and a0, a0, a4
+; RV32IM-NEXT: and a2, a2, a4
+; RV32IM-NEXT: slli a0, a0, 2
+; RV32IM-NEXT: or a0, a2, a0
+; RV32IM-NEXT: srli a2, a0, 1
+; RV32IM-NEXT: and a0, a0, a1
+; RV32IM-NEXT: and a2, a2, a1
+; RV32IM-NEXT: slli a0, a0, 1
+; RV32IM-NEXT: or a3, a2, a0
+; RV32IM-NEXT: andi a0, a3, 2
+; RV32IM-NEXT: andi a1, a3, 1
+; RV32IM-NEXT: and a4, a3, s0
+; RV32IM-NEXT: and a7, a3, t1
+; RV32IM-NEXT: and s0, a3, t2
+; RV32IM-NEXT: and ra, a3, t3
+; RV32IM-NEXT: and a2, a3, t4
+; RV32IM-NEXT: sw a2, 68(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a2, a3, s9
+; RV32IM-NEXT: sw a2, 64(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a2, a3, t0
+; RV32IM-NEXT: sw a2, 60(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a6, a3, a6
+; RV32IM-NEXT: and a5, a3, a5
+; RV32IM-NEXT: and s1, a3, s1
+; RV32IM-NEXT: sw s1, 56(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a2, a3, t5
+; RV32IM-NEXT: sw a2, 52(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and t6, a3, t6
+; RV32IM-NEXT: and a2, a3, s4
+; RV32IM-NEXT: sw a2, 48(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and s2, a3, s2
+; RV32IM-NEXT: and a2, a3, s3
+; RV32IM-NEXT: sw a2, 44(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a2, a3, s7
+; RV32IM-NEXT: sw a2, 40(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a2, a3, s5
+; RV32IM-NEXT: sw a2, 36(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a2, a3, s6
+; RV32IM-NEXT: sw a2, 32(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a2, a3, s11
+; RV32IM-NEXT: sw a2, 28(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a2, a3, s8
+; RV32IM-NEXT: sw a2, 24(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lui a2, 524288
+; RV32IM-NEXT: and a2, a3, a2
+; RV32IM-NEXT: sw a2, 20(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a0, a3, a0
+; RV32IM-NEXT: sw a0, 72(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a0, a3, a1
+; RV32IM-NEXT: sw a0, 16(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi a0, a3, 4
+; RV32IM-NEXT: mul a0, a3, a0
+; RV32IM-NEXT: sw a0, 12(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi a1, a3, 8
+; RV32IM-NEXT: mul a0, a3, a1
+; RV32IM-NEXT: sw a0, 0(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi a2, a3, 16
+; RV32IM-NEXT: mul s9, a3, a2
+; RV32IM-NEXT: andi t0, a3, 32
+; RV32IM-NEXT: mul s6, a3, t0
+; RV32IM-NEXT: andi t1, a3, 64
+; RV32IM-NEXT: mul a0, a3, t1
+; RV32IM-NEXT: sw a0, 4(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi t2, a3, 128
+; RV32IM-NEXT: mul a0, a3, t2
+; RV32IM-NEXT: sw a0, 76(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi t2, a3, 256
+; RV32IM-NEXT: mul s1, a3, t2
+; RV32IM-NEXT: andi t3, a3, 512
+; RV32IM-NEXT: mul t5, a3, t3
+; RV32IM-NEXT: andi t4, a3, 1024
+; RV32IM-NEXT: mul s5, a3, t4
+; RV32IM-NEXT: mul s8, a3, a4
+; RV32IM-NEXT: mul a0, a3, a7
+; RV32IM-NEXT: sw a0, 8(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul t2, a3, s0
+; RV32IM-NEXT: mul a7, a3, ra
+; RV32IM-NEXT: lw a0, 68(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s0, a3, a0
+; RV32IM-NEXT: lw a0, 64(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s4, a3, a0
+; RV32IM-NEXT: lw a0, 60(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s7, a3, a0
+; RV32IM-NEXT: mul a0, a3, a6
+; RV32IM-NEXT: sw a0, 68(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a6, a3, a5
+; RV32IM-NEXT: lw a0, 56(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a4, a3, a0
+; RV32IM-NEXT: lw a0, 52(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul t1, a3, a0
+; RV32IM-NEXT: mul t4, a3, t6
+; RV32IM-NEXT: lw a0, 48(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s3, a3, a0
+; RV32IM-NEXT: mul a2, a3, s2
+; RV32IM-NEXT: lw a0, 44(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a1, a3, a0
+; RV32IM-NEXT: lw a0, 40(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a5, a3, a0
+; RV32IM-NEXT: lw a0, 36(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul t0, a3, a0
+; RV32IM-NEXT: lw a0, 32(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul t3, a3, a0
+; RV32IM-NEXT: lw a0, 28(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul t6, a3, a0
+; RV32IM-NEXT: lw a0, 24(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s2, a3, a0
+; RV32IM-NEXT: lw a0, 20(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a3, a3, a0
+; RV32IM-NEXT: lw a0, 72(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s11, 16(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a0, s11, a0
+; RV32IM-NEXT: lw s11, 12(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw ra, 0(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor s11, s11, ra
+; RV32IM-NEXT: xor s6, s9, s6
+; RV32IM-NEXT: xor t5, s1, t5
+; RV32IM-NEXT: xor a7, t2, a7
+; RV32IM-NEXT: xor a4, a6, a4
+; RV32IM-NEXT: xor a1, a2, a1
+; RV32IM-NEXT: xor a0, a0, s11
+; RV32IM-NEXT: lw a2, 4(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a2, s6, a2
+; RV32IM-NEXT: xor a6, t5, s5
+; RV32IM-NEXT: xor a7, a7, s0
+; RV32IM-NEXT: xor a4, a4, t1
+; RV32IM-NEXT: xor a1, a1, a5
+; RV32IM-NEXT: xor a0, a0, a2
+; RV32IM-NEXT: xor a2, a6, s8
+; RV32IM-NEXT: xor a5, a7, s4
+; RV32IM-NEXT: xor a4, a4, t4
+; RV32IM-NEXT: xor a1, a1, t0
+; RV32IM-NEXT: lw a6, 76(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a0, a0, a6
+; RV32IM-NEXT: lw a6, 8(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a2, a2, a6
+; RV32IM-NEXT: xor a5, a5, s7
+; RV32IM-NEXT: xor a4, a4, s3
+; RV32IM-NEXT: xor a1, a1, t3
+; RV32IM-NEXT: lw a6, 68(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a5, a5, a6
+; RV32IM-NEXT: xor a1, a1, t6
+; RV32IM-NEXT: xor a2, a0, a2
+; RV32IM-NEXT: xor a2, a2, a5
+; RV32IM-NEXT: slli a0, a0, 24
+; RV32IM-NEXT: xor a1, a1, s2
+; RV32IM-NEXT: xor a2, a2, a4
+; RV32IM-NEXT: xor a1, a1, a3
+; RV32IM-NEXT: and a3, a2, s10
+; RV32IM-NEXT: srli a4, a2, 8
+; RV32IM-NEXT: xor a1, a2, a1
+; RV32IM-NEXT: slli a3, a3, 8
+; RV32IM-NEXT: and a2, a4, s10
+; RV32IM-NEXT: srli a1, a1, 24
+; RV32IM-NEXT: or a0, a0, a3
+; RV32IM-NEXT: or a1, a2, a1
+; RV32IM-NEXT: or a0, a0, a1
+; RV32IM-NEXT: srli a1, a0, 4
+; RV32IM-NEXT: lw a2, 80(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: and a0, a0, a2
+; RV32IM-NEXT: and a1, a1, a2
+; RV32IM-NEXT: slli a0, a0, 4
+; RV32IM-NEXT: or a0, a1, a0
+; RV32IM-NEXT: srli a1, a0, 2
+; RV32IM-NEXT: lw a2, 84(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: and a0, a0, a2
+; RV32IM-NEXT: and a1, a1, a2
+; RV32IM-NEXT: slli a0, a0, 2
+; RV32IM-NEXT: or a0, a1, a0
+; RV32IM-NEXT: srli a1, a0, 1
+; RV32IM-NEXT: lw a2, 88(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: and a0, a0, a2
+; RV32IM-NEXT: and a1, a1, a2
+; RV32IM-NEXT: slli a0, a0, 1
+; RV32IM-NEXT: or a0, a1, a0
+; RV32IM-NEXT: lw ra, 140(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s0, 136(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s1, 132(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s2, 128(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s3, 124(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s4, 120(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s5, 116(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s6, 112(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s7, 108(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s8, 104(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s9, 100(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s10, 96(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s11, 92(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: addi sp, sp, 144
+; RV32IM-NEXT: ret
+;
+; RV64IM-LABEL: clmulr_i16:
+; RV64IM: # %bb.0:
+; RV64IM-NEXT: addi sp, sp, -448
+; RV64IM-NEXT: sd ra, 440(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s0, 432(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s1, 424(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s2, 416(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s3, 408(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s4, 400(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s5, 392(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s6, 384(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s7, 376(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s8, 368(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s9, 360(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s10, 352(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s11, 344(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: srli a2, a0, 24
+; RV64IM-NEXT: srli a6, a0, 8
+; RV64IM-NEXT: li a3, 255
+; RV64IM-NEXT: srli a5, a0, 40
+; RV64IM-NEXT: lui s3, 16
+; RV64IM-NEXT: srli s0, a0, 56
+; RV64IM-NEXT: srliw t2, a0, 24
+; RV64IM-NEXT: slli t0, a0, 56
+; RV64IM-NEXT: lui t3, 61681
+; RV64IM-NEXT: lui t4, 209715
+; RV64IM-NEXT: lui t6, 349525
+; RV64IM-NEXT: li a7, 1
+; RV64IM-NEXT: lui s5, 2
+; RV64IM-NEXT: lui t1, 4
+; RV64IM-NEXT: lui a4, 128
+; RV64IM-NEXT: lui s7, 256
+; RV64IM-NEXT: lui s8, 4096
+; RV64IM-NEXT: lui s10, 8192
+; RV64IM-NEXT: lui a1, 4080
+; RV64IM-NEXT: and a2, a2, a1
+; RV64IM-NEXT: slli a3, a3, 24
+; RV64IM-NEXT: sd a3, 336(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: addi s1, s3, -256
+; RV64IM-NEXT: and t5, a0, a1
+; RV64IM-NEXT: slli a1, t2, 32
+; RV64IM-NEXT: addi s9, t3, -241
+; RV64IM-NEXT: addi t4, t4, 819
+; RV64IM-NEXT: addi t2, t6, 1365
+; RV64IM-NEXT: slli t3, a7, 11
+; RV64IM-NEXT: slli s11, a7, 32
+; RV64IM-NEXT: slli ra, a7, 33
+; RV64IM-NEXT: slli t6, a7, 34
+; RV64IM-NEXT: slli s2, a7, 35
+; RV64IM-NEXT: slli s4, a7, 36
+; RV64IM-NEXT: sd s4, 256(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a3, a6, a3
+; RV64IM-NEXT: or a2, a3, a2
+; RV64IM-NEXT: slli a3, a7, 37
+; RV64IM-NEXT: sd a3, 248(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s1, 304(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a3, a5, s1
+; RV64IM-NEXT: or a3, a3, s0
+; RV64IM-NEXT: slli a5, a7, 38
+; RV64IM-NEXT: sd a5, 232(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli t5, t5, 24
+; RV64IM-NEXT: and a0, a0, s1
+; RV64IM-NEXT: or a1, t5, a1
+; RV64IM-NEXT: slli a5, s9, 32
+; RV64IM-NEXT: add a5, s9, a5
+; RV64IM-NEXT: slli s0, t4, 32
+; RV64IM-NEXT: add t4, t4, s0
+; RV64IM-NEXT: slli s4, t2, 32
+; RV64IM-NEXT: slli a0, a0, 40
+; RV64IM-NEXT: add t2, t2, s4
+; RV64IM-NEXT: or a2, a2, a3
+; RV64IM-NEXT: or a0, t0, a0
+; RV64IM-NEXT: or a0, a0, a1
+; RV64IM-NEXT: or a0, a0, a2
+; RV64IM-NEXT: srli a1, a0, 4
+; RV64IM-NEXT: sd a5, 312(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, a0, a5
+; RV64IM-NEXT: and a1, a1, a5
+; RV64IM-NEXT: slli a0, a0, 4
+; RV64IM-NEXT: or a0, a1, a0
+; RV64IM-NEXT: srli a1, a0, 2
+; RV64IM-NEXT: sd t4, 320(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, a0, t4
+; RV64IM-NEXT: and a1, a1, t4
+; RV64IM-NEXT: slli a0, a0, 2
+; RV64IM-NEXT: or a0, a1, a0
+; RV64IM-NEXT: srli a1, a0, 1
+; RV64IM-NEXT: sd t2, 328(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, a0, t2
+; RV64IM-NEXT: and a1, a1, t2
+; RV64IM-NEXT: slli a0, a0, 1
+; RV64IM-NEXT: or t0, a1, a0
+; RV64IM-NEXT: andi a0, t0, 2
+; RV64IM-NEXT: andi a1, t0, 1
+; RV64IM-NEXT: andi a2, t0, 4
+; RV64IM-NEXT: andi a3, t0, 8
+; RV64IM-NEXT: andi a5, t0, 16
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: xor a0, a1, a0
+; RV64IM-NEXT: sd a0, 296(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi a0, t0, 32
+; RV64IM-NEXT: mul a1, t0, a2
+; RV64IM-NEXT: mul a2, t0, a3
+; RV64IM-NEXT: xor a1, a1, a2
+; RV64IM-NEXT: sd a1, 288(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi a1, t0, 256
+; RV64IM-NEXT: mul a2, t0, a5
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: xor a0, a2, a0
+; RV64IM-NEXT: sd a0, 280(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi a0, t0, 512
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: xor a0, a1, a0
+; RV64IM-NEXT: sd a0, 272(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli t4, a7, 39
+; RV64IM-NEXT: and a0, t0, s5
+; RV64IM-NEXT: and a1, t0, t1
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: xor a0, a0, a1
+; RV64IM-NEXT: sd a0, 264(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 40
+; RV64IM-NEXT: and a1, t0, a4
+; RV64IM-NEXT: and a2, t0, s7
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: xor a1, a1, a2
+; RV64IM-NEXT: sd a1, 240(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a1, a7, 41
+; RV64IM-NEXT: and a2, t0, s8
+; RV64IM-NEXT: and a3, t0, s10
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: mul a3, t0, a3
+; RV64IM-NEXT: xor a2, a2, a3
+; RV64IM-NEXT: sd a2, 224(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a2, a7, 48
+; RV64IM-NEXT: and a3, t0, s11
+; RV64IM-NEXT: and a4, t0, ra
+; RV64IM-NEXT: mul a3, t0, a3
+; RV64IM-NEXT: mul a4, t0, a4
+; RV64IM-NEXT: xor a3, a3, a4
+; RV64IM-NEXT: sd a3, 216(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a7, 49
+; RV64IM-NEXT: and a0, t0, a0
+; RV64IM-NEXT: and a1, t0, a1
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: xor a0, a0, a1
+; RV64IM-NEXT: sd a0, 208(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 56
+; RV64IM-NEXT: and a1, t0, a2
+; RV64IM-NEXT: and a2, t0, a3
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: xor a1, a1, a2
+; RV64IM-NEXT: sd a1, 200(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a1, a7, 57
+; RV64IM-NEXT: and a0, t0, a0
+; RV64IM-NEXT: and a1, t0, a1
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: xor a0, a0, a1
+; RV64IM-NEXT: sd a0, 192(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a2, a7, 42
+; RV64IM-NEXT: slli ra, a7, 43
+; RV64IM-NEXT: slli a3, a7, 44
+; RV64IM-NEXT: slli a4, a7, 45
+; RV64IM-NEXT: slli t5, a7, 46
+; RV64IM-NEXT: slli s0, a7, 47
+; RV64IM-NEXT: slli s1, a7, 50
+; RV64IM-NEXT: slli a0, a7, 51
+; RV64IM-NEXT: sd a0, 184(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 52
+; RV64IM-NEXT: sd a0, 176(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 53
+; RV64IM-NEXT: sd a0, 168(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 54
+; RV64IM-NEXT: sd a0, 160(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 55
+; RV64IM-NEXT: sd a0, 152(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 58
+; RV64IM-NEXT: sd a0, 144(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 59
+; RV64IM-NEXT: sd a0, 136(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 60
+; RV64IM-NEXT: sd a0, 120(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 61
+; RV64IM-NEXT: sd a0, 80(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a7, a7, 62
+; RV64IM-NEXT: sd a7, 48(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, t0, t3
+; RV64IM-NEXT: sd a0, 128(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s7, 1
+; RV64IM-NEXT: and a0, t0, s7
+; RV64IM-NEXT: sd a0, 112(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s8, 8
+; RV64IM-NEXT: and a0, t0, s8
+; RV64IM-NEXT: sd a0, 104(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, t0, s3
+; RV64IM-NEXT: sd a0, 96(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s6, 32
+; RV64IM-NEXT: and a0, t0, s6
+; RV64IM-NEXT: sd a0, 88(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s10, 64
+; RV64IM-NEXT: and a0, t0, s10
+; RV64IM-NEXT: sd a0, 72(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s11, 512
+; RV64IM-NEXT: and a0, t0, s11
+; RV64IM-NEXT: sd a0, 64(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s4, 1024
+; RV64IM-NEXT: and a0, t0, s4
+; RV64IM-NEXT: sd a0, 56(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s5, 2048
+; RV64IM-NEXT: and a0, t0, s5
+; RV64IM-NEXT: sd a0, 40(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s9, 16384
+; RV64IM-NEXT: and a0, t0, s9
+; RV64IM-NEXT: sd a0, 32(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui a5, 32768
+; RV64IM-NEXT: and a5, t0, a5
+; RV64IM-NEXT: lui a6, 65536
+; RV64IM-NEXT: and a6, t0, a6
+; RV64IM-NEXT: lui t1, 131072
+; RV64IM-NEXT: and t1, t0, t1
+; RV64IM-NEXT: lui t2, 262144
+; RV64IM-NEXT: and t2, t0, t2
+; RV64IM-NEXT: and a0, t0, t6
+; RV64IM-NEXT: sd a0, 24(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, t0, s2
+; RV64IM-NEXT: sd a0, 16(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a0, 256(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, t0, a0
+; RV64IM-NEXT: sd a0, 8(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a0, 248(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, t0, a0
+; RV64IM-NEXT: sd a0, 0(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a0, 232(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, t0, a0
+; RV64IM-NEXT: and a1, t0, t4
+; RV64IM-NEXT: and a7, t0, a2
+; RV64IM-NEXT: and ra, t0, ra
+; RV64IM-NEXT: and t3, t0, a3
+; RV64IM-NEXT: and t4, t0, a4
+; RV64IM-NEXT: and t5, t0, t5
+; RV64IM-NEXT: and t6, t0, s0
+; RV64IM-NEXT: and s0, t0, s1
+; RV64IM-NEXT: ld a2, 184(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s1, t0, a2
+; RV64IM-NEXT: ld a2, 176(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s2, t0, a2
+; RV64IM-NEXT: ld a2, 168(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s3, t0, a2
+; RV64IM-NEXT: ld a2, 160(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s4, t0, a2
+; RV64IM-NEXT: ld a2, 152(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s5, t0, a2
+; RV64IM-NEXT: ld a2, 144(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s6, t0, a2
+; RV64IM-NEXT: ld a2, 136(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s7, t0, a2
+; RV64IM-NEXT: ld a2, 120(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s8, t0, a2
+; RV64IM-NEXT: ld a2, 80(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s9, t0, a2
+; RV64IM-NEXT: ld a2, 48(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s10, t0, a2
+; RV64IM-NEXT: andi s11, t0, 64
+; RV64IM-NEXT: mul a2, t0, s11
+; RV64IM-NEXT: sd a2, 80(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi s11, t0, 128
+; RV64IM-NEXT: mul a2, t0, s11
+; RV64IM-NEXT: sd a2, 232(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi s11, t0, 1024
+; RV64IM-NEXT: mul a2, t0, s11
+; RV64IM-NEXT: sd a2, 48(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 128(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 120(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 112(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 176(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 104(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul s11, t0, a2
+; RV64IM-NEXT: ld a2, 96(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 104(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 88(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 168(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 72(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 256(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 64(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a4, t0, a2
+; RV64IM-NEXT: ld a2, 56(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 96(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 40(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 136(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 32(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a3, t0, a2
+; RV64IM-NEXT: mul a2, t0, a5
+; RV64IM-NEXT: sd a2, 88(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a2, t0, a6
+; RV64IM-NEXT: sd a2, 128(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a2, t0, t1
+; RV64IM-NEXT: sd a2, 160(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a2, t0, t2
+; RV64IM-NEXT: sd a2, 248(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: srliw t2, t0, 31
+; RV64IM-NEXT: slli t2, t2, 31
+; RV64IM-NEXT: ld a2, 24(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: ld a5, 16(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a5, t0, a5
+; RV64IM-NEXT: ld a6, 8(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul t1, t0, a6
+; RV64IM-NEXT: ld a6, 0(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a6, t0, a6
+; RV64IM-NEXT: sd a6, 112(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: sd a0, 152(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a0, t0, a1
+; RV64IM-NEXT: sd a0, 184(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a7, t0, a7
+; RV64IM-NEXT: mul ra, t0, ra
+; RV64IM-NEXT: mul a6, t0, t3
+; RV64IM-NEXT: mul t4, t0, t4
+; RV64IM-NEXT: mul t5, t0, t5
+; RV64IM-NEXT: mul a0, t0, t6
+; RV64IM-NEXT: sd a0, 144(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul t6, t0, s0
+; RV64IM-NEXT: mul s0, t0, s1
+; RV64IM-NEXT: mul s1, t0, s2
+; RV64IM-NEXT: mul s2, t0, s3
+; RV64IM-NEXT: mul s3, t0, s4
+; RV64IM-NEXT: mul s4, t0, s5
+; RV64IM-NEXT: mul s5, t0, s6
+; RV64IM-NEXT: mul s6, t0, s7
+; RV64IM-NEXT: mul s7, t0, s8
+; RV64IM-NEXT: mul s8, t0, s9
+; RV64IM-NEXT: mul s9, t0, s10
+; RV64IM-NEXT: srli s10, t0, 63
+; RV64IM-NEXT: slli s10, s10, 63
+; RV64IM-NEXT: mul t2, t0, t2
+; RV64IM-NEXT: mul t0, t0, s10
+; RV64IM-NEXT: ld a0, 296(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld a1, 288(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s10, a0, a1
+; RV64IM-NEXT: ld a0, 280(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld a1, 80(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a0, a0, a1
+; RV64IM-NEXT: ld a1, 272(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld t3, 48(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a1, a1, t3
+; RV64IM-NEXT: ld t3, 264(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s11, t3, s11
+; RV64IM-NEXT: ld t3, 240(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, t3, a4
+; RV64IM-NEXT: ld t3, 224(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, t3, a3
+; RV64IM-NEXT: ld t3, 216(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, t3, a2
+; RV64IM-NEXT: ld t3, 208(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a7, t3, a7
+; RV64IM-NEXT: ld t3, 200(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor t6, t3, t6
+; RV64IM-NEXT: ld t3, 192(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s5, t3, s5
+; RV64IM-NEXT: xor a0, s10, a0
+; RV64IM-NEXT: ld t3, 120(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a1, a1, t3
+; RV64IM-NEXT: ld t3, 104(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s10, s11, t3
+; RV64IM-NEXT: ld t3, 96(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, a4, t3
+; RV64IM-NEXT: ld t3, 88(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a3, t3
+; RV64IM-NEXT: xor a2, a2, a5
+; RV64IM-NEXT: xor a5, a7, ra
+; RV64IM-NEXT: xor a7, t6, s0
+; RV64IM-NEXT: xor t6, s5, s6
+; RV64IM-NEXT: ld t3, 232(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a0, a0, t3
+; RV64IM-NEXT: ld t3, 176(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a1, a1, t3
+; RV64IM-NEXT: ld t3, 168(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s0, s10, t3
+; RV64IM-NEXT: ld t3, 136(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, a4, t3
+; RV64IM-NEXT: ld t3, 128(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a3, t3
+; RV64IM-NEXT: xor a2, a2, t1
+; RV64IM-NEXT: xor a5, a5, a6
+; RV64IM-NEXT: xor a6, a7, s1
+; RV64IM-NEXT: xor a7, t6, s7
+; RV64IM-NEXT: ld t1, 256(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor t1, s0, t1
+; RV64IM-NEXT: ld t3, 160(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a3, t3
+; RV64IM-NEXT: ld t3, 112(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a2, t3
+; RV64IM-NEXT: xor a5, a5, t4
+; RV64IM-NEXT: xor a6, a6, s2
+; RV64IM-NEXT: xor a7, a7, s8
+; RV64IM-NEXT: xor a1, a0, a1
+; RV64IM-NEXT: xor a1, a1, t1
+; RV64IM-NEXT: ld t1, 248(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a3, t1
+; RV64IM-NEXT: ld t1, 152(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a2, t1
+; RV64IM-NEXT: xor a5, a5, t5
+; RV64IM-NEXT: xor a6, a6, s3
+; RV64IM-NEXT: xor a7, a7, s9
+; RV64IM-NEXT: xor a1, a1, a4
+; RV64IM-NEXT: xor a3, a3, t2
+; RV64IM-NEXT: ld a4, 184(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a2, a4
+; RV64IM-NEXT: ld a4, 144(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, a5, a4
+; RV64IM-NEXT: xor a5, a6, s4
+; RV64IM-NEXT: slli a0, a0, 56
+; RV64IM-NEXT: xor a6, a7, t0
+; RV64IM-NEXT: ld t0, 304(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a7, a1, t0
+; RV64IM-NEXT: xor a1, a1, a3
+; RV64IM-NEXT: slli a7, a7, 40
+; RV64IM-NEXT: xor a1, a1, a2
+; RV64IM-NEXT: or a0, a0, a7
+; RV64IM-NEXT: lui a7, 4080
+; RV64IM-NEXT: and a2, a1, a7
+; RV64IM-NEXT: xor a4, a1, a4
+; RV64IM-NEXT: srli a1, a1, 8
+; RV64IM-NEXT: slli a2, a2, 24
+; RV64IM-NEXT: xor a5, a4, a5
+; RV64IM-NEXT: ld a3, 336(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a1, a1, a3
+; RV64IM-NEXT: srli a4, a4, 24
+; RV64IM-NEXT: srliw a3, a5, 24
+; RV64IM-NEXT: and a4, a4, a7
+; RV64IM-NEXT: srli a7, a5, 40
+; RV64IM-NEXT: xor a5, a5, a6
+; RV64IM-NEXT: slli a3, a3, 32
+; RV64IM-NEXT: or a1, a1, a4
+; RV64IM-NEXT: and a4, a7, t0
+; RV64IM-NEXT: srli a5, a5, 56
+; RV64IM-NEXT: or a2, a2, a3
+; RV64IM-NEXT: or a4, a4, a5
+; RV64IM-NEXT: or a0, a0, a2
+; RV64IM-NEXT: or a1, a1, a4
+; RV64IM-NEXT: or a0, a0, a1
+; RV64IM-NEXT: srli a1, a0, 4
+; RV64IM-NEXT: ld a2, 312(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, a0, a2
+; RV64IM-NEXT: and a1, a1, a2
+; RV64IM-NEXT: slli a0, a0, 4
+; RV64IM-NEXT: or a0, a1, a0
+; RV64IM-NEXT: srli a1, a0, 2
+; RV64IM-NEXT: ld a2, 320(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, a0, a2
+; RV64IM-NEXT: and a1, a1, a2
+; RV64IM-NEXT: slli a0, a0, 2
+; RV64IM-NEXT: or a0, a1, a0
+; RV64IM-NEXT: srli a1, a0, 1
+; RV64IM-NEXT: ld a2, 328(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, a0, a2
+; RV64IM-NEXT: and a1, a1, a2
+; RV64IM-NEXT: slli a0, a0, 1
+; RV64IM-NEXT: or a0, a1, a0
+; RV64IM-NEXT: ld ra, 440(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s0, 432(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s1, 424(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s2, 416(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s3, 408(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s4, 400(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s5, 392(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s6, 384(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s7, 376(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s8, 368(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s9, 360(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s10, 352(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s11, 344(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: addi sp, sp, 448
+; RV64IM-NEXT: ret
+ %res = call i16 @llvm.clmulr.i16(i16 %a, i16 %b)
+ ret i16 %res
+}
+
+define i32 @clmulr_i32(i32 %a, i32 %b) nounwind {
+; RV32IM-LABEL: clmulr_i32:
+; RV32IM: # %bb.0:
+; RV32IM-NEXT: addi sp, sp, -144
+; RV32IM-NEXT: sw ra, 140(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s0, 136(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s1, 132(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s2, 128(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s3, 124(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s4, 120(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s5, 116(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s6, 112(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s7, 108(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s8, 104(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s9, 100(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s10, 96(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s11, 92(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: srli a3, a0, 8
+; RV32IM-NEXT: lui s9, 16
+; RV32IM-NEXT: srli a4, a0, 24
+; RV32IM-NEXT: slli a2, a0, 24
+; RV32IM-NEXT: lui a7, 61681
+; RV32IM-NEXT: lui ra, 209715
+; RV32IM-NEXT: lui a1, 349525
+; RV32IM-NEXT: li s0, 1
+; RV32IM-NEXT: lui t1, 1
+; RV32IM-NEXT: lui t2, 2
+; RV32IM-NEXT: lui t3, 4
+; RV32IM-NEXT: lui t4, 8
+; RV32IM-NEXT: lui t0, 32
+; RV32IM-NEXT: lui a6, 64
+; RV32IM-NEXT: lui a5, 128
+; RV32IM-NEXT: lui s1, 256
+; RV32IM-NEXT: lui t5, 512
+; RV32IM-NEXT: lui t6, 1024
+; RV32IM-NEXT: lui s4, 2048
+; RV32IM-NEXT: lui s2, 4096
+; RV32IM-NEXT: lui s3, 8192
+; RV32IM-NEXT: lui s7, 16384
+; RV32IM-NEXT: lui s5, 32768
+; RV32IM-NEXT: lui s6, 65536
+; RV32IM-NEXT: lui s11, 131072
+; RV32IM-NEXT: lui s8, 262144
+; RV32IM-NEXT: addi s10, s9, -256
+; RV32IM-NEXT: and a3, a3, s10
+; RV32IM-NEXT: or a3, a3, a4
+; RV32IM-NEXT: addi a7, a7, -241
+; RV32IM-NEXT: sw a7, 80(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: addi a4, ra, 819
+; RV32IM-NEXT: sw a4, 84(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: addi a1, a1, 1365
+; RV32IM-NEXT: sw a1, 88(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: slli s0, s0, 11
+; RV32IM-NEXT: and a0, a0, s10
+; RV32IM-NEXT: slli a0, a0, 8
+; RV32IM-NEXT: or a0, a2, a0
+; RV32IM-NEXT: or a0, a0, a3
+; RV32IM-NEXT: srli a2, a0, 4
+; RV32IM-NEXT: and a0, a0, a7
+; RV32IM-NEXT: and a2, a2, a7
+; RV32IM-NEXT: slli a0, a0, 4
+; RV32IM-NEXT: or a0, a2, a0
+; RV32IM-NEXT: srli a2, a0, 2
+; RV32IM-NEXT: and a0, a0, a4
+; RV32IM-NEXT: and a2, a2, a4
+; RV32IM-NEXT: slli a0, a0, 2
+; RV32IM-NEXT: or a0, a2, a0
+; RV32IM-NEXT: srli a2, a0, 1
+; RV32IM-NEXT: and a0, a0, a1
+; RV32IM-NEXT: and a2, a2, a1
+; RV32IM-NEXT: slli a0, a0, 1
+; RV32IM-NEXT: or a3, a2, a0
+; RV32IM-NEXT: andi a0, a3, 2
+; RV32IM-NEXT: andi a1, a3, 1
+; RV32IM-NEXT: and a4, a3, s0
+; RV32IM-NEXT: and a7, a3, t1
+; RV32IM-NEXT: and s0, a3, t2
+; RV32IM-NEXT: and ra, a3, t3
+; RV32IM-NEXT: and a2, a3, t4
+; RV32IM-NEXT: sw a2, 68(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a2, a3, s9
+; RV32IM-NEXT: sw a2, 64(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a2, a3, t0
+; RV32IM-NEXT: sw a2, 60(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a6, a3, a6
+; RV32IM-NEXT: and a5, a3, a5
+; RV32IM-NEXT: and s1, a3, s1
+; RV32IM-NEXT: sw s1, 56(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a2, a3, t5
+; RV32IM-NEXT: sw a2, 52(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and t6, a3, t6
+; RV32IM-NEXT: and a2, a3, s4
+; RV32IM-NEXT: sw a2, 48(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and s2, a3, s2
+; RV32IM-NEXT: and a2, a3, s3
+; RV32IM-NEXT: sw a2, 44(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a2, a3, s7
+; RV32IM-NEXT: sw a2, 40(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a2, a3, s5
+; RV32IM-NEXT: sw a2, 36(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a2, a3, s6
+; RV32IM-NEXT: sw a2, 32(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a2, a3, s11
+; RV32IM-NEXT: sw a2, 28(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a2, a3, s8
+; RV32IM-NEXT: sw a2, 24(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lui a2, 524288
+; RV32IM-NEXT: and a2, a3, a2
+; RV32IM-NEXT: sw a2, 20(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a0, a3, a0
+; RV32IM-NEXT: sw a0, 72(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a0, a3, a1
+; RV32IM-NEXT: sw a0, 16(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi a0, a3, 4
+; RV32IM-NEXT: mul a0, a3, a0
+; RV32IM-NEXT: sw a0, 12(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi a1, a3, 8
+; RV32IM-NEXT: mul a0, a3, a1
+; RV32IM-NEXT: sw a0, 0(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi a2, a3, 16
+; RV32IM-NEXT: mul s9, a3, a2
+; RV32IM-NEXT: andi t0, a3, 32
+; RV32IM-NEXT: mul s6, a3, t0
+; RV32IM-NEXT: andi t1, a3, 64
+; RV32IM-NEXT: mul a0, a3, t1
+; RV32IM-NEXT: sw a0, 4(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi t2, a3, 128
+; RV32IM-NEXT: mul a0, a3, t2
+; RV32IM-NEXT: sw a0, 76(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi t2, a3, 256
+; RV32IM-NEXT: mul s1, a3, t2
+; RV32IM-NEXT: andi t3, a3, 512
+; RV32IM-NEXT: mul t5, a3, t3
+; RV32IM-NEXT: andi t4, a3, 1024
+; RV32IM-NEXT: mul s5, a3, t4
+; RV32IM-NEXT: mul s8, a3, a4
+; RV32IM-NEXT: mul a0, a3, a7
+; RV32IM-NEXT: sw a0, 8(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul t2, a3, s0
+; RV32IM-NEXT: mul a7, a3, ra
+; RV32IM-NEXT: lw a0, 68(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s0, a3, a0
+; RV32IM-NEXT: lw a0, 64(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s4, a3, a0
+; RV32IM-NEXT: lw a0, 60(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s7, a3, a0
+; RV32IM-NEXT: mul a0, a3, a6
+; RV32IM-NEXT: sw a0, 68(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a6, a3, a5
+; RV32IM-NEXT: lw a0, 56(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a4, a3, a0
+; RV32IM-NEXT: lw a0, 52(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul t1, a3, a0
+; RV32IM-NEXT: mul t4, a3, t6
+; RV32IM-NEXT: lw a0, 48(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s3, a3, a0
+; RV32IM-NEXT: mul a2, a3, s2
+; RV32IM-NEXT: lw a0, 44(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a1, a3, a0
+; RV32IM-NEXT: lw a0, 40(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a5, a3, a0
+; RV32IM-NEXT: lw a0, 36(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul t0, a3, a0
+; RV32IM-NEXT: lw a0, 32(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul t3, a3, a0
+; RV32IM-NEXT: lw a0, 28(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul t6, a3, a0
+; RV32IM-NEXT: lw a0, 24(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s2, a3, a0
+; RV32IM-NEXT: lw a0, 20(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a3, a3, a0
+; RV32IM-NEXT: lw a0, 72(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s11, 16(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a0, s11, a0
+; RV32IM-NEXT: lw s11, 12(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw ra, 0(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor s11, s11, ra
+; RV32IM-NEXT: xor s6, s9, s6
+; RV32IM-NEXT: xor t5, s1, t5
+; RV32IM-NEXT: xor a7, t2, a7
+; RV32IM-NEXT: xor a4, a6, a4
+; RV32IM-NEXT: xor a1, a2, a1
+; RV32IM-NEXT: xor a0, a0, s11
+; RV32IM-NEXT: lw a2, 4(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a2, s6, a2
+; RV32IM-NEXT: xor a6, t5, s5
+; RV32IM-NEXT: xor a7, a7, s0
+; RV32IM-NEXT: xor a4, a4, t1
+; RV32IM-NEXT: xor a1, a1, a5
+; RV32IM-NEXT: xor a0, a0, a2
+; RV32IM-NEXT: xor a2, a6, s8
+; RV32IM-NEXT: xor a5, a7, s4
+; RV32IM-NEXT: xor a4, a4, t4
+; RV32IM-NEXT: xor a1, a1, t0
+; RV32IM-NEXT: lw a6, 76(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a0, a0, a6
+; RV32IM-NEXT: lw a6, 8(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a2, a2, a6
+; RV32IM-NEXT: xor a5, a5, s7
+; RV32IM-NEXT: xor a4, a4, s3
+; RV32IM-NEXT: xor a1, a1, t3
+; RV32IM-NEXT: lw a6, 68(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a5, a5, a6
+; RV32IM-NEXT: xor a1, a1, t6
+; RV32IM-NEXT: xor a2, a0, a2
+; RV32IM-NEXT: xor a2, a2, a5
+; RV32IM-NEXT: slli a0, a0, 24
+; RV32IM-NEXT: xor a1, a1, s2
+; RV32IM-NEXT: xor a2, a2, a4
+; RV32IM-NEXT: xor a1, a1, a3
+; RV32IM-NEXT: and a3, a2, s10
+; RV32IM-NEXT: srli a4, a2, 8
+; RV32IM-NEXT: xor a1, a2, a1
+; RV32IM-NEXT: slli a3, a3, 8
+; RV32IM-NEXT: and a2, a4, s10
+; RV32IM-NEXT: srli a1, a1, 24
+; RV32IM-NEXT: or a0, a0, a3
+; RV32IM-NEXT: or a1, a2, a1
+; RV32IM-NEXT: or a0, a0, a1
+; RV32IM-NEXT: srli a1, a0, 4
+; RV32IM-NEXT: lw a2, 80(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: and a0, a0, a2
+; RV32IM-NEXT: and a1, a1, a2
+; RV32IM-NEXT: slli a0, a0, 4
+; RV32IM-NEXT: or a0, a1, a0
+; RV32IM-NEXT: srli a1, a0, 2
+; RV32IM-NEXT: lw a2, 84(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: and a0, a0, a2
+; RV32IM-NEXT: and a1, a1, a2
+; RV32IM-NEXT: slli a0, a0, 2
+; RV32IM-NEXT: or a0, a1, a0
+; RV32IM-NEXT: srli a1, a0, 1
+; RV32IM-NEXT: lw a2, 88(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: and a0, a0, a2
+; RV32IM-NEXT: and a1, a1, a2
+; RV32IM-NEXT: slli a0, a0, 1
+; RV32IM-NEXT: or a0, a1, a0
+; RV32IM-NEXT: lw ra, 140(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s0, 136(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s1, 132(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s2, 128(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s3, 124(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s4, 120(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s5, 116(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s6, 112(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s7, 108(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s8, 104(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s9, 100(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s10, 96(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s11, 92(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: addi sp, sp, 144
+; RV32IM-NEXT: ret
+;
+; RV64IM-LABEL: clmulr_i32:
+; RV64IM: # %bb.0:
+; RV64IM-NEXT: addi sp, sp, -448
+; RV64IM-NEXT: sd ra, 440(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s0, 432(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s1, 424(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s2, 416(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s3, 408(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s4, 400(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s5, 392(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s6, 384(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s7, 376(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s8, 368(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s9, 360(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s10, 352(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s11, 344(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: srli a2, a0, 24
+; RV64IM-NEXT: srli a6, a0, 8
+; RV64IM-NEXT: li a3, 255
+; RV64IM-NEXT: srli a5, a0, 40
+; RV64IM-NEXT: lui s3, 16
+; RV64IM-NEXT: srli s0, a0, 56
+; RV64IM-NEXT: srliw t2, a0, 24
+; RV64IM-NEXT: slli t0, a0, 56
+; RV64IM-NEXT: lui t3, 61681
+; RV64IM-NEXT: lui t4, 209715
+; RV64IM-NEXT: lui t6, 349525
+; RV64IM-NEXT: li a7, 1
+; RV64IM-NEXT: lui s5, 2
+; RV64IM-NEXT: lui t1, 4
+; RV64IM-NEXT: lui a4, 128
+; RV64IM-NEXT: lui s7, 256
+; RV64IM-NEXT: lui s8, 4096
+; RV64IM-NEXT: lui s10, 8192
+; RV64IM-NEXT: lui a1, 4080
+; RV64IM-NEXT: and a2, a2, a1
+; RV64IM-NEXT: slli a3, a3, 24
+; RV64IM-NEXT: sd a3, 336(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: addi s1, s3, -256
+; RV64IM-NEXT: and t5, a0, a1
+; RV64IM-NEXT: slli a1, t2, 32
+; RV64IM-NEXT: addi s9, t3, -241
+; RV64IM-NEXT: addi t4, t4, 819
+; RV64IM-NEXT: addi t2, t6, 1365
+; RV64IM-NEXT: slli t3, a7, 11
+; RV64IM-NEXT: slli s11, a7, 32
+; RV64IM-NEXT: slli ra, a7, 33
+; RV64IM-NEXT: slli t6, a7, 34
+; RV64IM-NEXT: slli s2, a7, 35
+; RV64IM-NEXT: slli s4, a7, 36
+; RV64IM-NEXT: sd s4, 256(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a3, a6, a3
+; RV64IM-NEXT: or a2, a3, a2
+; RV64IM-NEXT: slli a3, a7, 37
+; RV64IM-NEXT: sd a3, 248(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s1, 304(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a3, a5, s1
+; RV64IM-NEXT: or a3, a3, s0
+; RV64IM-NEXT: slli a5, a7, 38
+; RV64IM-NEXT: sd a5, 232(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli t5, t5, 24
+; RV64IM-NEXT: and a0, a0, s1
+; RV64IM-NEXT: or a1, t5, a1
+; RV64IM-NEXT: slli a5, s9, 32
+; RV64IM-NEXT: add a5, s9, a5
+; RV64IM-NEXT: slli s0, t4, 32
+; RV64IM-NEXT: add t4, t4, s0
+; RV64IM-NEXT: slli s4, t2, 32
+; RV64IM-NEXT: slli a0, a0, 40
+; RV64IM-NEXT: add t2, t2, s4
+; RV64IM-NEXT: or a2, a2, a3
+; RV64IM-NEXT: or a0, t0, a0
+; RV64IM-NEXT: or a0, a0, a1
+; RV64IM-NEXT: or a0, a0, a2
+; RV64IM-NEXT: srli a1, a0, 4
+; RV64IM-NEXT: sd a5, 312(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, a0, a5
+; RV64IM-NEXT: and a1, a1, a5
+; RV64IM-NEXT: slli a0, a0, 4
+; RV64IM-NEXT: or a0, a1, a0
+; RV64IM-NEXT: srli a1, a0, 2
+; RV64IM-NEXT: sd t4, 320(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, a0, t4
+; RV64IM-NEXT: and a1, a1, t4
+; RV64IM-NEXT: slli a0, a0, 2
+; RV64IM-NEXT: or a0, a1, a0
+; RV64IM-NEXT: srli a1, a0, 1
+; RV64IM-NEXT: sd t2, 328(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, a0, t2
+; RV64IM-NEXT: and a1, a1, t2
+; RV64IM-NEXT: slli a0, a0, 1
+; RV64IM-NEXT: or t0, a1, a0
+; RV64IM-NEXT: andi a0, t0, 2
+; RV64IM-NEXT: andi a1, t0, 1
+; RV64IM-NEXT: andi a2, t0, 4
+; RV64IM-NEXT: andi a3, t0, 8
+; RV64IM-NEXT: andi a5, t0, 16
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: xor a0, a1, a0
+; RV64IM-NEXT: sd a0, 296(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi a0, t0, 32
+; RV64IM-NEXT: mul a1, t0, a2
+; RV64IM-NEXT: mul a2, t0, a3
+; RV64IM-NEXT: xor a1, a1, a2
+; RV64IM-NEXT: sd a1, 288(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi a1, t0, 256
+; RV64IM-NEXT: mul a2, t0, a5
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: xor a0, a2, a0
+; RV64IM-NEXT: sd a0, 280(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi a0, t0, 512
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: xor a0, a1, a0
+; RV64IM-NEXT: sd a0, 272(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli t4, a7, 39
+; RV64IM-NEXT: and a0, t0, s5
+; RV64IM-NEXT: and a1, t0, t1
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: xor a0, a0, a1
+; RV64IM-NEXT: sd a0, 264(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 40
+; RV64IM-NEXT: and a1, t0, a4
+; RV64IM-NEXT: and a2, t0, s7
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: xor a1, a1, a2
+; RV64IM-NEXT: sd a1, 240(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a1, a7, 41
+; RV64IM-NEXT: and a2, t0, s8
+; RV64IM-NEXT: and a3, t0, s10
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: mul a3, t0, a3
+; RV64IM-NEXT: xor a2, a2, a3
+; RV64IM-NEXT: sd a2, 224(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a2, a7, 48
+; RV64IM-NEXT: and a3, t0, s11
+; RV64IM-NEXT: and a4, t0, ra
+; RV64IM-NEXT: mul a3, t0, a3
+; RV64IM-NEXT: mul a4, t0, a4
+; RV64IM-NEXT: xor a3, a3, a4
+; RV64IM-NEXT: sd a3, 216(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a7, 49
+; RV64IM-NEXT: and a0, t0, a0
+; RV64IM-NEXT: and a1, t0, a1
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: xor a0, a0, a1
+; RV64IM-NEXT: sd a0, 208(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 56
+; RV64IM-NEXT: and a1, t0, a2
+; RV64IM-NEXT: and a2, t0, a3
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: xor a1, a1, a2
+; RV64IM-NEXT: sd a1, 200(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a1, a7, 57
+; RV64IM-NEXT: and a0, t0, a0
+; RV64IM-NEXT: and a1, t0, a1
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: xor a0, a0, a1
+; RV64IM-NEXT: sd a0, 192(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a2, a7, 42
+; RV64IM-NEXT: slli ra, a7, 43
+; RV64IM-NEXT: slli a3, a7, 44
+; RV64IM-NEXT: slli a4, a7, 45
+; RV64IM-NEXT: slli t5, a7, 46
+; RV64IM-NEXT: slli s0, a7, 47
+; RV64IM-NEXT: slli s1, a7, 50
+; RV64IM-NEXT: slli a0, a7, 51
+; RV64IM-NEXT: sd a0, 184(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 52
+; RV64IM-NEXT: sd a0, 176(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 53
+; RV64IM-NEXT: sd a0, 168(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 54
+; RV64IM-NEXT: sd a0, 160(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 55
+; RV64IM-NEXT: sd a0, 152(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 58
+; RV64IM-NEXT: sd a0, 144(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 59
+; RV64IM-NEXT: sd a0, 136(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 60
+; RV64IM-NEXT: sd a0, 120(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 61
+; RV64IM-NEXT: sd a0, 80(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a7, a7, 62
+; RV64IM-NEXT: sd a7, 48(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, t0, t3
+; RV64IM-NEXT: sd a0, 128(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s7, 1
+; RV64IM-NEXT: and a0, t0, s7
+; RV64IM-NEXT: sd a0, 112(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s8, 8
+; RV64IM-NEXT: and a0, t0, s8
+; RV64IM-NEXT: sd a0, 104(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, t0, s3
+; RV64IM-NEXT: sd a0, 96(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s6, 32
+; RV64IM-NEXT: and a0, t0, s6
+; RV64IM-NEXT: sd a0, 88(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s10, 64
+; RV64IM-NEXT: and a0, t0, s10
+; RV64IM-NEXT: sd a0, 72(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s11, 512
+; RV64IM-NEXT: and a0, t0, s11
+; RV64IM-NEXT: sd a0, 64(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s4, 1024
+; RV64IM-NEXT: and a0, t0, s4
+; RV64IM-NEXT: sd a0, 56(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s5, 2048
+; RV64IM-NEXT: and a0, t0, s5
+; RV64IM-NEXT: sd a0, 40(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s9, 16384
+; RV64IM-NEXT: and a0, t0, s9
+; RV64IM-NEXT: sd a0, 32(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui a5, 32768
+; RV64IM-NEXT: and a5, t0, a5
+; RV64IM-NEXT: lui a6, 65536
+; RV64IM-NEXT: and a6, t0, a6
+; RV64IM-NEXT: lui t1, 131072
+; RV64IM-NEXT: and t1, t0, t1
+; RV64IM-NEXT: lui t2, 262144
+; RV64IM-NEXT: and t2, t0, t2
+; RV64IM-NEXT: and a0, t0, t6
+; RV64IM-NEXT: sd a0, 24(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, t0, s2
+; RV64IM-NEXT: sd a0, 16(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a0, 256(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, t0, a0
+; RV64IM-NEXT: sd a0, 8(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a0, 248(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, t0, a0
+; RV64IM-NEXT: sd a0, 0(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a0, 232(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, t0, a0
+; RV64IM-NEXT: and a1, t0, t4
+; RV64IM-NEXT: and a7, t0, a2
+; RV64IM-NEXT: and ra, t0, ra
+; RV64IM-NEXT: and t3, t0, a3
+; RV64IM-NEXT: and t4, t0, a4
+; RV64IM-NEXT: and t5, t0, t5
+; RV64IM-NEXT: and t6, t0, s0
+; RV64IM-NEXT: and s0, t0, s1
+; RV64IM-NEXT: ld a2, 184(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s1, t0, a2
+; RV64IM-NEXT: ld a2, 176(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s2, t0, a2
+; RV64IM-NEXT: ld a2, 168(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s3, t0, a2
+; RV64IM-NEXT: ld a2, 160(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s4, t0, a2
+; RV64IM-NEXT: ld a2, 152(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s5, t0, a2
+; RV64IM-NEXT: ld a2, 144(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s6, t0, a2
+; RV64IM-NEXT: ld a2, 136(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s7, t0, a2
+; RV64IM-NEXT: ld a2, 120(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s8, t0, a2
+; RV64IM-NEXT: ld a2, 80(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s9, t0, a2
+; RV64IM-NEXT: ld a2, 48(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s10, t0, a2
+; RV64IM-NEXT: andi s11, t0, 64
+; RV64IM-NEXT: mul a2, t0, s11
+; RV64IM-NEXT: sd a2, 80(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi s11, t0, 128
+; RV64IM-NEXT: mul a2, t0, s11
+; RV64IM-NEXT: sd a2, 232(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi s11, t0, 1024
+; RV64IM-NEXT: mul a2, t0, s11
+; RV64IM-NEXT: sd a2, 48(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 128(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 120(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 112(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 176(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 104(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul s11, t0, a2
+; RV64IM-NEXT: ld a2, 96(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 104(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 88(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 168(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 72(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 256(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 64(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a4, t0, a2
+; RV64IM-NEXT: ld a2, 56(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 96(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 40(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 136(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 32(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a3, t0, a2
+; RV64IM-NEXT: mul a2, t0, a5
+; RV64IM-NEXT: sd a2, 88(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a2, t0, a6
+; RV64IM-NEXT: sd a2, 128(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a2, t0, t1
+; RV64IM-NEXT: sd a2, 160(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a2, t0, t2
+; RV64IM-NEXT: sd a2, 248(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: srliw t2, t0, 31
+; RV64IM-NEXT: slli t2, t2, 31
+; RV64IM-NEXT: ld a2, 24(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: ld a5, 16(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a5, t0, a5
+; RV64IM-NEXT: ld a6, 8(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul t1, t0, a6
+; RV64IM-NEXT: ld a6, 0(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a6, t0, a6
+; RV64IM-NEXT: sd a6, 112(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: sd a0, 152(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a0, t0, a1
+; RV64IM-NEXT: sd a0, 184(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a7, t0, a7
+; RV64IM-NEXT: mul ra, t0, ra
+; RV64IM-NEXT: mul a6, t0, t3
+; RV64IM-NEXT: mul t4, t0, t4
+; RV64IM-NEXT: mul t5, t0, t5
+; RV64IM-NEXT: mul a0, t0, t6
+; RV64IM-NEXT: sd a0, 144(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul t6, t0, s0
+; RV64IM-NEXT: mul s0, t0, s1
+; RV64IM-NEXT: mul s1, t0, s2
+; RV64IM-NEXT: mul s2, t0, s3
+; RV64IM-NEXT: mul s3, t0, s4
+; RV64IM-NEXT: mul s4, t0, s5
+; RV64IM-NEXT: mul s5, t0, s6
+; RV64IM-NEXT: mul s6, t0, s7
+; RV64IM-NEXT: mul s7, t0, s8
+; RV64IM-NEXT: mul s8, t0, s9
+; RV64IM-NEXT: mul s9, t0, s10
+; RV64IM-NEXT: srli s10, t0, 63
+; RV64IM-NEXT: slli s10, s10, 63
+; RV64IM-NEXT: mul t2, t0, t2
+; RV64IM-NEXT: mul t0, t0, s10
+; RV64IM-NEXT: ld a0, 296(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld a1, 288(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s10, a0, a1
+; RV64IM-NEXT: ld a0, 280(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld a1, 80(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a0, a0, a1
+; RV64IM-NEXT: ld a1, 272(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld t3, 48(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a1, a1, t3
+; RV64IM-NEXT: ld t3, 264(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s11, t3, s11
+; RV64IM-NEXT: ld t3, 240(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, t3, a4
+; RV64IM-NEXT: ld t3, 224(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, t3, a3
+; RV64IM-NEXT: ld t3, 216(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, t3, a2
+; RV64IM-NEXT: ld t3, 208(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a7, t3, a7
+; RV64IM-NEXT: ld t3, 200(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor t6, t3, t6
+; RV64IM-NEXT: ld t3, 192(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s5, t3, s5
+; RV64IM-NEXT: xor a0, s10, a0
+; RV64IM-NEXT: ld t3, 120(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a1, a1, t3
+; RV64IM-NEXT: ld t3, 104(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s10, s11, t3
+; RV64IM-NEXT: ld t3, 96(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, a4, t3
+; RV64IM-NEXT: ld t3, 88(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a3, t3
+; RV64IM-NEXT: xor a2, a2, a5
+; RV64IM-NEXT: xor a5, a7, ra
+; RV64IM-NEXT: xor a7, t6, s0
+; RV64IM-NEXT: xor t6, s5, s6
+; RV64IM-NEXT: ld t3, 232(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a0, a0, t3
+; RV64IM-NEXT: ld t3, 176(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a1, a1, t3
+; RV64IM-NEXT: ld t3, 168(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s0, s10, t3
+; RV64IM-NEXT: ld t3, 136(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, a4, t3
+; RV64IM-NEXT: ld t3, 128(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a3, t3
+; RV64IM-NEXT: xor a2, a2, t1
+; RV64IM-NEXT: xor a5, a5, a6
+; RV64IM-NEXT: xor a6, a7, s1
+; RV64IM-NEXT: xor a7, t6, s7
+; RV64IM-NEXT: ld t1, 256(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor t1, s0, t1
+; RV64IM-NEXT: ld t3, 160(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a3, t3
+; RV64IM-NEXT: ld t3, 112(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a2, t3
+; RV64IM-NEXT: xor a5, a5, t4
+; RV64IM-NEXT: xor a6, a6, s2
+; RV64IM-NEXT: xor a7, a7, s8
+; RV64IM-NEXT: xor a1, a0, a1
+; RV64IM-NEXT: xor a1, a1, t1
+; RV64IM-NEXT: ld t1, 248(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a3, t1
+; RV64IM-NEXT: ld t1, 152(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a2, t1
+; RV64IM-NEXT: xor a5, a5, t5
+; RV64IM-NEXT: xor a6, a6, s3
+; RV64IM-NEXT: xor a7, a7, s9
+; RV64IM-NEXT: xor a1, a1, a4
+; RV64IM-NEXT: xor a3, a3, t2
+; RV64IM-NEXT: ld a4, 184(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a2, a4
+; RV64IM-NEXT: ld a4, 144(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, a5, a4
+; RV64IM-NEXT: xor a5, a6, s4
+; RV64IM-NEXT: slli a0, a0, 56
+; RV64IM-NEXT: xor a6, a7, t0
+; RV64IM-NEXT: ld t0, 304(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a7, a1, t0
+; RV64IM-NEXT: xor a1, a1, a3
+; RV64IM-NEXT: slli a7, a7, 40
+; RV64IM-NEXT: xor a1, a1, a2
+; RV64IM-NEXT: or a0, a0, a7
+; RV64IM-NEXT: lui a7, 4080
+; RV64IM-NEXT: and a2, a1, a7
+; RV64IM-NEXT: xor a4, a1, a4
+; RV64IM-NEXT: srli a1, a1, 8
+; RV64IM-NEXT: slli a2, a2, 24
+; RV64IM-NEXT: xor a5, a4, a5
+; RV64IM-NEXT: ld a3, 336(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a1, a1, a3
+; RV64IM-NEXT: srli a4, a4, 24
+; RV64IM-NEXT: srliw a3, a5, 24
+; RV64IM-NEXT: and a4, a4, a7
+; RV64IM-NEXT: srli a7, a5, 40
+; RV64IM-NEXT: xor a5, a5, a6
+; RV64IM-NEXT: slli a3, a3, 32
+; RV64IM-NEXT: or a1, a1, a4
+; RV64IM-NEXT: and a4, a7, t0
+; RV64IM-NEXT: srli a5, a5, 56
+; RV64IM-NEXT: or a2, a2, a3
+; RV64IM-NEXT: or a4, a4, a5
+; RV64IM-NEXT: or a0, a0, a2
+; RV64IM-NEXT: or a1, a1, a4
+; RV64IM-NEXT: or a0, a0, a1
+; RV64IM-NEXT: srli a1, a0, 4
+; RV64IM-NEXT: ld a2, 312(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, a0, a2
+; RV64IM-NEXT: and a1, a1, a2
+; RV64IM-NEXT: slli a0, a0, 4
+; RV64IM-NEXT: or a0, a1, a0
+; RV64IM-NEXT: srli a1, a0, 2
+; RV64IM-NEXT: ld a2, 320(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, a0, a2
+; RV64IM-NEXT: and a1, a1, a2
+; RV64IM-NEXT: slli a0, a0, 2
+; RV64IM-NEXT: or a0, a1, a0
+; RV64IM-NEXT: srli a1, a0, 1
+; RV64IM-NEXT: ld a2, 328(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, a0, a2
+; RV64IM-NEXT: and a1, a1, a2
+; RV64IM-NEXT: slli a0, a0, 1
+; RV64IM-NEXT: or a0, a1, a0
+; RV64IM-NEXT: ld ra, 440(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s0, 432(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s1, 424(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s2, 416(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s3, 408(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s4, 400(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s5, 392(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s6, 384(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s7, 376(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s8, 368(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s9, 360(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s10, 352(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s11, 344(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: addi sp, sp, 448
+; RV64IM-NEXT: ret
+ %res = call i32 @llvm.clmulr.i32(i32 %a, i32 %b)
+ ret i32 %res
+}
+
+define i64 @clmulr_i64(i64 %a, i64 %b) nounwind {
+; RV32IM-LABEL: clmulr_i64:
+; RV32IM: # %bb.0:
+; RV32IM-NEXT: addi sp, sp, -512
+; RV32IM-NEXT: sw ra, 508(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s0, 504(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s1, 500(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s2, 496(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s3, 492(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s4, 488(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s5, 484(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s6, 480(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s7, 476(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s8, 472(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s9, 468(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s10, 464(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s11, 460(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: srli t3, a0, 8
+; RV32IM-NEXT: lui s8, 16
+; RV32IM-NEXT: srli t4, a0, 24
+; RV32IM-NEXT: slli s2, a0, 24
+; RV32IM-NEXT: lui t5, 61681
+; RV32IM-NEXT: lui t6, 209715
+; RV32IM-NEXT: lui s0, 349525
+; RV32IM-NEXT: srli s4, a1, 8
+; RV32IM-NEXT: srli s1, a1, 24
+; RV32IM-NEXT: slli s3, a1, 24
+; RV32IM-NEXT: li s10, 1
+; RV32IM-NEXT: lui a3, 1
+; RV32IM-NEXT: lui a4, 2
+; RV32IM-NEXT: lui a5, 4
+; RV32IM-NEXT: lui a6, 8
+; RV32IM-NEXT: lui a7, 32
+; RV32IM-NEXT: lui t0, 64
+; RV32IM-NEXT: lui t1, 128
+; RV32IM-NEXT: lui t2, 256
+; RV32IM-NEXT: lui a2, 512
+; RV32IM-NEXT: addi s7, s8, -256
+; RV32IM-NEXT: sw s7, 396(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: addi s6, t5, -241
+; RV32IM-NEXT: addi s5, t6, 819
+; RV32IM-NEXT: addi t6, s0, 1365
+; RV32IM-NEXT: slli s10, s10, 11
+; RV32IM-NEXT: and t3, t3, s7
+; RV32IM-NEXT: and a0, a0, s7
+; RV32IM-NEXT: and t5, s4, s7
+; RV32IM-NEXT: and a1, a1, s7
+; RV32IM-NEXT: or t3, t3, t4
+; RV32IM-NEXT: slli a0, a0, 8
+; RV32IM-NEXT: or t4, t5, s1
+; RV32IM-NEXT: slli a1, a1, 8
+; RV32IM-NEXT: or a0, s2, a0
+; RV32IM-NEXT: or a1, s3, a1
+; RV32IM-NEXT: or a0, a0, t3
+; RV32IM-NEXT: or a1, a1, t4
+; RV32IM-NEXT: srli t3, a0, 4
+; RV32IM-NEXT: sw s6, 400(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a0, a0, s6
+; RV32IM-NEXT: srli t4, a1, 4
+; RV32IM-NEXT: and a1, a1, s6
+; RV32IM-NEXT: and t3, t3, s6
+; RV32IM-NEXT: slli a0, a0, 4
+; RV32IM-NEXT: and t4, t4, s6
+; RV32IM-NEXT: slli a1, a1, 4
+; RV32IM-NEXT: or a0, t3, a0
+; RV32IM-NEXT: or a1, t4, a1
+; RV32IM-NEXT: srli t3, a0, 2
+; RV32IM-NEXT: sw s5, 404(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a0, a0, s5
+; RV32IM-NEXT: srli t4, a1, 2
+; RV32IM-NEXT: and a1, a1, s5
+; RV32IM-NEXT: and t3, t3, s5
+; RV32IM-NEXT: slli a0, a0, 2
+; RV32IM-NEXT: and t4, t4, s5
+; RV32IM-NEXT: slli a1, a1, 2
+; RV32IM-NEXT: or a0, t3, a0
+; RV32IM-NEXT: or a1, t4, a1
+; RV32IM-NEXT: srli t3, a0, 1
+; RV32IM-NEXT: sw t6, 408(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a0, a0, t6
+; RV32IM-NEXT: srli t4, a1, 1
+; RV32IM-NEXT: and a1, a1, t6
+; RV32IM-NEXT: and t3, t3, t6
+; RV32IM-NEXT: slli a0, a0, 1
+; RV32IM-NEXT: and t4, t4, t6
+; RV32IM-NEXT: slli a1, a1, 1
+; RV32IM-NEXT: or s2, t3, a0
+; RV32IM-NEXT: or a0, t4, a1
+; RV32IM-NEXT: and a1, a0, s10
+; RV32IM-NEXT: sw a1, 432(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a1, a0, a3
+; RV32IM-NEXT: sw a1, 436(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a1, a0, a4
+; RV32IM-NEXT: sw a1, 440(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a1, a0, a5
+; RV32IM-NEXT: sw a1, 340(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a1, a0, a6
+; RV32IM-NEXT: sw a1, 412(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a1, a0, s8
+; RV32IM-NEXT: sw a1, 444(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a1, a0, a7
+; RV32IM-NEXT: sw a1, 452(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and ra, a0, t0
+; RV32IM-NEXT: and a1, a0, t1
+; RV32IM-NEXT: sw a1, 344(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a1, a0, t2
+; RV32IM-NEXT: sw a1, 448(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a1, a0, a2
+; RV32IM-NEXT: sw a1, 456(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a1, s2, s10
+; RV32IM-NEXT: sw a1, 384(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a1, s2, a3
+; RV32IM-NEXT: sw a1, 380(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a1, s2, a4
+; RV32IM-NEXT: sw a1, 376(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a1, s2, a5
+; RV32IM-NEXT: sw a1, 368(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a1, s2, a6
+; RV32IM-NEXT: sw a1, 348(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a1, s2, s8
+; RV32IM-NEXT: sw a1, 336(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a1, s2, a7
+; RV32IM-NEXT: sw a1, 324(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a1, s2, t0
+; RV32IM-NEXT: sw a1, 320(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a1, s2, t1
+; RV32IM-NEXT: sw a1, 312(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a1, s2, t2
+; RV32IM-NEXT: sw a1, 308(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a1, s2, a2
+; RV32IM-NEXT: sw a1, 300(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lui a1, 1024
+; RV32IM-NEXT: and a2, a0, a1
+; RV32IM-NEXT: sw a2, 424(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a1, s2, a1
+; RV32IM-NEXT: sw a1, 164(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lui a1, 2048
+; RV32IM-NEXT: and a2, a0, a1
+; RV32IM-NEXT: sw a2, 428(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a1, s2, a1
+; RV32IM-NEXT: sw a1, 136(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lui a1, 4096
+; RV32IM-NEXT: and a2, a0, a1
+; RV32IM-NEXT: sw a2, 416(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a1, s2, a1
+; RV32IM-NEXT: sw a1, 132(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lui a1, 8192
+; RV32IM-NEXT: and s1, a0, a1
+; RV32IM-NEXT: sw s1, 108(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a1, s2, a1
+; RV32IM-NEXT: sw a1, 128(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lui a1, 16384
+; RV32IM-NEXT: and a2, a0, a1
+; RV32IM-NEXT: sw a2, 48(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a1, s2, a1
+; RV32IM-NEXT: sw a1, 112(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lui a1, 32768
+; RV32IM-NEXT: and a2, a0, a1
+; RV32IM-NEXT: sw a2, 420(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a1, s2, a1
+; RV32IM-NEXT: sw a1, 104(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lui a1, 65536
+; RV32IM-NEXT: and t3, a0, a1
+; RV32IM-NEXT: sw t3, 116(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a1, s2, a1
+; RV32IM-NEXT: sw a1, 100(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lui a1, 131072
+; RV32IM-NEXT: and a2, a0, a1
+; RV32IM-NEXT: sw a2, 16(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a1, s2, a1
+; RV32IM-NEXT: sw a1, 72(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lui a1, 262144
+; RV32IM-NEXT: and t2, a0, a1
+; RV32IM-NEXT: sw t2, 120(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a1, s2, a1
+; RV32IM-NEXT: sw a1, 68(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lui a1, 524288
+; RV32IM-NEXT: and t1, a0, a1
+; RV32IM-NEXT: sw t1, 124(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a1, s2, a1
+; RV32IM-NEXT: sw a1, 64(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi t0, a0, 4
+; RV32IM-NEXT: sw t0, 96(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi t4, a0, 2
+; RV32IM-NEXT: andi a7, a0, 1
+; RV32IM-NEXT: sw a7, 92(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi t5, a0, 8
+; RV32IM-NEXT: andi a6, a0, 16
+; RV32IM-NEXT: sw a6, 84(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi a5, a0, 32
+; RV32IM-NEXT: sw a5, 80(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi a4, a0, 64
+; RV32IM-NEXT: sw a4, 76(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi a3, a0, 128
+; RV32IM-NEXT: sw a3, 88(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi a2, a0, 256
+; RV32IM-NEXT: andi a1, a0, 512
+; RV32IM-NEXT: andi s11, a0, 1024
+; RV32IM-NEXT: andi s3, s2, 1
+; RV32IM-NEXT: andi s5, s2, 2
+; RV32IM-NEXT: andi s7, s2, 4
+; RV32IM-NEXT: andi t6, s2, 8
+; RV32IM-NEXT: andi s0, s2, 16
+; RV32IM-NEXT: sw s0, 392(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi s0, s2, 32
+; RV32IM-NEXT: andi s4, s2, 64
+; RV32IM-NEXT: andi s6, s2, 128
+; RV32IM-NEXT: andi s8, s2, 256
+; RV32IM-NEXT: andi s9, s2, 512
+; RV32IM-NEXT: andi s10, s2, 1024
+; RV32IM-NEXT: sw s10, 360(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul s10, s2, t0
+; RV32IM-NEXT: sw s10, 292(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul s10, s2, t4
+; RV32IM-NEXT: sw s10, 288(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul s10, s2, a7
+; RV32IM-NEXT: sw s10, 332(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul s10, s2, t5
+; RV32IM-NEXT: sw s10, 284(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul s10, s2, a6
+; RV32IM-NEXT: sw s10, 280(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul s10, s2, a5
+; RV32IM-NEXT: sw s10, 276(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul s10, s2, a4
+; RV32IM-NEXT: sw s10, 272(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul s10, s2, a3
+; RV32IM-NEXT: sw s10, 268(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul s10, s2, a2
+; RV32IM-NEXT: mv t0, a2
+; RV32IM-NEXT: sw s10, 264(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul s10, s2, a1
+; RV32IM-NEXT: mv a7, a1
+; RV32IM-NEXT: sw s10, 260(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul s10, s2, s11
+; RV32IM-NEXT: mv a6, s11
+; RV32IM-NEXT: sw s10, 256(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw s10, 432(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s10, s2, s10
+; RV32IM-NEXT: sw s10, 252(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw s10, 436(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s10, s2, s10
+; RV32IM-NEXT: sw s10, 248(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw s10, 440(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s10, s2, s10
+; RV32IM-NEXT: sw s10, 244(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw s10, 340(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s11, s2, s10
+; RV32IM-NEXT: sw s11, 240(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw s11, 412(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s11, s2, s11
+; RV32IM-NEXT: sw s11, 236(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw s11, 444(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s11, s2, s11
+; RV32IM-NEXT: sw s11, 232(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw s11, 452(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s11, s2, s11
+; RV32IM-NEXT: sw s11, 228(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul s11, s2, ra
+; RV32IM-NEXT: sw s11, 224(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mv a5, ra
+; RV32IM-NEXT: lw s11, 344(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul ra, s2, s11
+; RV32IM-NEXT: sw ra, 220(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw ra, 448(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul ra, s2, ra
+; RV32IM-NEXT: sw ra, 216(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw ra, 456(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul ra, s2, ra
+; RV32IM-NEXT: sw ra, 212(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw ra, 424(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul ra, s2, ra
+; RV32IM-NEXT: sw ra, 208(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw ra, 428(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul ra, s2, ra
+; RV32IM-NEXT: sw ra, 204(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw ra, 416(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul ra, s2, ra
+; RV32IM-NEXT: sw ra, 200(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul ra, s2, s1
+; RV32IM-NEXT: sw ra, 196(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw ra, 48(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s1, s2, ra
+; RV32IM-NEXT: sw s1, 192(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw s1, 420(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s1, s2, s1
+; RV32IM-NEXT: sw s1, 188(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul s1, s2, t3
+; RV32IM-NEXT: sw s1, 184(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw s1, 16(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a4, s2, s1
+; RV32IM-NEXT: sw a4, 180(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a4, s2, t2
+; RV32IM-NEXT: sw a4, 176(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a3, s2, t1
+; RV32IM-NEXT: sw a3, 172(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul s2, a0, s3
+; RV32IM-NEXT: sw s2, 352(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul s2, a0, s5
+; RV32IM-NEXT: sw s2, 364(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul s2, a0, s7
+; RV32IM-NEXT: sw s2, 372(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a4, a0, t6
+; RV32IM-NEXT: sw a4, 388(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 392(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a4, a0, a1
+; RV32IM-NEXT: sw a4, 392(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a2, a0, s0
+; RV32IM-NEXT: sw a2, 160(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a2, a0, s4
+; RV32IM-NEXT: sw a2, 156(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a2, a0, s6
+; RV32IM-NEXT: sw a2, 304(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a2, a0, s8
+; RV32IM-NEXT: sw a2, 152(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a2, a0, s9
+; RV32IM-NEXT: sw a2, 148(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 360(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a2, a0, a1
+; RV32IM-NEXT: sw a2, 296(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a2, 384(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a2, a0, a2
+; RV32IM-NEXT: sw a2, 316(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a2, 380(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a4, a0, a2
+; RV32IM-NEXT: sw a4, 328(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a2, 376(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a4, a0, a2
+; RV32IM-NEXT: sw a4, 356(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a2, 368(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a4, a0, a2
+; RV32IM-NEXT: sw a4, 360(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a2, 348(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a4, a0, a2
+; RV32IM-NEXT: sw a4, 368(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a2, 336(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a4, a0, a2
+; RV32IM-NEXT: sw a4, 376(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a2, 324(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a4, a0, a2
+; RV32IM-NEXT: sw a4, 380(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a2, 320(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a4, a0, a2
+; RV32IM-NEXT: sw a4, 384(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a2, 312(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a2, a0, a2
+; RV32IM-NEXT: sw a2, 144(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a2, 308(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a2, a0, a2
+; RV32IM-NEXT: sw a2, 140(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a2, 300(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a2, a0, a2
+; RV32IM-NEXT: sw a2, 168(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a2, 164(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a2, a0, a2
+; RV32IM-NEXT: sw a2, 308(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a2, 136(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a2, a0, a2
+; RV32IM-NEXT: sw a2, 320(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 132(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a2, a0, a1
+; RV32IM-NEXT: sw a2, 132(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 128(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a2, a0, a1
+; RV32IM-NEXT: sw a2, 128(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 112(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a2, a0, a1
+; RV32IM-NEXT: sw a2, 164(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 104(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a2, a0, a1
+; RV32IM-NEXT: sw a2, 300(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 100(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a2, a0, a1
+; RV32IM-NEXT: sw a2, 312(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 72(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a4, a0, a1
+; RV32IM-NEXT: sw a4, 324(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 68(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a4, a0, a1
+; RV32IM-NEXT: sw a4, 336(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 64(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a4, a0, a1
+; RV32IM-NEXT: sw a4, 348(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mulhu t6, a0, t4
+; RV32IM-NEXT: mul a1, a0, t4
+; RV32IM-NEXT: sw a1, 104(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 92(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 100(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 96(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mulhu t2, a0, a1
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 96(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mulhu t3, a0, t5
+; RV32IM-NEXT: mul a1, a0, t5
+; RV32IM-NEXT: sw a1, 92(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 84(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mulhu t4, a0, a1
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 84(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 80(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mulhu s0, a0, a1
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 80(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 76(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mulhu s2, a0, a1
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 112(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 88(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mulhu s3, a0, a1
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 136(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mulhu a2, a0, t0
+; RV32IM-NEXT: sw a2, 64(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a1, a0, t0
+; RV32IM-NEXT: sw a1, 76(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mulhu a2, a0, a7
+; RV32IM-NEXT: sw a2, 60(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a1, a0, a7
+; RV32IM-NEXT: sw a1, 72(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mulhu a2, a0, a6
+; RV32IM-NEXT: sw a2, 52(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a1, a0, a6
+; RV32IM-NEXT: sw a1, 88(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 432(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mulhu a2, a0, a1
+; RV32IM-NEXT: sw a2, 40(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 432(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 436(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mulhu a2, a0, a1
+; RV32IM-NEXT: sw a2, 36(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 436(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 440(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mulhu a2, a0, a1
+; RV32IM-NEXT: sw a2, 32(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 68(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mulhu a2, a0, s10
+; RV32IM-NEXT: sw a2, 28(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a1, a0, s10
+; RV32IM-NEXT: sw a1, 340(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 412(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mulhu a2, a0, a1
+; RV32IM-NEXT: sw a2, 24(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 412(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 444(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mulhu a2, a0, a1
+; RV32IM-NEXT: sw a2, 20(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 440(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 452(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mulhu a2, a0, a1
+; RV32IM-NEXT: sw a2, 12(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 444(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mulhu a2, a0, a5
+; RV32IM-NEXT: sw a2, 8(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a1, a0, a5
+; RV32IM-NEXT: sw a1, 452(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mv a1, s11
+; RV32IM-NEXT: mulhu s11, a0, s11
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 56(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 448(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mulhu a5, a0, a1
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 44(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 456(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mulhu s10, a0, a1
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 344(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 424(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mulhu s8, a0, a1
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 424(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 428(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mulhu s9, a0, a1
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 456(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 416(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mulhu a7, a0, a1
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 4(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 108(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mulhu a3, a0, a1
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 0(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mulhu a2, a0, ra
+; RV32IM-NEXT: mul a1, a0, ra
+; RV32IM-NEXT: sw a1, 48(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 420(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mulhu t5, a0, a1
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 108(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 116(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mulhu t0, a0, a1
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 416(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mulhu a6, a0, s1
+; RV32IM-NEXT: mul a1, a0, s1
+; RV32IM-NEXT: sw a1, 420(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 120(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mulhu a4, a0, a1
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 428(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw t1, 124(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mulhu a1, a0, t1
+; RV32IM-NEXT: mul a0, a0, t1
+; RV32IM-NEXT: sw a0, 448(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a0, 292(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or a0, t2, a0
+; RV32IM-NEXT: sw a0, 116(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a0, 288(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or s7, t6, a0
+; RV32IM-NEXT: lw a0, 284(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or s5, t3, a0
+; RV32IM-NEXT: lw a0, 280(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or s6, t4, a0
+; RV32IM-NEXT: lw a0, 276(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or s4, s0, a0
+; RV32IM-NEXT: lw a0, 272(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or a0, s2, a0
+; RV32IM-NEXT: sw a0, 124(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a0, 268(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or s3, s3, a0
+; RV32IM-NEXT: lw a0, 264(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw t1, 64(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or s2, t1, a0
+; RV32IM-NEXT: lw a0, 260(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw t1, 60(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or a0, t1, a0
+; RV32IM-NEXT: sw a0, 120(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a0, 256(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw t1, 52(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or a0, t1, a0
+; RV32IM-NEXT: sw a0, 272(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a0, 252(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s0, 40(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or s0, s0, a0
+; RV32IM-NEXT: lw a0, 248(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw t1, 36(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or t6, t1, a0
+; RV32IM-NEXT: lw a0, 244(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw t1, 32(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or a0, t1, a0
+; RV32IM-NEXT: sw a0, 252(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a0, 240(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw t1, 28(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or a0, t1, a0
+; RV32IM-NEXT: sw a0, 264(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a0, 236(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw t1, 24(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or a0, t1, a0
+; RV32IM-NEXT: sw a0, 284(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a0, 232(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw t1, 20(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or t4, t1, a0
+; RV32IM-NEXT: lw a0, 228(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw t1, 12(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or t3, t1, a0
+; RV32IM-NEXT: lw a0, 224(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw t1, 8(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or a0, t1, a0
+; RV32IM-NEXT: sw a0, 248(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a0, 220(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or a0, s11, a0
+; RV32IM-NEXT: sw a0, 260(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a0, 216(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or a0, a5, a0
+; RV32IM-NEXT: sw a0, 276(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a0, 212(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or a0, s10, a0
+; RV32IM-NEXT: sw a0, 288(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a0, 208(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or s8, s8, a0
+; RV32IM-NEXT: lw a0, 204(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or s10, s9, a0
+; RV32IM-NEXT: lw a0, 200(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or s11, a7, a0
+; RV32IM-NEXT: lw a0, 196(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or a0, a3, a0
+; RV32IM-NEXT: sw a0, 256(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a0, 192(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or a0, a2, a0
+; RV32IM-NEXT: sw a0, 268(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a0, 188(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or a0, t5, a0
+; RV32IM-NEXT: sw a0, 280(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a0, 184(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or a0, t0, a0
+; RV32IM-NEXT: sw a0, 292(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a0, 180(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or t2, a6, a0
+; RV32IM-NEXT: lw a0, 176(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or t1, a4, a0
+; RV32IM-NEXT: lw s1, 172(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or s1, a1, s1
+; RV32IM-NEXT: lw a0, 160(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw a1, 156(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t0, a0, a1
+; RV32IM-NEXT: lw a0, 152(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw a1, 148(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t5, a0, a1
+; RV32IM-NEXT: lw a0, 144(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw a1, 140(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a6, a0, a1
+; RV32IM-NEXT: lw a0, 132(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw a1, 128(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor s9, a0, a1
+; RV32IM-NEXT: lw a0, 104(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw a1, 100(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a7, a1, a0
+; RV32IM-NEXT: lw a0, 96(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw a1, 92(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a0, a0, a1
+; RV32IM-NEXT: lw a1, 84(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw a2, 80(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a1, a1, a2
+; RV32IM-NEXT: lw a2, 76(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw a3, 72(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a2, a2, a3
+; RV32IM-NEXT: lw a3, 68(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw a4, 340(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a3, a3, a4
+; RV32IM-NEXT: lw a4, 56(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw a5, 44(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a4, a4, a5
+; RV32IM-NEXT: lw a5, 4(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw ra, 0(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a5, a5, ra
+; RV32IM-NEXT: lw ra, 332(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor s7, ra, s7
+; RV32IM-NEXT: lw ra, 116(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor s5, ra, s5
+; RV32IM-NEXT: xor s4, s6, s4
+; RV32IM-NEXT: xor s2, s3, s2
+; RV32IM-NEXT: xor t6, s0, t6
+; RV32IM-NEXT: xor t3, t4, t3
+; RV32IM-NEXT: xor t4, s8, s10
+; RV32IM-NEXT: xor t1, t2, t1
+; RV32IM-NEXT: lw t2, 304(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t0, t0, t2
+; RV32IM-NEXT: lw t2, 296(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t2, t5, t2
+; RV32IM-NEXT: lw t5, 168(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a6, a6, t5
+; RV32IM-NEXT: lw t5, 164(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t5, s9, t5
+; RV32IM-NEXT: xor a0, a7, a0
+; RV32IM-NEXT: lw a7, 112(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a1, a1, a7
+; RV32IM-NEXT: lw a7, 88(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a2, a2, a7
+; RV32IM-NEXT: lw a7, 412(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a3, a3, a7
+; RV32IM-NEXT: lw a7, 344(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a4, a4, a7
+; RV32IM-NEXT: lw a7, 48(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a5, a5, a7
+; RV32IM-NEXT: xor a7, s7, s5
+; RV32IM-NEXT: lw s0, 124(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor s0, s4, s0
+; RV32IM-NEXT: lw s3, 120(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor s2, s2, s3
+; RV32IM-NEXT: lw s3, 252(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t6, t6, s3
+; RV32IM-NEXT: lw s3, 248(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t3, t3, s3
+; RV32IM-NEXT: xor t4, t4, s11
+; RV32IM-NEXT: xor t1, t1, s1
+; RV32IM-NEXT: lw s1, 316(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t2, t2, s1
+; RV32IM-NEXT: lw s1, 308(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a6, a6, s1
+; RV32IM-NEXT: lw s1, 300(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t5, t5, s1
+; RV32IM-NEXT: xor a0, a0, a1
+; RV32IM-NEXT: lw a1, 432(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a1, a2, a1
+; RV32IM-NEXT: lw a2, 440(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a2, a3, a2
+; RV32IM-NEXT: lw a3, 424(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a3, a4, a3
+; RV32IM-NEXT: lw a4, 108(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a4, a5, a4
+; RV32IM-NEXT: xor a5, a7, s0
+; RV32IM-NEXT: lw a7, 272(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a7, s2, a7
+; RV32IM-NEXT: lw s0, 264(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t6, t6, s0
+; RV32IM-NEXT: lw s0, 260(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t3, t3, s0
+; RV32IM-NEXT: lw s0, 256(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t4, t4, s0
+; RV32IM-NEXT: lw s0, 352(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t1, t1, s0
+; RV32IM-NEXT: lw s0, 328(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t2, t2, s0
+; RV32IM-NEXT: lw s0, 320(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a6, a6, s0
+; RV32IM-NEXT: lw s0, 312(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t5, t5, s0
+; RV32IM-NEXT: lw s0, 136(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a0, a0, s0
+; RV32IM-NEXT: lw s0, 436(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a1, a1, s0
+; RV32IM-NEXT: lw s0, 444(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a2, a2, s0
+; RV32IM-NEXT: lw s0, 456(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a3, a3, s0
+; RV32IM-NEXT: lw s0, 416(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a4, a4, s0
+; RV32IM-NEXT: xor a5, a5, a7
+; RV32IM-NEXT: lw a7, 284(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a7, t6, a7
+; RV32IM-NEXT: lw t6, 276(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t3, t3, t6
+; RV32IM-NEXT: lw t6, 268(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t4, t4, t6
+; RV32IM-NEXT: lw t6, 364(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t1, t1, t6
+; RV32IM-NEXT: lw t6, 356(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t2, t2, t6
+; RV32IM-NEXT: lw t6, 324(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t5, t5, t6
+; RV32IM-NEXT: lw t6, 452(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a2, a2, t6
+; RV32IM-NEXT: lw t6, 420(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a4, a4, t6
+; RV32IM-NEXT: xor a5, a5, a7
+; RV32IM-NEXT: lw a7, 288(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a7, t3, a7
+; RV32IM-NEXT: lw t3, 280(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t3, t4, t3
+; RV32IM-NEXT: lw t4, 372(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t1, t1, t4
+; RV32IM-NEXT: lw t4, 360(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t2, t2, t4
+; RV32IM-NEXT: lw t4, 336(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t4, t5, t4
+; RV32IM-NEXT: xor a1, a0, a1
+; RV32IM-NEXT: xor a1, a1, a2
+; RV32IM-NEXT: lw a2, 428(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a2, a4, a2
+; RV32IM-NEXT: xor a4, a5, a7
+; RV32IM-NEXT: lw a5, 292(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a5, t3, a5
+; RV32IM-NEXT: lw a7, 388(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a7, t1, a7
+; RV32IM-NEXT: lw t1, 368(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t1, t2, t1
+; RV32IM-NEXT: lw t2, 348(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t2, t4, t2
+; RV32IM-NEXT: xor a1, a1, a3
+; RV32IM-NEXT: lw a3, 448(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a2, a2, a3
+; RV32IM-NEXT: xor a4, a4, a5
+; RV32IM-NEXT: lw a3, 392(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a3, a7, a3
+; RV32IM-NEXT: lw a5, 376(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a5, t1, a5
+; RV32IM-NEXT: xor a3, a4, a3
+; RV32IM-NEXT: lw a4, 380(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a4, a5, a4
+; RV32IM-NEXT: xor a3, a3, t0
+; RV32IM-NEXT: slli a0, a0, 24
+; RV32IM-NEXT: lw a5, 384(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a4, a4, a5
+; RV32IM-NEXT: lw a7, 396(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: and a5, a1, a7
+; RV32IM-NEXT: slli a5, a5, 8
+; RV32IM-NEXT: or a0, a0, a5
+; RV32IM-NEXT: xor a2, a1, a2
+; RV32IM-NEXT: srli a1, a1, 8
+; RV32IM-NEXT: and a1, a1, a7
+; RV32IM-NEXT: srli a2, a2, 24
+; RV32IM-NEXT: or a1, a1, a2
+; RV32IM-NEXT: or a0, a0, a1
+; RV32IM-NEXT: xor a4, a3, a4
+; RV32IM-NEXT: xor a1, a4, a6
+; RV32IM-NEXT: and a2, a1, a7
+; RV32IM-NEXT: xor a4, a1, t2
+; RV32IM-NEXT: srli a1, a1, 8
+; RV32IM-NEXT: and a1, a1, a7
+; RV32IM-NEXT: srli a5, a0, 4
+; RV32IM-NEXT: lw a6, 400(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: and a0, a0, a6
+; RV32IM-NEXT: and a5, a5, a6
+; RV32IM-NEXT: slli a0, a0, 4
+; RV32IM-NEXT: or a0, a5, a0
+; RV32IM-NEXT: slli a3, a3, 24
+; RV32IM-NEXT: slli a2, a2, 8
+; RV32IM-NEXT: or a2, a3, a2
+; RV32IM-NEXT: srli a4, a4, 24
+; RV32IM-NEXT: or a1, a1, a4
+; RV32IM-NEXT: or a1, a2, a1
+; RV32IM-NEXT: srli a2, a0, 2
+; RV32IM-NEXT: lw a3, 404(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: and a0, a0, a3
+; RV32IM-NEXT: and a2, a2, a3
+; RV32IM-NEXT: slli a0, a0, 2
+; RV32IM-NEXT: or a0, a2, a0
+; RV32IM-NEXT: srli a2, a1, 4
+; RV32IM-NEXT: and a1, a1, a6
+; RV32IM-NEXT: and a2, a2, a6
+; RV32IM-NEXT: slli a1, a1, 4
+; RV32IM-NEXT: or a1, a2, a1
+; RV32IM-NEXT: srli a2, a1, 2
+; RV32IM-NEXT: and a1, a1, a3
+; RV32IM-NEXT: and a2, a2, a3
+; RV32IM-NEXT: srli a3, a0, 1
+; RV32IM-NEXT: lw a5, 408(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: and a4, a0, a5
+; RV32IM-NEXT: and a3, a3, a5
+; RV32IM-NEXT: slli a1, a1, 2
+; RV32IM-NEXT: or a1, a2, a1
+; RV32IM-NEXT: srli a0, a1, 1
+; RV32IM-NEXT: and a1, a1, a5
+; RV32IM-NEXT: and a0, a0, a5
+; RV32IM-NEXT: slli a1, a1, 1
+; RV32IM-NEXT: or a0, a0, a1
+; RV32IM-NEXT: slli a1, a4, 1
+; RV32IM-NEXT: or a1, a3, a1
+; RV32IM-NEXT: lw ra, 508(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s0, 504(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s1, 500(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s2, 496(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s3, 492(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s4, 488(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s5, 484(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s6, 480(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s7, 476(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s8, 472(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s9, 468(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s10, 464(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s11, 460(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: addi sp, sp, 512
+; RV32IM-NEXT: ret
+;
+; RV64IM-LABEL: clmulr_i64:
+; RV64IM: # %bb.0:
+; RV64IM-NEXT: addi sp, sp, -448
+; RV64IM-NEXT: sd ra, 440(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s0, 432(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s1, 424(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s2, 416(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s3, 408(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s4, 400(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s5, 392(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s6, 384(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s7, 376(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s8, 368(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s9, 360(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s10, 352(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s11, 344(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: srli a2, a0, 24
+; RV64IM-NEXT: srli a6, a0, 8
+; RV64IM-NEXT: li a3, 255
+; RV64IM-NEXT: srli a5, a0, 40
+; RV64IM-NEXT: lui s3, 16
+; RV64IM-NEXT: srli s0, a0, 56
+; RV64IM-NEXT: srliw t2, a0, 24
+; RV64IM-NEXT: slli t0, a0, 56
+; RV64IM-NEXT: lui t3, 61681
+; RV64IM-NEXT: lui t4, 209715
+; RV64IM-NEXT: lui t6, 349525
+; RV64IM-NEXT: li a7, 1
+; RV64IM-NEXT: lui s5, 2
+; RV64IM-NEXT: lui t1, 4
+; RV64IM-NEXT: lui a4, 128
+; RV64IM-NEXT: lui s7, 256
+; RV64IM-NEXT: lui s8, 4096
+; RV64IM-NEXT: lui s10, 8192
+; RV64IM-NEXT: lui a1, 4080
+; RV64IM-NEXT: and a2, a2, a1
+; RV64IM-NEXT: slli a3, a3, 24
+; RV64IM-NEXT: sd a3, 336(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: addi s1, s3, -256
+; RV64IM-NEXT: and t5, a0, a1
+; RV64IM-NEXT: slli a1, t2, 32
+; RV64IM-NEXT: addi s9, t3, -241
+; RV64IM-NEXT: addi t4, t4, 819
+; RV64IM-NEXT: addi t2, t6, 1365
+; RV64IM-NEXT: slli t3, a7, 11
+; RV64IM-NEXT: slli s11, a7, 32
+; RV64IM-NEXT: slli ra, a7, 33
+; RV64IM-NEXT: slli t6, a7, 34
+; RV64IM-NEXT: slli s2, a7, 35
+; RV64IM-NEXT: slli s4, a7, 36
+; RV64IM-NEXT: sd s4, 256(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a3, a6, a3
+; RV64IM-NEXT: or a2, a3, a2
+; RV64IM-NEXT: slli a3, a7, 37
+; RV64IM-NEXT: sd a3, 248(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s1, 304(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a3, a5, s1
+; RV64IM-NEXT: or a3, a3, s0
+; RV64IM-NEXT: slli a5, a7, 38
+; RV64IM-NEXT: sd a5, 232(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli t5, t5, 24
+; RV64IM-NEXT: and a0, a0, s1
+; RV64IM-NEXT: or a1, t5, a1
+; RV64IM-NEXT: slli a5, s9, 32
+; RV64IM-NEXT: add a5, s9, a5
+; RV64IM-NEXT: slli s0, t4, 32
+; RV64IM-NEXT: add t4, t4, s0
+; RV64IM-NEXT: slli s4, t2, 32
+; RV64IM-NEXT: slli a0, a0, 40
+; RV64IM-NEXT: add t2, t2, s4
+; RV64IM-NEXT: or a2, a2, a3
+; RV64IM-NEXT: or a0, t0, a0
+; RV64IM-NEXT: or a0, a0, a1
+; RV64IM-NEXT: or a0, a0, a2
+; RV64IM-NEXT: srli a1, a0, 4
+; RV64IM-NEXT: sd a5, 312(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, a0, a5
+; RV64IM-NEXT: and a1, a1, a5
+; RV64IM-NEXT: slli a0, a0, 4
+; RV64IM-NEXT: or a0, a1, a0
+; RV64IM-NEXT: srli a1, a0, 2
+; RV64IM-NEXT: sd t4, 320(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, a0, t4
+; RV64IM-NEXT: and a1, a1, t4
+; RV64IM-NEXT: slli a0, a0, 2
+; RV64IM-NEXT: or a0, a1, a0
+; RV64IM-NEXT: srli a1, a0, 1
+; RV64IM-NEXT: sd t2, 328(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, a0, t2
+; RV64IM-NEXT: and a1, a1, t2
+; RV64IM-NEXT: slli a0, a0, 1
+; RV64IM-NEXT: or t0, a1, a0
+; RV64IM-NEXT: andi a0, t0, 2
+; RV64IM-NEXT: andi a1, t0, 1
+; RV64IM-NEXT: andi a2, t0, 4
+; RV64IM-NEXT: andi a3, t0, 8
+; RV64IM-NEXT: andi a5, t0, 16
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: xor a0, a1, a0
+; RV64IM-NEXT: sd a0, 296(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi a0, t0, 32
+; RV64IM-NEXT: mul a1, t0, a2
+; RV64IM-NEXT: mul a2, t0, a3
+; RV64IM-NEXT: xor a1, a1, a2
+; RV64IM-NEXT: sd a1, 288(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi a1, t0, 256
+; RV64IM-NEXT: mul a2, t0, a5
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: xor a0, a2, a0
+; RV64IM-NEXT: sd a0, 280(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi a0, t0, 512
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: xor a0, a1, a0
+; RV64IM-NEXT: sd a0, 272(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli t4, a7, 39
+; RV64IM-NEXT: and a0, t0, s5
+; RV64IM-NEXT: and a1, t0, t1
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: xor a0, a0, a1
+; RV64IM-NEXT: sd a0, 264(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 40
+; RV64IM-NEXT: and a1, t0, a4
+; RV64IM-NEXT: and a2, t0, s7
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: xor a1, a1, a2
+; RV64IM-NEXT: sd a1, 240(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a1, a7, 41
+; RV64IM-NEXT: and a2, t0, s8
+; RV64IM-NEXT: and a3, t0, s10
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: mul a3, t0, a3
+; RV64IM-NEXT: xor a2, a2, a3
+; RV64IM-NEXT: sd a2, 224(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a2, a7, 48
+; RV64IM-NEXT: and a3, t0, s11
+; RV64IM-NEXT: and a4, t0, ra
+; RV64IM-NEXT: mul a3, t0, a3
+; RV64IM-NEXT: mul a4, t0, a4
+; RV64IM-NEXT: xor a3, a3, a4
+; RV64IM-NEXT: sd a3, 216(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a7, 49
+; RV64IM-NEXT: and a0, t0, a0
+; RV64IM-NEXT: and a1, t0, a1
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: xor a0, a0, a1
+; RV64IM-NEXT: sd a0, 208(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 56
+; RV64IM-NEXT: and a1, t0, a2
+; RV64IM-NEXT: and a2, t0, a3
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: xor a1, a1, a2
+; RV64IM-NEXT: sd a1, 200(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a1, a7, 57
+; RV64IM-NEXT: and a0, t0, a0
+; RV64IM-NEXT: and a1, t0, a1
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: xor a0, a0, a1
+; RV64IM-NEXT: sd a0, 192(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a2, a7, 42
+; RV64IM-NEXT: slli ra, a7, 43
+; RV64IM-NEXT: slli a3, a7, 44
+; RV64IM-NEXT: slli a4, a7, 45
+; RV64IM-NEXT: slli t5, a7, 46
+; RV64IM-NEXT: slli s0, a7, 47
+; RV64IM-NEXT: slli s1, a7, 50
+; RV64IM-NEXT: slli a0, a7, 51
+; RV64IM-NEXT: sd a0, 184(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 52
+; RV64IM-NEXT: sd a0, 176(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 53
+; RV64IM-NEXT: sd a0, 168(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 54
+; RV64IM-NEXT: sd a0, 160(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 55
+; RV64IM-NEXT: sd a0, 152(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 58
+; RV64IM-NEXT: sd a0, 144(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 59
+; RV64IM-NEXT: sd a0, 136(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 60
+; RV64IM-NEXT: sd a0, 120(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 61
+; RV64IM-NEXT: sd a0, 80(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a7, a7, 62
+; RV64IM-NEXT: sd a7, 48(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, t0, t3
+; RV64IM-NEXT: sd a0, 128(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s7, 1
+; RV64IM-NEXT: and a0, t0, s7
+; RV64IM-NEXT: sd a0, 112(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s8, 8
+; RV64IM-NEXT: and a0, t0, s8
+; RV64IM-NEXT: sd a0, 104(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, t0, s3
+; RV64IM-NEXT: sd a0, 96(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s6, 32
+; RV64IM-NEXT: and a0, t0, s6
+; RV64IM-NEXT: sd a0, 88(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s10, 64
+; RV64IM-NEXT: and a0, t0, s10
+; RV64IM-NEXT: sd a0, 72(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s11, 512
+; RV64IM-NEXT: and a0, t0, s11
+; RV64IM-NEXT: sd a0, 64(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s4, 1024
+; RV64IM-NEXT: and a0, t0, s4
+; RV64IM-NEXT: sd a0, 56(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s5, 2048
+; RV64IM-NEXT: and a0, t0, s5
+; RV64IM-NEXT: sd a0, 40(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s9, 16384
+; RV64IM-NEXT: and a0, t0, s9
+; RV64IM-NEXT: sd a0, 32(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui a5, 32768
+; RV64IM-NEXT: and a5, t0, a5
+; RV64IM-NEXT: lui a6, 65536
+; RV64IM-NEXT: and a6, t0, a6
+; RV64IM-NEXT: lui t1, 131072
+; RV64IM-NEXT: and t1, t0, t1
+; RV64IM-NEXT: lui t2, 262144
+; RV64IM-NEXT: and t2, t0, t2
+; RV64IM-NEXT: and a0, t0, t6
+; RV64IM-NEXT: sd a0, 24(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, t0, s2
+; RV64IM-NEXT: sd a0, 16(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a0, 256(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, t0, a0
+; RV64IM-NEXT: sd a0, 8(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a0, 248(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, t0, a0
+; RV64IM-NEXT: sd a0, 0(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a0, 232(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, t0, a0
+; RV64IM-NEXT: and a1, t0, t4
+; RV64IM-NEXT: and a7, t0, a2
+; RV64IM-NEXT: and ra, t0, ra
+; RV64IM-NEXT: and t3, t0, a3
+; RV64IM-NEXT: and t4, t0, a4
+; RV64IM-NEXT: and t5, t0, t5
+; RV64IM-NEXT: and t6, t0, s0
+; RV64IM-NEXT: and s0, t0, s1
+; RV64IM-NEXT: ld a2, 184(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s1, t0, a2
+; RV64IM-NEXT: ld a2, 176(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s2, t0, a2
+; RV64IM-NEXT: ld a2, 168(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s3, t0, a2
+; RV64IM-NEXT: ld a2, 160(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s4, t0, a2
+; RV64IM-NEXT: ld a2, 152(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s5, t0, a2
+; RV64IM-NEXT: ld a2, 144(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s6, t0, a2
+; RV64IM-NEXT: ld a2, 136(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s7, t0, a2
+; RV64IM-NEXT: ld a2, 120(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s8, t0, a2
+; RV64IM-NEXT: ld a2, 80(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s9, t0, a2
+; RV64IM-NEXT: ld a2, 48(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s10, t0, a2
+; RV64IM-NEXT: andi s11, t0, 64
+; RV64IM-NEXT: mul a2, t0, s11
+; RV64IM-NEXT: sd a2, 80(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi s11, t0, 128
+; RV64IM-NEXT: mul a2, t0, s11
+; RV64IM-NEXT: sd a2, 232(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi s11, t0, 1024
+; RV64IM-NEXT: mul a2, t0, s11
+; RV64IM-NEXT: sd a2, 48(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 128(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 120(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 112(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 176(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 104(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul s11, t0, a2
+; RV64IM-NEXT: ld a2, 96(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 104(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 88(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 168(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 72(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 256(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 64(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a4, t0, a2
+; RV64IM-NEXT: ld a2, 56(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 96(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 40(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 136(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 32(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a3, t0, a2
+; RV64IM-NEXT: mul a2, t0, a5
+; RV64IM-NEXT: sd a2, 88(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a2, t0, a6
+; RV64IM-NEXT: sd a2, 128(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a2, t0, t1
+; RV64IM-NEXT: sd a2, 160(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a2, t0, t2
+; RV64IM-NEXT: sd a2, 248(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: srliw t2, t0, 31
+; RV64IM-NEXT: slli t2, t2, 31
+; RV64IM-NEXT: ld a2, 24(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: ld a5, 16(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a5, t0, a5
+; RV64IM-NEXT: ld a6, 8(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul t1, t0, a6
+; RV64IM-NEXT: ld a6, 0(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a6, t0, a6
+; RV64IM-NEXT: sd a6, 112(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: sd a0, 152(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a0, t0, a1
+; RV64IM-NEXT: sd a0, 184(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a7, t0, a7
+; RV64IM-NEXT: mul ra, t0, ra
+; RV64IM-NEXT: mul a6, t0, t3
+; RV64IM-NEXT: mul t4, t0, t4
+; RV64IM-NEXT: mul t5, t0, t5
+; RV64IM-NEXT: mul a0, t0, t6
+; RV64IM-NEXT: sd a0, 144(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul t6, t0, s0
+; RV64IM-NEXT: mul s0, t0, s1
+; RV64IM-NEXT: mul s1, t0, s2
+; RV64IM-NEXT: mul s2, t0, s3
+; RV64IM-NEXT: mul s3, t0, s4
+; RV64IM-NEXT: mul s4, t0, s5
+; RV64IM-NEXT: mul s5, t0, s6
+; RV64IM-NEXT: mul s6, t0, s7
+; RV64IM-NEXT: mul s7, t0, s8
+; RV64IM-NEXT: mul s8, t0, s9
+; RV64IM-NEXT: mul s9, t0, s10
+; RV64IM-NEXT: srli s10, t0, 63
+; RV64IM-NEXT: slli s10, s10, 63
+; RV64IM-NEXT: mul t2, t0, t2
+; RV64IM-NEXT: mul t0, t0, s10
+; RV64IM-NEXT: ld a0, 296(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld a1, 288(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s10, a0, a1
+; RV64IM-NEXT: ld a0, 280(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld a1, 80(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a0, a0, a1
+; RV64IM-NEXT: ld a1, 272(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld t3, 48(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a1, a1, t3
+; RV64IM-NEXT: ld t3, 264(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s11, t3, s11
+; RV64IM-NEXT: ld t3, 240(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, t3, a4
+; RV64IM-NEXT: ld t3, 224(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, t3, a3
+; RV64IM-NEXT: ld t3, 216(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, t3, a2
+; RV64IM-NEXT: ld t3, 208(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a7, t3, a7
+; RV64IM-NEXT: ld t3, 200(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor t6, t3, t6
+; RV64IM-NEXT: ld t3, 192(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s5, t3, s5
+; RV64IM-NEXT: xor a0, s10, a0
+; RV64IM-NEXT: ld t3, 120(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a1, a1, t3
+; RV64IM-NEXT: ld t3, 104(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s10, s11, t3
+; RV64IM-NEXT: ld t3, 96(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, a4, t3
+; RV64IM-NEXT: ld t3, 88(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a3, t3
+; RV64IM-NEXT: xor a2, a2, a5
+; RV64IM-NEXT: xor a5, a7, ra
+; RV64IM-NEXT: xor a7, t6, s0
+; RV64IM-NEXT: xor t6, s5, s6
+; RV64IM-NEXT: ld t3, 232(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a0, a0, t3
+; RV64IM-NEXT: ld t3, 176(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a1, a1, t3
+; RV64IM-NEXT: ld t3, 168(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s0, s10, t3
+; RV64IM-NEXT: ld t3, 136(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, a4, t3
+; RV64IM-NEXT: ld t3, 128(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a3, t3
+; RV64IM-NEXT: xor a2, a2, t1
+; RV64IM-NEXT: xor a5, a5, a6
+; RV64IM-NEXT: xor a6, a7, s1
+; RV64IM-NEXT: xor a7, t6, s7
+; RV64IM-NEXT: ld t1, 256(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor t1, s0, t1
+; RV64IM-NEXT: ld t3, 160(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a3, t3
+; RV64IM-NEXT: ld t3, 112(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a2, t3
+; RV64IM-NEXT: xor a5, a5, t4
+; RV64IM-NEXT: xor a6, a6, s2
+; RV64IM-NEXT: xor a7, a7, s8
+; RV64IM-NEXT: xor a1, a0, a1
+; RV64IM-NEXT: xor a1, a1, t1
+; RV64IM-NEXT: ld t1, 248(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a3, t1
+; RV64IM-NEXT: ld t1, 152(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a2, t1
+; RV64IM-NEXT: xor a5, a5, t5
+; RV64IM-NEXT: xor a6, a6, s3
+; RV64IM-NEXT: xor a7, a7, s9
+; RV64IM-NEXT: xor a1, a1, a4
+; RV64IM-NEXT: xor a3, a3, t2
+; RV64IM-NEXT: ld a4, 184(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a2, a4
+; RV64IM-NEXT: ld a4, 144(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, a5, a4
+; RV64IM-NEXT: xor a5, a6, s4
+; RV64IM-NEXT: slli a0, a0, 56
+; RV64IM-NEXT: xor a6, a7, t0
+; RV64IM-NEXT: ld t0, 304(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a7, a1, t0
+; RV64IM-NEXT: xor a1, a1, a3
+; RV64IM-NEXT: slli a7, a7, 40
+; RV64IM-NEXT: xor a1, a1, a2
+; RV64IM-NEXT: or a0, a0, a7
+; RV64IM-NEXT: lui a7, 4080
+; RV64IM-NEXT: and a2, a1, a7
+; RV64IM-NEXT: xor a4, a1, a4
+; RV64IM-NEXT: srli a1, a1, 8
+; RV64IM-NEXT: slli a2, a2, 24
+; RV64IM-NEXT: xor a5, a4, a5
+; RV64IM-NEXT: ld a3, 336(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a1, a1, a3
+; RV64IM-NEXT: srli a4, a4, 24
+; RV64IM-NEXT: srliw a3, a5, 24
+; RV64IM-NEXT: and a4, a4, a7
+; RV64IM-NEXT: srli a7, a5, 40
+; RV64IM-NEXT: xor a5, a5, a6
+; RV64IM-NEXT: slli a3, a3, 32
+; RV64IM-NEXT: or a1, a1, a4
+; RV64IM-NEXT: and a4, a7, t0
+; RV64IM-NEXT: srli a5, a5, 56
+; RV64IM-NEXT: or a2, a2, a3
+; RV64IM-NEXT: or a4, a4, a5
+; RV64IM-NEXT: or a0, a0, a2
+; RV64IM-NEXT: or a1, a1, a4
+; RV64IM-NEXT: or a0, a0, a1
+; RV64IM-NEXT: srli a1, a0, 4
+; RV64IM-NEXT: ld a2, 312(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, a0, a2
+; RV64IM-NEXT: and a1, a1, a2
+; RV64IM-NEXT: slli a0, a0, 4
+; RV64IM-NEXT: or a0, a1, a0
+; RV64IM-NEXT: srli a1, a0, 2
+; RV64IM-NEXT: ld a2, 320(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, a0, a2
+; RV64IM-NEXT: and a1, a1, a2
+; RV64IM-NEXT: slli a0, a0, 2
+; RV64IM-NEXT: or a0, a1, a0
+; RV64IM-NEXT: srli a1, a0, 1
+; RV64IM-NEXT: ld a2, 328(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, a0, a2
+; RV64IM-NEXT: and a1, a1, a2
+; RV64IM-NEXT: slli a0, a0, 1
+; RV64IM-NEXT: or a0, a1, a0
+; RV64IM-NEXT: ld ra, 440(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s0, 432(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s1, 424(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s2, 416(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s3, 408(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s4, 400(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s5, 392(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s6, 384(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s7, 376(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s8, 368(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s9, 360(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s10, 352(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s11, 344(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: addi sp, sp, 448
+; RV64IM-NEXT: ret
+ %res = call i64 @llvm.clmulr.i64(i64 %a, i64 %b)
+ ret i64 %res
+}
+
+define i4 @clmulr_constfold_i4() nounwind {
+; CHECK-LABEL: clmulr_constfold_i4:
+; CHECK: # %bb.0:
+; CHECK-NEXT: li a0, 0
+; CHECK-NEXT: ret
+ %res = call i4 @llvm.clmulr.i4(i4 1, i4 2)
+ ret i4 %res
+}
+
+define i16 @clmulr_constfold_i16() nounwind {
+; RV32IM-LABEL: clmulr_constfold_i16:
+; RV32IM: # %bb.0:
+; RV32IM-NEXT: lui a0, 699051
+; RV32IM-NEXT: addi a0, a0, -1366
+; RV32IM-NEXT: ret
+;
+; RV64IM-LABEL: clmulr_constfold_i16:
+; RV64IM: # %bb.0:
+; RV64IM-NEXT: lui a0, %hi(.LCPI13_0)
+; RV64IM-NEXT: ld a0, %lo(.LCPI13_0)(a0)
+; RV64IM-NEXT: ret
+ %res = call i16 @llvm.clmulr.i16(i16 -2, i16 -1)
+ ret i16 %res
+}
+
+define i4 @clmulh_i4(i4 %a, i4 %b) nounwind {
+; RV32IM-LABEL: clmulh_i4:
+; RV32IM: # %bb.0:
+; RV32IM-NEXT: addi sp, sp, -144
+; RV32IM-NEXT: sw ra, 140(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s0, 136(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s1, 132(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s2, 128(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s3, 124(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s4, 120(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s5, 116(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s6, 112(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s7, 108(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s8, 104(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s9, 100(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s10, 96(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s11, 92(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: srli a3, a0, 8
+; RV32IM-NEXT: lui a1, 16
+; RV32IM-NEXT: srli a6, a0, 24
+; RV32IM-NEXT: slli a4, a0, 24
+; RV32IM-NEXT: lui a2, 61681
+; RV32IM-NEXT: lui t0, 209715
+; RV32IM-NEXT: lui a5, 349525
+; RV32IM-NEXT: li t5, 1
+; RV32IM-NEXT: lui t1, 1
+; RV32IM-NEXT: lui t2, 2
+; RV32IM-NEXT: lui t3, 4
+; RV32IM-NEXT: lui t4, 8
+; RV32IM-NEXT: lui s0, 64
+; RV32IM-NEXT: lui s1, 128
+; RV32IM-NEXT: lui t6, 256
+; RV32IM-NEXT: lui s2, 512
+; RV32IM-NEXT: lui s3, 1024
+; RV32IM-NEXT: lui s4, 2048
+; RV32IM-NEXT: lui s5, 4096
+; RV32IM-NEXT: lui s6, 8192
+; RV32IM-NEXT: lui s7, 16384
+; RV32IM-NEXT: lui s8, 32768
+; RV32IM-NEXT: lui s9, 65536
+; RV32IM-NEXT: lui s10, 131072
+; RV32IM-NEXT: lui s11, 262144
+; RV32IM-NEXT: addi a7, a1, -256
+; RV32IM-NEXT: sw a7, 76(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a3, a3, a7
+; RV32IM-NEXT: or a3, a3, a6
+; RV32IM-NEXT: lui ra, 524288
+; RV32IM-NEXT: addi a6, a2, -241
+; RV32IM-NEXT: sw a6, 80(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: addi a2, t0, 819
+; RV32IM-NEXT: sw a2, 84(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a0, a0, a7
+; RV32IM-NEXT: slli a0, a0, 8
+; RV32IM-NEXT: or a4, a4, a0
+; RV32IM-NEXT: addi a0, a5, 1365
+; RV32IM-NEXT: sw a0, 88(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: slli t5, t5, 11
+; RV32IM-NEXT: or a3, a4, a3
+; RV32IM-NEXT: srli a4, a3, 4
+; RV32IM-NEXT: and a3, a3, a6
+; RV32IM-NEXT: and a4, a4, a6
+; RV32IM-NEXT: slli a3, a3, 4
+; RV32IM-NEXT: or a3, a4, a3
+; RV32IM-NEXT: srli a4, a3, 2
+; RV32IM-NEXT: and a3, a3, a2
+; RV32IM-NEXT: and a4, a4, a2
+; RV32IM-NEXT: slli a3, a3, 2
+; RV32IM-NEXT: or a3, a4, a3
+; RV32IM-NEXT: srli a4, a3, 1
+; RV32IM-NEXT: and a3, a3, a0
+; RV32IM-NEXT: and a4, a4, a0
+; RV32IM-NEXT: slli a3, a3, 1
+; RV32IM-NEXT: or a3, a4, a3
+; RV32IM-NEXT: andi a2, a3, 2
+; RV32IM-NEXT: and a0, a3, t5
+; RV32IM-NEXT: sw a0, 72(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and t1, a3, t1
+; RV32IM-NEXT: and t2, a3, t2
+; RV32IM-NEXT: and t3, a3, t3
+; RV32IM-NEXT: and t4, a3, t4
+; RV32IM-NEXT: and a1, a3, a1
+; RV32IM-NEXT: sw a1, 60(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lui a0, 32
+; RV32IM-NEXT: and a0, a3, a0
+; RV32IM-NEXT: sw a0, 56(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and s0, a3, s0
+; RV32IM-NEXT: sw s0, 52(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and s1, a3, s1
+; RV32IM-NEXT: sw s1, 48(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and t6, a3, t6
+; RV32IM-NEXT: and s2, a3, s2
+; RV32IM-NEXT: and a0, a3, s3
+; RV32IM-NEXT: sw a0, 44(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a0, a3, s4
+; RV32IM-NEXT: sw a0, 40(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a0, a3, s5
+; RV32IM-NEXT: sw a0, 36(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a0, a3, s6
+; RV32IM-NEXT: sw a0, 32(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a0, a3, s7
+; RV32IM-NEXT: sw a0, 28(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a0, a3, s8
+; RV32IM-NEXT: sw a0, 24(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a0, a3, s9
+; RV32IM-NEXT: sw a0, 20(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a0, a3, s10
+; RV32IM-NEXT: sw a0, 16(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a0, a3, s11
+; RV32IM-NEXT: sw a0, 12(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a0, a3, ra
+; RV32IM-NEXT: sw a0, 8(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a0, a3, a2
+; RV32IM-NEXT: sw a0, 64(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi ra, a3, 1
+; RV32IM-NEXT: mul a0, a3, ra
+; RV32IM-NEXT: sw a0, 4(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi a4, a3, 4
+; RV32IM-NEXT: mul ra, a3, a4
+; RV32IM-NEXT: andi a1, a3, 8
+; RV32IM-NEXT: mul s9, a3, a1
+; RV32IM-NEXT: andi a2, a3, 16
+; RV32IM-NEXT: mul s8, a3, a2
+; RV32IM-NEXT: andi a7, a3, 32
+; RV32IM-NEXT: mul s5, a3, a7
+; RV32IM-NEXT: andi a0, a3, 64
+; RV32IM-NEXT: mul s11, a3, a0
+; RV32IM-NEXT: andi a5, a3, 128
+; RV32IM-NEXT: mul a0, a3, a5
+; RV32IM-NEXT: sw a0, 68(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi a5, a3, 256
+; RV32IM-NEXT: mul s1, a3, a5
+; RV32IM-NEXT: andi a6, a3, 512
+; RV32IM-NEXT: mul t5, a3, a6
+; RV32IM-NEXT: andi t0, a3, 1024
+; RV32IM-NEXT: mul s3, a3, t0
+; RV32IM-NEXT: lw a0, 72(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s6, a3, a0
+; RV32IM-NEXT: mul a0, a3, t1
+; RV32IM-NEXT: sw a0, 0(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul t2, a3, t2
+; RV32IM-NEXT: mul a7, a3, t3
+; RV32IM-NEXT: mul s0, a3, t4
+; RV32IM-NEXT: lw a0, 60(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s4, a3, a0
+; RV32IM-NEXT: lw a0, 56(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s7, a3, a0
+; RV32IM-NEXT: lw a0, 52(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s10, a3, a0
+; RV32IM-NEXT: lw a0, 48(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a6, a3, a0
+; RV32IM-NEXT: mul a4, a3, t6
+; RV32IM-NEXT: mul t1, a3, s2
+; RV32IM-NEXT: lw a0, 44(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul t4, a3, a0
+; RV32IM-NEXT: lw a0, 40(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s2, a3, a0
+; RV32IM-NEXT: lw a0, 36(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a2, a3, a0
+; RV32IM-NEXT: lw a0, 32(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a1, a3, a0
+; RV32IM-NEXT: lw a0, 28(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a5, a3, a0
+; RV32IM-NEXT: lw a0, 24(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul t0, a3, a0
+; RV32IM-NEXT: lw a0, 20(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul t3, a3, a0
+; RV32IM-NEXT: lw a0, 16(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul t6, a3, a0
+; RV32IM-NEXT: lw a0, 12(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a0, a3, a0
+; RV32IM-NEXT: sw a0, 72(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a0, 8(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a0, a3, a0
+; RV32IM-NEXT: sw a0, 60(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a0, 64(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw a3, 4(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a0, a3, a0
+; RV32IM-NEXT: xor s9, ra, s9
+; RV32IM-NEXT: xor s5, s8, s5
+; RV32IM-NEXT: xor t5, s1, t5
+; RV32IM-NEXT: xor a7, t2, a7
+; RV32IM-NEXT: xor a4, a6, a4
+; RV32IM-NEXT: xor a1, a2, a1
+; RV32IM-NEXT: xor a0, a0, s9
+; RV32IM-NEXT: xor a2, s5, s11
+; RV32IM-NEXT: xor a6, t5, s3
+; RV32IM-NEXT: xor a7, a7, s0
+; RV32IM-NEXT: xor a4, a4, t1
+; RV32IM-NEXT: xor a1, a1, a5
+; RV32IM-NEXT: xor a0, a0, a2
+; RV32IM-NEXT: xor a2, a6, s6
+; RV32IM-NEXT: xor a5, a7, s4
+; RV32IM-NEXT: xor a4, a4, t4
+; RV32IM-NEXT: xor a1, a1, t0
+; RV32IM-NEXT: lw a6, 68(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a0, a0, a6
+; RV32IM-NEXT: lw a3, 0(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a2, a2, a3
+; RV32IM-NEXT: xor a5, a5, s7
+; RV32IM-NEXT: xor a4, a4, s2
+; RV32IM-NEXT: xor a1, a1, t3
+; RV32IM-NEXT: xor a5, a5, s10
+; RV32IM-NEXT: xor a1, a1, t6
+; RV32IM-NEXT: xor a2, a0, a2
+; RV32IM-NEXT: xor a2, a2, a5
+; RV32IM-NEXT: lui a5, 349525
+; RV32IM-NEXT: addi a5, a5, 1364
+; RV32IM-NEXT: slli a0, a0, 24
+; RV32IM-NEXT: lw a6, 72(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a1, a1, a6
+; RV32IM-NEXT: xor a2, a2, a4
+; RV32IM-NEXT: lw a3, 60(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a1, a1, a3
+; RV32IM-NEXT: lw a6, 76(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: and a3, a2, a6
+; RV32IM-NEXT: srli a4, a2, 8
+; RV32IM-NEXT: xor a1, a2, a1
+; RV32IM-NEXT: slli a3, a3, 8
+; RV32IM-NEXT: and a2, a4, a6
+; RV32IM-NEXT: srli a1, a1, 24
+; RV32IM-NEXT: or a0, a0, a3
+; RV32IM-NEXT: or a1, a2, a1
+; RV32IM-NEXT: or a0, a0, a1
+; RV32IM-NEXT: srli a1, a0, 4
+; RV32IM-NEXT: lw a2, 80(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: and a0, a0, a2
+; RV32IM-NEXT: and a1, a1, a2
+; RV32IM-NEXT: slli a0, a0, 4
+; RV32IM-NEXT: or a0, a1, a0
+; RV32IM-NEXT: srli a1, a0, 2
+; RV32IM-NEXT: lw a2, 84(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: and a0, a0, a2
+; RV32IM-NEXT: and a1, a1, a2
+; RV32IM-NEXT: slli a0, a0, 2
+; RV32IM-NEXT: or a0, a1, a0
+; RV32IM-NEXT: srli a1, a0, 1
+; RV32IM-NEXT: lw a2, 88(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: and a0, a0, a2
+; RV32IM-NEXT: and a1, a1, a5
+; RV32IM-NEXT: slli a0, a0, 1
+; RV32IM-NEXT: or a0, a1, a0
+; RV32IM-NEXT: srli a0, a0, 1
+; RV32IM-NEXT: lw ra, 140(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s0, 136(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s1, 132(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s2, 128(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s3, 124(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s4, 120(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s5, 116(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s6, 112(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s7, 108(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s8, 104(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s9, 100(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s10, 96(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s11, 92(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: addi sp, sp, 144
+; RV32IM-NEXT: ret
+;
+; RV64IM-LABEL: clmulh_i4:
+; RV64IM: # %bb.0:
+; RV64IM-NEXT: addi sp, sp, -448
+; RV64IM-NEXT: sd ra, 440(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s0, 432(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s1, 424(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s2, 416(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s3, 408(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s4, 400(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s5, 392(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s6, 384(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s7, 376(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s8, 368(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s9, 360(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s10, 352(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s11, 344(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: srli a2, a0, 24
+; RV64IM-NEXT: srli a6, a0, 8
+; RV64IM-NEXT: li a3, 255
+; RV64IM-NEXT: srli a5, a0, 40
+; RV64IM-NEXT: lui s2, 16
+; RV64IM-NEXT: srli s5, a0, 56
+; RV64IM-NEXT: srliw t2, a0, 24
+; RV64IM-NEXT: slli t0, a0, 56
+; RV64IM-NEXT: lui t3, 61681
+; RV64IM-NEXT: lui t4, 209715
+; RV64IM-NEXT: lui t6, 349525
+; RV64IM-NEXT: li a7, 1
+; RV64IM-NEXT: lui s4, 2
+; RV64IM-NEXT: lui t1, 4
+; RV64IM-NEXT: lui a4, 128
+; RV64IM-NEXT: lui s7, 256
+; RV64IM-NEXT: lui s8, 4096
+; RV64IM-NEXT: lui s10, 8192
+; RV64IM-NEXT: lui a1, 4080
+; RV64IM-NEXT: and a2, a2, a1
+; RV64IM-NEXT: slli a3, a3, 24
+; RV64IM-NEXT: sd a3, 336(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: addi s0, s2, -256
+; RV64IM-NEXT: and t5, a0, a1
+; RV64IM-NEXT: slli a1, t2, 32
+; RV64IM-NEXT: addi s9, t3, -241
+; RV64IM-NEXT: addi t4, t4, 819
+; RV64IM-NEXT: addi t2, t6, 1365
+; RV64IM-NEXT: slli t3, a7, 11
+; RV64IM-NEXT: slli s11, a7, 32
+; RV64IM-NEXT: slli ra, a7, 33
+; RV64IM-NEXT: slli t6, a7, 34
+; RV64IM-NEXT: slli s1, a7, 35
+; RV64IM-NEXT: slli s3, a7, 36
+; RV64IM-NEXT: and a3, a6, a3
+; RV64IM-NEXT: or a2, a3, a2
+; RV64IM-NEXT: slli a3, a7, 37
+; RV64IM-NEXT: sd a3, 256(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s0, 304(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a3, a5, s0
+; RV64IM-NEXT: or a3, a3, s5
+; RV64IM-NEXT: slli a5, a7, 38
+; RV64IM-NEXT: sd a5, 240(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli t5, t5, 24
+; RV64IM-NEXT: and a0, a0, s0
+; RV64IM-NEXT: or a1, t5, a1
+; RV64IM-NEXT: slli a5, s9, 32
+; RV64IM-NEXT: add a5, s9, a5
+; RV64IM-NEXT: slli s0, t4, 32
+; RV64IM-NEXT: add t4, t4, s0
+; RV64IM-NEXT: slli s5, t2, 32
+; RV64IM-NEXT: slli a0, a0, 40
+; RV64IM-NEXT: add t2, t2, s5
+; RV64IM-NEXT: or a2, a2, a3
+; RV64IM-NEXT: or a0, t0, a0
+; RV64IM-NEXT: or a0, a0, a1
+; RV64IM-NEXT: or a0, a0, a2
+; RV64IM-NEXT: srli a1, a0, 4
+; RV64IM-NEXT: sd a5, 312(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, a0, a5
+; RV64IM-NEXT: and a1, a1, a5
+; RV64IM-NEXT: slli a0, a0, 4
+; RV64IM-NEXT: or a0, a1, a0
+; RV64IM-NEXT: srli a1, a0, 2
+; RV64IM-NEXT: sd t4, 320(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, a0, t4
+; RV64IM-NEXT: and a1, a1, t4
+; RV64IM-NEXT: slli a0, a0, 2
+; RV64IM-NEXT: or a0, a1, a0
+; RV64IM-NEXT: srli a1, a0, 1
+; RV64IM-NEXT: sd t2, 328(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, a0, t2
+; RV64IM-NEXT: and a1, a1, t2
+; RV64IM-NEXT: slli a0, a0, 1
+; RV64IM-NEXT: or t0, a1, a0
+; RV64IM-NEXT: andi a0, t0, 2
+; RV64IM-NEXT: andi a1, t0, 1
+; RV64IM-NEXT: andi a2, t0, 4
+; RV64IM-NEXT: andi a3, t0, 8
+; RV64IM-NEXT: andi a5, t0, 16
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: xor a0, a1, a0
+; RV64IM-NEXT: sd a0, 296(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi a0, t0, 32
+; RV64IM-NEXT: mul a1, t0, a2
+; RV64IM-NEXT: mul a2, t0, a3
+; RV64IM-NEXT: xor a1, a1, a2
+; RV64IM-NEXT: sd a1, 288(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi a1, t0, 256
+; RV64IM-NEXT: mul a2, t0, a5
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: xor a0, a2, a0
+; RV64IM-NEXT: sd a0, 280(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi a0, t0, 512
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: xor a0, a1, a0
+; RV64IM-NEXT: sd a0, 272(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli t4, a7, 39
+; RV64IM-NEXT: and a0, t0, s4
+; RV64IM-NEXT: and a1, t0, t1
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: xor a0, a0, a1
+; RV64IM-NEXT: sd a0, 264(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 40
+; RV64IM-NEXT: and a1, t0, a4
+; RV64IM-NEXT: and a2, t0, s7
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: xor a1, a1, a2
+; RV64IM-NEXT: sd a1, 248(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a1, a7, 41
+; RV64IM-NEXT: and a2, t0, s8
+; RV64IM-NEXT: and a3, t0, s10
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: mul a3, t0, a3
+; RV64IM-NEXT: xor a2, a2, a3
+; RV64IM-NEXT: sd a2, 232(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a2, a7, 48
+; RV64IM-NEXT: and a3, t0, s11
+; RV64IM-NEXT: and a4, t0, ra
+; RV64IM-NEXT: mul a3, t0, a3
+; RV64IM-NEXT: mul a4, t0, a4
+; RV64IM-NEXT: xor a3, a3, a4
+; RV64IM-NEXT: sd a3, 224(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a7, 49
+; RV64IM-NEXT: and a0, t0, a0
+; RV64IM-NEXT: and a1, t0, a1
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: xor a0, a0, a1
+; RV64IM-NEXT: sd a0, 216(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 56
+; RV64IM-NEXT: and a1, t0, a2
+; RV64IM-NEXT: and a2, t0, a3
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: xor a1, a1, a2
+; RV64IM-NEXT: sd a1, 208(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a1, a7, 57
+; RV64IM-NEXT: and a0, t0, a0
+; RV64IM-NEXT: and a1, t0, a1
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: xor a0, a0, a1
+; RV64IM-NEXT: sd a0, 200(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a2, a7, 42
+; RV64IM-NEXT: slli ra, a7, 43
+; RV64IM-NEXT: slli a3, a7, 44
+; RV64IM-NEXT: slli a4, a7, 45
+; RV64IM-NEXT: slli t5, a7, 46
+; RV64IM-NEXT: slli s0, a7, 47
+; RV64IM-NEXT: slli a0, a7, 50
+; RV64IM-NEXT: sd a0, 192(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 51
+; RV64IM-NEXT: sd a0, 184(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 52
+; RV64IM-NEXT: sd a0, 176(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 53
+; RV64IM-NEXT: sd a0, 168(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 54
+; RV64IM-NEXT: sd a0, 160(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 55
+; RV64IM-NEXT: sd a0, 152(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 58
+; RV64IM-NEXT: sd a0, 144(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 59
+; RV64IM-NEXT: sd a0, 136(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 60
+; RV64IM-NEXT: sd a0, 120(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 61
+; RV64IM-NEXT: sd a0, 80(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a7, a7, 62
+; RV64IM-NEXT: sd a7, 48(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, t0, t3
+; RV64IM-NEXT: sd a0, 128(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s7, 1
+; RV64IM-NEXT: and a0, t0, s7
+; RV64IM-NEXT: sd a0, 112(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s8, 8
+; RV64IM-NEXT: and a0, t0, s8
+; RV64IM-NEXT: sd a0, 104(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, t0, s2
+; RV64IM-NEXT: sd a0, 96(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s5, 32
+; RV64IM-NEXT: and a0, t0, s5
+; RV64IM-NEXT: sd a0, 88(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s6, 64
+; RV64IM-NEXT: and a0, t0, s6
+; RV64IM-NEXT: sd a0, 72(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s10, 512
+; RV64IM-NEXT: and a0, t0, s10
+; RV64IM-NEXT: sd a0, 64(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s4, 1024
+; RV64IM-NEXT: and a0, t0, s4
+; RV64IM-NEXT: sd a0, 56(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s9, 2048
+; RV64IM-NEXT: and a0, t0, s9
+; RV64IM-NEXT: sd a0, 40(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s11, 16384
+; RV64IM-NEXT: and a0, t0, s11
+; RV64IM-NEXT: sd a0, 32(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui a5, 32768
+; RV64IM-NEXT: and a5, t0, a5
+; RV64IM-NEXT: lui a6, 65536
+; RV64IM-NEXT: and a6, t0, a6
+; RV64IM-NEXT: lui t1, 131072
+; RV64IM-NEXT: and t1, t0, t1
+; RV64IM-NEXT: lui t2, 262144
+; RV64IM-NEXT: and t2, t0, t2
+; RV64IM-NEXT: and a0, t0, t6
+; RV64IM-NEXT: sd a0, 24(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, t0, s1
+; RV64IM-NEXT: sd a0, 16(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, t0, s3
+; RV64IM-NEXT: sd a0, 8(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a0, 256(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, t0, a0
+; RV64IM-NEXT: sd a0, 0(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a0, 240(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, t0, a0
+; RV64IM-NEXT: and a1, t0, t4
+; RV64IM-NEXT: and a7, t0, a2
+; RV64IM-NEXT: and ra, t0, ra
+; RV64IM-NEXT: and t3, t0, a3
+; RV64IM-NEXT: and t4, t0, a4
+; RV64IM-NEXT: and t5, t0, t5
+; RV64IM-NEXT: and t6, t0, s0
+; RV64IM-NEXT: ld a2, 192(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s0, t0, a2
+; RV64IM-NEXT: ld a2, 184(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s1, t0, a2
+; RV64IM-NEXT: ld a2, 176(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s2, t0, a2
+; RV64IM-NEXT: ld a2, 168(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s3, t0, a2
+; RV64IM-NEXT: ld a2, 160(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s4, t0, a2
+; RV64IM-NEXT: ld a2, 152(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s5, t0, a2
+; RV64IM-NEXT: ld a2, 144(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s6, t0, a2
+; RV64IM-NEXT: ld a2, 136(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s7, t0, a2
+; RV64IM-NEXT: ld a2, 120(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s8, t0, a2
+; RV64IM-NEXT: ld a2, 80(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s9, t0, a2
+; RV64IM-NEXT: ld a2, 48(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s10, t0, a2
+; RV64IM-NEXT: andi s11, t0, 64
+; RV64IM-NEXT: mul a2, t0, s11
+; RV64IM-NEXT: sd a2, 80(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi s11, t0, 128
+; RV64IM-NEXT: mul a2, t0, s11
+; RV64IM-NEXT: sd a2, 192(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi s11, t0, 1024
+; RV64IM-NEXT: mul a2, t0, s11
+; RV64IM-NEXT: sd a2, 48(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 128(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 120(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 112(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 176(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 104(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul s11, t0, a2
+; RV64IM-NEXT: ld a2, 96(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 104(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 88(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 168(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 72(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 256(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 64(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a4, t0, a2
+; RV64IM-NEXT: ld a2, 56(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 96(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 40(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 136(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 32(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a3, t0, a2
+; RV64IM-NEXT: mul a2, t0, a5
+; RV64IM-NEXT: sd a2, 88(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a2, t0, a6
+; RV64IM-NEXT: sd a2, 128(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a2, t0, t1
+; RV64IM-NEXT: sd a2, 160(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a2, t0, t2
+; RV64IM-NEXT: sd a2, 240(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: srliw t2, t0, 31
+; RV64IM-NEXT: slli t2, t2, 31
+; RV64IM-NEXT: ld a2, 24(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: ld a5, 16(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a5, t0, a5
+; RV64IM-NEXT: ld a6, 8(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul t1, t0, a6
+; RV64IM-NEXT: ld a6, 0(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a6, t0, a6
+; RV64IM-NEXT: sd a6, 112(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: sd a0, 152(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a0, t0, a1
+; RV64IM-NEXT: sd a0, 184(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a7, t0, a7
+; RV64IM-NEXT: mul ra, t0, ra
+; RV64IM-NEXT: mul a6, t0, t3
+; RV64IM-NEXT: mul t4, t0, t4
+; RV64IM-NEXT: mul t5, t0, t5
+; RV64IM-NEXT: mul a0, t0, t6
+; RV64IM-NEXT: sd a0, 144(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul t6, t0, s0
+; RV64IM-NEXT: mul s0, t0, s1
+; RV64IM-NEXT: mul s1, t0, s2
+; RV64IM-NEXT: mul s2, t0, s3
+; RV64IM-NEXT: mul s3, t0, s4
+; RV64IM-NEXT: mul s4, t0, s5
+; RV64IM-NEXT: mul s5, t0, s6
+; RV64IM-NEXT: mul s6, t0, s7
+; RV64IM-NEXT: mul s7, t0, s8
+; RV64IM-NEXT: mul s8, t0, s9
+; RV64IM-NEXT: mul s9, t0, s10
+; RV64IM-NEXT: srli s10, t0, 63
+; RV64IM-NEXT: slli s10, s10, 63
+; RV64IM-NEXT: mul t2, t0, t2
+; RV64IM-NEXT: mul t0, t0, s10
+; RV64IM-NEXT: ld a0, 296(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld a1, 288(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s10, a0, a1
+; RV64IM-NEXT: ld a0, 280(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld a1, 80(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a0, a0, a1
+; RV64IM-NEXT: ld a1, 272(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld t3, 48(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a1, a1, t3
+; RV64IM-NEXT: ld t3, 264(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s11, t3, s11
+; RV64IM-NEXT: ld t3, 248(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, t3, a4
+; RV64IM-NEXT: ld t3, 232(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, t3, a3
+; RV64IM-NEXT: ld t3, 224(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, t3, a2
+; RV64IM-NEXT: ld t3, 216(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a7, t3, a7
+; RV64IM-NEXT: ld t3, 208(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor t6, t3, t6
+; RV64IM-NEXT: ld t3, 200(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s5, t3, s5
+; RV64IM-NEXT: xor a0, s10, a0
+; RV64IM-NEXT: ld t3, 120(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a1, a1, t3
+; RV64IM-NEXT: ld t3, 104(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s10, s11, t3
+; RV64IM-NEXT: ld t3, 96(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, a4, t3
+; RV64IM-NEXT: ld t3, 88(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a3, t3
+; RV64IM-NEXT: xor a2, a2, a5
+; RV64IM-NEXT: xor a5, a7, ra
+; RV64IM-NEXT: xor a7, t6, s0
+; RV64IM-NEXT: xor t6, s5, s6
+; RV64IM-NEXT: ld t3, 192(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a0, a0, t3
+; RV64IM-NEXT: ld t3, 176(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a1, a1, t3
+; RV64IM-NEXT: ld t3, 168(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s0, s10, t3
+; RV64IM-NEXT: ld t3, 136(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, a4, t3
+; RV64IM-NEXT: ld t3, 128(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a3, t3
+; RV64IM-NEXT: xor a2, a2, t1
+; RV64IM-NEXT: xor a5, a5, a6
+; RV64IM-NEXT: xor a6, a7, s1
+; RV64IM-NEXT: xor a7, t6, s7
+; RV64IM-NEXT: ld t1, 256(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor t1, s0, t1
+; RV64IM-NEXT: ld t3, 160(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a3, t3
+; RV64IM-NEXT: ld t3, 112(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a2, t3
+; RV64IM-NEXT: xor a5, a5, t4
+; RV64IM-NEXT: xor a6, a6, s2
+; RV64IM-NEXT: xor a7, a7, s8
+; RV64IM-NEXT: xor a1, a0, a1
+; RV64IM-NEXT: xor a1, a1, t1
+; RV64IM-NEXT: ld t1, 240(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a3, t1
+; RV64IM-NEXT: ld t1, 152(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a2, t1
+; RV64IM-NEXT: xor a5, a5, t5
+; RV64IM-NEXT: xor a6, a6, s3
+; RV64IM-NEXT: xor a7, a7, s9
+; RV64IM-NEXT: xor a1, a1, a4
+; RV64IM-NEXT: xor a3, a3, t2
+; RV64IM-NEXT: ld a4, 184(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a2, a4
+; RV64IM-NEXT: ld a4, 144(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, a5, a4
+; RV64IM-NEXT: xor a5, a6, s4
+; RV64IM-NEXT: xor a6, a7, t0
+; RV64IM-NEXT: lui a7, %hi(.LCPI14_0)
+; RV64IM-NEXT: ld a7, %lo(.LCPI14_0)(a7)
+; RV64IM-NEXT: slli a0, a0, 56
+; RV64IM-NEXT: xor a3, a1, a3
+; RV64IM-NEXT: ld t1, 304(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a1, a1, t1
+; RV64IM-NEXT: slli a1, a1, 40
+; RV64IM-NEXT: xor a2, a3, a2
+; RV64IM-NEXT: or a0, a0, a1
+; RV64IM-NEXT: lui t0, 4080
+; RV64IM-NEXT: and a1, a2, t0
+; RV64IM-NEXT: xor a4, a2, a4
+; RV64IM-NEXT: srli a2, a2, 8
+; RV64IM-NEXT: slli a1, a1, 24
+; RV64IM-NEXT: xor a5, a4, a5
+; RV64IM-NEXT: ld a3, 336(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a2, a2, a3
+; RV64IM-NEXT: srli a4, a4, 24
+; RV64IM-NEXT: srliw a3, a5, 24
+; RV64IM-NEXT: and a4, a4, t0
+; RV64IM-NEXT: srli t0, a5, 40
+; RV64IM-NEXT: xor a5, a5, a6
+; RV64IM-NEXT: slli a3, a3, 32
+; RV64IM-NEXT: or a2, a2, a4
+; RV64IM-NEXT: and a4, t0, t1
+; RV64IM-NEXT: srli a5, a5, 56
+; RV64IM-NEXT: or a1, a1, a3
+; RV64IM-NEXT: or a4, a4, a5
+; RV64IM-NEXT: or a0, a0, a1
+; RV64IM-NEXT: or a2, a2, a4
+; RV64IM-NEXT: or a0, a0, a2
+; RV64IM-NEXT: srli a1, a0, 4
+; RV64IM-NEXT: ld a2, 312(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, a0, a2
+; RV64IM-NEXT: and a1, a1, a2
+; RV64IM-NEXT: slli a0, a0, 4
+; RV64IM-NEXT: or a0, a1, a0
+; RV64IM-NEXT: srli a1, a0, 2
+; RV64IM-NEXT: ld a2, 320(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, a0, a2
+; RV64IM-NEXT: and a1, a1, a2
+; RV64IM-NEXT: slli a0, a0, 2
+; RV64IM-NEXT: or a0, a1, a0
+; RV64IM-NEXT: srli a1, a0, 1
+; RV64IM-NEXT: ld a2, 328(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, a0, a2
+; RV64IM-NEXT: and a1, a1, a7
+; RV64IM-NEXT: slli a0, a0, 1
+; RV64IM-NEXT: or a0, a1, a0
+; RV64IM-NEXT: srli a0, a0, 1
+; RV64IM-NEXT: ld ra, 440(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s0, 432(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s1, 424(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s2, 416(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s3, 408(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s4, 400(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s5, 392(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s6, 384(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s7, 376(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s8, 368(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s9, 360(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s10, 352(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s11, 344(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: addi sp, sp, 448
+; RV64IM-NEXT: ret
+ %res = call i4 @llvm.clmulh.i4(i4 %a, i4 %b)
+ ret i4 %res
+}
+
+define i8 @clmulh_i8(i8 %a, i8 %b) nounwind {
+; RV32IM-LABEL: clmulh_i8:
+; RV32IM: # %bb.0:
+; RV32IM-NEXT: addi sp, sp, -144
+; RV32IM-NEXT: sw ra, 140(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s0, 136(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s1, 132(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s2, 128(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s3, 124(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s4, 120(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s5, 116(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s6, 112(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s7, 108(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s8, 104(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s9, 100(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s10, 96(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s11, 92(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: srli a3, a0, 8
+; RV32IM-NEXT: lui a1, 16
+; RV32IM-NEXT: srli a6, a0, 24
+; RV32IM-NEXT: slli a4, a0, 24
+; RV32IM-NEXT: lui a2, 61681
+; RV32IM-NEXT: lui t0, 209715
+; RV32IM-NEXT: lui a5, 349525
+; RV32IM-NEXT: li t5, 1
+; RV32IM-NEXT: lui t1, 1
+; RV32IM-NEXT: lui t2, 2
+; RV32IM-NEXT: lui t3, 4
+; RV32IM-NEXT: lui t4, 8
+; RV32IM-NEXT: lui s0, 64
+; RV32IM-NEXT: lui s1, 128
+; RV32IM-NEXT: lui t6, 256
+; RV32IM-NEXT: lui s2, 512
+; RV32IM-NEXT: lui s3, 1024
+; RV32IM-NEXT: lui s4, 2048
+; RV32IM-NEXT: lui s5, 4096
+; RV32IM-NEXT: lui s6, 8192
+; RV32IM-NEXT: lui s7, 16384
+; RV32IM-NEXT: lui s8, 32768
+; RV32IM-NEXT: lui s9, 65536
+; RV32IM-NEXT: lui s10, 131072
+; RV32IM-NEXT: lui s11, 262144
+; RV32IM-NEXT: addi a7, a1, -256
+; RV32IM-NEXT: sw a7, 76(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a3, a3, a7
+; RV32IM-NEXT: or a3, a3, a6
+; RV32IM-NEXT: lui ra, 524288
+; RV32IM-NEXT: addi a6, a2, -241
+; RV32IM-NEXT: sw a6, 80(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: addi a2, t0, 819
+; RV32IM-NEXT: sw a2, 84(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a0, a0, a7
+; RV32IM-NEXT: slli a0, a0, 8
+; RV32IM-NEXT: or a4, a4, a0
+; RV32IM-NEXT: addi a0, a5, 1365
+; RV32IM-NEXT: sw a0, 88(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: slli t5, t5, 11
+; RV32IM-NEXT: or a3, a4, a3
+; RV32IM-NEXT: srli a4, a3, 4
+; RV32IM-NEXT: and a3, a3, a6
+; RV32IM-NEXT: and a4, a4, a6
+; RV32IM-NEXT: slli a3, a3, 4
+; RV32IM-NEXT: or a3, a4, a3
+; RV32IM-NEXT: srli a4, a3, 2
+; RV32IM-NEXT: and a3, a3, a2
+; RV32IM-NEXT: and a4, a4, a2
+; RV32IM-NEXT: slli a3, a3, 2
+; RV32IM-NEXT: or a3, a4, a3
+; RV32IM-NEXT: srli a4, a3, 1
+; RV32IM-NEXT: and a3, a3, a0
+; RV32IM-NEXT: and a4, a4, a0
+; RV32IM-NEXT: slli a3, a3, 1
+; RV32IM-NEXT: or a3, a4, a3
+; RV32IM-NEXT: andi a2, a3, 2
+; RV32IM-NEXT: and a0, a3, t5
+; RV32IM-NEXT: sw a0, 72(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and t1, a3, t1
+; RV32IM-NEXT: and t2, a3, t2
+; RV32IM-NEXT: and t3, a3, t3
+; RV32IM-NEXT: and t4, a3, t4
+; RV32IM-NEXT: and a1, a3, a1
+; RV32IM-NEXT: sw a1, 60(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lui a0, 32
+; RV32IM-NEXT: and a0, a3, a0
+; RV32IM-NEXT: sw a0, 56(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and s0, a3, s0
+; RV32IM-NEXT: sw s0, 52(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and s1, a3, s1
+; RV32IM-NEXT: sw s1, 48(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and t6, a3, t6
+; RV32IM-NEXT: and s2, a3, s2
+; RV32IM-NEXT: and a0, a3, s3
+; RV32IM-NEXT: sw a0, 44(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a0, a3, s4
+; RV32IM-NEXT: sw a0, 40(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a0, a3, s5
+; RV32IM-NEXT: sw a0, 36(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a0, a3, s6
+; RV32IM-NEXT: sw a0, 32(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a0, a3, s7
+; RV32IM-NEXT: sw a0, 28(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a0, a3, s8
+; RV32IM-NEXT: sw a0, 24(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a0, a3, s9
+; RV32IM-NEXT: sw a0, 20(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a0, a3, s10
+; RV32IM-NEXT: sw a0, 16(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a0, a3, s11
+; RV32IM-NEXT: sw a0, 12(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a0, a3, ra
+; RV32IM-NEXT: sw a0, 8(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a0, a3, a2
+; RV32IM-NEXT: sw a0, 64(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi ra, a3, 1
+; RV32IM-NEXT: mul a0, a3, ra
+; RV32IM-NEXT: sw a0, 4(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi a4, a3, 4
+; RV32IM-NEXT: mul ra, a3, a4
+; RV32IM-NEXT: andi a1, a3, 8
+; RV32IM-NEXT: mul s9, a3, a1
+; RV32IM-NEXT: andi a2, a3, 16
+; RV32IM-NEXT: mul s8, a3, a2
+; RV32IM-NEXT: andi a7, a3, 32
+; RV32IM-NEXT: mul s5, a3, a7
+; RV32IM-NEXT: andi a0, a3, 64
+; RV32IM-NEXT: mul s11, a3, a0
+; RV32IM-NEXT: andi a5, a3, 128
+; RV32IM-NEXT: mul a0, a3, a5
+; RV32IM-NEXT: sw a0, 68(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi a5, a3, 256
+; RV32IM-NEXT: mul s1, a3, a5
+; RV32IM-NEXT: andi a6, a3, 512
+; RV32IM-NEXT: mul t5, a3, a6
+; RV32IM-NEXT: andi t0, a3, 1024
+; RV32IM-NEXT: mul s3, a3, t0
+; RV32IM-NEXT: lw a0, 72(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s6, a3, a0
+; RV32IM-NEXT: mul a0, a3, t1
+; RV32IM-NEXT: sw a0, 0(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul t2, a3, t2
+; RV32IM-NEXT: mul a7, a3, t3
+; RV32IM-NEXT: mul s0, a3, t4
+; RV32IM-NEXT: lw a0, 60(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s4, a3, a0
+; RV32IM-NEXT: lw a0, 56(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s7, a3, a0
+; RV32IM-NEXT: lw a0, 52(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s10, a3, a0
+; RV32IM-NEXT: lw a0, 48(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a6, a3, a0
+; RV32IM-NEXT: mul a4, a3, t6
+; RV32IM-NEXT: mul t1, a3, s2
+; RV32IM-NEXT: lw a0, 44(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul t4, a3, a0
+; RV32IM-NEXT: lw a0, 40(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s2, a3, a0
+; RV32IM-NEXT: lw a0, 36(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a2, a3, a0
+; RV32IM-NEXT: lw a0, 32(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a1, a3, a0
+; RV32IM-NEXT: lw a0, 28(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a5, a3, a0
+; RV32IM-NEXT: lw a0, 24(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul t0, a3, a0
+; RV32IM-NEXT: lw a0, 20(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul t3, a3, a0
+; RV32IM-NEXT: lw a0, 16(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul t6, a3, a0
+; RV32IM-NEXT: lw a0, 12(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a0, a3, a0
+; RV32IM-NEXT: sw a0, 72(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a0, 8(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a0, a3, a0
+; RV32IM-NEXT: sw a0, 60(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a0, 64(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw a3, 4(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a0, a3, a0
+; RV32IM-NEXT: xor s9, ra, s9
+; RV32IM-NEXT: xor s5, s8, s5
+; RV32IM-NEXT: xor t5, s1, t5
+; RV32IM-NEXT: xor a7, t2, a7
+; RV32IM-NEXT: xor a4, a6, a4
+; RV32IM-NEXT: xor a1, a2, a1
+; RV32IM-NEXT: xor a0, a0, s9
+; RV32IM-NEXT: xor a2, s5, s11
+; RV32IM-NEXT: xor a6, t5, s3
+; RV32IM-NEXT: xor a7, a7, s0
+; RV32IM-NEXT: xor a4, a4, t1
+; RV32IM-NEXT: xor a1, a1, a5
+; RV32IM-NEXT: xor a0, a0, a2
+; RV32IM-NEXT: xor a2, a6, s6
+; RV32IM-NEXT: xor a5, a7, s4
+; RV32IM-NEXT: xor a4, a4, t4
+; RV32IM-NEXT: xor a1, a1, t0
+; RV32IM-NEXT: lw a6, 68(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a0, a0, a6
+; RV32IM-NEXT: lw a3, 0(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a2, a2, a3
+; RV32IM-NEXT: xor a5, a5, s7
+; RV32IM-NEXT: xor a4, a4, s2
+; RV32IM-NEXT: xor a1, a1, t3
+; RV32IM-NEXT: xor a5, a5, s10
+; RV32IM-NEXT: xor a1, a1, t6
+; RV32IM-NEXT: xor a2, a0, a2
+; RV32IM-NEXT: xor a2, a2, a5
+; RV32IM-NEXT: lui a5, 349525
+; RV32IM-NEXT: addi a5, a5, 1364
+; RV32IM-NEXT: slli a0, a0, 24
+; RV32IM-NEXT: lw a6, 72(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a1, a1, a6
+; RV32IM-NEXT: xor a2, a2, a4
+; RV32IM-NEXT: lw a3, 60(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a1, a1, a3
+; RV32IM-NEXT: lw a6, 76(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: and a3, a2, a6
+; RV32IM-NEXT: srli a4, a2, 8
+; RV32IM-NEXT: xor a1, a2, a1
+; RV32IM-NEXT: slli a3, a3, 8
+; RV32IM-NEXT: and a2, a4, a6
+; RV32IM-NEXT: srli a1, a1, 24
+; RV32IM-NEXT: or a0, a0, a3
+; RV32IM-NEXT: or a1, a2, a1
+; RV32IM-NEXT: or a0, a0, a1
+; RV32IM-NEXT: srli a1, a0, 4
+; RV32IM-NEXT: lw a2, 80(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: and a0, a0, a2
+; RV32IM-NEXT: and a1, a1, a2
+; RV32IM-NEXT: slli a0, a0, 4
+; RV32IM-NEXT: or a0, a1, a0
+; RV32IM-NEXT: srli a1, a0, 2
+; RV32IM-NEXT: lw a2, 84(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: and a0, a0, a2
+; RV32IM-NEXT: and a1, a1, a2
+; RV32IM-NEXT: slli a0, a0, 2
+; RV32IM-NEXT: or a0, a1, a0
+; RV32IM-NEXT: srli a1, a0, 1
+; RV32IM-NEXT: lw a2, 88(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: and a0, a0, a2
+; RV32IM-NEXT: and a1, a1, a5
+; RV32IM-NEXT: slli a0, a0, 1
+; RV32IM-NEXT: or a0, a1, a0
+; RV32IM-NEXT: srli a0, a0, 1
+; RV32IM-NEXT: lw ra, 140(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s0, 136(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s1, 132(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s2, 128(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s3, 124(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s4, 120(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s5, 116(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s6, 112(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s7, 108(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s8, 104(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s9, 100(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s10, 96(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s11, 92(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: addi sp, sp, 144
+; RV32IM-NEXT: ret
+;
+; RV64IM-LABEL: clmulh_i8:
+; RV64IM: # %bb.0:
+; RV64IM-NEXT: addi sp, sp, -448
+; RV64IM-NEXT: sd ra, 440(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s0, 432(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s1, 424(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s2, 416(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s3, 408(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s4, 400(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s5, 392(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s6, 384(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s7, 376(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s8, 368(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s9, 360(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s10, 352(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s11, 344(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: srli a2, a0, 24
+; RV64IM-NEXT: srli a6, a0, 8
+; RV64IM-NEXT: li a3, 255
+; RV64IM-NEXT: srli a5, a0, 40
+; RV64IM-NEXT: lui s2, 16
+; RV64IM-NEXT: srli s5, a0, 56
+; RV64IM-NEXT: srliw t2, a0, 24
+; RV64IM-NEXT: slli t0, a0, 56
+; RV64IM-NEXT: lui t3, 61681
+; RV64IM-NEXT: lui t4, 209715
+; RV64IM-NEXT: lui t6, 349525
+; RV64IM-NEXT: li a7, 1
+; RV64IM-NEXT: lui s4, 2
+; RV64IM-NEXT: lui t1, 4
+; RV64IM-NEXT: lui a4, 128
+; RV64IM-NEXT: lui s7, 256
+; RV64IM-NEXT: lui s8, 4096
+; RV64IM-NEXT: lui s10, 8192
+; RV64IM-NEXT: lui a1, 4080
+; RV64IM-NEXT: and a2, a2, a1
+; RV64IM-NEXT: slli a3, a3, 24
+; RV64IM-NEXT: sd a3, 336(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: addi s0, s2, -256
+; RV64IM-NEXT: and t5, a0, a1
+; RV64IM-NEXT: slli a1, t2, 32
+; RV64IM-NEXT: addi s9, t3, -241
+; RV64IM-NEXT: addi t4, t4, 819
+; RV64IM-NEXT: addi t2, t6, 1365
+; RV64IM-NEXT: slli t3, a7, 11
+; RV64IM-NEXT: slli s11, a7, 32
+; RV64IM-NEXT: slli ra, a7, 33
+; RV64IM-NEXT: slli t6, a7, 34
+; RV64IM-NEXT: slli s1, a7, 35
+; RV64IM-NEXT: slli s3, a7, 36
+; RV64IM-NEXT: and a3, a6, a3
+; RV64IM-NEXT: or a2, a3, a2
+; RV64IM-NEXT: slli a3, a7, 37
+; RV64IM-NEXT: sd a3, 256(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s0, 304(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a3, a5, s0
+; RV64IM-NEXT: or a3, a3, s5
+; RV64IM-NEXT: slli a5, a7, 38
+; RV64IM-NEXT: sd a5, 240(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli t5, t5, 24
+; RV64IM-NEXT: and a0, a0, s0
+; RV64IM-NEXT: or a1, t5, a1
+; RV64IM-NEXT: slli a5, s9, 32
+; RV64IM-NEXT: add a5, s9, a5
+; RV64IM-NEXT: slli s0, t4, 32
+; RV64IM-NEXT: add t4, t4, s0
+; RV64IM-NEXT: slli s5, t2, 32
+; RV64IM-NEXT: slli a0, a0, 40
+; RV64IM-NEXT: add t2, t2, s5
+; RV64IM-NEXT: or a2, a2, a3
+; RV64IM-NEXT: or a0, t0, a0
+; RV64IM-NEXT: or a0, a0, a1
+; RV64IM-NEXT: or a0, a0, a2
+; RV64IM-NEXT: srli a1, a0, 4
+; RV64IM-NEXT: sd a5, 312(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, a0, a5
+; RV64IM-NEXT: and a1, a1, a5
+; RV64IM-NEXT: slli a0, a0, 4
+; RV64IM-NEXT: or a0, a1, a0
+; RV64IM-NEXT: srli a1, a0, 2
+; RV64IM-NEXT: sd t4, 320(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, a0, t4
+; RV64IM-NEXT: and a1, a1, t4
+; RV64IM-NEXT: slli a0, a0, 2
+; RV64IM-NEXT: or a0, a1, a0
+; RV64IM-NEXT: srli a1, a0, 1
+; RV64IM-NEXT: sd t2, 328(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, a0, t2
+; RV64IM-NEXT: and a1, a1, t2
+; RV64IM-NEXT: slli a0, a0, 1
+; RV64IM-NEXT: or t0, a1, a0
+; RV64IM-NEXT: andi a0, t0, 2
+; RV64IM-NEXT: andi a1, t0, 1
+; RV64IM-NEXT: andi a2, t0, 4
+; RV64IM-NEXT: andi a3, t0, 8
+; RV64IM-NEXT: andi a5, t0, 16
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: xor a0, a1, a0
+; RV64IM-NEXT: sd a0, 296(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi a0, t0, 32
+; RV64IM-NEXT: mul a1, t0, a2
+; RV64IM-NEXT: mul a2, t0, a3
+; RV64IM-NEXT: xor a1, a1, a2
+; RV64IM-NEXT: sd a1, 288(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi a1, t0, 256
+; RV64IM-NEXT: mul a2, t0, a5
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: xor a0, a2, a0
+; RV64IM-NEXT: sd a0, 280(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi a0, t0, 512
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: xor a0, a1, a0
+; RV64IM-NEXT: sd a0, 272(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli t4, a7, 39
+; RV64IM-NEXT: and a0, t0, s4
+; RV64IM-NEXT: and a1, t0, t1
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: xor a0, a0, a1
+; RV64IM-NEXT: sd a0, 264(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 40
+; RV64IM-NEXT: and a1, t0, a4
+; RV64IM-NEXT: and a2, t0, s7
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: xor a1, a1, a2
+; RV64IM-NEXT: sd a1, 248(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a1, a7, 41
+; RV64IM-NEXT: and a2, t0, s8
+; RV64IM-NEXT: and a3, t0, s10
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: mul a3, t0, a3
+; RV64IM-NEXT: xor a2, a2, a3
+; RV64IM-NEXT: sd a2, 232(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a2, a7, 48
+; RV64IM-NEXT: and a3, t0, s11
+; RV64IM-NEXT: and a4, t0, ra
+; RV64IM-NEXT: mul a3, t0, a3
+; RV64IM-NEXT: mul a4, t0, a4
+; RV64IM-NEXT: xor a3, a3, a4
+; RV64IM-NEXT: sd a3, 224(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a7, 49
+; RV64IM-NEXT: and a0, t0, a0
+; RV64IM-NEXT: and a1, t0, a1
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: xor a0, a0, a1
+; RV64IM-NEXT: sd a0, 216(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 56
+; RV64IM-NEXT: and a1, t0, a2
+; RV64IM-NEXT: and a2, t0, a3
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: xor a1, a1, a2
+; RV64IM-NEXT: sd a1, 208(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a1, a7, 57
+; RV64IM-NEXT: and a0, t0, a0
+; RV64IM-NEXT: and a1, t0, a1
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: xor a0, a0, a1
+; RV64IM-NEXT: sd a0, 200(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a2, a7, 42
+; RV64IM-NEXT: slli ra, a7, 43
+; RV64IM-NEXT: slli a3, a7, 44
+; RV64IM-NEXT: slli a4, a7, 45
+; RV64IM-NEXT: slli t5, a7, 46
+; RV64IM-NEXT: slli s0, a7, 47
+; RV64IM-NEXT: slli a0, a7, 50
+; RV64IM-NEXT: sd a0, 192(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 51
+; RV64IM-NEXT: sd a0, 184(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 52
+; RV64IM-NEXT: sd a0, 176(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 53
+; RV64IM-NEXT: sd a0, 168(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 54
+; RV64IM-NEXT: sd a0, 160(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 55
+; RV64IM-NEXT: sd a0, 152(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 58
+; RV64IM-NEXT: sd a0, 144(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 59
+; RV64IM-NEXT: sd a0, 136(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 60
+; RV64IM-NEXT: sd a0, 120(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 61
+; RV64IM-NEXT: sd a0, 80(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a7, a7, 62
+; RV64IM-NEXT: sd a7, 48(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, t0, t3
+; RV64IM-NEXT: sd a0, 128(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s7, 1
+; RV64IM-NEXT: and a0, t0, s7
+; RV64IM-NEXT: sd a0, 112(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s8, 8
+; RV64IM-NEXT: and a0, t0, s8
+; RV64IM-NEXT: sd a0, 104(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, t0, s2
+; RV64IM-NEXT: sd a0, 96(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s5, 32
+; RV64IM-NEXT: and a0, t0, s5
+; RV64IM-NEXT: sd a0, 88(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s6, 64
+; RV64IM-NEXT: and a0, t0, s6
+; RV64IM-NEXT: sd a0, 72(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s10, 512
+; RV64IM-NEXT: and a0, t0, s10
+; RV64IM-NEXT: sd a0, 64(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s4, 1024
+; RV64IM-NEXT: and a0, t0, s4
+; RV64IM-NEXT: sd a0, 56(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s9, 2048
+; RV64IM-NEXT: and a0, t0, s9
+; RV64IM-NEXT: sd a0, 40(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s11, 16384
+; RV64IM-NEXT: and a0, t0, s11
+; RV64IM-NEXT: sd a0, 32(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui a5, 32768
+; RV64IM-NEXT: and a5, t0, a5
+; RV64IM-NEXT: lui a6, 65536
+; RV64IM-NEXT: and a6, t0, a6
+; RV64IM-NEXT: lui t1, 131072
+; RV64IM-NEXT: and t1, t0, t1
+; RV64IM-NEXT: lui t2, 262144
+; RV64IM-NEXT: and t2, t0, t2
+; RV64IM-NEXT: and a0, t0, t6
+; RV64IM-NEXT: sd a0, 24(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, t0, s1
+; RV64IM-NEXT: sd a0, 16(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, t0, s3
+; RV64IM-NEXT: sd a0, 8(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a0, 256(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, t0, a0
+; RV64IM-NEXT: sd a0, 0(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a0, 240(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, t0, a0
+; RV64IM-NEXT: and a1, t0, t4
+; RV64IM-NEXT: and a7, t0, a2
+; RV64IM-NEXT: and ra, t0, ra
+; RV64IM-NEXT: and t3, t0, a3
+; RV64IM-NEXT: and t4, t0, a4
+; RV64IM-NEXT: and t5, t0, t5
+; RV64IM-NEXT: and t6, t0, s0
+; RV64IM-NEXT: ld a2, 192(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s0, t0, a2
+; RV64IM-NEXT: ld a2, 184(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s1, t0, a2
+; RV64IM-NEXT: ld a2, 176(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s2, t0, a2
+; RV64IM-NEXT: ld a2, 168(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s3, t0, a2
+; RV64IM-NEXT: ld a2, 160(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s4, t0, a2
+; RV64IM-NEXT: ld a2, 152(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s5, t0, a2
+; RV64IM-NEXT: ld a2, 144(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s6, t0, a2
+; RV64IM-NEXT: ld a2, 136(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s7, t0, a2
+; RV64IM-NEXT: ld a2, 120(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s8, t0, a2
+; RV64IM-NEXT: ld a2, 80(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s9, t0, a2
+; RV64IM-NEXT: ld a2, 48(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s10, t0, a2
+; RV64IM-NEXT: andi s11, t0, 64
+; RV64IM-NEXT: mul a2, t0, s11
+; RV64IM-NEXT: sd a2, 80(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi s11, t0, 128
+; RV64IM-NEXT: mul a2, t0, s11
+; RV64IM-NEXT: sd a2, 192(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi s11, t0, 1024
+; RV64IM-NEXT: mul a2, t0, s11
+; RV64IM-NEXT: sd a2, 48(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 128(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 120(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 112(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 176(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 104(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul s11, t0, a2
+; RV64IM-NEXT: ld a2, 96(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 104(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 88(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 168(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 72(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 256(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 64(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a4, t0, a2
+; RV64IM-NEXT: ld a2, 56(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 96(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 40(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 136(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 32(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a3, t0, a2
+; RV64IM-NEXT: mul a2, t0, a5
+; RV64IM-NEXT: sd a2, 88(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a2, t0, a6
+; RV64IM-NEXT: sd a2, 128(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a2, t0, t1
+; RV64IM-NEXT: sd a2, 160(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a2, t0, t2
+; RV64IM-NEXT: sd a2, 240(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: srliw t2, t0, 31
+; RV64IM-NEXT: slli t2, t2, 31
+; RV64IM-NEXT: ld a2, 24(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: ld a5, 16(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a5, t0, a5
+; RV64IM-NEXT: ld a6, 8(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul t1, t0, a6
+; RV64IM-NEXT: ld a6, 0(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a6, t0, a6
+; RV64IM-NEXT: sd a6, 112(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: sd a0, 152(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a0, t0, a1
+; RV64IM-NEXT: sd a0, 184(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a7, t0, a7
+; RV64IM-NEXT: mul ra, t0, ra
+; RV64IM-NEXT: mul a6, t0, t3
+; RV64IM-NEXT: mul t4, t0, t4
+; RV64IM-NEXT: mul t5, t0, t5
+; RV64IM-NEXT: mul a0, t0, t6
+; RV64IM-NEXT: sd a0, 144(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul t6, t0, s0
+; RV64IM-NEXT: mul s0, t0, s1
+; RV64IM-NEXT: mul s1, t0, s2
+; RV64IM-NEXT: mul s2, t0, s3
+; RV64IM-NEXT: mul s3, t0, s4
+; RV64IM-NEXT: mul s4, t0, s5
+; RV64IM-NEXT: mul s5, t0, s6
+; RV64IM-NEXT: mul s6, t0, s7
+; RV64IM-NEXT: mul s7, t0, s8
+; RV64IM-NEXT: mul s8, t0, s9
+; RV64IM-NEXT: mul s9, t0, s10
+; RV64IM-NEXT: srli s10, t0, 63
+; RV64IM-NEXT: slli s10, s10, 63
+; RV64IM-NEXT: mul t2, t0, t2
+; RV64IM-NEXT: mul t0, t0, s10
+; RV64IM-NEXT: ld a0, 296(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld a1, 288(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s10, a0, a1
+; RV64IM-NEXT: ld a0, 280(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld a1, 80(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a0, a0, a1
+; RV64IM-NEXT: ld a1, 272(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld t3, 48(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a1, a1, t3
+; RV64IM-NEXT: ld t3, 264(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s11, t3, s11
+; RV64IM-NEXT: ld t3, 248(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, t3, a4
+; RV64IM-NEXT: ld t3, 232(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, t3, a3
+; RV64IM-NEXT: ld t3, 224(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, t3, a2
+; RV64IM-NEXT: ld t3, 216(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a7, t3, a7
+; RV64IM-NEXT: ld t3, 208(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor t6, t3, t6
+; RV64IM-NEXT: ld t3, 200(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s5, t3, s5
+; RV64IM-NEXT: xor a0, s10, a0
+; RV64IM-NEXT: ld t3, 120(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a1, a1, t3
+; RV64IM-NEXT: ld t3, 104(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s10, s11, t3
+; RV64IM-NEXT: ld t3, 96(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, a4, t3
+; RV64IM-NEXT: ld t3, 88(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a3, t3
+; RV64IM-NEXT: xor a2, a2, a5
+; RV64IM-NEXT: xor a5, a7, ra
+; RV64IM-NEXT: xor a7, t6, s0
+; RV64IM-NEXT: xor t6, s5, s6
+; RV64IM-NEXT: ld t3, 192(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a0, a0, t3
+; RV64IM-NEXT: ld t3, 176(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a1, a1, t3
+; RV64IM-NEXT: ld t3, 168(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s0, s10, t3
+; RV64IM-NEXT: ld t3, 136(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, a4, t3
+; RV64IM-NEXT: ld t3, 128(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a3, t3
+; RV64IM-NEXT: xor a2, a2, t1
+; RV64IM-NEXT: xor a5, a5, a6
+; RV64IM-NEXT: xor a6, a7, s1
+; RV64IM-NEXT: xor a7, t6, s7
+; RV64IM-NEXT: ld t1, 256(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor t1, s0, t1
+; RV64IM-NEXT: ld t3, 160(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a3, t3
+; RV64IM-NEXT: ld t3, 112(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a2, t3
+; RV64IM-NEXT: xor a5, a5, t4
+; RV64IM-NEXT: xor a6, a6, s2
+; RV64IM-NEXT: xor a7, a7, s8
+; RV64IM-NEXT: xor a1, a0, a1
+; RV64IM-NEXT: xor a1, a1, t1
+; RV64IM-NEXT: ld t1, 240(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a3, t1
+; RV64IM-NEXT: ld t1, 152(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a2, t1
+; RV64IM-NEXT: xor a5, a5, t5
+; RV64IM-NEXT: xor a6, a6, s3
+; RV64IM-NEXT: xor a7, a7, s9
+; RV64IM-NEXT: xor a1, a1, a4
+; RV64IM-NEXT: xor a3, a3, t2
+; RV64IM-NEXT: ld a4, 184(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a2, a4
+; RV64IM-NEXT: ld a4, 144(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, a5, a4
+; RV64IM-NEXT: xor a5, a6, s4
+; RV64IM-NEXT: xor a6, a7, t0
+; RV64IM-NEXT: lui a7, %hi(.LCPI15_0)
+; RV64IM-NEXT: ld a7, %lo(.LCPI15_0)(a7)
+; RV64IM-NEXT: slli a0, a0, 56
+; RV64IM-NEXT: xor a3, a1, a3
+; RV64IM-NEXT: ld t1, 304(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a1, a1, t1
+; RV64IM-NEXT: slli a1, a1, 40
+; RV64IM-NEXT: xor a2, a3, a2
+; RV64IM-NEXT: or a0, a0, a1
+; RV64IM-NEXT: lui t0, 4080
+; RV64IM-NEXT: and a1, a2, t0
+; RV64IM-NEXT: xor a4, a2, a4
+; RV64IM-NEXT: srli a2, a2, 8
+; RV64IM-NEXT: slli a1, a1, 24
+; RV64IM-NEXT: xor a5, a4, a5
+; RV64IM-NEXT: ld a3, 336(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a2, a2, a3
+; RV64IM-NEXT: srli a4, a4, 24
+; RV64IM-NEXT: srliw a3, a5, 24
+; RV64IM-NEXT: and a4, a4, t0
+; RV64IM-NEXT: srli t0, a5, 40
+; RV64IM-NEXT: xor a5, a5, a6
+; RV64IM-NEXT: slli a3, a3, 32
+; RV64IM-NEXT: or a2, a2, a4
+; RV64IM-NEXT: and a4, t0, t1
+; RV64IM-NEXT: srli a5, a5, 56
+; RV64IM-NEXT: or a1, a1, a3
+; RV64IM-NEXT: or a4, a4, a5
+; RV64IM-NEXT: or a0, a0, a1
+; RV64IM-NEXT: or a2, a2, a4
+; RV64IM-NEXT: or a0, a0, a2
+; RV64IM-NEXT: srli a1, a0, 4
+; RV64IM-NEXT: ld a2, 312(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, a0, a2
+; RV64IM-NEXT: and a1, a1, a2
+; RV64IM-NEXT: slli a0, a0, 4
+; RV64IM-NEXT: or a0, a1, a0
+; RV64IM-NEXT: srli a1, a0, 2
+; RV64IM-NEXT: ld a2, 320(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, a0, a2
+; RV64IM-NEXT: and a1, a1, a2
+; RV64IM-NEXT: slli a0, a0, 2
+; RV64IM-NEXT: or a0, a1, a0
+; RV64IM-NEXT: srli a1, a0, 1
+; RV64IM-NEXT: ld a2, 328(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, a0, a2
+; RV64IM-NEXT: and a1, a1, a7
+; RV64IM-NEXT: slli a0, a0, 1
+; RV64IM-NEXT: or a0, a1, a0
+; RV64IM-NEXT: srli a0, a0, 1
+; RV64IM-NEXT: ld ra, 440(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s0, 432(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s1, 424(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s2, 416(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s3, 408(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s4, 400(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s5, 392(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s6, 384(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s7, 376(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s8, 368(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s9, 360(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s10, 352(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s11, 344(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: addi sp, sp, 448
+; RV64IM-NEXT: ret
+ %res = call i8 @llvm.clmulh.i8(i8 %a, i8 %b)
+ ret i8 %res
+}
+
+define i16 @clmulh_i16(i16 %a, i16 %b) nounwind {
+; RV32IM-LABEL: clmulh_i16:
+; RV32IM: # %bb.0:
+; RV32IM-NEXT: addi sp, sp, -144
+; RV32IM-NEXT: sw ra, 140(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s0, 136(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s1, 132(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s2, 128(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s3, 124(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s4, 120(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s5, 116(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s6, 112(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s7, 108(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s8, 104(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s9, 100(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s10, 96(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s11, 92(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: srli a3, a0, 8
+; RV32IM-NEXT: lui a1, 16
+; RV32IM-NEXT: srli a6, a0, 24
+; RV32IM-NEXT: slli a4, a0, 24
+; RV32IM-NEXT: lui a2, 61681
+; RV32IM-NEXT: lui t0, 209715
+; RV32IM-NEXT: lui a5, 349525
+; RV32IM-NEXT: li t5, 1
+; RV32IM-NEXT: lui t1, 1
+; RV32IM-NEXT: lui t2, 2
+; RV32IM-NEXT: lui t3, 4
+; RV32IM-NEXT: lui t4, 8
+; RV32IM-NEXT: lui s0, 64
+; RV32IM-NEXT: lui s1, 128
+; RV32IM-NEXT: lui t6, 256
+; RV32IM-NEXT: lui s2, 512
+; RV32IM-NEXT: lui s3, 1024
+; RV32IM-NEXT: lui s4, 2048
+; RV32IM-NEXT: lui s5, 4096
+; RV32IM-NEXT: lui s6, 8192
+; RV32IM-NEXT: lui s7, 16384
+; RV32IM-NEXT: lui s8, 32768
+; RV32IM-NEXT: lui s9, 65536
+; RV32IM-NEXT: lui s10, 131072
+; RV32IM-NEXT: lui s11, 262144
+; RV32IM-NEXT: addi a7, a1, -256
+; RV32IM-NEXT: sw a7, 76(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a3, a3, a7
+; RV32IM-NEXT: or a3, a3, a6
+; RV32IM-NEXT: lui ra, 524288
+; RV32IM-NEXT: addi a6, a2, -241
+; RV32IM-NEXT: sw a6, 80(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: addi a2, t0, 819
+; RV32IM-NEXT: sw a2, 84(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a0, a0, a7
+; RV32IM-NEXT: slli a0, a0, 8
+; RV32IM-NEXT: or a4, a4, a0
+; RV32IM-NEXT: addi a0, a5, 1365
+; RV32IM-NEXT: sw a0, 88(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: slli t5, t5, 11
+; RV32IM-NEXT: or a3, a4, a3
+; RV32IM-NEXT: srli a4, a3, 4
+; RV32IM-NEXT: and a3, a3, a6
+; RV32IM-NEXT: and a4, a4, a6
+; RV32IM-NEXT: slli a3, a3, 4
+; RV32IM-NEXT: or a3, a4, a3
+; RV32IM-NEXT: srli a4, a3, 2
+; RV32IM-NEXT: and a3, a3, a2
+; RV32IM-NEXT: and a4, a4, a2
+; RV32IM-NEXT: slli a3, a3, 2
+; RV32IM-NEXT: or a3, a4, a3
+; RV32IM-NEXT: srli a4, a3, 1
+; RV32IM-NEXT: and a3, a3, a0
+; RV32IM-NEXT: and a4, a4, a0
+; RV32IM-NEXT: slli a3, a3, 1
+; RV32IM-NEXT: or a3, a4, a3
+; RV32IM-NEXT: andi a2, a3, 2
+; RV32IM-NEXT: and a0, a3, t5
+; RV32IM-NEXT: sw a0, 72(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and t1, a3, t1
+; RV32IM-NEXT: and t2, a3, t2
+; RV32IM-NEXT: and t3, a3, t3
+; RV32IM-NEXT: and t4, a3, t4
+; RV32IM-NEXT: and a1, a3, a1
+; RV32IM-NEXT: sw a1, 60(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lui a0, 32
+; RV32IM-NEXT: and a0, a3, a0
+; RV32IM-NEXT: sw a0, 56(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and s0, a3, s0
+; RV32IM-NEXT: sw s0, 52(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and s1, a3, s1
+; RV32IM-NEXT: sw s1, 48(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and t6, a3, t6
+; RV32IM-NEXT: and s2, a3, s2
+; RV32IM-NEXT: and a0, a3, s3
+; RV32IM-NEXT: sw a0, 44(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a0, a3, s4
+; RV32IM-NEXT: sw a0, 40(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a0, a3, s5
+; RV32IM-NEXT: sw a0, 36(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a0, a3, s6
+; RV32IM-NEXT: sw a0, 32(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a0, a3, s7
+; RV32IM-NEXT: sw a0, 28(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a0, a3, s8
+; RV32IM-NEXT: sw a0, 24(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a0, a3, s9
+; RV32IM-NEXT: sw a0, 20(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a0, a3, s10
+; RV32IM-NEXT: sw a0, 16(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a0, a3, s11
+; RV32IM-NEXT: sw a0, 12(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a0, a3, ra
+; RV32IM-NEXT: sw a0, 8(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a0, a3, a2
+; RV32IM-NEXT: sw a0, 64(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi ra, a3, 1
+; RV32IM-NEXT: mul a0, a3, ra
+; RV32IM-NEXT: sw a0, 4(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi a4, a3, 4
+; RV32IM-NEXT: mul ra, a3, a4
+; RV32IM-NEXT: andi a1, a3, 8
+; RV32IM-NEXT: mul s9, a3, a1
+; RV32IM-NEXT: andi a2, a3, 16
+; RV32IM-NEXT: mul s8, a3, a2
+; RV32IM-NEXT: andi a7, a3, 32
+; RV32IM-NEXT: mul s5, a3, a7
+; RV32IM-NEXT: andi a0, a3, 64
+; RV32IM-NEXT: mul s11, a3, a0
+; RV32IM-NEXT: andi a5, a3, 128
+; RV32IM-NEXT: mul a0, a3, a5
+; RV32IM-NEXT: sw a0, 68(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi a5, a3, 256
+; RV32IM-NEXT: mul s1, a3, a5
+; RV32IM-NEXT: andi a6, a3, 512
+; RV32IM-NEXT: mul t5, a3, a6
+; RV32IM-NEXT: andi t0, a3, 1024
+; RV32IM-NEXT: mul s3, a3, t0
+; RV32IM-NEXT: lw a0, 72(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s6, a3, a0
+; RV32IM-NEXT: mul a0, a3, t1
+; RV32IM-NEXT: sw a0, 0(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul t2, a3, t2
+; RV32IM-NEXT: mul a7, a3, t3
+; RV32IM-NEXT: mul s0, a3, t4
+; RV32IM-NEXT: lw a0, 60(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s4, a3, a0
+; RV32IM-NEXT: lw a0, 56(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s7, a3, a0
+; RV32IM-NEXT: lw a0, 52(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s10, a3, a0
+; RV32IM-NEXT: lw a0, 48(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a6, a3, a0
+; RV32IM-NEXT: mul a4, a3, t6
+; RV32IM-NEXT: mul t1, a3, s2
+; RV32IM-NEXT: lw a0, 44(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul t4, a3, a0
+; RV32IM-NEXT: lw a0, 40(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s2, a3, a0
+; RV32IM-NEXT: lw a0, 36(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a2, a3, a0
+; RV32IM-NEXT: lw a0, 32(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a1, a3, a0
+; RV32IM-NEXT: lw a0, 28(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a5, a3, a0
+; RV32IM-NEXT: lw a0, 24(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul t0, a3, a0
+; RV32IM-NEXT: lw a0, 20(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul t3, a3, a0
+; RV32IM-NEXT: lw a0, 16(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul t6, a3, a0
+; RV32IM-NEXT: lw a0, 12(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a0, a3, a0
+; RV32IM-NEXT: sw a0, 72(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a0, 8(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a0, a3, a0
+; RV32IM-NEXT: sw a0, 60(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a0, 64(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw a3, 4(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a0, a3, a0
+; RV32IM-NEXT: xor s9, ra, s9
+; RV32IM-NEXT: xor s5, s8, s5
+; RV32IM-NEXT: xor t5, s1, t5
+; RV32IM-NEXT: xor a7, t2, a7
+; RV32IM-NEXT: xor a4, a6, a4
+; RV32IM-NEXT: xor a1, a2, a1
+; RV32IM-NEXT: xor a0, a0, s9
+; RV32IM-NEXT: xor a2, s5, s11
+; RV32IM-NEXT: xor a6, t5, s3
+; RV32IM-NEXT: xor a7, a7, s0
+; RV32IM-NEXT: xor a4, a4, t1
+; RV32IM-NEXT: xor a1, a1, a5
+; RV32IM-NEXT: xor a0, a0, a2
+; RV32IM-NEXT: xor a2, a6, s6
+; RV32IM-NEXT: xor a5, a7, s4
+; RV32IM-NEXT: xor a4, a4, t4
+; RV32IM-NEXT: xor a1, a1, t0
+; RV32IM-NEXT: lw a6, 68(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a0, a0, a6
+; RV32IM-NEXT: lw a3, 0(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a2, a2, a3
+; RV32IM-NEXT: xor a5, a5, s7
+; RV32IM-NEXT: xor a4, a4, s2
+; RV32IM-NEXT: xor a1, a1, t3
+; RV32IM-NEXT: xor a5, a5, s10
+; RV32IM-NEXT: xor a1, a1, t6
+; RV32IM-NEXT: xor a2, a0, a2
+; RV32IM-NEXT: xor a2, a2, a5
+; RV32IM-NEXT: lui a5, 349525
+; RV32IM-NEXT: addi a5, a5, 1364
+; RV32IM-NEXT: slli a0, a0, 24
+; RV32IM-NEXT: lw a6, 72(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a1, a1, a6
+; RV32IM-NEXT: xor a2, a2, a4
+; RV32IM-NEXT: lw a3, 60(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a1, a1, a3
+; RV32IM-NEXT: lw a6, 76(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: and a3, a2, a6
+; RV32IM-NEXT: srli a4, a2, 8
+; RV32IM-NEXT: xor a1, a2, a1
+; RV32IM-NEXT: slli a3, a3, 8
+; RV32IM-NEXT: and a2, a4, a6
+; RV32IM-NEXT: srli a1, a1, 24
+; RV32IM-NEXT: or a0, a0, a3
+; RV32IM-NEXT: or a1, a2, a1
+; RV32IM-NEXT: or a0, a0, a1
+; RV32IM-NEXT: srli a1, a0, 4
+; RV32IM-NEXT: lw a2, 80(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: and a0, a0, a2
+; RV32IM-NEXT: and a1, a1, a2
+; RV32IM-NEXT: slli a0, a0, 4
+; RV32IM-NEXT: or a0, a1, a0
+; RV32IM-NEXT: srli a1, a0, 2
+; RV32IM-NEXT: lw a2, 84(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: and a0, a0, a2
+; RV32IM-NEXT: and a1, a1, a2
+; RV32IM-NEXT: slli a0, a0, 2
+; RV32IM-NEXT: or a0, a1, a0
+; RV32IM-NEXT: srli a1, a0, 1
+; RV32IM-NEXT: lw a2, 88(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: and a0, a0, a2
+; RV32IM-NEXT: and a1, a1, a5
+; RV32IM-NEXT: slli a0, a0, 1
+; RV32IM-NEXT: or a0, a1, a0
+; RV32IM-NEXT: srli a0, a0, 1
+; RV32IM-NEXT: lw ra, 140(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s0, 136(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s1, 132(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s2, 128(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s3, 124(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s4, 120(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s5, 116(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s6, 112(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s7, 108(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s8, 104(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s9, 100(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s10, 96(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s11, 92(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: addi sp, sp, 144
+; RV32IM-NEXT: ret
+;
+; RV64IM-LABEL: clmulh_i16:
+; RV64IM: # %bb.0:
+; RV64IM-NEXT: addi sp, sp, -448
+; RV64IM-NEXT: sd ra, 440(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s0, 432(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s1, 424(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s2, 416(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s3, 408(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s4, 400(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s5, 392(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s6, 384(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s7, 376(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s8, 368(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s9, 360(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s10, 352(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s11, 344(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: srli a2, a0, 24
+; RV64IM-NEXT: srli a6, a0, 8
+; RV64IM-NEXT: li a3, 255
+; RV64IM-NEXT: srli a5, a0, 40
+; RV64IM-NEXT: lui s2, 16
+; RV64IM-NEXT: srli s5, a0, 56
+; RV64IM-NEXT: srliw t2, a0, 24
+; RV64IM-NEXT: slli t0, a0, 56
+; RV64IM-NEXT: lui t3, 61681
+; RV64IM-NEXT: lui t4, 209715
+; RV64IM-NEXT: lui t6, 349525
+; RV64IM-NEXT: li a7, 1
+; RV64IM-NEXT: lui s4, 2
+; RV64IM-NEXT: lui t1, 4
+; RV64IM-NEXT: lui a4, 128
+; RV64IM-NEXT: lui s7, 256
+; RV64IM-NEXT: lui s8, 4096
+; RV64IM-NEXT: lui s10, 8192
+; RV64IM-NEXT: lui a1, 4080
+; RV64IM-NEXT: and a2, a2, a1
+; RV64IM-NEXT: slli a3, a3, 24
+; RV64IM-NEXT: sd a3, 336(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: addi s0, s2, -256
+; RV64IM-NEXT: and t5, a0, a1
+; RV64IM-NEXT: slli a1, t2, 32
+; RV64IM-NEXT: addi s9, t3, -241
+; RV64IM-NEXT: addi t4, t4, 819
+; RV64IM-NEXT: addi t2, t6, 1365
+; RV64IM-NEXT: slli t3, a7, 11
+; RV64IM-NEXT: slli s11, a7, 32
+; RV64IM-NEXT: slli ra, a7, 33
+; RV64IM-NEXT: slli t6, a7, 34
+; RV64IM-NEXT: slli s1, a7, 35
+; RV64IM-NEXT: slli s3, a7, 36
+; RV64IM-NEXT: and a3, a6, a3
+; RV64IM-NEXT: or a2, a3, a2
+; RV64IM-NEXT: slli a3, a7, 37
+; RV64IM-NEXT: sd a3, 256(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s0, 304(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a3, a5, s0
+; RV64IM-NEXT: or a3, a3, s5
+; RV64IM-NEXT: slli a5, a7, 38
+; RV64IM-NEXT: sd a5, 240(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli t5, t5, 24
+; RV64IM-NEXT: and a0, a0, s0
+; RV64IM-NEXT: or a1, t5, a1
+; RV64IM-NEXT: slli a5, s9, 32
+; RV64IM-NEXT: add a5, s9, a5
+; RV64IM-NEXT: slli s0, t4, 32
+; RV64IM-NEXT: add t4, t4, s0
+; RV64IM-NEXT: slli s5, t2, 32
+; RV64IM-NEXT: slli a0, a0, 40
+; RV64IM-NEXT: add t2, t2, s5
+; RV64IM-NEXT: or a2, a2, a3
+; RV64IM-NEXT: or a0, t0, a0
+; RV64IM-NEXT: or a0, a0, a1
+; RV64IM-NEXT: or a0, a0, a2
+; RV64IM-NEXT: srli a1, a0, 4
+; RV64IM-NEXT: sd a5, 312(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, a0, a5
+; RV64IM-NEXT: and a1, a1, a5
+; RV64IM-NEXT: slli a0, a0, 4
+; RV64IM-NEXT: or a0, a1, a0
+; RV64IM-NEXT: srli a1, a0, 2
+; RV64IM-NEXT: sd t4, 320(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, a0, t4
+; RV64IM-NEXT: and a1, a1, t4
+; RV64IM-NEXT: slli a0, a0, 2
+; RV64IM-NEXT: or a0, a1, a0
+; RV64IM-NEXT: srli a1, a0, 1
+; RV64IM-NEXT: sd t2, 328(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, a0, t2
+; RV64IM-NEXT: and a1, a1, t2
+; RV64IM-NEXT: slli a0, a0, 1
+; RV64IM-NEXT: or t0, a1, a0
+; RV64IM-NEXT: andi a0, t0, 2
+; RV64IM-NEXT: andi a1, t0, 1
+; RV64IM-NEXT: andi a2, t0, 4
+; RV64IM-NEXT: andi a3, t0, 8
+; RV64IM-NEXT: andi a5, t0, 16
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: xor a0, a1, a0
+; RV64IM-NEXT: sd a0, 296(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi a0, t0, 32
+; RV64IM-NEXT: mul a1, t0, a2
+; RV64IM-NEXT: mul a2, t0, a3
+; RV64IM-NEXT: xor a1, a1, a2
+; RV64IM-NEXT: sd a1, 288(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi a1, t0, 256
+; RV64IM-NEXT: mul a2, t0, a5
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: xor a0, a2, a0
+; RV64IM-NEXT: sd a0, 280(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi a0, t0, 512
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: xor a0, a1, a0
+; RV64IM-NEXT: sd a0, 272(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli t4, a7, 39
+; RV64IM-NEXT: and a0, t0, s4
+; RV64IM-NEXT: and a1, t0, t1
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: xor a0, a0, a1
+; RV64IM-NEXT: sd a0, 264(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 40
+; RV64IM-NEXT: and a1, t0, a4
+; RV64IM-NEXT: and a2, t0, s7
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: xor a1, a1, a2
+; RV64IM-NEXT: sd a1, 248(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a1, a7, 41
+; RV64IM-NEXT: and a2, t0, s8
+; RV64IM-NEXT: and a3, t0, s10
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: mul a3, t0, a3
+; RV64IM-NEXT: xor a2, a2, a3
+; RV64IM-NEXT: sd a2, 232(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a2, a7, 48
+; RV64IM-NEXT: and a3, t0, s11
+; RV64IM-NEXT: and a4, t0, ra
+; RV64IM-NEXT: mul a3, t0, a3
+; RV64IM-NEXT: mul a4, t0, a4
+; RV64IM-NEXT: xor a3, a3, a4
+; RV64IM-NEXT: sd a3, 224(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a7, 49
+; RV64IM-NEXT: and a0, t0, a0
+; RV64IM-NEXT: and a1, t0, a1
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: xor a0, a0, a1
+; RV64IM-NEXT: sd a0, 216(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 56
+; RV64IM-NEXT: and a1, t0, a2
+; RV64IM-NEXT: and a2, t0, a3
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: xor a1, a1, a2
+; RV64IM-NEXT: sd a1, 208(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a1, a7, 57
+; RV64IM-NEXT: and a0, t0, a0
+; RV64IM-NEXT: and a1, t0, a1
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: xor a0, a0, a1
+; RV64IM-NEXT: sd a0, 200(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a2, a7, 42
+; RV64IM-NEXT: slli ra, a7, 43
+; RV64IM-NEXT: slli a3, a7, 44
+; RV64IM-NEXT: slli a4, a7, 45
+; RV64IM-NEXT: slli t5, a7, 46
+; RV64IM-NEXT: slli s0, a7, 47
+; RV64IM-NEXT: slli a0, a7, 50
+; RV64IM-NEXT: sd a0, 192(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 51
+; RV64IM-NEXT: sd a0, 184(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 52
+; RV64IM-NEXT: sd a0, 176(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 53
+; RV64IM-NEXT: sd a0, 168(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 54
+; RV64IM-NEXT: sd a0, 160(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 55
+; RV64IM-NEXT: sd a0, 152(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 58
+; RV64IM-NEXT: sd a0, 144(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 59
+; RV64IM-NEXT: sd a0, 136(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 60
+; RV64IM-NEXT: sd a0, 120(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 61
+; RV64IM-NEXT: sd a0, 80(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a7, a7, 62
+; RV64IM-NEXT: sd a7, 48(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, t0, t3
+; RV64IM-NEXT: sd a0, 128(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s7, 1
+; RV64IM-NEXT: and a0, t0, s7
+; RV64IM-NEXT: sd a0, 112(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s8, 8
+; RV64IM-NEXT: and a0, t0, s8
+; RV64IM-NEXT: sd a0, 104(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, t0, s2
+; RV64IM-NEXT: sd a0, 96(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s5, 32
+; RV64IM-NEXT: and a0, t0, s5
+; RV64IM-NEXT: sd a0, 88(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s6, 64
+; RV64IM-NEXT: and a0, t0, s6
+; RV64IM-NEXT: sd a0, 72(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s10, 512
+; RV64IM-NEXT: and a0, t0, s10
+; RV64IM-NEXT: sd a0, 64(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s4, 1024
+; RV64IM-NEXT: and a0, t0, s4
+; RV64IM-NEXT: sd a0, 56(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s9, 2048
+; RV64IM-NEXT: and a0, t0, s9
+; RV64IM-NEXT: sd a0, 40(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s11, 16384
+; RV64IM-NEXT: and a0, t0, s11
+; RV64IM-NEXT: sd a0, 32(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui a5, 32768
+; RV64IM-NEXT: and a5, t0, a5
+; RV64IM-NEXT: lui a6, 65536
+; RV64IM-NEXT: and a6, t0, a6
+; RV64IM-NEXT: lui t1, 131072
+; RV64IM-NEXT: and t1, t0, t1
+; RV64IM-NEXT: lui t2, 262144
+; RV64IM-NEXT: and t2, t0, t2
+; RV64IM-NEXT: and a0, t0, t6
+; RV64IM-NEXT: sd a0, 24(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, t0, s1
+; RV64IM-NEXT: sd a0, 16(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, t0, s3
+; RV64IM-NEXT: sd a0, 8(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a0, 256(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, t0, a0
+; RV64IM-NEXT: sd a0, 0(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a0, 240(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, t0, a0
+; RV64IM-NEXT: and a1, t0, t4
+; RV64IM-NEXT: and a7, t0, a2
+; RV64IM-NEXT: and ra, t0, ra
+; RV64IM-NEXT: and t3, t0, a3
+; RV64IM-NEXT: and t4, t0, a4
+; RV64IM-NEXT: and t5, t0, t5
+; RV64IM-NEXT: and t6, t0, s0
+; RV64IM-NEXT: ld a2, 192(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s0, t0, a2
+; RV64IM-NEXT: ld a2, 184(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s1, t0, a2
+; RV64IM-NEXT: ld a2, 176(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s2, t0, a2
+; RV64IM-NEXT: ld a2, 168(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s3, t0, a2
+; RV64IM-NEXT: ld a2, 160(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s4, t0, a2
+; RV64IM-NEXT: ld a2, 152(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s5, t0, a2
+; RV64IM-NEXT: ld a2, 144(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s6, t0, a2
+; RV64IM-NEXT: ld a2, 136(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s7, t0, a2
+; RV64IM-NEXT: ld a2, 120(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s8, t0, a2
+; RV64IM-NEXT: ld a2, 80(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s9, t0, a2
+; RV64IM-NEXT: ld a2, 48(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s10, t0, a2
+; RV64IM-NEXT: andi s11, t0, 64
+; RV64IM-NEXT: mul a2, t0, s11
+; RV64IM-NEXT: sd a2, 80(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi s11, t0, 128
+; RV64IM-NEXT: mul a2, t0, s11
+; RV64IM-NEXT: sd a2, 192(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi s11, t0, 1024
+; RV64IM-NEXT: mul a2, t0, s11
+; RV64IM-NEXT: sd a2, 48(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 128(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 120(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 112(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 176(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 104(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul s11, t0, a2
+; RV64IM-NEXT: ld a2, 96(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 104(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 88(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 168(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 72(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 256(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 64(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a4, t0, a2
+; RV64IM-NEXT: ld a2, 56(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 96(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 40(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 136(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 32(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a3, t0, a2
+; RV64IM-NEXT: mul a2, t0, a5
+; RV64IM-NEXT: sd a2, 88(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a2, t0, a6
+; RV64IM-NEXT: sd a2, 128(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a2, t0, t1
+; RV64IM-NEXT: sd a2, 160(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a2, t0, t2
+; RV64IM-NEXT: sd a2, 240(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: srliw t2, t0, 31
+; RV64IM-NEXT: slli t2, t2, 31
+; RV64IM-NEXT: ld a2, 24(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: ld a5, 16(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a5, t0, a5
+; RV64IM-NEXT: ld a6, 8(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul t1, t0, a6
+; RV64IM-NEXT: ld a6, 0(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a6, t0, a6
+; RV64IM-NEXT: sd a6, 112(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: sd a0, 152(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a0, t0, a1
+; RV64IM-NEXT: sd a0, 184(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a7, t0, a7
+; RV64IM-NEXT: mul ra, t0, ra
+; RV64IM-NEXT: mul a6, t0, t3
+; RV64IM-NEXT: mul t4, t0, t4
+; RV64IM-NEXT: mul t5, t0, t5
+; RV64IM-NEXT: mul a0, t0, t6
+; RV64IM-NEXT: sd a0, 144(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul t6, t0, s0
+; RV64IM-NEXT: mul s0, t0, s1
+; RV64IM-NEXT: mul s1, t0, s2
+; RV64IM-NEXT: mul s2, t0, s3
+; RV64IM-NEXT: mul s3, t0, s4
+; RV64IM-NEXT: mul s4, t0, s5
+; RV64IM-NEXT: mul s5, t0, s6
+; RV64IM-NEXT: mul s6, t0, s7
+; RV64IM-NEXT: mul s7, t0, s8
+; RV64IM-NEXT: mul s8, t0, s9
+; RV64IM-NEXT: mul s9, t0, s10
+; RV64IM-NEXT: srli s10, t0, 63
+; RV64IM-NEXT: slli s10, s10, 63
+; RV64IM-NEXT: mul t2, t0, t2
+; RV64IM-NEXT: mul t0, t0, s10
+; RV64IM-NEXT: ld a0, 296(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld a1, 288(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s10, a0, a1
+; RV64IM-NEXT: ld a0, 280(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld a1, 80(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a0, a0, a1
+; RV64IM-NEXT: ld a1, 272(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld t3, 48(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a1, a1, t3
+; RV64IM-NEXT: ld t3, 264(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s11, t3, s11
+; RV64IM-NEXT: ld t3, 248(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, t3, a4
+; RV64IM-NEXT: ld t3, 232(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, t3, a3
+; RV64IM-NEXT: ld t3, 224(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, t3, a2
+; RV64IM-NEXT: ld t3, 216(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a7, t3, a7
+; RV64IM-NEXT: ld t3, 208(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor t6, t3, t6
+; RV64IM-NEXT: ld t3, 200(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s5, t3, s5
+; RV64IM-NEXT: xor a0, s10, a0
+; RV64IM-NEXT: ld t3, 120(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a1, a1, t3
+; RV64IM-NEXT: ld t3, 104(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s10, s11, t3
+; RV64IM-NEXT: ld t3, 96(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, a4, t3
+; RV64IM-NEXT: ld t3, 88(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a3, t3
+; RV64IM-NEXT: xor a2, a2, a5
+; RV64IM-NEXT: xor a5, a7, ra
+; RV64IM-NEXT: xor a7, t6, s0
+; RV64IM-NEXT: xor t6, s5, s6
+; RV64IM-NEXT: ld t3, 192(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a0, a0, t3
+; RV64IM-NEXT: ld t3, 176(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a1, a1, t3
+; RV64IM-NEXT: ld t3, 168(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s0, s10, t3
+; RV64IM-NEXT: ld t3, 136(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, a4, t3
+; RV64IM-NEXT: ld t3, 128(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a3, t3
+; RV64IM-NEXT: xor a2, a2, t1
+; RV64IM-NEXT: xor a5, a5, a6
+; RV64IM-NEXT: xor a6, a7, s1
+; RV64IM-NEXT: xor a7, t6, s7
+; RV64IM-NEXT: ld t1, 256(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor t1, s0, t1
+; RV64IM-NEXT: ld t3, 160(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a3, t3
+; RV64IM-NEXT: ld t3, 112(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a2, t3
+; RV64IM-NEXT: xor a5, a5, t4
+; RV64IM-NEXT: xor a6, a6, s2
+; RV64IM-NEXT: xor a7, a7, s8
+; RV64IM-NEXT: xor a1, a0, a1
+; RV64IM-NEXT: xor a1, a1, t1
+; RV64IM-NEXT: ld t1, 240(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a3, t1
+; RV64IM-NEXT: ld t1, 152(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a2, t1
+; RV64IM-NEXT: xor a5, a5, t5
+; RV64IM-NEXT: xor a6, a6, s3
+; RV64IM-NEXT: xor a7, a7, s9
+; RV64IM-NEXT: xor a1, a1, a4
+; RV64IM-NEXT: xor a3, a3, t2
+; RV64IM-NEXT: ld a4, 184(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a2, a4
+; RV64IM-NEXT: ld a4, 144(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, a5, a4
+; RV64IM-NEXT: xor a5, a6, s4
+; RV64IM-NEXT: xor a6, a7, t0
+; RV64IM-NEXT: lui a7, %hi(.LCPI16_0)
+; RV64IM-NEXT: ld a7, %lo(.LCPI16_0)(a7)
+; RV64IM-NEXT: slli a0, a0, 56
+; RV64IM-NEXT: xor a3, a1, a3
+; RV64IM-NEXT: ld t1, 304(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a1, a1, t1
+; RV64IM-NEXT: slli a1, a1, 40
+; RV64IM-NEXT: xor a2, a3, a2
+; RV64IM-NEXT: or a0, a0, a1
+; RV64IM-NEXT: lui t0, 4080
+; RV64IM-NEXT: and a1, a2, t0
+; RV64IM-NEXT: xor a4, a2, a4
+; RV64IM-NEXT: srli a2, a2, 8
+; RV64IM-NEXT: slli a1, a1, 24
+; RV64IM-NEXT: xor a5, a4, a5
+; RV64IM-NEXT: ld a3, 336(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a2, a2, a3
+; RV64IM-NEXT: srli a4, a4, 24
+; RV64IM-NEXT: srliw a3, a5, 24
+; RV64IM-NEXT: and a4, a4, t0
+; RV64IM-NEXT: srli t0, a5, 40
+; RV64IM-NEXT: xor a5, a5, a6
+; RV64IM-NEXT: slli a3, a3, 32
+; RV64IM-NEXT: or a2, a2, a4
+; RV64IM-NEXT: and a4, t0, t1
+; RV64IM-NEXT: srli a5, a5, 56
+; RV64IM-NEXT: or a1, a1, a3
+; RV64IM-NEXT: or a4, a4, a5
+; RV64IM-NEXT: or a0, a0, a1
+; RV64IM-NEXT: or a2, a2, a4
+; RV64IM-NEXT: or a0, a0, a2
+; RV64IM-NEXT: srli a1, a0, 4
+; RV64IM-NEXT: ld a2, 312(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, a0, a2
+; RV64IM-NEXT: and a1, a1, a2
+; RV64IM-NEXT: slli a0, a0, 4
+; RV64IM-NEXT: or a0, a1, a0
+; RV64IM-NEXT: srli a1, a0, 2
+; RV64IM-NEXT: ld a2, 320(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, a0, a2
+; RV64IM-NEXT: and a1, a1, a2
+; RV64IM-NEXT: slli a0, a0, 2
+; RV64IM-NEXT: or a0, a1, a0
+; RV64IM-NEXT: srli a1, a0, 1
+; RV64IM-NEXT: ld a2, 328(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, a0, a2
+; RV64IM-NEXT: and a1, a1, a7
+; RV64IM-NEXT: slli a0, a0, 1
+; RV64IM-NEXT: or a0, a1, a0
+; RV64IM-NEXT: srli a0, a0, 1
+; RV64IM-NEXT: ld ra, 440(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s0, 432(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s1, 424(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s2, 416(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s3, 408(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s4, 400(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s5, 392(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s6, 384(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s7, 376(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s8, 368(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s9, 360(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s10, 352(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s11, 344(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: addi sp, sp, 448
+; RV64IM-NEXT: ret
+ %res = call i16 @llvm.clmulh.i16(i16 %a, i16 %b)
+ ret i16 %res
+}
+
+define i32 @clmulh_i32(i32 %a, i32 %b) nounwind {
+; RV32IM-LABEL: clmulh_i32:
+; RV32IM: # %bb.0:
+; RV32IM-NEXT: addi sp, sp, -144
+; RV32IM-NEXT: sw ra, 140(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s0, 136(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s1, 132(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s2, 128(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s3, 124(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s4, 120(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s5, 116(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s6, 112(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s7, 108(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s8, 104(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s9, 100(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s10, 96(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s11, 92(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: srli a3, a0, 8
+; RV32IM-NEXT: lui a1, 16
+; RV32IM-NEXT: srli a6, a0, 24
+; RV32IM-NEXT: slli a4, a0, 24
+; RV32IM-NEXT: lui a2, 61681
+; RV32IM-NEXT: lui t0, 209715
+; RV32IM-NEXT: lui a5, 349525
+; RV32IM-NEXT: li t5, 1
+; RV32IM-NEXT: lui t1, 1
+; RV32IM-NEXT: lui t2, 2
+; RV32IM-NEXT: lui t3, 4
+; RV32IM-NEXT: lui t4, 8
+; RV32IM-NEXT: lui s0, 64
+; RV32IM-NEXT: lui s1, 128
+; RV32IM-NEXT: lui t6, 256
+; RV32IM-NEXT: lui s2, 512
+; RV32IM-NEXT: lui s3, 1024
+; RV32IM-NEXT: lui s4, 2048
+; RV32IM-NEXT: lui s5, 4096
+; RV32IM-NEXT: lui s6, 8192
+; RV32IM-NEXT: lui s7, 16384
+; RV32IM-NEXT: lui s8, 32768
+; RV32IM-NEXT: lui s9, 65536
+; RV32IM-NEXT: lui s10, 131072
+; RV32IM-NEXT: lui s11, 262144
+; RV32IM-NEXT: addi a7, a1, -256
+; RV32IM-NEXT: sw a7, 76(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a3, a3, a7
+; RV32IM-NEXT: or a3, a3, a6
+; RV32IM-NEXT: lui ra, 524288
+; RV32IM-NEXT: addi a6, a2, -241
+; RV32IM-NEXT: sw a6, 80(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: addi a2, t0, 819
+; RV32IM-NEXT: sw a2, 84(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a0, a0, a7
+; RV32IM-NEXT: slli a0, a0, 8
+; RV32IM-NEXT: or a4, a4, a0
+; RV32IM-NEXT: addi a0, a5, 1365
+; RV32IM-NEXT: sw a0, 88(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: slli t5, t5, 11
+; RV32IM-NEXT: or a3, a4, a3
+; RV32IM-NEXT: srli a4, a3, 4
+; RV32IM-NEXT: and a3, a3, a6
+; RV32IM-NEXT: and a4, a4, a6
+; RV32IM-NEXT: slli a3, a3, 4
+; RV32IM-NEXT: or a3, a4, a3
+; RV32IM-NEXT: srli a4, a3, 2
+; RV32IM-NEXT: and a3, a3, a2
+; RV32IM-NEXT: and a4, a4, a2
+; RV32IM-NEXT: slli a3, a3, 2
+; RV32IM-NEXT: or a3, a4, a3
+; RV32IM-NEXT: srli a4, a3, 1
+; RV32IM-NEXT: and a3, a3, a0
+; RV32IM-NEXT: and a4, a4, a0
+; RV32IM-NEXT: slli a3, a3, 1
+; RV32IM-NEXT: or a3, a4, a3
+; RV32IM-NEXT: andi a2, a3, 2
+; RV32IM-NEXT: and a0, a3, t5
+; RV32IM-NEXT: sw a0, 72(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and t1, a3, t1
+; RV32IM-NEXT: and t2, a3, t2
+; RV32IM-NEXT: and t3, a3, t3
+; RV32IM-NEXT: and t4, a3, t4
+; RV32IM-NEXT: and a1, a3, a1
+; RV32IM-NEXT: sw a1, 60(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lui a0, 32
+; RV32IM-NEXT: and a0, a3, a0
+; RV32IM-NEXT: sw a0, 56(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and s0, a3, s0
+; RV32IM-NEXT: sw s0, 52(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and s1, a3, s1
+; RV32IM-NEXT: sw s1, 48(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and t6, a3, t6
+; RV32IM-NEXT: and s2, a3, s2
+; RV32IM-NEXT: and a0, a3, s3
+; RV32IM-NEXT: sw a0, 44(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a0, a3, s4
+; RV32IM-NEXT: sw a0, 40(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a0, a3, s5
+; RV32IM-NEXT: sw a0, 36(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a0, a3, s6
+; RV32IM-NEXT: sw a0, 32(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a0, a3, s7
+; RV32IM-NEXT: sw a0, 28(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a0, a3, s8
+; RV32IM-NEXT: sw a0, 24(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a0, a3, s9
+; RV32IM-NEXT: sw a0, 20(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a0, a3, s10
+; RV32IM-NEXT: sw a0, 16(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a0, a3, s11
+; RV32IM-NEXT: sw a0, 12(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a0, a3, ra
+; RV32IM-NEXT: sw a0, 8(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a0, a3, a2
+; RV32IM-NEXT: sw a0, 64(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi ra, a3, 1
+; RV32IM-NEXT: mul a0, a3, ra
+; RV32IM-NEXT: sw a0, 4(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi a4, a3, 4
+; RV32IM-NEXT: mul ra, a3, a4
+; RV32IM-NEXT: andi a1, a3, 8
+; RV32IM-NEXT: mul s9, a3, a1
+; RV32IM-NEXT: andi a2, a3, 16
+; RV32IM-NEXT: mul s8, a3, a2
+; RV32IM-NEXT: andi a7, a3, 32
+; RV32IM-NEXT: mul s5, a3, a7
+; RV32IM-NEXT: andi a0, a3, 64
+; RV32IM-NEXT: mul s11, a3, a0
+; RV32IM-NEXT: andi a5, a3, 128
+; RV32IM-NEXT: mul a0, a3, a5
+; RV32IM-NEXT: sw a0, 68(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi a5, a3, 256
+; RV32IM-NEXT: mul s1, a3, a5
+; RV32IM-NEXT: andi a6, a3, 512
+; RV32IM-NEXT: mul t5, a3, a6
+; RV32IM-NEXT: andi t0, a3, 1024
+; RV32IM-NEXT: mul s3, a3, t0
+; RV32IM-NEXT: lw a0, 72(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s6, a3, a0
+; RV32IM-NEXT: mul a0, a3, t1
+; RV32IM-NEXT: sw a0, 0(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul t2, a3, t2
+; RV32IM-NEXT: mul a7, a3, t3
+; RV32IM-NEXT: mul s0, a3, t4
+; RV32IM-NEXT: lw a0, 60(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s4, a3, a0
+; RV32IM-NEXT: lw a0, 56(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s7, a3, a0
+; RV32IM-NEXT: lw a0, 52(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s10, a3, a0
+; RV32IM-NEXT: lw a0, 48(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a6, a3, a0
+; RV32IM-NEXT: mul a4, a3, t6
+; RV32IM-NEXT: mul t1, a3, s2
+; RV32IM-NEXT: lw a0, 44(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul t4, a3, a0
+; RV32IM-NEXT: lw a0, 40(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s2, a3, a0
+; RV32IM-NEXT: lw a0, 36(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a2, a3, a0
+; RV32IM-NEXT: lw a0, 32(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a1, a3, a0
+; RV32IM-NEXT: lw a0, 28(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a5, a3, a0
+; RV32IM-NEXT: lw a0, 24(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul t0, a3, a0
+; RV32IM-NEXT: lw a0, 20(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul t3, a3, a0
+; RV32IM-NEXT: lw a0, 16(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul t6, a3, a0
+; RV32IM-NEXT: lw a0, 12(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a0, a3, a0
+; RV32IM-NEXT: sw a0, 72(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a0, 8(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a0, a3, a0
+; RV32IM-NEXT: sw a0, 60(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a0, 64(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw a3, 4(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a0, a3, a0
+; RV32IM-NEXT: xor s9, ra, s9
+; RV32IM-NEXT: xor s5, s8, s5
+; RV32IM-NEXT: xor t5, s1, t5
+; RV32IM-NEXT: xor a7, t2, a7
+; RV32IM-NEXT: xor a4, a6, a4
+; RV32IM-NEXT: xor a1, a2, a1
+; RV32IM-NEXT: xor a0, a0, s9
+; RV32IM-NEXT: xor a2, s5, s11
+; RV32IM-NEXT: xor a6, t5, s3
+; RV32IM-NEXT: xor a7, a7, s0
+; RV32IM-NEXT: xor a4, a4, t1
+; RV32IM-NEXT: xor a1, a1, a5
+; RV32IM-NEXT: xor a0, a0, a2
+; RV32IM-NEXT: xor a2, a6, s6
+; RV32IM-NEXT: xor a5, a7, s4
+; RV32IM-NEXT: xor a4, a4, t4
+; RV32IM-NEXT: xor a1, a1, t0
+; RV32IM-NEXT: lw a6, 68(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a0, a0, a6
+; RV32IM-NEXT: lw a3, 0(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a2, a2, a3
+; RV32IM-NEXT: xor a5, a5, s7
+; RV32IM-NEXT: xor a4, a4, s2
+; RV32IM-NEXT: xor a1, a1, t3
+; RV32IM-NEXT: xor a5, a5, s10
+; RV32IM-NEXT: xor a1, a1, t6
+; RV32IM-NEXT: xor a2, a0, a2
+; RV32IM-NEXT: xor a2, a2, a5
+; RV32IM-NEXT: lui a5, 349525
+; RV32IM-NEXT: addi a5, a5, 1364
+; RV32IM-NEXT: slli a0, a0, 24
+; RV32IM-NEXT: lw a6, 72(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a1, a1, a6
+; RV32IM-NEXT: xor a2, a2, a4
+; RV32IM-NEXT: lw a3, 60(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a1, a1, a3
+; RV32IM-NEXT: lw a6, 76(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: and a3, a2, a6
+; RV32IM-NEXT: srli a4, a2, 8
+; RV32IM-NEXT: xor a1, a2, a1
+; RV32IM-NEXT: slli a3, a3, 8
+; RV32IM-NEXT: and a2, a4, a6
+; RV32IM-NEXT: srli a1, a1, 24
+; RV32IM-NEXT: or a0, a0, a3
+; RV32IM-NEXT: or a1, a2, a1
+; RV32IM-NEXT: or a0, a0, a1
+; RV32IM-NEXT: srli a1, a0, 4
+; RV32IM-NEXT: lw a2, 80(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: and a0, a0, a2
+; RV32IM-NEXT: and a1, a1, a2
+; RV32IM-NEXT: slli a0, a0, 4
+; RV32IM-NEXT: or a0, a1, a0
+; RV32IM-NEXT: srli a1, a0, 2
+; RV32IM-NEXT: lw a2, 84(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: and a0, a0, a2
+; RV32IM-NEXT: and a1, a1, a2
+; RV32IM-NEXT: slli a0, a0, 2
+; RV32IM-NEXT: or a0, a1, a0
+; RV32IM-NEXT: srli a1, a0, 1
+; RV32IM-NEXT: lw a2, 88(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: and a0, a0, a2
+; RV32IM-NEXT: and a1, a1, a5
+; RV32IM-NEXT: slli a0, a0, 1
+; RV32IM-NEXT: or a0, a1, a0
+; RV32IM-NEXT: srli a0, a0, 1
+; RV32IM-NEXT: lw ra, 140(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s0, 136(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s1, 132(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s2, 128(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s3, 124(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s4, 120(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s5, 116(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s6, 112(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s7, 108(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s8, 104(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s9, 100(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s10, 96(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s11, 92(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: addi sp, sp, 144
+; RV32IM-NEXT: ret
+;
+; RV64IM-LABEL: clmulh_i32:
+; RV64IM: # %bb.0:
+; RV64IM-NEXT: addi sp, sp, -448
+; RV64IM-NEXT: sd ra, 440(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s0, 432(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s1, 424(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s2, 416(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s3, 408(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s4, 400(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s5, 392(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s6, 384(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s7, 376(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s8, 368(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s9, 360(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s10, 352(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s11, 344(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: srli a2, a0, 24
+; RV64IM-NEXT: srli a6, a0, 8
+; RV64IM-NEXT: li a3, 255
+; RV64IM-NEXT: srli a5, a0, 40
+; RV64IM-NEXT: lui s2, 16
+; RV64IM-NEXT: srli s5, a0, 56
+; RV64IM-NEXT: srliw t2, a0, 24
+; RV64IM-NEXT: slli t0, a0, 56
+; RV64IM-NEXT: lui t3, 61681
+; RV64IM-NEXT: lui t4, 209715
+; RV64IM-NEXT: lui t6, 349525
+; RV64IM-NEXT: li a7, 1
+; RV64IM-NEXT: lui s4, 2
+; RV64IM-NEXT: lui t1, 4
+; RV64IM-NEXT: lui a4, 128
+; RV64IM-NEXT: lui s7, 256
+; RV64IM-NEXT: lui s8, 4096
+; RV64IM-NEXT: lui s10, 8192
+; RV64IM-NEXT: lui a1, 4080
+; RV64IM-NEXT: and a2, a2, a1
+; RV64IM-NEXT: slli a3, a3, 24
+; RV64IM-NEXT: sd a3, 336(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: addi s0, s2, -256
+; RV64IM-NEXT: and t5, a0, a1
+; RV64IM-NEXT: slli a1, t2, 32
+; RV64IM-NEXT: addi s9, t3, -241
+; RV64IM-NEXT: addi t4, t4, 819
+; RV64IM-NEXT: addi t2, t6, 1365
+; RV64IM-NEXT: slli t3, a7, 11
+; RV64IM-NEXT: slli s11, a7, 32
+; RV64IM-NEXT: slli ra, a7, 33
+; RV64IM-NEXT: slli t6, a7, 34
+; RV64IM-NEXT: slli s1, a7, 35
+; RV64IM-NEXT: slli s3, a7, 36
+; RV64IM-NEXT: and a3, a6, a3
+; RV64IM-NEXT: or a2, a3, a2
+; RV64IM-NEXT: slli a3, a7, 37
+; RV64IM-NEXT: sd a3, 256(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s0, 304(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a3, a5, s0
+; RV64IM-NEXT: or a3, a3, s5
+; RV64IM-NEXT: slli a5, a7, 38
+; RV64IM-NEXT: sd a5, 240(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli t5, t5, 24
+; RV64IM-NEXT: and a0, a0, s0
+; RV64IM-NEXT: or a1, t5, a1
+; RV64IM-NEXT: slli a5, s9, 32
+; RV64IM-NEXT: add a5, s9, a5
+; RV64IM-NEXT: slli s0, t4, 32
+; RV64IM-NEXT: add t4, t4, s0
+; RV64IM-NEXT: slli s5, t2, 32
+; RV64IM-NEXT: slli a0, a0, 40
+; RV64IM-NEXT: add t2, t2, s5
+; RV64IM-NEXT: or a2, a2, a3
+; RV64IM-NEXT: or a0, t0, a0
+; RV64IM-NEXT: or a0, a0, a1
+; RV64IM-NEXT: or a0, a0, a2
+; RV64IM-NEXT: srli a1, a0, 4
+; RV64IM-NEXT: sd a5, 312(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, a0, a5
+; RV64IM-NEXT: and a1, a1, a5
+; RV64IM-NEXT: slli a0, a0, 4
+; RV64IM-NEXT: or a0, a1, a0
+; RV64IM-NEXT: srli a1, a0, 2
+; RV64IM-NEXT: sd t4, 320(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, a0, t4
+; RV64IM-NEXT: and a1, a1, t4
+; RV64IM-NEXT: slli a0, a0, 2
+; RV64IM-NEXT: or a0, a1, a0
+; RV64IM-NEXT: srli a1, a0, 1
+; RV64IM-NEXT: sd t2, 328(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, a0, t2
+; RV64IM-NEXT: and a1, a1, t2
+; RV64IM-NEXT: slli a0, a0, 1
+; RV64IM-NEXT: or t0, a1, a0
+; RV64IM-NEXT: andi a0, t0, 2
+; RV64IM-NEXT: andi a1, t0, 1
+; RV64IM-NEXT: andi a2, t0, 4
+; RV64IM-NEXT: andi a3, t0, 8
+; RV64IM-NEXT: andi a5, t0, 16
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: xor a0, a1, a0
+; RV64IM-NEXT: sd a0, 296(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi a0, t0, 32
+; RV64IM-NEXT: mul a1, t0, a2
+; RV64IM-NEXT: mul a2, t0, a3
+; RV64IM-NEXT: xor a1, a1, a2
+; RV64IM-NEXT: sd a1, 288(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi a1, t0, 256
+; RV64IM-NEXT: mul a2, t0, a5
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: xor a0, a2, a0
+; RV64IM-NEXT: sd a0, 280(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi a0, t0, 512
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: xor a0, a1, a0
+; RV64IM-NEXT: sd a0, 272(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli t4, a7, 39
+; RV64IM-NEXT: and a0, t0, s4
+; RV64IM-NEXT: and a1, t0, t1
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: xor a0, a0, a1
+; RV64IM-NEXT: sd a0, 264(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 40
+; RV64IM-NEXT: and a1, t0, a4
+; RV64IM-NEXT: and a2, t0, s7
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: xor a1, a1, a2
+; RV64IM-NEXT: sd a1, 248(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a1, a7, 41
+; RV64IM-NEXT: and a2, t0, s8
+; RV64IM-NEXT: and a3, t0, s10
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: mul a3, t0, a3
+; RV64IM-NEXT: xor a2, a2, a3
+; RV64IM-NEXT: sd a2, 232(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a2, a7, 48
+; RV64IM-NEXT: and a3, t0, s11
+; RV64IM-NEXT: and a4, t0, ra
+; RV64IM-NEXT: mul a3, t0, a3
+; RV64IM-NEXT: mul a4, t0, a4
+; RV64IM-NEXT: xor a3, a3, a4
+; RV64IM-NEXT: sd a3, 224(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a7, 49
+; RV64IM-NEXT: and a0, t0, a0
+; RV64IM-NEXT: and a1, t0, a1
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: xor a0, a0, a1
+; RV64IM-NEXT: sd a0, 216(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 56
+; RV64IM-NEXT: and a1, t0, a2
+; RV64IM-NEXT: and a2, t0, a3
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: xor a1, a1, a2
+; RV64IM-NEXT: sd a1, 208(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a1, a7, 57
+; RV64IM-NEXT: and a0, t0, a0
+; RV64IM-NEXT: and a1, t0, a1
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: xor a0, a0, a1
+; RV64IM-NEXT: sd a0, 200(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a2, a7, 42
+; RV64IM-NEXT: slli ra, a7, 43
+; RV64IM-NEXT: slli a3, a7, 44
+; RV64IM-NEXT: slli a4, a7, 45
+; RV64IM-NEXT: slli t5, a7, 46
+; RV64IM-NEXT: slli s0, a7, 47
+; RV64IM-NEXT: slli a0, a7, 50
+; RV64IM-NEXT: sd a0, 192(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 51
+; RV64IM-NEXT: sd a0, 184(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 52
+; RV64IM-NEXT: sd a0, 176(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 53
+; RV64IM-NEXT: sd a0, 168(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 54
+; RV64IM-NEXT: sd a0, 160(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 55
+; RV64IM-NEXT: sd a0, 152(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 58
+; RV64IM-NEXT: sd a0, 144(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 59
+; RV64IM-NEXT: sd a0, 136(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 60
+; RV64IM-NEXT: sd a0, 120(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 61
+; RV64IM-NEXT: sd a0, 80(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a7, a7, 62
+; RV64IM-NEXT: sd a7, 48(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, t0, t3
+; RV64IM-NEXT: sd a0, 128(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s7, 1
+; RV64IM-NEXT: and a0, t0, s7
+; RV64IM-NEXT: sd a0, 112(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s8, 8
+; RV64IM-NEXT: and a0, t0, s8
+; RV64IM-NEXT: sd a0, 104(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, t0, s2
+; RV64IM-NEXT: sd a0, 96(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s5, 32
+; RV64IM-NEXT: and a0, t0, s5
+; RV64IM-NEXT: sd a0, 88(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s6, 64
+; RV64IM-NEXT: and a0, t0, s6
+; RV64IM-NEXT: sd a0, 72(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s10, 512
+; RV64IM-NEXT: and a0, t0, s10
+; RV64IM-NEXT: sd a0, 64(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s4, 1024
+; RV64IM-NEXT: and a0, t0, s4
+; RV64IM-NEXT: sd a0, 56(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s9, 2048
+; RV64IM-NEXT: and a0, t0, s9
+; RV64IM-NEXT: sd a0, 40(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s11, 16384
+; RV64IM-NEXT: and a0, t0, s11
+; RV64IM-NEXT: sd a0, 32(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui a5, 32768
+; RV64IM-NEXT: and a5, t0, a5
+; RV64IM-NEXT: lui a6, 65536
+; RV64IM-NEXT: and a6, t0, a6
+; RV64IM-NEXT: lui t1, 131072
+; RV64IM-NEXT: and t1, t0, t1
+; RV64IM-NEXT: lui t2, 262144
+; RV64IM-NEXT: and t2, t0, t2
+; RV64IM-NEXT: and a0, t0, t6
+; RV64IM-NEXT: sd a0, 24(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, t0, s1
+; RV64IM-NEXT: sd a0, 16(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, t0, s3
+; RV64IM-NEXT: sd a0, 8(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a0, 256(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, t0, a0
+; RV64IM-NEXT: sd a0, 0(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a0, 240(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, t0, a0
+; RV64IM-NEXT: and a1, t0, t4
+; RV64IM-NEXT: and a7, t0, a2
+; RV64IM-NEXT: and ra, t0, ra
+; RV64IM-NEXT: and t3, t0, a3
+; RV64IM-NEXT: and t4, t0, a4
+; RV64IM-NEXT: and t5, t0, t5
+; RV64IM-NEXT: and t6, t0, s0
+; RV64IM-NEXT: ld a2, 192(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s0, t0, a2
+; RV64IM-NEXT: ld a2, 184(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s1, t0, a2
+; RV64IM-NEXT: ld a2, 176(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s2, t0, a2
+; RV64IM-NEXT: ld a2, 168(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s3, t0, a2
+; RV64IM-NEXT: ld a2, 160(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s4, t0, a2
+; RV64IM-NEXT: ld a2, 152(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s5, t0, a2
+; RV64IM-NEXT: ld a2, 144(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s6, t0, a2
+; RV64IM-NEXT: ld a2, 136(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s7, t0, a2
+; RV64IM-NEXT: ld a2, 120(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s8, t0, a2
+; RV64IM-NEXT: ld a2, 80(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s9, t0, a2
+; RV64IM-NEXT: ld a2, 48(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s10, t0, a2
+; RV64IM-NEXT: andi s11, t0, 64
+; RV64IM-NEXT: mul a2, t0, s11
+; RV64IM-NEXT: sd a2, 80(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi s11, t0, 128
+; RV64IM-NEXT: mul a2, t0, s11
+; RV64IM-NEXT: sd a2, 192(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi s11, t0, 1024
+; RV64IM-NEXT: mul a2, t0, s11
+; RV64IM-NEXT: sd a2, 48(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 128(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 120(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 112(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 176(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 104(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul s11, t0, a2
+; RV64IM-NEXT: ld a2, 96(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 104(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 88(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 168(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 72(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 256(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 64(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a4, t0, a2
+; RV64IM-NEXT: ld a2, 56(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 96(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 40(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 136(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 32(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a3, t0, a2
+; RV64IM-NEXT: mul a2, t0, a5
+; RV64IM-NEXT: sd a2, 88(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a2, t0, a6
+; RV64IM-NEXT: sd a2, 128(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a2, t0, t1
+; RV64IM-NEXT: sd a2, 160(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a2, t0, t2
+; RV64IM-NEXT: sd a2, 240(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: srliw t2, t0, 31
+; RV64IM-NEXT: slli t2, t2, 31
+; RV64IM-NEXT: ld a2, 24(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: ld a5, 16(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a5, t0, a5
+; RV64IM-NEXT: ld a6, 8(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul t1, t0, a6
+; RV64IM-NEXT: ld a6, 0(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a6, t0, a6
+; RV64IM-NEXT: sd a6, 112(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: sd a0, 152(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a0, t0, a1
+; RV64IM-NEXT: sd a0, 184(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a7, t0, a7
+; RV64IM-NEXT: mul ra, t0, ra
+; RV64IM-NEXT: mul a6, t0, t3
+; RV64IM-NEXT: mul t4, t0, t4
+; RV64IM-NEXT: mul t5, t0, t5
+; RV64IM-NEXT: mul a0, t0, t6
+; RV64IM-NEXT: sd a0, 144(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul t6, t0, s0
+; RV64IM-NEXT: mul s0, t0, s1
+; RV64IM-NEXT: mul s1, t0, s2
+; RV64IM-NEXT: mul s2, t0, s3
+; RV64IM-NEXT: mul s3, t0, s4
+; RV64IM-NEXT: mul s4, t0, s5
+; RV64IM-NEXT: mul s5, t0, s6
+; RV64IM-NEXT: mul s6, t0, s7
+; RV64IM-NEXT: mul s7, t0, s8
+; RV64IM-NEXT: mul s8, t0, s9
+; RV64IM-NEXT: mul s9, t0, s10
+; RV64IM-NEXT: srli s10, t0, 63
+; RV64IM-NEXT: slli s10, s10, 63
+; RV64IM-NEXT: mul t2, t0, t2
+; RV64IM-NEXT: mul t0, t0, s10
+; RV64IM-NEXT: ld a0, 296(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld a1, 288(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s10, a0, a1
+; RV64IM-NEXT: ld a0, 280(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld a1, 80(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a0, a0, a1
+; RV64IM-NEXT: ld a1, 272(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld t3, 48(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a1, a1, t3
+; RV64IM-NEXT: ld t3, 264(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s11, t3, s11
+; RV64IM-NEXT: ld t3, 248(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, t3, a4
+; RV64IM-NEXT: ld t3, 232(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, t3, a3
+; RV64IM-NEXT: ld t3, 224(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, t3, a2
+; RV64IM-NEXT: ld t3, 216(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a7, t3, a7
+; RV64IM-NEXT: ld t3, 208(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor t6, t3, t6
+; RV64IM-NEXT: ld t3, 200(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s5, t3, s5
+; RV64IM-NEXT: xor a0, s10, a0
+; RV64IM-NEXT: ld t3, 120(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a1, a1, t3
+; RV64IM-NEXT: ld t3, 104(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s10, s11, t3
+; RV64IM-NEXT: ld t3, 96(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, a4, t3
+; RV64IM-NEXT: ld t3, 88(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a3, t3
+; RV64IM-NEXT: xor a2, a2, a5
+; RV64IM-NEXT: xor a5, a7, ra
+; RV64IM-NEXT: xor a7, t6, s0
+; RV64IM-NEXT: xor t6, s5, s6
+; RV64IM-NEXT: ld t3, 192(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a0, a0, t3
+; RV64IM-NEXT: ld t3, 176(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a1, a1, t3
+; RV64IM-NEXT: ld t3, 168(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s0, s10, t3
+; RV64IM-NEXT: ld t3, 136(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, a4, t3
+; RV64IM-NEXT: ld t3, 128(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a3, t3
+; RV64IM-NEXT: xor a2, a2, t1
+; RV64IM-NEXT: xor a5, a5, a6
+; RV64IM-NEXT: xor a6, a7, s1
+; RV64IM-NEXT: xor a7, t6, s7
+; RV64IM-NEXT: ld t1, 256(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor t1, s0, t1
+; RV64IM-NEXT: ld t3, 160(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a3, t3
+; RV64IM-NEXT: ld t3, 112(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a2, t3
+; RV64IM-NEXT: xor a5, a5, t4
+; RV64IM-NEXT: xor a6, a6, s2
+; RV64IM-NEXT: xor a7, a7, s8
+; RV64IM-NEXT: xor a1, a0, a1
+; RV64IM-NEXT: xor a1, a1, t1
+; RV64IM-NEXT: ld t1, 240(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a3, t1
+; RV64IM-NEXT: ld t1, 152(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a2, t1
+; RV64IM-NEXT: xor a5, a5, t5
+; RV64IM-NEXT: xor a6, a6, s3
+; RV64IM-NEXT: xor a7, a7, s9
+; RV64IM-NEXT: xor a1, a1, a4
+; RV64IM-NEXT: xor a3, a3, t2
+; RV64IM-NEXT: ld a4, 184(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a2, a4
+; RV64IM-NEXT: ld a4, 144(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, a5, a4
+; RV64IM-NEXT: xor a5, a6, s4
+; RV64IM-NEXT: xor a6, a7, t0
+; RV64IM-NEXT: lui a7, %hi(.LCPI17_0)
+; RV64IM-NEXT: ld a7, %lo(.LCPI17_0)(a7)
+; RV64IM-NEXT: slli a0, a0, 56
+; RV64IM-NEXT: xor a3, a1, a3
+; RV64IM-NEXT: ld t1, 304(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a1, a1, t1
+; RV64IM-NEXT: slli a1, a1, 40
+; RV64IM-NEXT: xor a2, a3, a2
+; RV64IM-NEXT: or a0, a0, a1
+; RV64IM-NEXT: lui t0, 4080
+; RV64IM-NEXT: and a1, a2, t0
+; RV64IM-NEXT: xor a4, a2, a4
+; RV64IM-NEXT: srli a2, a2, 8
+; RV64IM-NEXT: slli a1, a1, 24
+; RV64IM-NEXT: xor a5, a4, a5
+; RV64IM-NEXT: ld a3, 336(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a2, a2, a3
+; RV64IM-NEXT: srli a4, a4, 24
+; RV64IM-NEXT: srliw a3, a5, 24
+; RV64IM-NEXT: and a4, a4, t0
+; RV64IM-NEXT: srli t0, a5, 40
+; RV64IM-NEXT: xor a5, a5, a6
+; RV64IM-NEXT: slli a3, a3, 32
+; RV64IM-NEXT: or a2, a2, a4
+; RV64IM-NEXT: and a4, t0, t1
+; RV64IM-NEXT: srli a5, a5, 56
+; RV64IM-NEXT: or a1, a1, a3
+; RV64IM-NEXT: or a4, a4, a5
+; RV64IM-NEXT: or a0, a0, a1
+; RV64IM-NEXT: or a2, a2, a4
+; RV64IM-NEXT: or a0, a0, a2
+; RV64IM-NEXT: srli a1, a0, 4
+; RV64IM-NEXT: ld a2, 312(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, a0, a2
+; RV64IM-NEXT: and a1, a1, a2
+; RV64IM-NEXT: slli a0, a0, 4
+; RV64IM-NEXT: or a0, a1, a0
+; RV64IM-NEXT: srli a1, a0, 2
+; RV64IM-NEXT: ld a2, 320(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, a0, a2
+; RV64IM-NEXT: and a1, a1, a2
+; RV64IM-NEXT: slli a0, a0, 2
+; RV64IM-NEXT: or a0, a1, a0
+; RV64IM-NEXT: srli a1, a0, 1
+; RV64IM-NEXT: ld a2, 328(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, a0, a2
+; RV64IM-NEXT: and a1, a1, a7
+; RV64IM-NEXT: slli a0, a0, 1
+; RV64IM-NEXT: or a0, a1, a0
+; RV64IM-NEXT: srli a0, a0, 1
+; RV64IM-NEXT: ld ra, 440(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s0, 432(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s1, 424(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s2, 416(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s3, 408(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s4, 400(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s5, 392(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s6, 384(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s7, 376(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s8, 368(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s9, 360(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s10, 352(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s11, 344(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: addi sp, sp, 448
+; RV64IM-NEXT: ret
+ %res = call i32 @llvm.clmulh.i32(i32 %a, i32 %b)
+ ret i32 %res
+}
+
+define i64 @clmulh_i64(i64 %a, i64 %b) nounwind {
+; RV32IM-LABEL: clmulh_i64:
+; RV32IM: # %bb.0:
+; RV32IM-NEXT: addi sp, sp, -512
+; RV32IM-NEXT: sw ra, 508(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s0, 504(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s1, 500(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s2, 496(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s3, 492(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s4, 488(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s5, 484(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s6, 480(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s7, 476(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s8, 472(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s9, 468(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s10, 464(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: sw s11, 460(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: srli a4, a0, 8
+; RV32IM-NEXT: lui s7, 16
+; RV32IM-NEXT: srli a6, a0, 24
+; RV32IM-NEXT: slli a7, a0, 24
+; RV32IM-NEXT: lui t3, 61681
+; RV32IM-NEXT: lui t0, 209715
+; RV32IM-NEXT: lui s3, 349525
+; RV32IM-NEXT: srli t5, a1, 8
+; RV32IM-NEXT: srli t6, a1, 24
+; RV32IM-NEXT: slli t4, a1, 24
+; RV32IM-NEXT: li s0, 1
+; RV32IM-NEXT: lui s8, 1
+; RV32IM-NEXT: lui t1, 2
+; RV32IM-NEXT: lui t2, 4
+; RV32IM-NEXT: lui a5, 8
+; RV32IM-NEXT: lui s9, 32
+; RV32IM-NEXT: lui a3, 64
+; RV32IM-NEXT: lui s1, 128
+; RV32IM-NEXT: lui a2, 256
+; RV32IM-NEXT: lui s2, 524288
+; RV32IM-NEXT: addi s6, s7, -256
+; RV32IM-NEXT: sw s6, 400(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: addi s5, t3, -241
+; RV32IM-NEXT: addi s4, t0, 819
+; RV32IM-NEXT: addi t3, s3, 1365
+; RV32IM-NEXT: slli s0, s0, 11
+; RV32IM-NEXT: and a4, a4, s6
+; RV32IM-NEXT: and a0, a0, s6
+; RV32IM-NEXT: and t0, t5, s6
+; RV32IM-NEXT: and a1, a1, s6
+; RV32IM-NEXT: or a4, a4, a6
+; RV32IM-NEXT: slli a0, a0, 8
+; RV32IM-NEXT: or a6, t0, t6
+; RV32IM-NEXT: slli a1, a1, 8
+; RV32IM-NEXT: or a0, a7, a0
+; RV32IM-NEXT: or a1, t4, a1
+; RV32IM-NEXT: or a0, a0, a4
+; RV32IM-NEXT: or a1, a1, a6
+; RV32IM-NEXT: srli a4, a0, 4
+; RV32IM-NEXT: sw s5, 404(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a0, a0, s5
+; RV32IM-NEXT: srli a6, a1, 4
+; RV32IM-NEXT: and a1, a1, s5
+; RV32IM-NEXT: and a4, a4, s5
+; RV32IM-NEXT: slli a0, a0, 4
+; RV32IM-NEXT: and a6, a6, s5
+; RV32IM-NEXT: slli a1, a1, 4
+; RV32IM-NEXT: or a0, a4, a0
+; RV32IM-NEXT: or a1, a6, a1
+; RV32IM-NEXT: srli a4, a0, 2
+; RV32IM-NEXT: sw s4, 408(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a0, a0, s4
+; RV32IM-NEXT: srli a6, a1, 2
+; RV32IM-NEXT: and a1, a1, s4
+; RV32IM-NEXT: and a4, a4, s4
+; RV32IM-NEXT: slli a0, a0, 2
+; RV32IM-NEXT: and a6, a6, s4
+; RV32IM-NEXT: slli a1, a1, 2
+; RV32IM-NEXT: or a0, a4, a0
+; RV32IM-NEXT: or a1, a6, a1
+; RV32IM-NEXT: srli a4, a0, 1
+; RV32IM-NEXT: sw t3, 412(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a0, a0, t3
+; RV32IM-NEXT: srli a6, a1, 1
+; RV32IM-NEXT: and a1, a1, t3
+; RV32IM-NEXT: and a4, a4, t3
+; RV32IM-NEXT: slli a0, a0, 1
+; RV32IM-NEXT: and a6, a6, t3
+; RV32IM-NEXT: slli a7, a1, 1
+; RV32IM-NEXT: or a1, a4, a0
+; RV32IM-NEXT: or a0, a6, a7
+; RV32IM-NEXT: and a4, a0, s0
+; RV32IM-NEXT: sw a4, 440(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and ra, a0, s8
+; RV32IM-NEXT: and a4, a0, t1
+; RV32IM-NEXT: sw a4, 156(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a4, a0, t2
+; RV32IM-NEXT: sw a4, 420(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a4, a0, a5
+; RV32IM-NEXT: sw a4, 424(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a4, a0, s7
+; RV32IM-NEXT: sw a4, 432(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a4, a0, s9
+; RV32IM-NEXT: sw a4, 436(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a4, a0, a3
+; RV32IM-NEXT: sw a4, 448(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a4, a0, s1
+; RV32IM-NEXT: sw a4, 444(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a4, a0, a2
+; RV32IM-NEXT: sw a4, 452(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a4, a0, s2
+; RV32IM-NEXT: sw a4, 456(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and s0, a1, s0
+; RV32IM-NEXT: sw s0, 388(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a4, a1, s8
+; RV32IM-NEXT: sw a4, 384(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a4, a1, t1
+; RV32IM-NEXT: sw a4, 376(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a4, a1, t2
+; RV32IM-NEXT: sw a4, 372(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a5, a1, a5
+; RV32IM-NEXT: sw a5, 352(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a4, a1, s7
+; RV32IM-NEXT: sw a4, 340(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a4, a1, s9
+; RV32IM-NEXT: sw a4, 336(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a3, a1, a3
+; RV32IM-NEXT: sw a3, 328(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and s1, a1, s1
+; RV32IM-NEXT: sw s1, 324(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a2, a1, a2
+; RV32IM-NEXT: sw a2, 316(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lui a2, 512
+; RV32IM-NEXT: and s10, a0, a2
+; RV32IM-NEXT: and a2, a1, a2
+; RV32IM-NEXT: sw a2, 184(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lui a2, 1024
+; RV32IM-NEXT: and a3, a0, a2
+; RV32IM-NEXT: sw a3, 428(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a2, a1, a2
+; RV32IM-NEXT: sw a2, 180(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lui a2, 2048
+; RV32IM-NEXT: and s11, a0, a2
+; RV32IM-NEXT: sw s11, 104(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a2, a1, a2
+; RV32IM-NEXT: sw a2, 148(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lui a2, 4096
+; RV32IM-NEXT: and a3, a0, a2
+; RV32IM-NEXT: sw a3, 68(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a2, a1, a2
+; RV32IM-NEXT: sw a2, 144(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lui a2, 8192
+; RV32IM-NEXT: and a3, a0, a2
+; RV32IM-NEXT: sw a3, 416(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a2, a1, a2
+; RV32IM-NEXT: sw a2, 140(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lui s0, 16384
+; RV32IM-NEXT: and t6, a0, s0
+; RV32IM-NEXT: sw t6, 132(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and s0, a1, s0
+; RV32IM-NEXT: sw s0, 128(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lui a2, 32768
+; RV32IM-NEXT: and a3, a0, a2
+; RV32IM-NEXT: sw a3, 20(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a2, a1, a2
+; RV32IM-NEXT: sw a2, 120(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lui s1, 65536
+; RV32IM-NEXT: and t5, a0, s1
+; RV32IM-NEXT: and s1, a1, s1
+; RV32IM-NEXT: sw s1, 116(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lui a2, 131072
+; RV32IM-NEXT: and t4, a0, a2
+; RV32IM-NEXT: sw t4, 92(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a2, a1, a2
+; RV32IM-NEXT: sw a2, 108(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lui a2, 262144
+; RV32IM-NEXT: and t3, a0, a2
+; RV32IM-NEXT: sw t3, 136(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: and a2, a1, a2
+; RV32IM-NEXT: sw a2, 96(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi a7, a0, 4
+; RV32IM-NEXT: sw a7, 112(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi s0, a0, 2
+; RV32IM-NEXT: andi t1, a0, 1
+; RV32IM-NEXT: andi s3, a0, 8
+; RV32IM-NEXT: andi t0, a0, 16
+; RV32IM-NEXT: andi a6, a0, 32
+; RV32IM-NEXT: sw a6, 88(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi a5, a0, 64
+; RV32IM-NEXT: sw a5, 84(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi a4, a0, 128
+; RV32IM-NEXT: sw a4, 100(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi a2, a0, 256
+; RV32IM-NEXT: sw a2, 124(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi a3, a0, 512
+; RV32IM-NEXT: andi t2, a0, 1024
+; RV32IM-NEXT: andi s2, a1, 1
+; RV32IM-NEXT: andi s4, a1, 2
+; RV32IM-NEXT: andi s5, a1, 4
+; RV32IM-NEXT: andi s9, a1, 8
+; RV32IM-NEXT: andi s8, a1, 16
+; RV32IM-NEXT: andi s1, a1, 32
+; RV32IM-NEXT: sw s1, 364(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi s1, a1, 64
+; RV32IM-NEXT: sw s1, 360(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi s1, a1, 128
+; RV32IM-NEXT: sw s1, 344(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi s7, a1, 256
+; RV32IM-NEXT: andi s1, a1, 512
+; RV32IM-NEXT: sw s1, 332(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: andi s1, a1, 1024
+; RV32IM-NEXT: mul s6, a1, a7
+; RV32IM-NEXT: sw s6, 308(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul s6, a1, s0
+; RV32IM-NEXT: sw s6, 304(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul s6, a1, t1
+; RV32IM-NEXT: mv a7, t1
+; RV32IM-NEXT: sw s6, 348(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul s6, a1, s3
+; RV32IM-NEXT: sw s6, 300(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul s6, a1, t0
+; RV32IM-NEXT: sw s6, 296(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul s6, a1, a6
+; RV32IM-NEXT: sw s6, 292(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul s6, a1, a5
+; RV32IM-NEXT: sw s6, 288(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul s6, a1, a4
+; RV32IM-NEXT: sw s6, 284(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul s6, a1, a2
+; RV32IM-NEXT: sw s6, 280(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul s6, a1, a3
+; RV32IM-NEXT: mv a2, a3
+; RV32IM-NEXT: sw s6, 276(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul s6, a1, t2
+; RV32IM-NEXT: mv t1, t2
+; RV32IM-NEXT: sw s6, 272(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw s6, 440(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s6, a1, s6
+; RV32IM-NEXT: sw s6, 268(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul s6, a1, ra
+; RV32IM-NEXT: sw s6, 264(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mv a4, ra
+; RV32IM-NEXT: lw s6, 156(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul ra, a1, s6
+; RV32IM-NEXT: sw ra, 260(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw ra, 420(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul ra, a1, ra
+; RV32IM-NEXT: sw ra, 256(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw ra, 424(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul ra, a1, ra
+; RV32IM-NEXT: sw ra, 252(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw ra, 432(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul ra, a1, ra
+; RV32IM-NEXT: sw ra, 248(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw ra, 436(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul ra, a1, ra
+; RV32IM-NEXT: sw ra, 244(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw ra, 448(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul ra, a1, ra
+; RV32IM-NEXT: sw ra, 240(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw ra, 444(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul ra, a1, ra
+; RV32IM-NEXT: sw ra, 236(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw ra, 452(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul ra, a1, ra
+; RV32IM-NEXT: sw ra, 232(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul ra, a1, s10
+; RV32IM-NEXT: sw ra, 228(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mv a3, s10
+; RV32IM-NEXT: lw s10, 428(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s10, a1, s10
+; RV32IM-NEXT: sw s10, 224(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul s10, a1, s11
+; RV32IM-NEXT: sw s10, 220(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw s10, 68(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s11, a1, s10
+; RV32IM-NEXT: sw s11, 216(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw s11, 416(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul s11, a1, s11
+; RV32IM-NEXT: sw s11, 212(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul s11, a1, t6
+; RV32IM-NEXT: sw s11, 208(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw s11, 20(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a6, a1, s11
+; RV32IM-NEXT: sw a6, 204(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a6, a1, t5
+; RV32IM-NEXT: sw a6, 200(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mv a6, t5
+; RV32IM-NEXT: mul a5, a1, t4
+; RV32IM-NEXT: sw a5, 196(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a5, a1, t3
+; RV32IM-NEXT: sw a5, 192(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw ra, 456(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a1, a1, ra
+; RV32IM-NEXT: sw a1, 188(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a1, a0, s2
+; RV32IM-NEXT: sw a1, 356(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a1, a0, s4
+; RV32IM-NEXT: sw a1, 368(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a1, a0, s5
+; RV32IM-NEXT: sw a1, 380(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a1, a0, s9
+; RV32IM-NEXT: sw a1, 392(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a1, a0, s8
+; RV32IM-NEXT: sw a1, 396(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 364(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 176(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 360(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 172(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 344(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 320(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a1, a0, s7
+; RV32IM-NEXT: sw a1, 168(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 332(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 164(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a1, a0, s1
+; RV32IM-NEXT: sw a1, 312(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 388(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 332(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 384(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 344(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 376(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 360(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 372(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 364(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 352(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 372(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 340(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 376(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 336(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 384(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 328(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 388(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 324(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 160(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 316(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 152(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 184(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 184(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 180(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 324(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 148(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 336(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 144(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 144(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 140(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 140(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 128(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 180(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 120(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 316(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 116(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 328(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 108(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 340(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 96(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 352(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mulhu t2, a0, s0
+; RV32IM-NEXT: mul a1, a0, s0
+; RV32IM-NEXT: sw a1, 120(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a1, a0, a7
+; RV32IM-NEXT: sw a1, 116(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 112(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mulhu t3, a0, a1
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 112(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mulhu t4, a0, s3
+; RV32IM-NEXT: mul a1, a0, s3
+; RV32IM-NEXT: sw a1, 108(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mulhu t5, a0, t0
+; RV32IM-NEXT: mul a1, a0, t0
+; RV32IM-NEXT: sw a1, 96(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 88(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mulhu t6, a0, a1
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 88(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 84(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mulhu s0, a0, a1
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 128(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 100(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mulhu s1, a0, a1
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 148(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 124(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mulhu a5, a0, a1
+; RV32IM-NEXT: sw a5, 64(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 84(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mv a1, a2
+; RV32IM-NEXT: mulhu a2, a0, a2
+; RV32IM-NEXT: sw a2, 60(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 80(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mulhu a2, a0, t1
+; RV32IM-NEXT: sw a2, 52(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a1, a0, t1
+; RV32IM-NEXT: sw a1, 100(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 440(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mulhu a2, a0, a1
+; RV32IM-NEXT: sw a2, 44(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 124(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mulhu a2, a0, a4
+; RV32IM-NEXT: sw a2, 40(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a1, a0, a4
+; RV32IM-NEXT: sw a1, 440(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mulhu a2, a0, s6
+; RV32IM-NEXT: sw a2, 36(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a1, a0, s6
+; RV32IM-NEXT: sw a1, 156(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 420(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mulhu a2, a0, a1
+; RV32IM-NEXT: sw a2, 32(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 76(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 424(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mulhu a2, a0, a1
+; RV32IM-NEXT: sw a2, 28(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 424(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 432(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mulhu a2, a0, a1
+; RV32IM-NEXT: sw a2, 24(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 432(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 436(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mulhu a2, a0, a1
+; RV32IM-NEXT: sw a2, 16(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 436(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 448(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mulhu a2, a0, a1
+; RV32IM-NEXT: sw a2, 12(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 448(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a2, 444(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mulhu a1, a0, a2
+; RV32IM-NEXT: sw a1, 8(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mul a1, a0, a2
+; RV32IM-NEXT: sw a1, 56(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a2, 452(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mulhu ra, a0, a2
+; RV32IM-NEXT: mul a1, a0, a2
+; RV32IM-NEXT: sw a1, 48(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mulhu a5, a0, a3
+; RV32IM-NEXT: mul a1, a0, a3
+; RV32IM-NEXT: sw a1, 72(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 428(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mulhu s9, a0, a1
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 428(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 104(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mulhu s6, a0, a1
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 452(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mulhu a7, a0, s10
+; RV32IM-NEXT: mul a1, a0, s10
+; RV32IM-NEXT: sw a1, 68(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 416(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mulhu s3, a0, a1
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 4(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 132(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mulhu a3, a0, a1
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 104(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mulhu a2, a0, s11
+; RV32IM-NEXT: mul a1, a0, s11
+; RV32IM-NEXT: sw a1, 132(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: mulhu t0, a0, a6
+; RV32IM-NEXT: mul a1, a0, a6
+; RV32IM-NEXT: sw a1, 416(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 92(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mulhu a6, a0, a1
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 420(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a1, 136(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mulhu a4, a0, a1
+; RV32IM-NEXT: mul a1, a0, a1
+; RV32IM-NEXT: sw a1, 444(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw t1, 456(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: mulhu a1, a0, t1
+; RV32IM-NEXT: mul a0, a0, t1
+; RV32IM-NEXT: sw a0, 456(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a0, 308(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or a0, t3, a0
+; RV32IM-NEXT: sw a0, 20(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a0, 304(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or s5, t2, a0
+; RV32IM-NEXT: lw a0, 300(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or s7, t4, a0
+; RV32IM-NEXT: lw a0, 296(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or s8, t5, a0
+; RV32IM-NEXT: lw a0, 292(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or s4, t6, a0
+; RV32IM-NEXT: lw a0, 288(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or a0, s0, a0
+; RV32IM-NEXT: sw a0, 136(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a0, 284(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or s2, s1, a0
+; RV32IM-NEXT: lw a0, 280(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s1, 64(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or s1, s1, a0
+; RV32IM-NEXT: lw a0, 276(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw t1, 60(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or a0, t1, a0
+; RV32IM-NEXT: sw a0, 92(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a0, 272(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw t1, 52(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or a0, t1, a0
+; RV32IM-NEXT: sw a0, 288(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a0, 268(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw t1, 44(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or t6, t1, a0
+; RV32IM-NEXT: lw a0, 264(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw t1, 40(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or t5, t1, a0
+; RV32IM-NEXT: lw a0, 260(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw t1, 36(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or a0, t1, a0
+; RV32IM-NEXT: sw a0, 268(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a0, 256(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw t1, 32(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or a0, t1, a0
+; RV32IM-NEXT: sw a0, 280(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a0, 252(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw t1, 28(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or a0, t1, a0
+; RV32IM-NEXT: sw a0, 300(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a0, 248(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw t1, 24(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or t4, t1, a0
+; RV32IM-NEXT: lw a0, 244(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw t1, 16(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or t3, t1, a0
+; RV32IM-NEXT: lw a0, 240(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw t1, 12(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or a0, t1, a0
+; RV32IM-NEXT: sw a0, 264(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a0, 236(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw t1, 8(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or a0, t1, a0
+; RV32IM-NEXT: sw a0, 276(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a0, 232(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or a0, ra, a0
+; RV32IM-NEXT: sw a0, 292(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a0, 228(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or a0, a5, a0
+; RV32IM-NEXT: sw a0, 304(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a0, 224(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or s9, s9, a0
+; RV32IM-NEXT: lw a0, 220(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or s6, s6, a0
+; RV32IM-NEXT: lw a0, 216(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or s10, a7, a0
+; RV32IM-NEXT: lw a0, 212(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or a0, s3, a0
+; RV32IM-NEXT: sw a0, 272(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a0, 208(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or a0, a3, a0
+; RV32IM-NEXT: sw a0, 284(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a0, 204(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or a0, a2, a0
+; RV32IM-NEXT: sw a0, 296(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a0, 200(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or a0, t0, a0
+; RV32IM-NEXT: sw a0, 308(sp) # 4-byte Folded Spill
+; RV32IM-NEXT: lw a0, 196(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or t2, a6, a0
+; RV32IM-NEXT: lw a0, 192(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or t1, a4, a0
+; RV32IM-NEXT: lw s0, 188(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: or s0, a1, s0
+; RV32IM-NEXT: lw a0, 176(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw a1, 172(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t0, a0, a1
+; RV32IM-NEXT: lw a0, 168(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw a1, 164(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a6, a0, a1
+; RV32IM-NEXT: lw a0, 160(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw a1, 152(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor s3, a0, a1
+; RV32IM-NEXT: lw a0, 144(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw a1, 140(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor ra, a0, a1
+; RV32IM-NEXT: lw a0, 120(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw a1, 116(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a7, a1, a0
+; RV32IM-NEXT: lw a0, 112(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw a1, 108(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a0, a0, a1
+; RV32IM-NEXT: lw a1, 96(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw a2, 88(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a1, a1, a2
+; RV32IM-NEXT: lw a2, 84(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw a3, 80(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a2, a2, a3
+; RV32IM-NEXT: lw a3, 156(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw a4, 76(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a3, a3, a4
+; RV32IM-NEXT: lw a4, 56(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw a5, 48(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a4, a4, a5
+; RV32IM-NEXT: lw a5, 68(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s11, 4(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a5, a5, s11
+; RV32IM-NEXT: lw s11, 348(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor s5, s11, s5
+; RV32IM-NEXT: lw s11, 20(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor s7, s11, s7
+; RV32IM-NEXT: xor s4, s8, s4
+; RV32IM-NEXT: xor s1, s2, s1
+; RV32IM-NEXT: xor t5, t6, t5
+; RV32IM-NEXT: xor t3, t4, t3
+; RV32IM-NEXT: xor t4, s9, s6
+; RV32IM-NEXT: xor t1, t2, t1
+; RV32IM-NEXT: lw t2, 320(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t0, t0, t2
+; RV32IM-NEXT: lw t2, 312(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a6, a6, t2
+; RV32IM-NEXT: lw t2, 184(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t2, s3, t2
+; RV32IM-NEXT: lw t6, 180(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t6, ra, t6
+; RV32IM-NEXT: xor a0, a7, a0
+; RV32IM-NEXT: lw a7, 128(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a1, a1, a7
+; RV32IM-NEXT: lw a7, 100(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a2, a2, a7
+; RV32IM-NEXT: lw a7, 424(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a3, a3, a7
+; RV32IM-NEXT: lw a7, 72(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a4, a4, a7
+; RV32IM-NEXT: lw a7, 104(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a5, a5, a7
+; RV32IM-NEXT: xor a7, s5, s7
+; RV32IM-NEXT: lw s2, 136(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor s2, s4, s2
+; RV32IM-NEXT: lw s3, 92(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor s1, s1, s3
+; RV32IM-NEXT: lw s3, 268(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t5, t5, s3
+; RV32IM-NEXT: lw s3, 264(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t3, t3, s3
+; RV32IM-NEXT: xor t4, t4, s10
+; RV32IM-NEXT: xor t1, t1, s0
+; RV32IM-NEXT: lw s0, 332(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a6, a6, s0
+; RV32IM-NEXT: lw s0, 324(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t2, t2, s0
+; RV32IM-NEXT: lw s0, 316(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t6, t6, s0
+; RV32IM-NEXT: xor a0, a0, a1
+; RV32IM-NEXT: lw a1, 124(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a1, a2, a1
+; RV32IM-NEXT: lw a2, 432(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a2, a3, a2
+; RV32IM-NEXT: lw a3, 428(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a3, a4, a3
+; RV32IM-NEXT: lw a4, 132(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a4, a5, a4
+; RV32IM-NEXT: xor a5, a7, s2
+; RV32IM-NEXT: lw a7, 288(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a7, s1, a7
+; RV32IM-NEXT: lw s0, 280(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t5, t5, s0
+; RV32IM-NEXT: lw s0, 276(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t3, t3, s0
+; RV32IM-NEXT: lw s0, 272(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t4, t4, s0
+; RV32IM-NEXT: lw s0, 356(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t1, t1, s0
+; RV32IM-NEXT: lw s0, 344(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a6, a6, s0
+; RV32IM-NEXT: lw s0, 336(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t2, t2, s0
+; RV32IM-NEXT: lw s0, 328(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t6, t6, s0
+; RV32IM-NEXT: lw s0, 148(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a0, a0, s0
+; RV32IM-NEXT: lw s0, 440(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a1, a1, s0
+; RV32IM-NEXT: lw s0, 436(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a2, a2, s0
+; RV32IM-NEXT: lw s0, 452(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a3, a3, s0
+; RV32IM-NEXT: lw s0, 416(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a4, a4, s0
+; RV32IM-NEXT: xor a5, a5, a7
+; RV32IM-NEXT: lw a7, 300(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a7, t5, a7
+; RV32IM-NEXT: lw t5, 292(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t3, t3, t5
+; RV32IM-NEXT: lw t5, 284(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t4, t4, t5
+; RV32IM-NEXT: lw t5, 368(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t1, t1, t5
+; RV32IM-NEXT: lw t5, 360(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a6, a6, t5
+; RV32IM-NEXT: lw t5, 340(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t5, t6, t5
+; RV32IM-NEXT: lw t6, 448(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a2, a2, t6
+; RV32IM-NEXT: lw t6, 420(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a4, a4, t6
+; RV32IM-NEXT: xor a5, a5, a7
+; RV32IM-NEXT: lw a7, 304(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a7, t3, a7
+; RV32IM-NEXT: lw t3, 296(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t3, t4, t3
+; RV32IM-NEXT: lw t4, 380(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t1, t1, t4
+; RV32IM-NEXT: lw t4, 364(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a6, a6, t4
+; RV32IM-NEXT: lw t4, 352(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor t4, t5, t4
+; RV32IM-NEXT: xor a1, a0, a1
+; RV32IM-NEXT: xor a1, a1, a2
+; RV32IM-NEXT: lw a2, 444(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a2, a4, a2
+; RV32IM-NEXT: xor a4, a5, a7
+; RV32IM-NEXT: lw a5, 308(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a5, t3, a5
+; RV32IM-NEXT: lw a7, 392(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a7, t1, a7
+; RV32IM-NEXT: lw t1, 372(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a6, a6, t1
+; RV32IM-NEXT: xor a1, a1, a3
+; RV32IM-NEXT: lw a3, 456(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a2, a2, a3
+; RV32IM-NEXT: xor a4, a4, a5
+; RV32IM-NEXT: lw a3, 396(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a3, a7, a3
+; RV32IM-NEXT: lw a5, 376(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a5, a6, a5
+; RV32IM-NEXT: xor a3, a4, a3
+; RV32IM-NEXT: lw a4, 384(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a4, a5, a4
+; RV32IM-NEXT: xor a3, a3, t0
+; RV32IM-NEXT: slli a0, a0, 24
+; RV32IM-NEXT: lw a5, 388(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: xor a4, a4, a5
+; RV32IM-NEXT: lw a6, 400(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: and a5, a1, a6
+; RV32IM-NEXT: slli a5, a5, 8
+; RV32IM-NEXT: or a0, a0, a5
+; RV32IM-NEXT: xor a2, a1, a2
+; RV32IM-NEXT: srli a1, a1, 8
+; RV32IM-NEXT: and a1, a1, a6
+; RV32IM-NEXT: srli a2, a2, 24
+; RV32IM-NEXT: or a1, a1, a2
+; RV32IM-NEXT: or a0, a0, a1
+; RV32IM-NEXT: xor a4, a3, a4
+; RV32IM-NEXT: xor a1, a4, t2
+; RV32IM-NEXT: and a2, a1, a6
+; RV32IM-NEXT: xor a4, a1, t4
+; RV32IM-NEXT: srli a1, a1, 8
+; RV32IM-NEXT: and a1, a1, a6
+; RV32IM-NEXT: srli a5, a0, 4
+; RV32IM-NEXT: lw a6, 404(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: and a0, a0, a6
+; RV32IM-NEXT: and a5, a5, a6
+; RV32IM-NEXT: slli a0, a0, 4
+; RV32IM-NEXT: or a0, a5, a0
+; RV32IM-NEXT: slli a3, a3, 24
+; RV32IM-NEXT: slli a2, a2, 8
+; RV32IM-NEXT: or a2, a3, a2
+; RV32IM-NEXT: srli a4, a4, 24
+; RV32IM-NEXT: or a1, a1, a4
+; RV32IM-NEXT: lui a3, 349525
+; RV32IM-NEXT: addi a3, a3, 1364
+; RV32IM-NEXT: or a1, a2, a1
+; RV32IM-NEXT: srli a2, a0, 2
+; RV32IM-NEXT: lw a5, 408(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: and a0, a0, a5
+; RV32IM-NEXT: and a2, a2, a5
+; RV32IM-NEXT: slli a0, a0, 2
+; RV32IM-NEXT: or a0, a2, a0
+; RV32IM-NEXT: srli a2, a1, 4
+; RV32IM-NEXT: and a1, a1, a6
+; RV32IM-NEXT: and a2, a2, a6
+; RV32IM-NEXT: slli a1, a1, 4
+; RV32IM-NEXT: srli a4, a0, 1
+; RV32IM-NEXT: lw a6, 412(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: and a0, a0, a6
+; RV32IM-NEXT: or a1, a2, a1
+; RV32IM-NEXT: and a2, a4, a3
+; RV32IM-NEXT: slli a0, a0, 1
+; RV32IM-NEXT: or a2, a2, a0
+; RV32IM-NEXT: srli a0, a1, 2
+; RV32IM-NEXT: and a1, a1, a5
+; RV32IM-NEXT: and a0, a0, a5
+; RV32IM-NEXT: slli a1, a1, 2
+; RV32IM-NEXT: or a0, a0, a1
+; RV32IM-NEXT: and a1, a0, a6
+; RV32IM-NEXT: srli a0, a0, 1
+; RV32IM-NEXT: and a0, a0, a3
+; RV32IM-NEXT: slli a1, a1, 1
+; RV32IM-NEXT: or a0, a0, a1
+; RV32IM-NEXT: slli a4, a4, 31
+; RV32IM-NEXT: srli a0, a0, 1
+; RV32IM-NEXT: or a0, a0, a4
+; RV32IM-NEXT: srli a1, a2, 1
+; RV32IM-NEXT: lw ra, 508(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s0, 504(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s1, 500(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s2, 496(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s3, 492(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s4, 488(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s5, 484(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s6, 480(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s7, 476(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s8, 472(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s9, 468(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s10, 464(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: lw s11, 460(sp) # 4-byte Folded Reload
+; RV32IM-NEXT: addi sp, sp, 512
+; RV32IM-NEXT: ret
+;
+; RV64IM-LABEL: clmulh_i64:
+; RV64IM: # %bb.0:
+; RV64IM-NEXT: addi sp, sp, -448
+; RV64IM-NEXT: sd ra, 440(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s0, 432(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s1, 424(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s2, 416(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s3, 408(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s4, 400(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s5, 392(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s6, 384(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s7, 376(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s8, 368(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s9, 360(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s10, 352(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s11, 344(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: srli a2, a0, 24
+; RV64IM-NEXT: srli a6, a0, 8
+; RV64IM-NEXT: li a3, 255
+; RV64IM-NEXT: srli a5, a0, 40
+; RV64IM-NEXT: lui s2, 16
+; RV64IM-NEXT: srli s5, a0, 56
+; RV64IM-NEXT: srliw t2, a0, 24
+; RV64IM-NEXT: slli t0, a0, 56
+; RV64IM-NEXT: lui t3, 61681
+; RV64IM-NEXT: lui t4, 209715
+; RV64IM-NEXT: lui t6, 349525
+; RV64IM-NEXT: li a7, 1
+; RV64IM-NEXT: lui s4, 2
+; RV64IM-NEXT: lui t1, 4
+; RV64IM-NEXT: lui a4, 128
+; RV64IM-NEXT: lui s7, 256
+; RV64IM-NEXT: lui s8, 4096
+; RV64IM-NEXT: lui s10, 8192
+; RV64IM-NEXT: lui a1, 4080
+; RV64IM-NEXT: and a2, a2, a1
+; RV64IM-NEXT: slli a3, a3, 24
+; RV64IM-NEXT: sd a3, 336(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: addi s0, s2, -256
+; RV64IM-NEXT: and t5, a0, a1
+; RV64IM-NEXT: slli a1, t2, 32
+; RV64IM-NEXT: addi s9, t3, -241
+; RV64IM-NEXT: addi t4, t4, 819
+; RV64IM-NEXT: addi t2, t6, 1365
+; RV64IM-NEXT: slli t3, a7, 11
+; RV64IM-NEXT: slli s11, a7, 32
+; RV64IM-NEXT: slli ra, a7, 33
+; RV64IM-NEXT: slli t6, a7, 34
+; RV64IM-NEXT: slli s1, a7, 35
+; RV64IM-NEXT: slli s3, a7, 36
+; RV64IM-NEXT: and a3, a6, a3
+; RV64IM-NEXT: or a2, a3, a2
+; RV64IM-NEXT: slli a3, a7, 37
+; RV64IM-NEXT: sd a3, 256(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: sd s0, 304(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a3, a5, s0
+; RV64IM-NEXT: or a3, a3, s5
+; RV64IM-NEXT: slli a5, a7, 38
+; RV64IM-NEXT: sd a5, 240(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli t5, t5, 24
+; RV64IM-NEXT: and a0, a0, s0
+; RV64IM-NEXT: or a1, t5, a1
+; RV64IM-NEXT: slli a5, s9, 32
+; RV64IM-NEXT: add a5, s9, a5
+; RV64IM-NEXT: slli s0, t4, 32
+; RV64IM-NEXT: add t4, t4, s0
+; RV64IM-NEXT: slli s5, t2, 32
+; RV64IM-NEXT: slli a0, a0, 40
+; RV64IM-NEXT: add t2, t2, s5
+; RV64IM-NEXT: or a2, a2, a3
+; RV64IM-NEXT: or a0, t0, a0
+; RV64IM-NEXT: or a0, a0, a1
+; RV64IM-NEXT: or a0, a0, a2
+; RV64IM-NEXT: srli a1, a0, 4
+; RV64IM-NEXT: sd a5, 312(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, a0, a5
+; RV64IM-NEXT: and a1, a1, a5
+; RV64IM-NEXT: slli a0, a0, 4
+; RV64IM-NEXT: or a0, a1, a0
+; RV64IM-NEXT: srli a1, a0, 2
+; RV64IM-NEXT: sd t4, 320(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, a0, t4
+; RV64IM-NEXT: and a1, a1, t4
+; RV64IM-NEXT: slli a0, a0, 2
+; RV64IM-NEXT: or a0, a1, a0
+; RV64IM-NEXT: srli a1, a0, 1
+; RV64IM-NEXT: sd t2, 328(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, a0, t2
+; RV64IM-NEXT: and a1, a1, t2
+; RV64IM-NEXT: slli a0, a0, 1
+; RV64IM-NEXT: or t0, a1, a0
+; RV64IM-NEXT: andi a0, t0, 2
+; RV64IM-NEXT: andi a1, t0, 1
+; RV64IM-NEXT: andi a2, t0, 4
+; RV64IM-NEXT: andi a3, t0, 8
+; RV64IM-NEXT: andi a5, t0, 16
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: xor a0, a1, a0
+; RV64IM-NEXT: sd a0, 296(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi a0, t0, 32
+; RV64IM-NEXT: mul a1, t0, a2
+; RV64IM-NEXT: mul a2, t0, a3
+; RV64IM-NEXT: xor a1, a1, a2
+; RV64IM-NEXT: sd a1, 288(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi a1, t0, 256
+; RV64IM-NEXT: mul a2, t0, a5
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: xor a0, a2, a0
+; RV64IM-NEXT: sd a0, 280(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi a0, t0, 512
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: xor a0, a1, a0
+; RV64IM-NEXT: sd a0, 272(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli t4, a7, 39
+; RV64IM-NEXT: and a0, t0, s4
+; RV64IM-NEXT: and a1, t0, t1
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: xor a0, a0, a1
+; RV64IM-NEXT: sd a0, 264(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 40
+; RV64IM-NEXT: and a1, t0, a4
+; RV64IM-NEXT: and a2, t0, s7
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: xor a1, a1, a2
+; RV64IM-NEXT: sd a1, 248(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a1, a7, 41
+; RV64IM-NEXT: and a2, t0, s8
+; RV64IM-NEXT: and a3, t0, s10
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: mul a3, t0, a3
+; RV64IM-NEXT: xor a2, a2, a3
+; RV64IM-NEXT: sd a2, 232(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a2, a7, 48
+; RV64IM-NEXT: and a3, t0, s11
+; RV64IM-NEXT: and a4, t0, ra
+; RV64IM-NEXT: mul a3, t0, a3
+; RV64IM-NEXT: mul a4, t0, a4
+; RV64IM-NEXT: xor a3, a3, a4
+; RV64IM-NEXT: sd a3, 224(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a3, a7, 49
+; RV64IM-NEXT: and a0, t0, a0
+; RV64IM-NEXT: and a1, t0, a1
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: xor a0, a0, a1
+; RV64IM-NEXT: sd a0, 216(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 56
+; RV64IM-NEXT: and a1, t0, a2
+; RV64IM-NEXT: and a2, t0, a3
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: xor a1, a1, a2
+; RV64IM-NEXT: sd a1, 208(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a1, a7, 57
+; RV64IM-NEXT: and a0, t0, a0
+; RV64IM-NEXT: and a1, t0, a1
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: mul a1, t0, a1
+; RV64IM-NEXT: xor a0, a0, a1
+; RV64IM-NEXT: sd a0, 200(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a2, a7, 42
+; RV64IM-NEXT: slli ra, a7, 43
+; RV64IM-NEXT: slli a3, a7, 44
+; RV64IM-NEXT: slli a4, a7, 45
+; RV64IM-NEXT: slli t5, a7, 46
+; RV64IM-NEXT: slli s0, a7, 47
+; RV64IM-NEXT: slli a0, a7, 50
+; RV64IM-NEXT: sd a0, 192(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 51
+; RV64IM-NEXT: sd a0, 184(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 52
+; RV64IM-NEXT: sd a0, 176(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 53
+; RV64IM-NEXT: sd a0, 168(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 54
+; RV64IM-NEXT: sd a0, 160(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 55
+; RV64IM-NEXT: sd a0, 152(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 58
+; RV64IM-NEXT: sd a0, 144(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 59
+; RV64IM-NEXT: sd a0, 136(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 60
+; RV64IM-NEXT: sd a0, 120(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a0, a7, 61
+; RV64IM-NEXT: sd a0, 80(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: slli a7, a7, 62
+; RV64IM-NEXT: sd a7, 48(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, t0, t3
+; RV64IM-NEXT: sd a0, 128(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s7, 1
+; RV64IM-NEXT: and a0, t0, s7
+; RV64IM-NEXT: sd a0, 112(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s8, 8
+; RV64IM-NEXT: and a0, t0, s8
+; RV64IM-NEXT: sd a0, 104(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, t0, s2
+; RV64IM-NEXT: sd a0, 96(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s5, 32
+; RV64IM-NEXT: and a0, t0, s5
+; RV64IM-NEXT: sd a0, 88(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s6, 64
+; RV64IM-NEXT: and a0, t0, s6
+; RV64IM-NEXT: sd a0, 72(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s10, 512
+; RV64IM-NEXT: and a0, t0, s10
+; RV64IM-NEXT: sd a0, 64(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s4, 1024
+; RV64IM-NEXT: and a0, t0, s4
+; RV64IM-NEXT: sd a0, 56(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s9, 2048
+; RV64IM-NEXT: and a0, t0, s9
+; RV64IM-NEXT: sd a0, 40(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui s11, 16384
+; RV64IM-NEXT: and a0, t0, s11
+; RV64IM-NEXT: sd a0, 32(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: lui a5, 32768
+; RV64IM-NEXT: and a5, t0, a5
+; RV64IM-NEXT: lui a6, 65536
+; RV64IM-NEXT: and a6, t0, a6
+; RV64IM-NEXT: lui t1, 131072
+; RV64IM-NEXT: and t1, t0, t1
+; RV64IM-NEXT: lui t2, 262144
+; RV64IM-NEXT: and t2, t0, t2
+; RV64IM-NEXT: and a0, t0, t6
+; RV64IM-NEXT: sd a0, 24(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, t0, s1
+; RV64IM-NEXT: sd a0, 16(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: and a0, t0, s3
+; RV64IM-NEXT: sd a0, 8(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a0, 256(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, t0, a0
+; RV64IM-NEXT: sd a0, 0(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a0, 240(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, t0, a0
+; RV64IM-NEXT: and a1, t0, t4
+; RV64IM-NEXT: and a7, t0, a2
+; RV64IM-NEXT: and ra, t0, ra
+; RV64IM-NEXT: and t3, t0, a3
+; RV64IM-NEXT: and t4, t0, a4
+; RV64IM-NEXT: and t5, t0, t5
+; RV64IM-NEXT: and t6, t0, s0
+; RV64IM-NEXT: ld a2, 192(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s0, t0, a2
+; RV64IM-NEXT: ld a2, 184(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s1, t0, a2
+; RV64IM-NEXT: ld a2, 176(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s2, t0, a2
+; RV64IM-NEXT: ld a2, 168(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s3, t0, a2
+; RV64IM-NEXT: ld a2, 160(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s4, t0, a2
+; RV64IM-NEXT: ld a2, 152(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s5, t0, a2
+; RV64IM-NEXT: ld a2, 144(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s6, t0, a2
+; RV64IM-NEXT: ld a2, 136(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s7, t0, a2
+; RV64IM-NEXT: ld a2, 120(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s8, t0, a2
+; RV64IM-NEXT: ld a2, 80(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s9, t0, a2
+; RV64IM-NEXT: ld a2, 48(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and s10, t0, a2
+; RV64IM-NEXT: andi s11, t0, 64
+; RV64IM-NEXT: mul a2, t0, s11
+; RV64IM-NEXT: sd a2, 80(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi s11, t0, 128
+; RV64IM-NEXT: mul a2, t0, s11
+; RV64IM-NEXT: sd a2, 192(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: andi s11, t0, 1024
+; RV64IM-NEXT: mul a2, t0, s11
+; RV64IM-NEXT: sd a2, 48(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 128(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 120(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 112(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 176(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 104(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul s11, t0, a2
+; RV64IM-NEXT: ld a2, 96(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 104(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 88(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 168(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 72(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 256(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 64(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a4, t0, a2
+; RV64IM-NEXT: ld a2, 56(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 96(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 40(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: sd a2, 136(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: ld a2, 32(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a3, t0, a2
+; RV64IM-NEXT: mul a2, t0, a5
+; RV64IM-NEXT: sd a2, 88(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a2, t0, a6
+; RV64IM-NEXT: sd a2, 128(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a2, t0, t1
+; RV64IM-NEXT: sd a2, 160(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a2, t0, t2
+; RV64IM-NEXT: sd a2, 240(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: srliw t2, t0, 31
+; RV64IM-NEXT: slli t2, t2, 31
+; RV64IM-NEXT: ld a2, 24(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a2, t0, a2
+; RV64IM-NEXT: ld a5, 16(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a5, t0, a5
+; RV64IM-NEXT: ld a6, 8(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul t1, t0, a6
+; RV64IM-NEXT: ld a6, 0(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: mul a6, t0, a6
+; RV64IM-NEXT: sd a6, 112(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a0, t0, a0
+; RV64IM-NEXT: sd a0, 152(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a0, t0, a1
+; RV64IM-NEXT: sd a0, 184(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul a7, t0, a7
+; RV64IM-NEXT: mul ra, t0, ra
+; RV64IM-NEXT: mul a6, t0, t3
+; RV64IM-NEXT: mul t4, t0, t4
+; RV64IM-NEXT: mul t5, t0, t5
+; RV64IM-NEXT: mul a0, t0, t6
+; RV64IM-NEXT: sd a0, 144(sp) # 8-byte Folded Spill
+; RV64IM-NEXT: mul t6, t0, s0
+; RV64IM-NEXT: mul s0, t0, s1
+; RV64IM-NEXT: mul s1, t0, s2
+; RV64IM-NEXT: mul s2, t0, s3
+; RV64IM-NEXT: mul s3, t0, s4
+; RV64IM-NEXT: mul s4, t0, s5
+; RV64IM-NEXT: mul s5, t0, s6
+; RV64IM-NEXT: mul s6, t0, s7
+; RV64IM-NEXT: mul s7, t0, s8
+; RV64IM-NEXT: mul s8, t0, s9
+; RV64IM-NEXT: mul s9, t0, s10
+; RV64IM-NEXT: srli s10, t0, 63
+; RV64IM-NEXT: slli s10, s10, 63
+; RV64IM-NEXT: mul t2, t0, t2
+; RV64IM-NEXT: mul t0, t0, s10
+; RV64IM-NEXT: ld a0, 296(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld a1, 288(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s10, a0, a1
+; RV64IM-NEXT: ld a0, 280(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld a1, 80(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a0, a0, a1
+; RV64IM-NEXT: ld a1, 272(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld t3, 48(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a1, a1, t3
+; RV64IM-NEXT: ld t3, 264(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s11, t3, s11
+; RV64IM-NEXT: ld t3, 248(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, t3, a4
+; RV64IM-NEXT: ld t3, 232(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, t3, a3
+; RV64IM-NEXT: ld t3, 224(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, t3, a2
+; RV64IM-NEXT: ld t3, 216(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a7, t3, a7
+; RV64IM-NEXT: ld t3, 208(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor t6, t3, t6
+; RV64IM-NEXT: ld t3, 200(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s5, t3, s5
+; RV64IM-NEXT: xor a0, s10, a0
+; RV64IM-NEXT: ld t3, 120(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a1, a1, t3
+; RV64IM-NEXT: ld t3, 104(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s10, s11, t3
+; RV64IM-NEXT: ld t3, 96(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, a4, t3
+; RV64IM-NEXT: ld t3, 88(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a3, t3
+; RV64IM-NEXT: xor a2, a2, a5
+; RV64IM-NEXT: xor a5, a7, ra
+; RV64IM-NEXT: xor a7, t6, s0
+; RV64IM-NEXT: xor t6, s5, s6
+; RV64IM-NEXT: ld t3, 192(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a0, a0, t3
+; RV64IM-NEXT: ld t3, 176(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a1, a1, t3
+; RV64IM-NEXT: ld t3, 168(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor s0, s10, t3
+; RV64IM-NEXT: ld t3, 136(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, a4, t3
+; RV64IM-NEXT: ld t3, 128(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a3, t3
+; RV64IM-NEXT: xor a2, a2, t1
+; RV64IM-NEXT: xor a5, a5, a6
+; RV64IM-NEXT: xor a6, a7, s1
+; RV64IM-NEXT: xor a7, t6, s7
+; RV64IM-NEXT: ld t1, 256(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor t1, s0, t1
+; RV64IM-NEXT: ld t3, 160(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a3, t3
+; RV64IM-NEXT: ld t3, 112(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a2, t3
+; RV64IM-NEXT: xor a5, a5, t4
+; RV64IM-NEXT: xor a6, a6, s2
+; RV64IM-NEXT: xor a7, a7, s8
+; RV64IM-NEXT: xor a1, a0, a1
+; RV64IM-NEXT: xor a1, a1, t1
+; RV64IM-NEXT: ld t1, 240(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a3, a3, t1
+; RV64IM-NEXT: ld t1, 152(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a2, t1
+; RV64IM-NEXT: xor a5, a5, t5
+; RV64IM-NEXT: xor a6, a6, s3
+; RV64IM-NEXT: xor a7, a7, s9
+; RV64IM-NEXT: xor a1, a1, a4
+; RV64IM-NEXT: xor a3, a3, t2
+; RV64IM-NEXT: ld a4, 184(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a2, a2, a4
+; RV64IM-NEXT: ld a4, 144(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: xor a4, a5, a4
+; RV64IM-NEXT: xor a5, a6, s4
+; RV64IM-NEXT: xor a6, a7, t0
+; RV64IM-NEXT: lui a7, %hi(.LCPI18_0)
+; RV64IM-NEXT: ld a7, %lo(.LCPI18_0)(a7)
+; RV64IM-NEXT: slli a0, a0, 56
+; RV64IM-NEXT: xor a3, a1, a3
+; RV64IM-NEXT: ld t1, 304(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a1, a1, t1
+; RV64IM-NEXT: slli a1, a1, 40
+; RV64IM-NEXT: xor a2, a3, a2
+; RV64IM-NEXT: or a0, a0, a1
+; RV64IM-NEXT: lui t0, 4080
+; RV64IM-NEXT: and a1, a2, t0
+; RV64IM-NEXT: xor a4, a2, a4
+; RV64IM-NEXT: srli a2, a2, 8
+; RV64IM-NEXT: slli a1, a1, 24
+; RV64IM-NEXT: xor a5, a4, a5
+; RV64IM-NEXT: ld a3, 336(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a2, a2, a3
+; RV64IM-NEXT: srli a4, a4, 24
+; RV64IM-NEXT: srliw a3, a5, 24
+; RV64IM-NEXT: and a4, a4, t0
+; RV64IM-NEXT: srli t0, a5, 40
+; RV64IM-NEXT: xor a5, a5, a6
+; RV64IM-NEXT: slli a3, a3, 32
+; RV64IM-NEXT: or a2, a2, a4
+; RV64IM-NEXT: and a4, t0, t1
+; RV64IM-NEXT: srli a5, a5, 56
+; RV64IM-NEXT: or a1, a1, a3
+; RV64IM-NEXT: or a4, a4, a5
+; RV64IM-NEXT: or a0, a0, a1
+; RV64IM-NEXT: or a2, a2, a4
+; RV64IM-NEXT: or a0, a0, a2
+; RV64IM-NEXT: srli a1, a0, 4
+; RV64IM-NEXT: ld a2, 312(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, a0, a2
+; RV64IM-NEXT: and a1, a1, a2
+; RV64IM-NEXT: slli a0, a0, 4
+; RV64IM-NEXT: or a0, a1, a0
+; RV64IM-NEXT: srli a1, a0, 2
+; RV64IM-NEXT: ld a2, 320(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, a0, a2
+; RV64IM-NEXT: and a1, a1, a2
+; RV64IM-NEXT: slli a0, a0, 2
+; RV64IM-NEXT: or a0, a1, a0
+; RV64IM-NEXT: srli a1, a0, 1
+; RV64IM-NEXT: ld a2, 328(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: and a0, a0, a2
+; RV64IM-NEXT: and a1, a1, a7
+; RV64IM-NEXT: slli a0, a0, 1
+; RV64IM-NEXT: or a0, a1, a0
+; RV64IM-NEXT: srli a0, a0, 1
+; RV64IM-NEXT: ld ra, 440(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s0, 432(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s1, 424(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s2, 416(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s3, 408(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s4, 400(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s5, 392(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s6, 384(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s7, 376(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s8, 368(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s9, 360(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s10, 352(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: ld s11, 344(sp) # 8-byte Folded Reload
+; RV64IM-NEXT: addi sp, sp, 448
+; RV64IM-NEXT: ret
+ %res = call i64 @llvm.clmulh.i64(i64 %a, i64 %b)
+ ret i64 %res
+}
+
+define i4 @clmulh_constfold_i4() nounwind {
+; CHECK-LABEL: clmulh_constfold_i4:
+; CHECK: # %bb.0:
+; CHECK-NEXT: li a0, 0
+; CHECK-NEXT: ret
+ %res = call i4 @llvm.clmulh.i4(i4 1, i4 2)
+ ret i4 %res
+}
+
+define i16 @clmulh_constfold_i16() nounwind {
+; RV32IM-LABEL: clmulh_constfold_i16:
+; RV32IM: # %bb.0:
+; RV32IM-NEXT: lui a0, 349525
+; RV32IM-NEXT: addi a0, a0, 1365
+; RV32IM-NEXT: ret
+;
+; RV64IM-LABEL: clmulh_constfold_i16:
+; RV64IM: # %bb.0:
+; RV64IM-NEXT: lui a0, 349525
+; RV64IM-NEXT: addi a0, a0, 1365
+; RV64IM-NEXT: slli a1, a0, 32
+; RV64IM-NEXT: add a0, a0, a1
+; RV64IM-NEXT: ret
+ %res = call i16 @llvm.clmulh.i16(i16 -2, i16 -1)
+ ret i16 %res
+}
diff --git a/llvm/test/CodeGen/RISCV/rvv/clmul-sdnode.ll b/llvm/test/CodeGen/RISCV/rvv/clmul-sdnode.ll
new file mode 100644
index 0000000000000..a9d9f105c044e
--- /dev/null
+++ b/llvm/test/CodeGen/RISCV/rvv/clmul-sdnode.ll
@@ -0,0 +1,42843 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=riscv32 -verify-machineinstrs -mattr=+v < %s | FileCheck %s --check-prefixes=CHECK,RV32
+; RUN: llc -mtriple=riscv64 -verify-machineinstrs -mattr=+v < %s | FileCheck %s --check-prefixes=CHECK,RV64
+
+define <vscale x 1 x i32> @clmul_nxv1i32(<vscale x 1 x i32> %x, <vscale x 1 x i32> %y) nounwind {
+; CHECK-LABEL: clmul_nxv1i32:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli a0, zero, e32, mf2, ta, ma
+; CHECK-NEXT: vand.vi v10, v9, 2
+; CHECK-NEXT: vand.vi v11, v9, 1
+; CHECK-NEXT: vmul.vv v10, v8, v10
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v11, v10
+; CHECK-NEXT: vand.vi v11, v9, 4
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vi v11, v9, 8
+; CHECK-NEXT: li a0, 16
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: li a0, 32
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: li a0, 64
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: li a0, 128
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: li a0, 256
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: li a0, 512
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: li a0, 1024
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: li a0, 1
+; CHECK-NEXT: slli a0, a0, 11
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 1
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 2
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 4
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 8
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 16
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 32
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 64
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 128
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 256
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 512
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 1024
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 2048
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 4096
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 8192
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 16384
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 32768
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 65536
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 131072
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 262144
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 524288
+; CHECK-NEXT: vand.vx v9, v9, a0
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vmul.vv v8, v8, v9
+; CHECK-NEXT: vxor.vv v8, v10, v8
+; CHECK-NEXT: ret
+ %a = call <vscale x 1 x i32> @llvm.clmul.nxv1i32(<vscale x 1 x i32> %x, <vscale x 1 x i32> %y)
+ ret <vscale x 1 x i32> %a
+}
+
+define <vscale x 2 x i32> @clmul_nxv2i32(<vscale x 2 x i32> %x, <vscale x 2 x i32> %y) nounwind {
+; CHECK-LABEL: clmul_nxv2i32:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli a0, zero, e32, m1, ta, ma
+; CHECK-NEXT: vand.vi v10, v9, 2
+; CHECK-NEXT: vand.vi v11, v9, 1
+; CHECK-NEXT: vmul.vv v10, v8, v10
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v11, v10
+; CHECK-NEXT: vand.vi v11, v9, 4
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vi v11, v9, 8
+; CHECK-NEXT: li a0, 16
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: li a0, 32
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: li a0, 64
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: li a0, 128
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: li a0, 256
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: li a0, 512
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: li a0, 1024
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: li a0, 1
+; CHECK-NEXT: slli a0, a0, 11
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 1
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 2
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 4
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 8
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 16
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 32
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 64
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 128
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 256
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 512
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 1024
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 2048
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 4096
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 8192
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 16384
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 32768
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 65536
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 131072
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 262144
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 524288
+; CHECK-NEXT: vand.vx v9, v9, a0
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vmul.vv v8, v8, v9
+; CHECK-NEXT: vxor.vv v8, v10, v8
+; CHECK-NEXT: ret
+ %a = call <vscale x 2 x i32> @llvm.clmul.nxv2i32(<vscale x 2 x i32> %x, <vscale x 2 x i32> %y)
+ ret <vscale x 2 x i32> %a
+}
+
+define <vscale x 4 x i32> @clmul_nxv4i32(<vscale x 4 x i32> %x, <vscale x 4 x i32> %y) nounwind {
+; CHECK-LABEL: clmul_nxv4i32:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli a0, zero, e32, m2, ta, ma
+; CHECK-NEXT: vand.vi v12, v10, 2
+; CHECK-NEXT: vand.vi v14, v10, 1
+; CHECK-NEXT: vmul.vv v12, v8, v12
+; CHECK-NEXT: vmul.vv v14, v8, v14
+; CHECK-NEXT: vxor.vv v12, v14, v12
+; CHECK-NEXT: vand.vi v14, v10, 4
+; CHECK-NEXT: vmul.vv v14, v8, v14
+; CHECK-NEXT: vxor.vv v12, v12, v14
+; CHECK-NEXT: vand.vi v14, v10, 8
+; CHECK-NEXT: li a0, 16
+; CHECK-NEXT: vmul.vv v14, v8, v14
+; CHECK-NEXT: vxor.vv v12, v12, v14
+; CHECK-NEXT: vand.vx v14, v10, a0
+; CHECK-NEXT: li a0, 32
+; CHECK-NEXT: vmul.vv v14, v8, v14
+; CHECK-NEXT: vxor.vv v12, v12, v14
+; CHECK-NEXT: vand.vx v14, v10, a0
+; CHECK-NEXT: li a0, 64
+; CHECK-NEXT: vmul.vv v14, v8, v14
+; CHECK-NEXT: vxor.vv v12, v12, v14
+; CHECK-NEXT: vand.vx v14, v10, a0
+; CHECK-NEXT: li a0, 128
+; CHECK-NEXT: vmul.vv v14, v8, v14
+; CHECK-NEXT: vxor.vv v12, v12, v14
+; CHECK-NEXT: vand.vx v14, v10, a0
+; CHECK-NEXT: li a0, 256
+; CHECK-NEXT: vmul.vv v14, v8, v14
+; CHECK-NEXT: vxor.vv v12, v12, v14
+; CHECK-NEXT: vand.vx v14, v10, a0
+; CHECK-NEXT: li a0, 512
+; CHECK-NEXT: vmul.vv v14, v8, v14
+; CHECK-NEXT: vxor.vv v12, v12, v14
+; CHECK-NEXT: vand.vx v14, v10, a0
+; CHECK-NEXT: li a0, 1024
+; CHECK-NEXT: vmul.vv v14, v8, v14
+; CHECK-NEXT: vxor.vv v12, v12, v14
+; CHECK-NEXT: vand.vx v14, v10, a0
+; CHECK-NEXT: li a0, 1
+; CHECK-NEXT: slli a0, a0, 11
+; CHECK-NEXT: vmul.vv v14, v8, v14
+; CHECK-NEXT: vxor.vv v12, v12, v14
+; CHECK-NEXT: vand.vx v14, v10, a0
+; CHECK-NEXT: lui a0, 1
+; CHECK-NEXT: vmul.vv v14, v8, v14
+; CHECK-NEXT: vxor.vv v12, v12, v14
+; CHECK-NEXT: vand.vx v14, v10, a0
+; CHECK-NEXT: lui a0, 2
+; CHECK-NEXT: vmul.vv v14, v8, v14
+; CHECK-NEXT: vxor.vv v12, v12, v14
+; CHECK-NEXT: vand.vx v14, v10, a0
+; CHECK-NEXT: lui a0, 4
+; CHECK-NEXT: vmul.vv v14, v8, v14
+; CHECK-NEXT: vxor.vv v12, v12, v14
+; CHECK-NEXT: vand.vx v14, v10, a0
+; CHECK-NEXT: lui a0, 8
+; CHECK-NEXT: vmul.vv v14, v8, v14
+; CHECK-NEXT: vxor.vv v12, v12, v14
+; CHECK-NEXT: vand.vx v14, v10, a0
+; CHECK-NEXT: lui a0, 16
+; CHECK-NEXT: vmul.vv v14, v8, v14
+; CHECK-NEXT: vxor.vv v12, v12, v14
+; CHECK-NEXT: vand.vx v14, v10, a0
+; CHECK-NEXT: lui a0, 32
+; CHECK-NEXT: vmul.vv v14, v8, v14
+; CHECK-NEXT: vxor.vv v12, v12, v14
+; CHECK-NEXT: vand.vx v14, v10, a0
+; CHECK-NEXT: lui a0, 64
+; CHECK-NEXT: vmul.vv v14, v8, v14
+; CHECK-NEXT: vxor.vv v12, v12, v14
+; CHECK-NEXT: vand.vx v14, v10, a0
+; CHECK-NEXT: lui a0, 128
+; CHECK-NEXT: vmul.vv v14, v8, v14
+; CHECK-NEXT: vxor.vv v12, v12, v14
+; CHECK-NEXT: vand.vx v14, v10, a0
+; CHECK-NEXT: lui a0, 256
+; CHECK-NEXT: vmul.vv v14, v8, v14
+; CHECK-NEXT: vxor.vv v12, v12, v14
+; CHECK-NEXT: vand.vx v14, v10, a0
+; CHECK-NEXT: lui a0, 512
+; CHECK-NEXT: vmul.vv v14, v8, v14
+; CHECK-NEXT: vxor.vv v12, v12, v14
+; CHECK-NEXT: vand.vx v14, v10, a0
+; CHECK-NEXT: lui a0, 1024
+; CHECK-NEXT: vmul.vv v14, v8, v14
+; CHECK-NEXT: vxor.vv v12, v12, v14
+; CHECK-NEXT: vand.vx v14, v10, a0
+; CHECK-NEXT: lui a0, 2048
+; CHECK-NEXT: vmul.vv v14, v8, v14
+; CHECK-NEXT: vxor.vv v12, v12, v14
+; CHECK-NEXT: vand.vx v14, v10, a0
+; CHECK-NEXT: lui a0, 4096
+; CHECK-NEXT: vmul.vv v14, v8, v14
+; CHECK-NEXT: vxor.vv v12, v12, v14
+; CHECK-NEXT: vand.vx v14, v10, a0
+; CHECK-NEXT: lui a0, 8192
+; CHECK-NEXT: vmul.vv v14, v8, v14
+; CHECK-NEXT: vxor.vv v12, v12, v14
+; CHECK-NEXT: vand.vx v14, v10, a0
+; CHECK-NEXT: lui a0, 16384
+; CHECK-NEXT: vmul.vv v14, v8, v14
+; CHECK-NEXT: vxor.vv v12, v12, v14
+; CHECK-NEXT: vand.vx v14, v10, a0
+; CHECK-NEXT: lui a0, 32768
+; CHECK-NEXT: vmul.vv v14, v8, v14
+; CHECK-NEXT: vxor.vv v12, v12, v14
+; CHECK-NEXT: vand.vx v14, v10, a0
+; CHECK-NEXT: lui a0, 65536
+; CHECK-NEXT: vmul.vv v14, v8, v14
+; CHECK-NEXT: vxor.vv v12, v12, v14
+; CHECK-NEXT: vand.vx v14, v10, a0
+; CHECK-NEXT: lui a0, 131072
+; CHECK-NEXT: vmul.vv v14, v8, v14
+; CHECK-NEXT: vxor.vv v12, v12, v14
+; CHECK-NEXT: vand.vx v14, v10, a0
+; CHECK-NEXT: lui a0, 262144
+; CHECK-NEXT: vmul.vv v14, v8, v14
+; CHECK-NEXT: vxor.vv v12, v12, v14
+; CHECK-NEXT: vand.vx v14, v10, a0
+; CHECK-NEXT: lui a0, 524288
+; CHECK-NEXT: vand.vx v10, v10, a0
+; CHECK-NEXT: vmul.vv v14, v8, v14
+; CHECK-NEXT: vxor.vv v12, v12, v14
+; CHECK-NEXT: vmul.vv v8, v8, v10
+; CHECK-NEXT: vxor.vv v8, v12, v8
+; CHECK-NEXT: ret
+ %a = call <vscale x 4 x i32> @llvm.clmul.nxv4i32(<vscale x 4 x i32> %x, <vscale x 4 x i32> %y)
+ ret <vscale x 4 x i32> %a
+}
+
+define <vscale x 8 x i32> @clmul_nxv8i32(<vscale x 8 x i32> %x, <vscale x 8 x i32> %y) nounwind {
+; CHECK-LABEL: clmul_nxv8i32:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli a0, zero, e32, m4, ta, ma
+; CHECK-NEXT: vand.vi v12, v8, 2
+; CHECK-NEXT: vand.vi v16, v8, 1
+; CHECK-NEXT: vmul.vv v12, v8, v12
+; CHECK-NEXT: vmul.vv v16, v8, v16
+; CHECK-NEXT: vxor.vv v12, v16, v12
+; CHECK-NEXT: vand.vi v16, v8, 4
+; CHECK-NEXT: vmul.vv v16, v8, v16
+; CHECK-NEXT: vxor.vv v12, v12, v16
+; CHECK-NEXT: vand.vi v16, v8, 8
+; CHECK-NEXT: li a0, 16
+; CHECK-NEXT: vmul.vv v16, v8, v16
+; CHECK-NEXT: vxor.vv v12, v12, v16
+; CHECK-NEXT: vand.vx v16, v8, a0
+; CHECK-NEXT: li a0, 32
+; CHECK-NEXT: vmul.vv v16, v8, v16
+; CHECK-NEXT: vxor.vv v12, v12, v16
+; CHECK-NEXT: vand.vx v16, v8, a0
+; CHECK-NEXT: li a0, 64
+; CHECK-NEXT: vmul.vv v16, v8, v16
+; CHECK-NEXT: vxor.vv v12, v12, v16
+; CHECK-NEXT: vand.vx v16, v8, a0
+; CHECK-NEXT: li a0, 128
+; CHECK-NEXT: vmul.vv v16, v8, v16
+; CHECK-NEXT: vxor.vv v12, v12, v16
+; CHECK-NEXT: vand.vx v16, v8, a0
+; CHECK-NEXT: li a0, 256
+; CHECK-NEXT: vmul.vv v16, v8, v16
+; CHECK-NEXT: vxor.vv v12, v12, v16
+; CHECK-NEXT: vand.vx v16, v8, a0
+; CHECK-NEXT: li a0, 512
+; CHECK-NEXT: vmul.vv v16, v8, v16
+; CHECK-NEXT: vxor.vv v12, v12, v16
+; CHECK-NEXT: vand.vx v16, v8, a0
+; CHECK-NEXT: li a0, 1024
+; CHECK-NEXT: vmul.vv v16, v8, v16
+; CHECK-NEXT: vxor.vv v12, v12, v16
+; CHECK-NEXT: vand.vx v16, v8, a0
+; CHECK-NEXT: li a0, 1
+; CHECK-NEXT: slli a0, a0, 11
+; CHECK-NEXT: vmul.vv v16, v8, v16
+; CHECK-NEXT: vxor.vv v12, v12, v16
+; CHECK-NEXT: vand.vx v16, v8, a0
+; CHECK-NEXT: lui a0, 1
+; CHECK-NEXT: vmul.vv v16, v8, v16
+; CHECK-NEXT: vxor.vv v12, v12, v16
+; CHECK-NEXT: vand.vx v16, v8, a0
+; CHECK-NEXT: lui a0, 2
+; CHECK-NEXT: vmul.vv v16, v8, v16
+; CHECK-NEXT: vxor.vv v12, v12, v16
+; CHECK-NEXT: vand.vx v16, v8, a0
+; CHECK-NEXT: lui a0, 4
+; CHECK-NEXT: vmul.vv v16, v8, v16
+; CHECK-NEXT: vxor.vv v12, v12, v16
+; CHECK-NEXT: vand.vx v16, v8, a0
+; CHECK-NEXT: lui a0, 8
+; CHECK-NEXT: vmul.vv v16, v8, v16
+; CHECK-NEXT: vxor.vv v12, v12, v16
+; CHECK-NEXT: vand.vx v16, v8, a0
+; CHECK-NEXT: lui a0, 16
+; CHECK-NEXT: vmul.vv v16, v8, v16
+; CHECK-NEXT: vxor.vv v12, v12, v16
+; CHECK-NEXT: vand.vx v16, v8, a0
+; CHECK-NEXT: lui a0, 32
+; CHECK-NEXT: vmul.vv v16, v8, v16
+; CHECK-NEXT: vxor.vv v12, v12, v16
+; CHECK-NEXT: vand.vx v16, v8, a0
+; CHECK-NEXT: lui a0, 64
+; CHECK-NEXT: vmul.vv v16, v8, v16
+; CHECK-NEXT: vxor.vv v12, v12, v16
+; CHECK-NEXT: vand.vx v16, v8, a0
+; CHECK-NEXT: lui a0, 128
+; CHECK-NEXT: vmul.vv v16, v8, v16
+; CHECK-NEXT: vxor.vv v12, v12, v16
+; CHECK-NEXT: vand.vx v16, v8, a0
+; CHECK-NEXT: lui a0, 256
+; CHECK-NEXT: vmul.vv v16, v8, v16
+; CHECK-NEXT: vxor.vv v12, v12, v16
+; CHECK-NEXT: vand.vx v16, v8, a0
+; CHECK-NEXT: lui a0, 512
+; CHECK-NEXT: vmul.vv v16, v8, v16
+; CHECK-NEXT: vxor.vv v12, v12, v16
+; CHECK-NEXT: vand.vx v16, v8, a0
+; CHECK-NEXT: lui a0, 1024
+; CHECK-NEXT: vmul.vv v16, v8, v16
+; CHECK-NEXT: vxor.vv v12, v12, v16
+; CHECK-NEXT: vand.vx v16, v8, a0
+; CHECK-NEXT: lui a0, 2048
+; CHECK-NEXT: vmul.vv v16, v8, v16
+; CHECK-NEXT: vxor.vv v12, v12, v16
+; CHECK-NEXT: vand.vx v16, v8, a0
+; CHECK-NEXT: lui a0, 4096
+; CHECK-NEXT: vmul.vv v16, v8, v16
+; CHECK-NEXT: vxor.vv v12, v12, v16
+; CHECK-NEXT: vand.vx v16, v8, a0
+; CHECK-NEXT: lui a0, 8192
+; CHECK-NEXT: vmul.vv v16, v8, v16
+; CHECK-NEXT: vxor.vv v12, v12, v16
+; CHECK-NEXT: vand.vx v16, v8, a0
+; CHECK-NEXT: lui a0, 16384
+; CHECK-NEXT: vmul.vv v16, v8, v16
+; CHECK-NEXT: vxor.vv v12, v12, v16
+; CHECK-NEXT: vand.vx v16, v8, a0
+; CHECK-NEXT: lui a0, 32768
+; CHECK-NEXT: vmul.vv v16, v8, v16
+; CHECK-NEXT: vxor.vv v12, v12, v16
+; CHECK-NEXT: vand.vx v16, v8, a0
+; CHECK-NEXT: lui a0, 65536
+; CHECK-NEXT: vmul.vv v16, v8, v16
+; CHECK-NEXT: vxor.vv v12, v12, v16
+; CHECK-NEXT: vand.vx v16, v8, a0
+; CHECK-NEXT: lui a0, 131072
+; CHECK-NEXT: vmul.vv v16, v8, v16
+; CHECK-NEXT: vxor.vv v12, v12, v16
+; CHECK-NEXT: vand.vx v16, v8, a0
+; CHECK-NEXT: lui a0, 262144
+; CHECK-NEXT: vmul.vv v16, v8, v16
+; CHECK-NEXT: vxor.vv v12, v12, v16
+; CHECK-NEXT: vand.vx v16, v8, a0
+; CHECK-NEXT: lui a0, 524288
+; CHECK-NEXT: vmul.vv v16, v8, v16
+; CHECK-NEXT: vxor.vv v12, v12, v16
+; CHECK-NEXT: vand.vx v16, v8, a0
+; CHECK-NEXT: vmul.vv v8, v8, v16
+; CHECK-NEXT: vxor.vv v8, v12, v8
+; CHECK-NEXT: ret
+ %a = call <vscale x 8 x i32> @llvm.clmul.nxv8i32(<vscale x 8 x i32> %x, <vscale x 8 x i32> %x)
+ ret <vscale x 8 x i32> %a
+}
+
+define <vscale x 16 x i32> @clmul_nxv16i32(<vscale x 16 x i32> %x, <vscale x 16 x i32> %y) nounwind {
+; CHECK-LABEL: clmul_nxv16i32:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetvli a0, zero, e32, m8, ta, ma
+; CHECK-NEXT: vand.vi v24, v16, 2
+; CHECK-NEXT: vand.vi v0, v16, 1
+; CHECK-NEXT: vmul.vv v24, v8, v24
+; CHECK-NEXT: vmul.vv v0, v8, v0
+; CHECK-NEXT: vxor.vv v24, v0, v24
+; CHECK-NEXT: vand.vi v0, v16, 4
+; CHECK-NEXT: vmul.vv v0, v8, v0
+; CHECK-NEXT: vxor.vv v24, v24, v0
+; CHECK-NEXT: vand.vi v0, v16, 8
+; CHECK-NEXT: li a0, 16
+; CHECK-NEXT: vmul.vv v0, v8, v0
+; CHECK-NEXT: vxor.vv v24, v24, v0
+; CHECK-NEXT: vand.vx v0, v16, a0
+; CHECK-NEXT: li a0, 32
+; CHECK-NEXT: vmul.vv v0, v8, v0
+; CHECK-NEXT: vxor.vv v24, v24, v0
+; CHECK-NEXT: vand.vx v0, v16, a0
+; CHECK-NEXT: li a0, 64
+; CHECK-NEXT: vmul.vv v0, v8, v0
+; CHECK-NEXT: vxor.vv v24, v24, v0
+; CHECK-NEXT: vand.vx v0, v16, a0
+; CHECK-NEXT: li a0, 128
+; CHECK-NEXT: vmul.vv v0, v8, v0
+; CHECK-NEXT: vxor.vv v24, v24, v0
+; CHECK-NEXT: vand.vx v0, v16, a0
+; CHECK-NEXT: li a0, 256
+; CHECK-NEXT: vmul.vv v0, v8, v0
+; CHECK-NEXT: vxor.vv v24, v24, v0
+; CHECK-NEXT: vand.vx v0, v16, a0
+; CHECK-NEXT: li a0, 512
+; CHECK-NEXT: vmul.vv v0, v8, v0
+; CHECK-NEXT: vxor.vv v24, v24, v0
+; CHECK-NEXT: vand.vx v0, v16, a0
+; CHECK-NEXT: li a0, 1024
+; CHECK-NEXT: vmul.vv v0, v8, v0
+; CHECK-NEXT: vxor.vv v24, v24, v0
+; CHECK-NEXT: vand.vx v0, v16, a0
+; CHECK-NEXT: li a0, 1
+; CHECK-NEXT: slli a0, a0, 11
+; CHECK-NEXT: vmul.vv v0, v8, v0
+; CHECK-NEXT: vxor.vv v24, v24, v0
+; CHECK-NEXT: vand.vx v0, v16, a0
+; CHECK-NEXT: lui a0, 1
+; CHECK-NEXT: vmul.vv v0, v8, v0
+; CHECK-NEXT: vxor.vv v24, v24, v0
+; CHECK-NEXT: vand.vx v0, v16, a0
+; CHECK-NEXT: lui a0, 2
+; CHECK-NEXT: vmul.vv v0, v8, v0
+; CHECK-NEXT: vxor.vv v24, v24, v0
+; CHECK-NEXT: vand.vx v0, v16, a0
+; CHECK-NEXT: lui a0, 4
+; CHECK-NEXT: vmul.vv v0, v8, v0
+; CHECK-NEXT: vxor.vv v24, v24, v0
+; CHECK-NEXT: vand.vx v0, v16, a0
+; CHECK-NEXT: lui a0, 8
+; CHECK-NEXT: vmul.vv v0, v8, v0
+; CHECK-NEXT: vxor.vv v24, v24, v0
+; CHECK-NEXT: vand.vx v0, v16, a0
+; CHECK-NEXT: lui a0, 16
+; CHECK-NEXT: vmul.vv v0, v8, v0
+; CHECK-NEXT: vxor.vv v24, v24, v0
+; CHECK-NEXT: vand.vx v0, v16, a0
+; CHECK-NEXT: lui a0, 32
+; CHECK-NEXT: vmul.vv v0, v8, v0
+; CHECK-NEXT: vxor.vv v24, v24, v0
+; CHECK-NEXT: vand.vx v0, v16, a0
+; CHECK-NEXT: lui a0, 64
+; CHECK-NEXT: vmul.vv v0, v8, v0
+; CHECK-NEXT: vxor.vv v24, v24, v0
+; CHECK-NEXT: vand.vx v0, v16, a0
+; CHECK-NEXT: lui a0, 128
+; CHECK-NEXT: vmul.vv v0, v8, v0
+; CHECK-NEXT: vxor.vv v24, v24, v0
+; CHECK-NEXT: vand.vx v0, v16, a0
+; CHECK-NEXT: lui a0, 256
+; CHECK-NEXT: vmul.vv v0, v8, v0
+; CHECK-NEXT: vxor.vv v24, v24, v0
+; CHECK-NEXT: vand.vx v0, v16, a0
+; CHECK-NEXT: lui a0, 512
+; CHECK-NEXT: vmul.vv v0, v8, v0
+; CHECK-NEXT: vxor.vv v24, v24, v0
+; CHECK-NEXT: vand.vx v0, v16, a0
+; CHECK-NEXT: lui a0, 1024
+; CHECK-NEXT: vmul.vv v0, v8, v0
+; CHECK-NEXT: vxor.vv v24, v24, v0
+; CHECK-NEXT: vand.vx v0, v16, a0
+; CHECK-NEXT: lui a0, 2048
+; CHECK-NEXT: vmul.vv v0, v8, v0
+; CHECK-NEXT: vxor.vv v24, v24, v0
+; CHECK-NEXT: vand.vx v0, v16, a0
+; CHECK-NEXT: lui a0, 4096
+; CHECK-NEXT: vmul.vv v0, v8, v0
+; CHECK-NEXT: vxor.vv v24, v24, v0
+; CHECK-NEXT: vand.vx v0, v16, a0
+; CHECK-NEXT: lui a0, 8192
+; CHECK-NEXT: vmul.vv v0, v8, v0
+; CHECK-NEXT: vxor.vv v24, v24, v0
+; CHECK-NEXT: vand.vx v0, v16, a0
+; CHECK-NEXT: lui a0, 16384
+; CHECK-NEXT: vmul.vv v0, v8, v0
+; CHECK-NEXT: vxor.vv v24, v24, v0
+; CHECK-NEXT: vand.vx v0, v16, a0
+; CHECK-NEXT: lui a0, 32768
+; CHECK-NEXT: vmul.vv v0, v8, v0
+; CHECK-NEXT: vxor.vv v24, v24, v0
+; CHECK-NEXT: vand.vx v0, v16, a0
+; CHECK-NEXT: lui a0, 65536
+; CHECK-NEXT: vmul.vv v0, v8, v0
+; CHECK-NEXT: vxor.vv v24, v24, v0
+; CHECK-NEXT: vand.vx v0, v16, a0
+; CHECK-NEXT: lui a0, 131072
+; CHECK-NEXT: vmul.vv v0, v8, v0
+; CHECK-NEXT: vxor.vv v24, v24, v0
+; CHECK-NEXT: vand.vx v0, v16, a0
+; CHECK-NEXT: lui a0, 262144
+; CHECK-NEXT: vmul.vv v0, v8, v0
+; CHECK-NEXT: vxor.vv v24, v24, v0
+; CHECK-NEXT: vand.vx v0, v16, a0
+; CHECK-NEXT: lui a0, 524288
+; CHECK-NEXT: vand.vx v16, v16, a0
+; CHECK-NEXT: vmul.vv v0, v8, v0
+; CHECK-NEXT: vxor.vv v24, v24, v0
+; CHECK-NEXT: vmul.vv v8, v8, v16
+; CHECK-NEXT: vxor.vv v8, v24, v8
+; CHECK-NEXT: ret
+ %a = call <vscale x 16 x i32> @llvm.clmul.nxv16i32(<vscale x 16 x i32> %x, <vscale x 16 x i32> %y)
+ ret <vscale x 16 x i32> %a
+}
+
+define <vscale x 1 x i64> @clmul_nxv1i64(<vscale x 1 x i64> %x, <vscale x 1 x i64> %y) nounwind {
+; RV32-LABEL: clmul_nxv1i64:
+; RV32: # %bb.0:
+; RV32-NEXT: addi sp, sp, -352
+; RV32-NEXT: sw ra, 348(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s0, 344(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s1, 340(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s2, 336(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s3, 332(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s4, 328(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s5, 324(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s6, 320(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s7, 316(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s8, 312(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s9, 308(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s10, 304(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s11, 300(sp) # 4-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 3
+; RV32-NEXT: sub a0, a1, a0
+; RV32-NEXT: sub sp, sp, a0
+; RV32-NEXT: lui a1, 524288
+; RV32-NEXT: li t5, 1
+; RV32-NEXT: li a4, 2
+; RV32-NEXT: li a2, 4
+; RV32-NEXT: li s11, 8
+; RV32-NEXT: li a0, 16
+; RV32-NEXT: li ra, 32
+; RV32-NEXT: li s10, 64
+; RV32-NEXT: li s9, 128
+; RV32-NEXT: li s8, 256
+; RV32-NEXT: li s7, 512
+; RV32-NEXT: li s1, 1024
+; RV32-NEXT: lui s6, 1
+; RV32-NEXT: lui s5, 2
+; RV32-NEXT: lui s4, 4
+; RV32-NEXT: lui s3, 8
+; RV32-NEXT: lui s2, 16
+; RV32-NEXT: lui s0, 32
+; RV32-NEXT: lui t6, 64
+; RV32-NEXT: lui t4, 128
+; RV32-NEXT: lui t3, 256
+; RV32-NEXT: lui t2, 512
+; RV32-NEXT: lui t1, 1024
+; RV32-NEXT: lui t0, 2048
+; RV32-NEXT: lui a7, 4096
+; RV32-NEXT: lui a6, 8192
+; RV32-NEXT: lui a5, 16384
+; RV32-NEXT: lui a3, 32768
+; RV32-NEXT: sw a1, 272(sp)
+; RV32-NEXT: sw zero, 276(sp)
+; RV32-NEXT: sw zero, 264(sp)
+; RV32-NEXT: sw t5, 268(sp)
+; RV32-NEXT: sw zero, 256(sp)
+; RV32-NEXT: sw a4, 260(sp)
+; RV32-NEXT: lui a4, 65536
+; RV32-NEXT: sw zero, 248(sp)
+; RV32-NEXT: sw a2, 252(sp)
+; RV32-NEXT: lui a2, 131072
+; RV32-NEXT: sw zero, 240(sp)
+; RV32-NEXT: sw s11, 244(sp)
+; RV32-NEXT: vsetvli s11, zero, e64, m1, ta, ma
+; RV32-NEXT: vand.vi v13, v9, 2
+; RV32-NEXT: vand.vi v14, v9, 1
+; RV32-NEXT: vand.vi v12, v9, 4
+; RV32-NEXT: vand.vi v11, v9, 8
+; RV32-NEXT: sw zero, 232(sp)
+; RV32-NEXT: sw a0, 236(sp)
+; RV32-NEXT: vand.vx v10, v9, a0
+; RV32-NEXT: addi s11, sp, 272
+; RV32-NEXT: sw zero, 224(sp)
+; RV32-NEXT: sw ra, 228(sp)
+; RV32-NEXT: vand.vx v15, v9, ra
+; RV32-NEXT: addi ra, sp, 264
+; RV32-NEXT: sw zero, 216(sp)
+; RV32-NEXT: sw s10, 220(sp)
+; RV32-NEXT: vand.vx v16, v9, s10
+; RV32-NEXT: addi s10, sp, 256
+; RV32-NEXT: sw zero, 208(sp)
+; RV32-NEXT: sw s9, 212(sp)
+; RV32-NEXT: vand.vx v17, v9, s9
+; RV32-NEXT: addi s9, sp, 248
+; RV32-NEXT: sw zero, 200(sp)
+; RV32-NEXT: sw s8, 204(sp)
+; RV32-NEXT: vand.vx v18, v9, s8
+; RV32-NEXT: addi s8, sp, 240
+; RV32-NEXT: sw zero, 192(sp)
+; RV32-NEXT: sw s7, 196(sp)
+; RV32-NEXT: vand.vx v19, v9, s7
+; RV32-NEXT: addi s7, sp, 232
+; RV32-NEXT: sw zero, 184(sp)
+; RV32-NEXT: sw s1, 188(sp)
+; RV32-NEXT: vand.vx v20, v9, s1
+; RV32-NEXT: slli t5, t5, 11
+; RV32-NEXT: vand.vx v21, v9, s6
+; RV32-NEXT: sw zero, 176(sp)
+; RV32-NEXT: sw t5, 180(sp)
+; RV32-NEXT: sw zero, 168(sp)
+; RV32-NEXT: sw s6, 172(sp)
+; RV32-NEXT: addi s6, sp, 216
+; RV32-NEXT: vand.vx v22, v9, s5
+; RV32-NEXT: sw zero, 160(sp)
+; RV32-NEXT: sw s5, 164(sp)
+; RV32-NEXT: addi s5, sp, 208
+; RV32-NEXT: vand.vx v23, v9, s4
+; RV32-NEXT: sw zero, 152(sp)
+; RV32-NEXT: sw s4, 156(sp)
+; RV32-NEXT: addi s4, sp, 200
+; RV32-NEXT: vand.vx v24, v9, s3
+; RV32-NEXT: sw zero, 144(sp)
+; RV32-NEXT: sw s3, 148(sp)
+; RV32-NEXT: addi s3, sp, 192
+; RV32-NEXT: vand.vx v25, v9, s2
+; RV32-NEXT: sw zero, 136(sp)
+; RV32-NEXT: sw s2, 140(sp)
+; RV32-NEXT: addi s2, sp, 184
+; RV32-NEXT: vand.vx v26, v9, s0
+; RV32-NEXT: sw zero, 128(sp)
+; RV32-NEXT: sw s0, 132(sp)
+; RV32-NEXT: addi s1, sp, 176
+; RV32-NEXT: vand.vx v27, v9, t6
+; RV32-NEXT: sw zero, 120(sp)
+; RV32-NEXT: sw t6, 124(sp)
+; RV32-NEXT: addi s0, sp, 168
+; RV32-NEXT: vand.vx v28, v9, t4
+; RV32-NEXT: sw zero, 112(sp)
+; RV32-NEXT: sw t4, 116(sp)
+; RV32-NEXT: addi t6, sp, 160
+; RV32-NEXT: vand.vx v29, v9, t3
+; RV32-NEXT: sw zero, 104(sp)
+; RV32-NEXT: sw t3, 108(sp)
+; RV32-NEXT: addi t4, sp, 152
+; RV32-NEXT: vand.vx v30, v9, t2
+; RV32-NEXT: sw zero, 96(sp)
+; RV32-NEXT: sw t2, 100(sp)
+; RV32-NEXT: addi t3, sp, 144
+; RV32-NEXT: vand.vx v31, v9, t1
+; RV32-NEXT: sw zero, 88(sp)
+; RV32-NEXT: sw t1, 92(sp)
+; RV32-NEXT: addi t2, sp, 136
+; RV32-NEXT: vand.vx v7, v9, t0
+; RV32-NEXT: sw zero, 80(sp)
+; RV32-NEXT: sw t0, 84(sp)
+; RV32-NEXT: addi t1, sp, 128
+; RV32-NEXT: vand.vx v6, v9, a7
+; RV32-NEXT: sw zero, 72(sp)
+; RV32-NEXT: sw a7, 76(sp)
+; RV32-NEXT: addi t0, sp, 120
+; RV32-NEXT: vand.vx v5, v9, a6
+; RV32-NEXT: sw zero, 64(sp)
+; RV32-NEXT: sw a6, 68(sp)
+; RV32-NEXT: addi a7, sp, 112
+; RV32-NEXT: vand.vx v4, v9, a5
+; RV32-NEXT: sw zero, 56(sp)
+; RV32-NEXT: sw a5, 60(sp)
+; RV32-NEXT: addi a6, sp, 104
+; RV32-NEXT: vand.vx v3, v9, a3
+; RV32-NEXT: sw zero, 48(sp)
+; RV32-NEXT: sw a3, 52(sp)
+; RV32-NEXT: addi a5, sp, 96
+; RV32-NEXT: vand.vx v2, v9, a4
+; RV32-NEXT: sw zero, 40(sp)
+; RV32-NEXT: sw a4, 44(sp)
+; RV32-NEXT: addi a4, sp, 88
+; RV32-NEXT: vand.vx v1, v9, a2
+; RV32-NEXT: sw zero, 32(sp)
+; RV32-NEXT: sw a2, 36(sp)
+; RV32-NEXT: addi a3, sp, 80
+; RV32-NEXT: sw zero, 24(sp)
+; RV32-NEXT: lui a0, 262144
+; RV32-NEXT: sw a0, 28(sp)
+; RV32-NEXT: sw zero, 16(sp)
+; RV32-NEXT: sw a1, 20(sp)
+; RV32-NEXT: addi a2, sp, 72
+; RV32-NEXT: vand.vx v0, v9, t5
+; RV32-NEXT: addi a1, sp, 64
+; RV32-NEXT: vmul.vv v13, v8, v13
+; RV32-NEXT: vmul.vv v14, v8, v14
+; RV32-NEXT: vxor.vi v14, v14, 0
+; RV32-NEXT: vxor.vv v14, v14, v13
+; RV32-NEXT: vlse64.v v13, (s11), zero
+; RV32-NEXT: addi s11, sp, 56
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vxor.vv v14, v14, v12
+; RV32-NEXT: vlse64.v v12, (ra), zero
+; RV32-NEXT: csrr t5, vlenb
+; RV32-NEXT: slli t5, t5, 1
+; RV32-NEXT: mv ra, t5
+; RV32-NEXT: slli t5, t5, 1
+; RV32-NEXT: add t5, t5, ra
+; RV32-NEXT: add t5, sp, t5
+; RV32-NEXT: addi t5, t5, 288
+; RV32-NEXT: vs1r.v v12, (t5) # vscale x 8-byte Folded Spill
+; RV32-NEXT: addi ra, sp, 48
+; RV32-NEXT: vmul.vv v11, v8, v11
+; RV32-NEXT: vxor.vv v14, v14, v11
+; RV32-NEXT: vlse64.v v11, (s10), zero
+; RV32-NEXT: csrr t5, vlenb
+; RV32-NEXT: slli s10, t5, 2
+; RV32-NEXT: add t5, s10, t5
+; RV32-NEXT: add t5, sp, t5
+; RV32-NEXT: addi t5, t5, 288
+; RV32-NEXT: vs1r.v v11, (t5) # vscale x 8-byte Folded Spill
+; RV32-NEXT: addi s10, sp, 40
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: vxor.vv v14, v14, v10
+; RV32-NEXT: vlse64.v v10, (s9), zero
+; RV32-NEXT: csrr t5, vlenb
+; RV32-NEXT: slli t5, t5, 2
+; RV32-NEXT: add t5, sp, t5
+; RV32-NEXT: addi t5, t5, 288
+; RV32-NEXT: vs1r.v v10, (t5) # vscale x 8-byte Folded Spill
+; RV32-NEXT: addi t5, sp, 32
+; RV32-NEXT: vmul.vv v15, v8, v15
+; RV32-NEXT: vxor.vv v15, v14, v15
+; RV32-NEXT: vlse64.v v10, (s8), zero
+; RV32-NEXT: csrr s8, vlenb
+; RV32-NEXT: slli s9, s8, 1
+; RV32-NEXT: add s8, s9, s8
+; RV32-NEXT: add s8, sp, s8
+; RV32-NEXT: addi s8, s8, 288
+; RV32-NEXT: vs1r.v v10, (s8) # vscale x 8-byte Folded Spill
+; RV32-NEXT: addi s8, sp, 24
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v16, v15, v16
+; RV32-NEXT: vlse64.v v10, (s7), zero
+; RV32-NEXT: csrr s7, vlenb
+; RV32-NEXT: slli s7, s7, 1
+; RV32-NEXT: add s7, sp, s7
+; RV32-NEXT: addi s7, s7, 288
+; RV32-NEXT: vs1r.v v10, (s7) # vscale x 8-byte Folded Spill
+; RV32-NEXT: addi s7, sp, 16
+; RV32-NEXT: vmul.vv v17, v8, v17
+; RV32-NEXT: vmul.vv v18, v8, v18
+; RV32-NEXT: vmul.vv v19, v8, v19
+; RV32-NEXT: vmul.vv v20, v8, v20
+; RV32-NEXT: vmul.vv v21, v8, v21
+; RV32-NEXT: vmul.vv v22, v8, v22
+; RV32-NEXT: vmul.vv v23, v8, v23
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vmul.vv v25, v8, v25
+; RV32-NEXT: vmul.vv v26, v8, v26
+; RV32-NEXT: vmul.vv v27, v8, v27
+; RV32-NEXT: vmul.vv v28, v8, v28
+; RV32-NEXT: vmul.vv v29, v8, v29
+; RV32-NEXT: vmul.vv v30, v8, v30
+; RV32-NEXT: vmul.vv v31, v8, v31
+; RV32-NEXT: vmul.vv v7, v8, v7
+; RV32-NEXT: vmul.vv v6, v8, v6
+; RV32-NEXT: vmul.vv v5, v8, v5
+; RV32-NEXT: vmul.vv v4, v8, v4
+; RV32-NEXT: vmul.vv v3, v8, v3
+; RV32-NEXT: vmul.vv v2, v8, v2
+; RV32-NEXT: vmul.vv v1, v8, v1
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: vxor.vv v16, v16, v17
+; RV32-NEXT: addi s9, sp, 224
+; RV32-NEXT: vlse64.v v11, (s9), zero
+; RV32-NEXT: vxor.vv v16, v16, v18
+; RV32-NEXT: vlse64.v v10, (s6), zero
+; RV32-NEXT: csrr s6, vlenb
+; RV32-NEXT: add s6, sp, s6
+; RV32-NEXT: addi s6, s6, 288
+; RV32-NEXT: vs1r.v v10, (s6) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vxor.vv v16, v16, v19
+; RV32-NEXT: vlse64.v v10, (s5), zero
+; RV32-NEXT: addi s5, sp, 288
+; RV32-NEXT: vs1r.v v10, (s5) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vxor.vv v16, v16, v20
+; RV32-NEXT: vlse64.v v12, (s4), zero
+; RV32-NEXT: vxor.vv v16, v16, v0
+; RV32-NEXT: vlse64.v v0, (s3), zero
+; RV32-NEXT: vxor.vv v16, v16, v21
+; RV32-NEXT: vlse64.v v21, (s2), zero
+; RV32-NEXT: vxor.vv v16, v16, v22
+; RV32-NEXT: vlse64.v v22, (s1), zero
+; RV32-NEXT: vxor.vv v16, v16, v23
+; RV32-NEXT: vlse64.v v23, (s0), zero
+; RV32-NEXT: vxor.vv v16, v16, v24
+; RV32-NEXT: vlse64.v v24, (t6), zero
+; RV32-NEXT: vxor.vv v16, v16, v25
+; RV32-NEXT: vlse64.v v25, (t4), zero
+; RV32-NEXT: vxor.vv v16, v16, v26
+; RV32-NEXT: vlse64.v v26, (t3), zero
+; RV32-NEXT: vxor.vv v16, v16, v27
+; RV32-NEXT: vlse64.v v27, (t2), zero
+; RV32-NEXT: vxor.vv v16, v16, v28
+; RV32-NEXT: vlse64.v v28, (t1), zero
+; RV32-NEXT: vxor.vv v16, v16, v29
+; RV32-NEXT: vlse64.v v29, (t0), zero
+; RV32-NEXT: vxor.vv v16, v16, v30
+; RV32-NEXT: vlse64.v v30, (a7), zero
+; RV32-NEXT: vxor.vv v16, v16, v31
+; RV32-NEXT: vlse64.v v31, (a6), zero
+; RV32-NEXT: vxor.vv v16, v16, v7
+; RV32-NEXT: vlse64.v v7, (a5), zero
+; RV32-NEXT: vxor.vv v16, v16, v6
+; RV32-NEXT: vlse64.v v6, (a4), zero
+; RV32-NEXT: vxor.vv v16, v16, v5
+; RV32-NEXT: vlse64.v v5, (a3), zero
+; RV32-NEXT: vxor.vv v16, v16, v4
+; RV32-NEXT: vlse64.v v4, (a2), zero
+; RV32-NEXT: vxor.vv v16, v16, v3
+; RV32-NEXT: vlse64.v v3, (a1), zero
+; RV32-NEXT: vxor.vv v16, v16, v2
+; RV32-NEXT: vlse64.v v2, (s11), zero
+; RV32-NEXT: vxor.vv v1, v16, v1
+; RV32-NEXT: vlse64.v v10, (ra), zero
+; RV32-NEXT: vand.vv v13, v9, v13
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a1, a1, 1
+; RV32-NEXT: mv a2, a1
+; RV32-NEXT: slli a1, a1, 1
+; RV32-NEXT: add a1, a1, a2
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vl1r.v v14, (a1) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vand.vv v14, v9, v14
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a2, a1, 2
+; RV32-NEXT: add a1, a2, a1
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vl1r.v v15, (a1) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vand.vv v15, v9, v15
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a1, a1, 2
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vl1r.v v16, (a1) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vand.vv v16, v9, v16
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a2, a1, 1
+; RV32-NEXT: add a1, a2, a1
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vl1r.v v17, (a1) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vand.vv v17, v9, v17
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a1, a1, 1
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vl1r.v v18, (a1) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vand.vv v18, v9, v18
+; RV32-NEXT: vand.vv v19, v9, v11
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vl1r.v v11, (a1) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vand.vv v20, v9, v11
+; RV32-NEXT: addi a1, sp, 288
+; RV32-NEXT: vl1r.v v11, (a1) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vand.vv v11, v9, v11
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a1, a1, 1
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vs1r.v v11, (a1) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v11, v9, v12
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a2, a1, 1
+; RV32-NEXT: add a1, a2, a1
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vs1r.v v11, (a1) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v0, v9, v0
+; RV32-NEXT: vand.vv v21, v9, v21
+; RV32-NEXT: vand.vv v22, v9, v22
+; RV32-NEXT: vand.vv v23, v9, v23
+; RV32-NEXT: vand.vv v24, v9, v24
+; RV32-NEXT: vand.vv v25, v9, v25
+; RV32-NEXT: vand.vv v26, v9, v26
+; RV32-NEXT: vand.vv v27, v9, v27
+; RV32-NEXT: vand.vv v28, v9, v28
+; RV32-NEXT: vand.vv v29, v9, v29
+; RV32-NEXT: vand.vv v30, v9, v30
+; RV32-NEXT: vand.vv v31, v9, v31
+; RV32-NEXT: vand.vv v7, v9, v7
+; RV32-NEXT: vand.vv v6, v9, v6
+; RV32-NEXT: vand.vv v5, v9, v5
+; RV32-NEXT: vand.vv v4, v9, v4
+; RV32-NEXT: vand.vv v11, v9, v3
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a1, a1, 2
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vs1r.v v11, (a1) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v2, v9, v2
+; RV32-NEXT: vand.vv v10, v9, v10
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a1, a1, 1
+; RV32-NEXT: mv a2, a1
+; RV32-NEXT: slli a1, a1, 1
+; RV32-NEXT: add a1, a1, a2
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vs1r.v v10, (a1) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vlse64.v v10, (s10), zero
+; RV32-NEXT: vlse64.v v3, (t5), zero
+; RV32-NEXT: vlse64.v v11, (s8), zero
+; RV32-NEXT: vlse64.v v12, (s7), zero
+; RV32-NEXT: vand.vv v10, v9, v10
+; RV32-NEXT: vand.vv v3, v9, v3
+; RV32-NEXT: vand.vv v11, v9, v11
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a2, a1, 2
+; RV32-NEXT: add a1, a2, a1
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vs1r.v v11, (a1) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v9, v12
+; RV32-NEXT: vand.vx v9, v9, a0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: vxor.vv v9, v1, v9
+; RV32-NEXT: vmul.vv v11, v8, v13
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v14
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v15
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v16
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v17
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v18
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v19
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v20
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v11, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v11, v8, v11
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 1
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v11, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v11, v8, v11
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v0
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v21
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v22
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v23
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v24
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v25
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v26
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v27
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v28
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v29
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v30
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v31
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v7
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v6
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v5
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v4
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v11, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v11, v8, v11
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v2
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v11, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v11, v8, v11
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: vxor.vv v9, v9, v10
+; RV32-NEXT: vmul.vv v10, v8, v3
+; RV32-NEXT: vxor.vv v9, v9, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 2
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v10, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: vxor.vv v9, v9, v10
+; RV32-NEXT: vmul.vv v8, v8, v12
+; RV32-NEXT: vxor.vv v8, v9, v8
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 3
+; RV32-NEXT: sub a0, a1, a0
+; RV32-NEXT: add sp, sp, a0
+; RV32-NEXT: lw ra, 348(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s0, 344(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s1, 340(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s2, 336(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s3, 332(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s4, 328(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s5, 324(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s6, 320(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s7, 316(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s8, 312(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s9, 308(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s10, 304(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s11, 300(sp) # 4-byte Folded Reload
+; RV32-NEXT: addi sp, sp, 352
+; RV32-NEXT: ret
+;
+; RV64-LABEL: clmul_nxv1i64:
+; RV64: # %bb.0:
+; RV64-NEXT: vsetvli a0, zero, e64, m1, ta, ma
+; RV64-NEXT: vand.vi v10, v9, 2
+; RV64-NEXT: vand.vi v11, v9, 1
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v11, v10
+; RV64-NEXT: vand.vi v11, v9, 4
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vi v11, v9, 8
+; RV64-NEXT: li a0, 16
+; RV64-NEXT: li a1, 32
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a0
+; RV64-NEXT: li a0, 64
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: li a1, 128
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a0
+; RV64-NEXT: li a0, 256
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: li a1, 512
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a0
+; RV64-NEXT: li a2, 1024
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: li a0, 1
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a2
+; RV64-NEXT: slli a1, a0, 11
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 1
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 2
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 4
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 8
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 16
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 32
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 64
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 128
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 256
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 512
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 1024
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 2048
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 4096
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 8192
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 16384
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 32768
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 65536
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 131072
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 262144
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 31
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 32
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 33
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 34
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 35
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 36
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 37
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 38
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 39
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 40
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 41
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 42
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 43
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 44
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 45
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 46
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 47
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 48
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 49
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 50
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 51
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 52
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 53
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 54
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 55
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 56
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 57
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 58
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 59
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 60
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 61
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: li a1, -1
+; RV64-NEXT: slli a0, a0, 62
+; RV64-NEXT: slli a1, a1, 63
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a0
+; RV64-NEXT: vand.vx v9, v9, a1
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vmul.vv v8, v8, v9
+; RV64-NEXT: vxor.vv v8, v10, v8
+; RV64-NEXT: ret
+ %a = call <vscale x 1 x i64> @llvm.clmul.nxv1i64(<vscale x 1 x i64> %x, <vscale x 1 x i64> %y)
+ ret <vscale x 1 x i64> %a
+}
+
+define <vscale x 2 x i64> @clmul_nxv2i64(<vscale x 2 x i64> %x, <vscale x 2 x i64> %y) nounwind {
+; RV32-LABEL: clmul_nxv2i64:
+; RV32: # %bb.0:
+; RV32-NEXT: addi sp, sp, -352
+; RV32-NEXT: sw ra, 348(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s0, 344(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s1, 340(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s2, 336(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s3, 332(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s4, 328(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s5, 324(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s6, 320(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s7, 316(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s8, 312(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s9, 308(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s10, 304(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s11, 300(sp) # 4-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: sub sp, sp, a0
+; RV32-NEXT: lui a1, 524288
+; RV32-NEXT: li s2, 1
+; RV32-NEXT: li a3, 2
+; RV32-NEXT: li a2, 4
+; RV32-NEXT: li s7, 8
+; RV32-NEXT: li a0, 16
+; RV32-NEXT: li s6, 32
+; RV32-NEXT: li s5, 64
+; RV32-NEXT: li s4, 128
+; RV32-NEXT: li s1, 256
+; RV32-NEXT: li s0, 512
+; RV32-NEXT: li t5, 1024
+; RV32-NEXT: lui ra, 1
+; RV32-NEXT: lui s8, 2
+; RV32-NEXT: lui s10, 4
+; RV32-NEXT: lui s11, 8
+; RV32-NEXT: lui s9, 16
+; RV32-NEXT: lui s3, 32
+; RV32-NEXT: lui t6, 64
+; RV32-NEXT: lui t4, 128
+; RV32-NEXT: lui t3, 256
+; RV32-NEXT: lui t2, 512
+; RV32-NEXT: lui t1, 1024
+; RV32-NEXT: lui t0, 2048
+; RV32-NEXT: lui a7, 4096
+; RV32-NEXT: lui a6, 8192
+; RV32-NEXT: lui a5, 16384
+; RV32-NEXT: lui a4, 32768
+; RV32-NEXT: sw a1, 272(sp)
+; RV32-NEXT: sw zero, 276(sp)
+; RV32-NEXT: sw zero, 264(sp)
+; RV32-NEXT: sw s2, 268(sp)
+; RV32-NEXT: sw zero, 256(sp)
+; RV32-NEXT: sw a3, 260(sp)
+; RV32-NEXT: lui a3, 65536
+; RV32-NEXT: sw zero, 248(sp)
+; RV32-NEXT: sw a2, 252(sp)
+; RV32-NEXT: lui a2, 131072
+; RV32-NEXT: sw zero, 240(sp)
+; RV32-NEXT: sw s7, 244(sp)
+; RV32-NEXT: vsetvli s7, zero, e64, m2, ta, ma
+; RV32-NEXT: vand.vi v28, v10, 2
+; RV32-NEXT: vand.vi v20, v10, 1
+; RV32-NEXT: vand.vi v30, v10, 4
+; RV32-NEXT: vand.vi v14, v10, 8
+; RV32-NEXT: sw zero, 232(sp)
+; RV32-NEXT: sw a0, 236(sp)
+; RV32-NEXT: vand.vx v12, v10, a0
+; RV32-NEXT: addi s7, sp, 272
+; RV32-NEXT: sw zero, 224(sp)
+; RV32-NEXT: sw s6, 228(sp)
+; RV32-NEXT: vand.vx v16, v10, s6
+; RV32-NEXT: addi s6, sp, 264
+; RV32-NEXT: sw zero, 216(sp)
+; RV32-NEXT: sw s5, 220(sp)
+; RV32-NEXT: vand.vx v18, v10, s5
+; RV32-NEXT: addi s5, sp, 256
+; RV32-NEXT: sw zero, 208(sp)
+; RV32-NEXT: sw s4, 212(sp)
+; RV32-NEXT: vand.vx v0, v10, s4
+; RV32-NEXT: addi s4, sp, 248
+; RV32-NEXT: sw zero, 200(sp)
+; RV32-NEXT: sw s1, 204(sp)
+; RV32-NEXT: vand.vx v6, v10, s1
+; RV32-NEXT: addi s1, sp, 240
+; RV32-NEXT: sw zero, 192(sp)
+; RV32-NEXT: sw s0, 196(sp)
+; RV32-NEXT: vand.vx v4, v10, s0
+; RV32-NEXT: addi s0, sp, 232
+; RV32-NEXT: sw zero, 184(sp)
+; RV32-NEXT: sw t5, 188(sp)
+; RV32-NEXT: vand.vx v2, v10, t5
+; RV32-NEXT: slli s2, s2, 11
+; RV32-NEXT: vand.vx v24, v10, ra
+; RV32-NEXT: sw zero, 176(sp)
+; RV32-NEXT: sw s2, 180(sp)
+; RV32-NEXT: sw zero, 168(sp)
+; RV32-NEXT: sw ra, 172(sp)
+; RV32-NEXT: addi t5, sp, 216
+; RV32-NEXT: vand.vx v26, v10, s8
+; RV32-NEXT: sw zero, 160(sp)
+; RV32-NEXT: sw s8, 164(sp)
+; RV32-NEXT: addi s8, sp, 208
+; RV32-NEXT: vand.vx v22, v10, s10
+; RV32-NEXT: sw zero, 152(sp)
+; RV32-NEXT: sw s10, 156(sp)
+; RV32-NEXT: addi s10, sp, 200
+; RV32-NEXT: vmul.vv v28, v8, v28
+; RV32-NEXT: vmul.vv v20, v8, v20
+; RV32-NEXT: vxor.vi v20, v20, 0
+; RV32-NEXT: vxor.vv v20, v20, v28
+; RV32-NEXT: vand.vx v28, v10, s11
+; RV32-NEXT: sw zero, 144(sp)
+; RV32-NEXT: sw s11, 148(sp)
+; RV32-NEXT: addi s11, sp, 192
+; RV32-NEXT: vmul.vv v30, v8, v30
+; RV32-NEXT: vxor.vv v20, v20, v30
+; RV32-NEXT: vand.vx v30, v10, s9
+; RV32-NEXT: sw zero, 136(sp)
+; RV32-NEXT: sw s9, 140(sp)
+; RV32-NEXT: addi s9, sp, 184
+; RV32-NEXT: vmul.vv v14, v8, v14
+; RV32-NEXT: vxor.vv v14, v20, v14
+; RV32-NEXT: vand.vx v20, v10, s3
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv ra, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, ra
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v20, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: sw zero, 128(sp)
+; RV32-NEXT: sw s3, 132(sp)
+; RV32-NEXT: addi s3, sp, 176
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vxor.vv v12, v14, v12
+; RV32-NEXT: vand.vx v14, v10, t6
+; RV32-NEXT: sw zero, 120(sp)
+; RV32-NEXT: sw t6, 124(sp)
+; RV32-NEXT: addi t6, sp, 168
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: vand.vx v16, v10, t4
+; RV32-NEXT: sw zero, 112(sp)
+; RV32-NEXT: sw t4, 116(sp)
+; RV32-NEXT: addi t4, sp, 160
+; RV32-NEXT: vmul.vv v18, v8, v18
+; RV32-NEXT: vxor.vv v18, v12, v18
+; RV32-NEXT: vand.vx v12, v10, t3
+; RV32-NEXT: sw zero, 104(sp)
+; RV32-NEXT: sw t3, 108(sp)
+; RV32-NEXT: addi t3, sp, 152
+; RV32-NEXT: vmul.vv v20, v8, v0
+; RV32-NEXT: vxor.vv v18, v18, v20
+; RV32-NEXT: vand.vx v20, v10, t2
+; RV32-NEXT: sw zero, 96(sp)
+; RV32-NEXT: sw t2, 100(sp)
+; RV32-NEXT: addi t2, sp, 144
+; RV32-NEXT: vmul.vv v6, v8, v6
+; RV32-NEXT: vxor.vv v18, v18, v6
+; RV32-NEXT: vand.vx v6, v10, t1
+; RV32-NEXT: sw zero, 88(sp)
+; RV32-NEXT: sw t1, 92(sp)
+; RV32-NEXT: addi t1, sp, 136
+; RV32-NEXT: vmul.vv v4, v8, v4
+; RV32-NEXT: vxor.vv v18, v18, v4
+; RV32-NEXT: vand.vx v4, v10, t0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv ra, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add ra, ra, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, ra
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v4, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: sw zero, 80(sp)
+; RV32-NEXT: sw t0, 84(sp)
+; RV32-NEXT: addi t0, sp, 128
+; RV32-NEXT: vmul.vv v2, v8, v2
+; RV32-NEXT: vxor.vv v18, v18, v2
+; RV32-NEXT: vand.vx v2, v10, s2
+; RV32-NEXT: addi ra, sp, 120
+; RV32-NEXT: vmul.vv v2, v8, v2
+; RV32-NEXT: vxor.vv v18, v18, v2
+; RV32-NEXT: vand.vx v2, v10, a7
+; RV32-NEXT: sw zero, 72(sp)
+; RV32-NEXT: sw a7, 76(sp)
+; RV32-NEXT: addi a7, sp, 112
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vxor.vv v18, v18, v24
+; RV32-NEXT: vand.vx v4, v10, a6
+; RV32-NEXT: sw zero, 64(sp)
+; RV32-NEXT: sw a6, 68(sp)
+; RV32-NEXT: addi a6, sp, 104
+; RV32-NEXT: vmul.vv v26, v8, v26
+; RV32-NEXT: vxor.vv v18, v18, v26
+; RV32-NEXT: vand.vx v26, v10, a5
+; RV32-NEXT: sw zero, 56(sp)
+; RV32-NEXT: sw a5, 60(sp)
+; RV32-NEXT: addi a5, sp, 96
+; RV32-NEXT: vmul.vv v22, v8, v22
+; RV32-NEXT: vxor.vv v18, v18, v22
+; RV32-NEXT: vand.vx v24, v10, a4
+; RV32-NEXT: sw zero, 48(sp)
+; RV32-NEXT: sw a4, 52(sp)
+; RV32-NEXT: addi a4, sp, 88
+; RV32-NEXT: vmul.vv v28, v8, v28
+; RV32-NEXT: vxor.vv v18, v18, v28
+; RV32-NEXT: vand.vx v28, v10, a3
+; RV32-NEXT: sw zero, 40(sp)
+; RV32-NEXT: sw a3, 44(sp)
+; RV32-NEXT: addi a3, sp, 80
+; RV32-NEXT: vmul.vv v30, v8, v30
+; RV32-NEXT: vxor.vv v18, v18, v30
+; RV32-NEXT: vand.vx v30, v10, a2
+; RV32-NEXT: sw zero, 32(sp)
+; RV32-NEXT: sw a2, 36(sp)
+; RV32-NEXT: addi a2, sp, 72
+; RV32-NEXT: sw zero, 24(sp)
+; RV32-NEXT: lui a0, 262144
+; RV32-NEXT: sw a0, 28(sp)
+; RV32-NEXT: sw zero, 16(sp)
+; RV32-NEXT: sw a1, 20(sp)
+; RV32-NEXT: addi a1, sp, 64
+; RV32-NEXT: sw a6, 4(sp) # 4-byte Folded Spill
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 3
+; RV32-NEXT: mv s2, a6
+; RV32-NEXT: slli a6, a6, 2
+; RV32-NEXT: add a6, a6, s2
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 288
+; RV32-NEXT: vl2r.v v22, (a6) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v0, v8, v22
+; RV32-NEXT: vxor.vv v0, v18, v0
+; RV32-NEXT: vlse64.v v18, (s7), zero
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 3
+; RV32-NEXT: mv s2, a6
+; RV32-NEXT: slli a6, a6, 2
+; RV32-NEXT: add a6, a6, s2
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 288
+; RV32-NEXT: vs2r.v v18, (a6) # vscale x 16-byte Folded Spill
+; RV32-NEXT: addi s7, sp, 56
+; RV32-NEXT: vmul.vv v14, v8, v14
+; RV32-NEXT: vxor.vv v14, v0, v14
+; RV32-NEXT: vlse64.v v18, (s6), zero
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 2
+; RV32-NEXT: mv s2, a6
+; RV32-NEXT: slli a6, a6, 3
+; RV32-NEXT: add a6, a6, s2
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 288
+; RV32-NEXT: vs2r.v v18, (a6) # vscale x 16-byte Folded Spill
+; RV32-NEXT: addi s2, sp, 48
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v14, v14, v16
+; RV32-NEXT: vlse64.v v16, (s5), zero
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: mv s5, a6
+; RV32-NEXT: slli a6, a6, 4
+; RV32-NEXT: add a6, a6, s5
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 288
+; RV32-NEXT: vs2r.v v16, (a6) # vscale x 16-byte Folded Spill
+; RV32-NEXT: addi s5, sp, 40
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vxor.vv v12, v14, v12
+; RV32-NEXT: vlse64.v v14, (s4), zero
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 5
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 288
+; RV32-NEXT: vs2r.v v14, (a6) # vscale x 16-byte Folded Spill
+; RV32-NEXT: addi s4, sp, 32
+; RV32-NEXT: vmul.vv v20, v8, v20
+; RV32-NEXT: vxor.vv v20, v12, v20
+; RV32-NEXT: vlse64.v v12, (s1), zero
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: mv s1, a6
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: add s1, s1, a6
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: add s1, s1, a6
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: add a6, a6, s1
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 288
+; RV32-NEXT: vs2r.v v12, (a6) # vscale x 16-byte Folded Spill
+; RV32-NEXT: addi s1, sp, 24
+; RV32-NEXT: vmul.vv v6, v8, v6
+; RV32-NEXT: vxor.vv v20, v20, v6
+; RV32-NEXT: vlse64.v v12, (s0), zero
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 2
+; RV32-NEXT: mv s0, a6
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: add s0, s0, a6
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: add a6, a6, s0
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 288
+; RV32-NEXT: vs2r.v v12, (a6) # vscale x 16-byte Folded Spill
+; RV32-NEXT: addi s0, sp, 16
+; RV32-NEXT: csrr s6, vlenb
+; RV32-NEXT: slli s6, s6, 1
+; RV32-NEXT: mv a6, s6
+; RV32-NEXT: slli s6, s6, 1
+; RV32-NEXT: add a6, a6, s6
+; RV32-NEXT: slli s6, s6, 3
+; RV32-NEXT: add s6, s6, a6
+; RV32-NEXT: lw a6, 4(sp) # 4-byte Folded Reload
+; RV32-NEXT: add s6, sp, s6
+; RV32-NEXT: addi s6, s6, 288
+; RV32-NEXT: vl2r.v v12, (s6) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v6, v8, v12
+; RV32-NEXT: vmul.vv v2, v8, v2
+; RV32-NEXT: vmul.vv v4, v8, v4
+; RV32-NEXT: vmul.vv v26, v8, v26
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vmul.vv v28, v8, v28
+; RV32-NEXT: vmul.vv v30, v8, v30
+; RV32-NEXT: vxor.vv v20, v20, v6
+; RV32-NEXT: addi s6, sp, 224
+; RV32-NEXT: vlse64.v v0, (s6), zero
+; RV32-NEXT: vxor.vv v20, v20, v2
+; RV32-NEXT: vlse64.v v6, (t5), zero
+; RV32-NEXT: vxor.vv v20, v20, v4
+; RV32-NEXT: vlse64.v v22, (s8), zero
+; RV32-NEXT: vxor.vv v20, v20, v26
+; RV32-NEXT: vlse64.v v18, (s10), zero
+; RV32-NEXT: vxor.vv v20, v20, v24
+; RV32-NEXT: vlse64.v v16, (s11), zero
+; RV32-NEXT: vxor.vv v20, v20, v28
+; RV32-NEXT: vlse64.v v14, (s9), zero
+; RV32-NEXT: vxor.vv v2, v20, v30
+; RV32-NEXT: vlse64.v v12, (s3), zero
+; RV32-NEXT: csrr t5, vlenb
+; RV32-NEXT: slli t5, t5, 3
+; RV32-NEXT: mv s3, t5
+; RV32-NEXT: slli t5, t5, 2
+; RV32-NEXT: add t5, t5, s3
+; RV32-NEXT: add t5, sp, t5
+; RV32-NEXT: addi t5, t5, 288
+; RV32-NEXT: vl2r.v v20, (t5) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vand.vv v26, v10, v20
+; RV32-NEXT: csrr t5, vlenb
+; RV32-NEXT: slli t5, t5, 2
+; RV32-NEXT: mv s3, t5
+; RV32-NEXT: slli t5, t5, 3
+; RV32-NEXT: add t5, t5, s3
+; RV32-NEXT: add t5, sp, t5
+; RV32-NEXT: addi t5, t5, 288
+; RV32-NEXT: vl2r.v v20, (t5) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vand.vv v4, v10, v20
+; RV32-NEXT: csrr t5, vlenb
+; RV32-NEXT: slli t5, t5, 1
+; RV32-NEXT: mv s3, t5
+; RV32-NEXT: slli t5, t5, 4
+; RV32-NEXT: add t5, t5, s3
+; RV32-NEXT: add t5, sp, t5
+; RV32-NEXT: addi t5, t5, 288
+; RV32-NEXT: vl2r.v v20, (t5) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vand.vv v30, v10, v20
+; RV32-NEXT: csrr t5, vlenb
+; RV32-NEXT: slli t5, t5, 5
+; RV32-NEXT: add t5, sp, t5
+; RV32-NEXT: addi t5, t5, 288
+; RV32-NEXT: vl2r.v v20, (t5) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vand.vv v20, v10, v20
+; RV32-NEXT: csrr t5, vlenb
+; RV32-NEXT: slli t5, t5, 1
+; RV32-NEXT: mv s3, t5
+; RV32-NEXT: slli t5, t5, 1
+; RV32-NEXT: add s3, s3, t5
+; RV32-NEXT: slli t5, t5, 1
+; RV32-NEXT: add s3, s3, t5
+; RV32-NEXT: slli t5, t5, 1
+; RV32-NEXT: add t5, t5, s3
+; RV32-NEXT: add t5, sp, t5
+; RV32-NEXT: addi t5, t5, 288
+; RV32-NEXT: vl2r.v v24, (t5) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vand.vv v28, v10, v24
+; RV32-NEXT: csrr t5, vlenb
+; RV32-NEXT: slli t5, t5, 2
+; RV32-NEXT: mv s3, t5
+; RV32-NEXT: slli t5, t5, 1
+; RV32-NEXT: add s3, s3, t5
+; RV32-NEXT: slli t5, t5, 1
+; RV32-NEXT: add t5, t5, s3
+; RV32-NEXT: add t5, sp, t5
+; RV32-NEXT: addi t5, t5, 288
+; RV32-NEXT: vl2r.v v24, (t5) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vand.vv v24, v10, v24
+; RV32-NEXT: vand.vv v0, v10, v0
+; RV32-NEXT: vand.vv v6, v10, v6
+; RV32-NEXT: vand.vv v22, v10, v22
+; RV32-NEXT: vand.vv v18, v10, v18
+; RV32-NEXT: csrr t5, vlenb
+; RV32-NEXT: slli t5, t5, 3
+; RV32-NEXT: add t5, sp, t5
+; RV32-NEXT: addi t5, t5, 288
+; RV32-NEXT: vs2r.v v18, (t5) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v10, v16
+; RV32-NEXT: csrr t5, vlenb
+; RV32-NEXT: slli t5, t5, 2
+; RV32-NEXT: mv s3, t5
+; RV32-NEXT: slli t5, t5, 2
+; RV32-NEXT: add t5, t5, s3
+; RV32-NEXT: add t5, sp, t5
+; RV32-NEXT: addi t5, t5, 288
+; RV32-NEXT: vs2r.v v16, (t5) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v14, v10, v14
+; RV32-NEXT: csrr t5, vlenb
+; RV32-NEXT: slli t5, t5, 1
+; RV32-NEXT: mv s3, t5
+; RV32-NEXT: slli t5, t5, 1
+; RV32-NEXT: add s3, s3, t5
+; RV32-NEXT: slli t5, t5, 1
+; RV32-NEXT: add s3, s3, t5
+; RV32-NEXT: slli t5, t5, 1
+; RV32-NEXT: add t5, t5, s3
+; RV32-NEXT: add t5, sp, t5
+; RV32-NEXT: addi t5, t5, 288
+; RV32-NEXT: vs2r.v v14, (t5) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v10, v12
+; RV32-NEXT: csrr t5, vlenb
+; RV32-NEXT: slli t5, t5, 3
+; RV32-NEXT: mv s3, t5
+; RV32-NEXT: slli t5, t5, 2
+; RV32-NEXT: add t5, t5, s3
+; RV32-NEXT: add t5, sp, t5
+; RV32-NEXT: addi t5, t5, 288
+; RV32-NEXT: vs2r.v v12, (t5) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vlse64.v v12, (t6), zero
+; RV32-NEXT: vlse64.v v14, (t4), zero
+; RV32-NEXT: vlse64.v v16, (t3), zero
+; RV32-NEXT: vlse64.v v18, (t2), zero
+; RV32-NEXT: vand.vv v12, v10, v12
+; RV32-NEXT: csrr t2, vlenb
+; RV32-NEXT: slli t2, t2, 1
+; RV32-NEXT: mv t3, t2
+; RV32-NEXT: slli t2, t2, 1
+; RV32-NEXT: add t2, t2, t3
+; RV32-NEXT: add t2, sp, t2
+; RV32-NEXT: addi t2, t2, 288
+; RV32-NEXT: vs2r.v v12, (t2) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v10, v14
+; RV32-NEXT: csrr t2, vlenb
+; RV32-NEXT: slli t2, t2, 1
+; RV32-NEXT: mv t3, t2
+; RV32-NEXT: slli t2, t2, 3
+; RV32-NEXT: add t2, t2, t3
+; RV32-NEXT: add t2, sp, t2
+; RV32-NEXT: addi t2, t2, 288
+; RV32-NEXT: vs2r.v v12, (t2) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v10, v16
+; RV32-NEXT: csrr t2, vlenb
+; RV32-NEXT: slli t2, t2, 2
+; RV32-NEXT: mv t3, t2
+; RV32-NEXT: slli t2, t2, 1
+; RV32-NEXT: add t3, t3, t2
+; RV32-NEXT: slli t2, t2, 1
+; RV32-NEXT: add t2, t2, t3
+; RV32-NEXT: add t2, sp, t2
+; RV32-NEXT: addi t2, t2, 288
+; RV32-NEXT: vs2r.v v12, (t2) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v10, v18
+; RV32-NEXT: csrr t2, vlenb
+; RV32-NEXT: slli t2, t2, 1
+; RV32-NEXT: mv t3, t2
+; RV32-NEXT: slli t2, t2, 1
+; RV32-NEXT: add t3, t3, t2
+; RV32-NEXT: slli t2, t2, 3
+; RV32-NEXT: add t2, t2, t3
+; RV32-NEXT: add t2, sp, t2
+; RV32-NEXT: addi t2, t2, 288
+; RV32-NEXT: vs2r.v v12, (t2) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vlse64.v v12, (t1), zero
+; RV32-NEXT: vlse64.v v14, (t0), zero
+; RV32-NEXT: vlse64.v v16, (ra), zero
+; RV32-NEXT: vlse64.v v18, (a7), zero
+; RV32-NEXT: vand.vv v12, v10, v12
+; RV32-NEXT: csrr a7, vlenb
+; RV32-NEXT: slli a7, a7, 2
+; RV32-NEXT: add a7, sp, a7
+; RV32-NEXT: addi a7, a7, 288
+; RV32-NEXT: vs2r.v v12, (a7) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v10, v14
+; RV32-NEXT: csrr a7, vlenb
+; RV32-NEXT: slli a7, a7, 4
+; RV32-NEXT: add a7, sp, a7
+; RV32-NEXT: addi a7, a7, 288
+; RV32-NEXT: vs2r.v v12, (a7) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v10, v16
+; RV32-NEXT: csrr a7, vlenb
+; RV32-NEXT: slli a7, a7, 1
+; RV32-NEXT: mv t0, a7
+; RV32-NEXT: slli a7, a7, 2
+; RV32-NEXT: add t0, t0, a7
+; RV32-NEXT: slli a7, a7, 1
+; RV32-NEXT: add a7, a7, t0
+; RV32-NEXT: add a7, sp, a7
+; RV32-NEXT: addi a7, a7, 288
+; RV32-NEXT: vs2r.v v12, (a7) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v10, v18
+; RV32-NEXT: csrr a7, vlenb
+; RV32-NEXT: slli a7, a7, 2
+; RV32-NEXT: mv t0, a7
+; RV32-NEXT: slli a7, a7, 3
+; RV32-NEXT: add a7, a7, t0
+; RV32-NEXT: add a7, sp, a7
+; RV32-NEXT: addi a7, a7, 288
+; RV32-NEXT: vs2r.v v12, (a7) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vlse64.v v12, (a6), zero
+; RV32-NEXT: vlse64.v v14, (a5), zero
+; RV32-NEXT: vlse64.v v16, (a4), zero
+; RV32-NEXT: vlse64.v v18, (a3), zero
+; RV32-NEXT: vand.vv v12, v10, v12
+; RV32-NEXT: csrr a3, vlenb
+; RV32-NEXT: slli a3, a3, 1
+; RV32-NEXT: add a3, sp, a3
+; RV32-NEXT: addi a3, a3, 288
+; RV32-NEXT: vs2r.v v12, (a3) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v10, v14
+; RV32-NEXT: csrr a3, vlenb
+; RV32-NEXT: slli a3, a3, 1
+; RV32-NEXT: mv a4, a3
+; RV32-NEXT: slli a3, a3, 1
+; RV32-NEXT: add a4, a4, a3
+; RV32-NEXT: slli a3, a3, 1
+; RV32-NEXT: add a3, a3, a4
+; RV32-NEXT: add a3, sp, a3
+; RV32-NEXT: addi a3, a3, 288
+; RV32-NEXT: vs2r.v v12, (a3) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v10, v16
+; RV32-NEXT: csrr a3, vlenb
+; RV32-NEXT: slli a3, a3, 3
+; RV32-NEXT: mv a4, a3
+; RV32-NEXT: slli a3, a3, 1
+; RV32-NEXT: add a3, a3, a4
+; RV32-NEXT: add a3, sp, a3
+; RV32-NEXT: addi a3, a3, 288
+; RV32-NEXT: vs2r.v v12, (a3) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v10, v18
+; RV32-NEXT: csrr a3, vlenb
+; RV32-NEXT: slli a3, a3, 1
+; RV32-NEXT: mv a4, a3
+; RV32-NEXT: slli a3, a3, 4
+; RV32-NEXT: add a3, a3, a4
+; RV32-NEXT: add a3, sp, a3
+; RV32-NEXT: addi a3, a3, 288
+; RV32-NEXT: vs2r.v v12, (a3) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vlse64.v v12, (a2), zero
+; RV32-NEXT: vlse64.v v14, (a1), zero
+; RV32-NEXT: vlse64.v v16, (s7), zero
+; RV32-NEXT: vlse64.v v18, (s2), zero
+; RV32-NEXT: vand.vv v12, v10, v12
+; RV32-NEXT: addi a1, sp, 288
+; RV32-NEXT: vs2r.v v12, (a1) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v10, v14
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a1, a1, 2
+; RV32-NEXT: mv a2, a1
+; RV32-NEXT: slli a1, a1, 1
+; RV32-NEXT: add a1, a1, a2
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vs2r.v v12, (a1) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v10, v16
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a1, a1, 1
+; RV32-NEXT: mv a2, a1
+; RV32-NEXT: slli a1, a1, 1
+; RV32-NEXT: add a2, a2, a1
+; RV32-NEXT: slli a1, a1, 2
+; RV32-NEXT: add a1, a1, a2
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vs2r.v v12, (a1) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v10, v18
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a1, a1, 5
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vs2r.v v12, (a1) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vlse64.v v14, (s5), zero
+; RV32-NEXT: vlse64.v v16, (s4), zero
+; RV32-NEXT: vlse64.v v18, (s1), zero
+; RV32-NEXT: vlse64.v v12, (s0), zero
+; RV32-NEXT: vand.vv v14, v10, v14
+; RV32-NEXT: vand.vv v16, v10, v16
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a1, a1, 1
+; RV32-NEXT: mv a2, a1
+; RV32-NEXT: slli a1, a1, 2
+; RV32-NEXT: add a1, a1, a2
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vs2r.v v16, (a1) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v18, v10, v18
+; RV32-NEXT: vand.vv v16, v10, v12
+; RV32-NEXT: vand.vx v10, v10, a0
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: vxor.vv v10, v2, v10
+; RV32-NEXT: vmul.vv v12, v8, v26
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: vmul.vv v12, v8, v4
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: vmul.vv v12, v8, v30
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: vmul.vv v12, v8, v20
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: vmul.vv v12, v8, v28
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: vmul.vv v12, v8, v24
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: vmul.vv v12, v8, v0
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: vmul.vv v12, v8, v6
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: vmul.vv v12, v8, v22
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: addi a0, sp, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: vmul.vv v12, v8, v14
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: vmul.vv v12, v8, v18
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: vmul.vv v8, v8, v16
+; RV32-NEXT: vxor.vv v8, v10, v8
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add sp, sp, a0
+; RV32-NEXT: lw ra, 348(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s0, 344(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s1, 340(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s2, 336(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s3, 332(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s4, 328(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s5, 324(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s6, 320(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s7, 316(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s8, 312(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s9, 308(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s10, 304(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s11, 300(sp) # 4-byte Folded Reload
+; RV32-NEXT: addi sp, sp, 352
+; RV32-NEXT: ret
+;
+; RV64-LABEL: clmul_nxv2i64:
+; RV64: # %bb.0:
+; RV64-NEXT: vsetvli a0, zero, e64, m2, ta, ma
+; RV64-NEXT: vand.vi v12, v10, 2
+; RV64-NEXT: vand.vi v14, v10, 1
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v14, v12
+; RV64-NEXT: vand.vi v14, v10, 4
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vi v14, v10, 8
+; RV64-NEXT: li a0, 16
+; RV64-NEXT: li a1, 32
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a0
+; RV64-NEXT: li a0, 64
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: li a1, 128
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a0
+; RV64-NEXT: li a0, 256
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: li a1, 512
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a0
+; RV64-NEXT: li a2, 1024
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: li a0, 1
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a2
+; RV64-NEXT: slli a1, a0, 11
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: lui a1, 1
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: lui a1, 2
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: lui a1, 4
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: lui a1, 8
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: lui a1, 16
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: lui a1, 32
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: lui a1, 64
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: lui a1, 128
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: lui a1, 256
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: lui a1, 512
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: lui a1, 1024
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: lui a1, 2048
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: lui a1, 4096
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: lui a1, 8192
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: lui a1, 16384
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: lui a1, 32768
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: lui a1, 65536
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: lui a1, 131072
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: lui a1, 262144
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 31
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 32
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 33
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 34
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 35
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 36
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 37
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 38
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 39
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 40
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 41
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 42
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 43
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 44
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 45
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 46
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 47
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 48
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 49
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 50
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 51
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 52
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 53
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 54
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 55
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 56
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 57
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 58
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 59
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 60
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 61
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: li a1, -1
+; RV64-NEXT: slli a0, a0, 62
+; RV64-NEXT: slli a1, a1, 63
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a0
+; RV64-NEXT: vand.vx v10, v10, a1
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vmul.vv v8, v8, v10
+; RV64-NEXT: vxor.vv v8, v12, v8
+; RV64-NEXT: ret
+ %a = call <vscale x 2 x i64> @llvm.clmul.nxv2i64(<vscale x 2 x i64> %x, <vscale x 2 x i64> %y)
+ ret <vscale x 2 x i64> %a
+}
+
+define <vscale x 4 x i64> @clmul_nxv4i64(<vscale x 4 x i64> %x, <vscale x 4 x i64> %y) nounwind {
+; RV32-LABEL: clmul_nxv4i64:
+; RV32: # %bb.0:
+; RV32-NEXT: addi sp, sp, -352
+; RV32-NEXT: sw ra, 348(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s0, 344(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s1, 340(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s2, 336(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s3, 332(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s4, 328(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s5, 324(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s6, 320(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s7, 316(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s8, 312(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s9, 308(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s10, 304(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s11, 300(sp) # 4-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: sub sp, sp, a0
+; RV32-NEXT: lui a1, 524288
+; RV32-NEXT: li s4, 1
+; RV32-NEXT: li a3, 2
+; RV32-NEXT: li a2, 4
+; RV32-NEXT: li a0, 8
+; RV32-NEXT: li s3, 16
+; RV32-NEXT: li s2, 32
+; RV32-NEXT: li s5, 64
+; RV32-NEXT: li s6, 128
+; RV32-NEXT: li s8, 256
+; RV32-NEXT: li s1, 512
+; RV32-NEXT: li s7, 1024
+; RV32-NEXT: lui ra, 1
+; RV32-NEXT: lui s11, 2
+; RV32-NEXT: lui s10, 4
+; RV32-NEXT: lui s9, 8
+; RV32-NEXT: lui s0, 16
+; RV32-NEXT: lui t6, 32
+; RV32-NEXT: lui t5, 64
+; RV32-NEXT: lui t4, 128
+; RV32-NEXT: lui t3, 256
+; RV32-NEXT: lui t2, 512
+; RV32-NEXT: lui t1, 1024
+; RV32-NEXT: lui t0, 2048
+; RV32-NEXT: lui a7, 4096
+; RV32-NEXT: lui a6, 8192
+; RV32-NEXT: lui a5, 16384
+; RV32-NEXT: lui a4, 32768
+; RV32-NEXT: sw a1, 272(sp)
+; RV32-NEXT: sw zero, 276(sp)
+; RV32-NEXT: sw zero, 264(sp)
+; RV32-NEXT: sw s4, 268(sp)
+; RV32-NEXT: sw zero, 256(sp)
+; RV32-NEXT: sw a3, 260(sp)
+; RV32-NEXT: lui a3, 65536
+; RV32-NEXT: sw zero, 248(sp)
+; RV32-NEXT: sw a2, 252(sp)
+; RV32-NEXT: lui a2, 131072
+; RV32-NEXT: sw zero, 240(sp)
+; RV32-NEXT: sw a0, 244(sp)
+; RV32-NEXT: vsetvli a0, zero, e64, m4, ta, ma
+; RV32-NEXT: vand.vi v28, v12, 2
+; RV32-NEXT: vand.vi v4, v12, 1
+; RV32-NEXT: vand.vi v24, v12, 4
+; RV32-NEXT: vand.vi v20, v12, 8
+; RV32-NEXT: sw zero, 232(sp)
+; RV32-NEXT: sw s3, 236(sp)
+; RV32-NEXT: vand.vx v16, v12, s3
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v16, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: addi s3, sp, 272
+; RV32-NEXT: sw zero, 224(sp)
+; RV32-NEXT: sw s2, 228(sp)
+; RV32-NEXT: vand.vx v0, v12, s2
+; RV32-NEXT: addi s2, sp, 264
+; RV32-NEXT: sw zero, 216(sp)
+; RV32-NEXT: sw s5, 220(sp)
+; RV32-NEXT: vmul.vv v16, v8, v28
+; RV32-NEXT: vmul.vv v28, v8, v4
+; RV32-NEXT: vxor.vi v28, v28, 0
+; RV32-NEXT: vxor.vv v28, v28, v16
+; RV32-NEXT: vand.vx v16, v12, s5
+; RV32-NEXT: addi s5, sp, 256
+; RV32-NEXT: sw zero, 208(sp)
+; RV32-NEXT: sw s6, 212(sp)
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vxor.vv v28, v28, v24
+; RV32-NEXT: vand.vx v24, v12, s6
+; RV32-NEXT: addi s6, sp, 248
+; RV32-NEXT: sw zero, 200(sp)
+; RV32-NEXT: sw s8, 204(sp)
+; RV32-NEXT: vmul.vv v20, v8, v20
+; RV32-NEXT: vxor.vv v20, v28, v20
+; RV32-NEXT: vand.vx v28, v12, s8
+; RV32-NEXT: addi s8, sp, 240
+; RV32-NEXT: sw zero, 192(sp)
+; RV32-NEXT: sw s1, 196(sp)
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v4, v8, v4
+; RV32-NEXT: vxor.vv v20, v20, v4
+; RV32-NEXT: vand.vx v4, v12, s1
+; RV32-NEXT: sw zero, 184(sp)
+; RV32-NEXT: sw s7, 188(sp)
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: vxor.vv v20, v20, v0
+; RV32-NEXT: vand.vx v0, v12, s7
+; RV32-NEXT: slli a0, s4, 11
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v20, v20, v16
+; RV32-NEXT: vand.vx v16, v12, ra
+; RV32-NEXT: sw zero, 176(sp)
+; RV32-NEXT: sw a0, 180(sp)
+; RV32-NEXT: sw zero, 168(sp)
+; RV32-NEXT: sw ra, 172(sp)
+; RV32-NEXT: addi s4, sp, 216
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vxor.vv v24, v20, v24
+; RV32-NEXT: vand.vx v20, v12, s11
+; RV32-NEXT: sw zero, 160(sp)
+; RV32-NEXT: sw s11, 164(sp)
+; RV32-NEXT: addi s11, sp, 208
+; RV32-NEXT: vmul.vv v28, v8, v28
+; RV32-NEXT: vxor.vv v28, v24, v28
+; RV32-NEXT: vand.vx v24, v12, s10
+; RV32-NEXT: sw zero, 152(sp)
+; RV32-NEXT: sw s10, 156(sp)
+; RV32-NEXT: addi s10, sp, 200
+; RV32-NEXT: vmul.vv v4, v8, v4
+; RV32-NEXT: vxor.vv v4, v28, v4
+; RV32-NEXT: vand.vx v28, v12, s9
+; RV32-NEXT: sw zero, 144(sp)
+; RV32-NEXT: sw s9, 148(sp)
+; RV32-NEXT: addi s9, sp, 192
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: vxor.vv v4, v4, v0
+; RV32-NEXT: vand.vx v0, v12, a0
+; RV32-NEXT: addi ra, sp, 184
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: vxor.vv v0, v4, v0
+; RV32-NEXT: vand.vx v4, v12, s0
+; RV32-NEXT: sw zero, 136(sp)
+; RV32-NEXT: sw s0, 140(sp)
+; RV32-NEXT: addi s1, sp, 176
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v0, v0, v16
+; RV32-NEXT: vand.vx v16, v12, t6
+; RV32-NEXT: sw zero, 128(sp)
+; RV32-NEXT: sw t6, 132(sp)
+; RV32-NEXT: addi s0, sp, 168
+; RV32-NEXT: vmul.vv v20, v8, v20
+; RV32-NEXT: vxor.vv v0, v0, v20
+; RV32-NEXT: vand.vx v20, v12, t5
+; RV32-NEXT: sw zero, 120(sp)
+; RV32-NEXT: sw t5, 124(sp)
+; RV32-NEXT: addi t6, sp, 160
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vxor.vv v0, v0, v24
+; RV32-NEXT: vand.vx v24, v12, t4
+; RV32-NEXT: sw zero, 112(sp)
+; RV32-NEXT: sw t4, 116(sp)
+; RV32-NEXT: addi t5, sp, 152
+; RV32-NEXT: vmul.vv v28, v8, v28
+; RV32-NEXT: vxor.vv v0, v0, v28
+; RV32-NEXT: vand.vx v28, v12, t3
+; RV32-NEXT: sw zero, 104(sp)
+; RV32-NEXT: sw t3, 108(sp)
+; RV32-NEXT: addi t4, sp, 144
+; RV32-NEXT: vmul.vv v4, v8, v4
+; RV32-NEXT: vxor.vv v0, v0, v4
+; RV32-NEXT: vand.vx v4, v12, t2
+; RV32-NEXT: sw zero, 96(sp)
+; RV32-NEXT: sw t2, 100(sp)
+; RV32-NEXT: addi t3, sp, 136
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v16, v0, v16
+; RV32-NEXT: vand.vx v0, v12, t1
+; RV32-NEXT: sw zero, 88(sp)
+; RV32-NEXT: sw t1, 92(sp)
+; RV32-NEXT: addi t2, sp, 128
+; RV32-NEXT: vmul.vv v20, v8, v20
+; RV32-NEXT: vxor.vv v20, v16, v20
+; RV32-NEXT: vand.vx v16, v12, t0
+; RV32-NEXT: sw zero, 80(sp)
+; RV32-NEXT: sw t0, 84(sp)
+; RV32-NEXT: addi t1, sp, 120
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vxor.vv v24, v20, v24
+; RV32-NEXT: vand.vx v20, v12, a7
+; RV32-NEXT: sw zero, 72(sp)
+; RV32-NEXT: sw a7, 76(sp)
+; RV32-NEXT: addi t0, sp, 112
+; RV32-NEXT: vmul.vv v28, v8, v28
+; RV32-NEXT: vxor.vv v24, v24, v28
+; RV32-NEXT: vand.vx v28, v12, a6
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v28, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: sw zero, 64(sp)
+; RV32-NEXT: sw a6, 68(sp)
+; RV32-NEXT: addi a7, sp, 104
+; RV32-NEXT: vmul.vv v28, v8, v4
+; RV32-NEXT: vxor.vv v24, v24, v28
+; RV32-NEXT: vand.vx v28, v12, a5
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v28, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: sw zero, 56(sp)
+; RV32-NEXT: sw a5, 60(sp)
+; RV32-NEXT: addi a6, sp, 96
+; RV32-NEXT: vmul.vv v28, v8, v0
+; RV32-NEXT: vxor.vv v28, v24, v28
+; RV32-NEXT: vand.vx v24, v12, a4
+; RV32-NEXT: sw zero, 48(sp)
+; RV32-NEXT: sw a4, 52(sp)
+; RV32-NEXT: addi a5, sp, 88
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v16, v28, v16
+; RV32-NEXT: vand.vx v28, v12, a3
+; RV32-NEXT: sw zero, 40(sp)
+; RV32-NEXT: sw a3, 44(sp)
+; RV32-NEXT: addi a4, sp, 80
+; RV32-NEXT: vmul.vv v20, v8, v20
+; RV32-NEXT: vxor.vv v16, v16, v20
+; RV32-NEXT: vand.vx v4, v12, a2
+; RV32-NEXT: sw zero, 32(sp)
+; RV32-NEXT: sw a2, 36(sp)
+; RV32-NEXT: addi a3, sp, 72
+; RV32-NEXT: sw zero, 24(sp)
+; RV32-NEXT: lui a1, 262144
+; RV32-NEXT: sw a1, 28(sp)
+; RV32-NEXT: sw zero, 16(sp)
+; RV32-NEXT: lui a0, 524288
+; RV32-NEXT: sw a0, 20(sp)
+; RV32-NEXT: addi a2, sp, 64
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv s7, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add s7, s7, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add s7, s7, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, s7
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v20, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v20, v8, v20
+; RV32-NEXT: vxor.vv v20, v16, v20
+; RV32-NEXT: vlse64.v v16, (s3), zero
+; RV32-NEXT: addi s3, sp, 56
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv s7, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add s7, s7, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, s7
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v0, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: vxor.vv v0, v20, v0
+; RV32-NEXT: vlse64.v v20, (s2), zero
+; RV32-NEXT: addi s2, sp, 48
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vxor.vv v0, v0, v24
+; RV32-NEXT: vlse64.v v24, (s5), zero
+; RV32-NEXT: addi s5, sp, 40
+; RV32-NEXT: vmul.vv v28, v8, v28
+; RV32-NEXT: vxor.vv v0, v0, v28
+; RV32-NEXT: vlse64.v v28, (s6), zero
+; RV32-NEXT: addi s6, sp, 32
+; RV32-NEXT: vmul.vv v4, v8, v4
+; RV32-NEXT: vxor.vv v4, v0, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv s7, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add s7, s7, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add s7, s7, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, s7
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v4, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vlse64.v v4, (s8), zero
+; RV32-NEXT: addi s8, sp, 24
+; RV32-NEXT: vand.vv v16, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv s7, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, s7
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v16, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v12, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv s7, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add s7, s7, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, s7
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v16, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v12, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv s7, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add s7, s7, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, s7
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v16, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v12, v28
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv s7, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add s7, s7, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add s7, s7, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, s7
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v16, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v12, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv s7, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add s7, s7, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, s7
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v16, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 16
+; RV32-NEXT: addi s7, sp, 232
+; RV32-NEXT: vlse64.v v16, (s7), zero
+; RV32-NEXT: addi s7, sp, 224
+; RV32-NEXT: vlse64.v v20, (s7), zero
+; RV32-NEXT: vlse64.v v24, (s4), zero
+; RV32-NEXT: vlse64.v v28, (s11), zero
+; RV32-NEXT: vand.vv v16, v12, v16
+; RV32-NEXT: csrr s4, vlenb
+; RV32-NEXT: slli s4, s4, 4
+; RV32-NEXT: add s4, sp, s4
+; RV32-NEXT: addi s4, s4, 288
+; RV32-NEXT: vs4r.v v16, (s4) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v12, v20
+; RV32-NEXT: csrr s4, vlenb
+; RV32-NEXT: slli s4, s4, 2
+; RV32-NEXT: mv s7, s4
+; RV32-NEXT: slli s4, s4, 1
+; RV32-NEXT: add s7, s7, s4
+; RV32-NEXT: slli s4, s4, 2
+; RV32-NEXT: add s4, s4, s7
+; RV32-NEXT: add s4, sp, s4
+; RV32-NEXT: addi s4, s4, 288
+; RV32-NEXT: vs4r.v v16, (s4) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v12, v24
+; RV32-NEXT: csrr s4, vlenb
+; RV32-NEXT: slli s4, s4, 2
+; RV32-NEXT: mv s7, s4
+; RV32-NEXT: slli s4, s4, 4
+; RV32-NEXT: add s4, s4, s7
+; RV32-NEXT: add s4, sp, s4
+; RV32-NEXT: addi s4, s4, 288
+; RV32-NEXT: vs4r.v v16, (s4) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v12, v28
+; RV32-NEXT: csrr s4, vlenb
+; RV32-NEXT: slli s4, s4, 2
+; RV32-NEXT: mv s7, s4
+; RV32-NEXT: slli s4, s4, 1
+; RV32-NEXT: add s7, s7, s4
+; RV32-NEXT: slli s4, s4, 1
+; RV32-NEXT: add s7, s7, s4
+; RV32-NEXT: slli s4, s4, 2
+; RV32-NEXT: add s4, s4, s7
+; RV32-NEXT: add s4, sp, s4
+; RV32-NEXT: addi s4, s4, 288
+; RV32-NEXT: vs4r.v v16, (s4) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vlse64.v v20, (s10), zero
+; RV32-NEXT: vlse64.v v24, (s9), zero
+; RV32-NEXT: vlse64.v v28, (ra), zero
+; RV32-NEXT: vlse64.v v4, (s1), zero
+; RV32-NEXT: vand.vv v16, v12, v20
+; RV32-NEXT: csrr s1, vlenb
+; RV32-NEXT: slli s1, s1, 2
+; RV32-NEXT: mv s4, s1
+; RV32-NEXT: slli s1, s1, 1
+; RV32-NEXT: add s1, s1, s4
+; RV32-NEXT: add s1, sp, s1
+; RV32-NEXT: addi s1, s1, 288
+; RV32-NEXT: vs4r.v v16, (s1) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v12, v24
+; RV32-NEXT: csrr s1, vlenb
+; RV32-NEXT: slli s1, s1, 3
+; RV32-NEXT: mv s4, s1
+; RV32-NEXT: slli s1, s1, 2
+; RV32-NEXT: add s1, s1, s4
+; RV32-NEXT: add s1, sp, s1
+; RV32-NEXT: addi s1, s1, 288
+; RV32-NEXT: vs4r.v v16, (s1) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v12, v28
+; RV32-NEXT: csrr s1, vlenb
+; RV32-NEXT: slli s1, s1, 6
+; RV32-NEXT: add s1, sp, s1
+; RV32-NEXT: addi s1, s1, 288
+; RV32-NEXT: vs4r.v v16, (s1) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v12, v4
+; RV32-NEXT: csrr s1, vlenb
+; RV32-NEXT: slli s1, s1, 3
+; RV32-NEXT: mv s4, s1
+; RV32-NEXT: slli s1, s1, 1
+; RV32-NEXT: add s4, s4, s1
+; RV32-NEXT: slli s1, s1, 2
+; RV32-NEXT: add s1, s1, s4
+; RV32-NEXT: add s1, sp, s1
+; RV32-NEXT: addi s1, s1, 288
+; RV32-NEXT: vs4r.v v16, (s1) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vlse64.v v24, (s0), zero
+; RV32-NEXT: vlse64.v v28, (t6), zero
+; RV32-NEXT: vlse64.v v4, (t5), zero
+; RV32-NEXT: vlse64.v v0, (t4), zero
+; RV32-NEXT: vand.vv v16, v12, v24
+; RV32-NEXT: csrr t4, vlenb
+; RV32-NEXT: slli t4, t4, 3
+; RV32-NEXT: add t4, sp, t4
+; RV32-NEXT: addi t4, t4, 288
+; RV32-NEXT: vs4r.v v16, (t4) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v12, v28
+; RV32-NEXT: csrr t4, vlenb
+; RV32-NEXT: slli t4, t4, 2
+; RV32-NEXT: mv t5, t4
+; RV32-NEXT: slli t4, t4, 3
+; RV32-NEXT: add t4, t4, t5
+; RV32-NEXT: add t4, sp, t4
+; RV32-NEXT: addi t4, t4, 288
+; RV32-NEXT: vs4r.v v16, (t4) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v12, v4
+; RV32-NEXT: csrr t4, vlenb
+; RV32-NEXT: slli t4, t4, 2
+; RV32-NEXT: mv t5, t4
+; RV32-NEXT: slli t4, t4, 1
+; RV32-NEXT: add t5, t5, t4
+; RV32-NEXT: slli t4, t4, 1
+; RV32-NEXT: add t5, t5, t4
+; RV32-NEXT: slli t4, t4, 1
+; RV32-NEXT: add t4, t4, t5
+; RV32-NEXT: add t4, sp, t4
+; RV32-NEXT: addi t4, t4, 288
+; RV32-NEXT: vs4r.v v16, (t4) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v12, v0
+; RV32-NEXT: csrr t4, vlenb
+; RV32-NEXT: slli t4, t4, 2
+; RV32-NEXT: mv t5, t4
+; RV32-NEXT: slli t4, t4, 2
+; RV32-NEXT: add t5, t5, t4
+; RV32-NEXT: slli t4, t4, 2
+; RV32-NEXT: add t4, t4, t5
+; RV32-NEXT: add t4, sp, t4
+; RV32-NEXT: addi t4, t4, 288
+; RV32-NEXT: vs4r.v v16, (t4) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vlse64.v v28, (t3), zero
+; RV32-NEXT: vlse64.v v4, (t2), zero
+; RV32-NEXT: vlse64.v v0, (t1), zero
+; RV32-NEXT: vlse64.v v16, (t0), zero
+; RV32-NEXT: vand.vv v20, v12, v28
+; RV32-NEXT: csrr t0, vlenb
+; RV32-NEXT: slli t0, t0, 2
+; RV32-NEXT: add t0, sp, t0
+; RV32-NEXT: addi t0, t0, 288
+; RV32-NEXT: vs4r.v v20, (t0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v20, v12, v4
+; RV32-NEXT: csrr t0, vlenb
+; RV32-NEXT: slli t0, t0, 5
+; RV32-NEXT: add t0, sp, t0
+; RV32-NEXT: addi t0, t0, 288
+; RV32-NEXT: vs4r.v v20, (t0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v20, v12, v0
+; RV32-NEXT: csrr t0, vlenb
+; RV32-NEXT: slli t0, t0, 3
+; RV32-NEXT: mv t1, t0
+; RV32-NEXT: slli t0, t0, 1
+; RV32-NEXT: add t1, t1, t0
+; RV32-NEXT: slli t0, t0, 1
+; RV32-NEXT: add t0, t0, t1
+; RV32-NEXT: add t0, sp, t0
+; RV32-NEXT: addi t0, t0, 288
+; RV32-NEXT: vs4r.v v20, (t0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v12, v16
+; RV32-NEXT: csrr t0, vlenb
+; RV32-NEXT: slli t0, t0, 4
+; RV32-NEXT: mv t1, t0
+; RV32-NEXT: slli t0, t0, 2
+; RV32-NEXT: add t0, t0, t1
+; RV32-NEXT: add t0, sp, t0
+; RV32-NEXT: addi t0, t0, 288
+; RV32-NEXT: vs4r.v v16, (t0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vlse64.v v16, (a7), zero
+; RV32-NEXT: vlse64.v v0, (a6), zero
+; RV32-NEXT: vlse64.v v20, (a5), zero
+; RV32-NEXT: vlse64.v v24, (a4), zero
+; RV32-NEXT: vand.vv v4, v12, v16
+; RV32-NEXT: vand.vv v16, v12, v0
+; RV32-NEXT: csrr a4, vlenb
+; RV32-NEXT: slli a4, a4, 2
+; RV32-NEXT: mv a5, a4
+; RV32-NEXT: slli a4, a4, 1
+; RV32-NEXT: add a5, a5, a4
+; RV32-NEXT: slli a4, a4, 1
+; RV32-NEXT: add a4, a4, a5
+; RV32-NEXT: add a4, sp, a4
+; RV32-NEXT: addi a4, a4, 288
+; RV32-NEXT: vs4r.v v16, (a4) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v12, v20
+; RV32-NEXT: csrr a4, vlenb
+; RV32-NEXT: slli a4, a4, 2
+; RV32-NEXT: mv a5, a4
+; RV32-NEXT: slli a4, a4, 2
+; RV32-NEXT: add a5, a5, a4
+; RV32-NEXT: slli a4, a4, 1
+; RV32-NEXT: add a4, a4, a5
+; RV32-NEXT: add a4, sp, a4
+; RV32-NEXT: addi a4, a4, 288
+; RV32-NEXT: vs4r.v v16, (a4) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v12, v24
+; RV32-NEXT: csrr a4, vlenb
+; RV32-NEXT: slli a4, a4, 2
+; RV32-NEXT: mv a5, a4
+; RV32-NEXT: slli a4, a4, 1
+; RV32-NEXT: add a5, a5, a4
+; RV32-NEXT: slli a4, a4, 3
+; RV32-NEXT: add a4, a4, a5
+; RV32-NEXT: add a4, sp, a4
+; RV32-NEXT: addi a4, a4, 288
+; RV32-NEXT: vs4r.v v16, (a4) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vlse64.v v16, (a3), zero
+; RV32-NEXT: vlse64.v v20, (a2), zero
+; RV32-NEXT: vlse64.v v24, (s3), zero
+; RV32-NEXT: vlse64.v v28, (s2), zero
+; RV32-NEXT: vand.vv v0, v12, v16
+; RV32-NEXT: vand.vv v16, v12, v20
+; RV32-NEXT: csrr a2, vlenb
+; RV32-NEXT: slli a2, a2, 3
+; RV32-NEXT: mv a3, a2
+; RV32-NEXT: slli a2, a2, 1
+; RV32-NEXT: add a2, a2, a3
+; RV32-NEXT: add a2, sp, a2
+; RV32-NEXT: addi a2, a2, 288
+; RV32-NEXT: vs4r.v v16, (a2) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v12, v24
+; RV32-NEXT: csrr a2, vlenb
+; RV32-NEXT: slli a2, a2, 4
+; RV32-NEXT: mv a3, a2
+; RV32-NEXT: slli a2, a2, 1
+; RV32-NEXT: add a2, a2, a3
+; RV32-NEXT: add a2, sp, a2
+; RV32-NEXT: addi a2, a2, 288
+; RV32-NEXT: vs4r.v v16, (a2) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v12, v28
+; RV32-NEXT: csrr a2, vlenb
+; RV32-NEXT: slli a2, a2, 3
+; RV32-NEXT: mv a3, a2
+; RV32-NEXT: slli a2, a2, 3
+; RV32-NEXT: add a2, a2, a3
+; RV32-NEXT: add a2, sp, a2
+; RV32-NEXT: addi a2, a2, 288
+; RV32-NEXT: vs4r.v v16, (a2) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vlse64.v v16, (s5), zero
+; RV32-NEXT: vlse64.v v20, (s6), zero
+; RV32-NEXT: vlse64.v v24, (s8), zero
+; RV32-NEXT: vlse64.v v28, (a0), zero
+; RV32-NEXT: vand.vv v16, v12, v16
+; RV32-NEXT: addi a0, sp, 288
+; RV32-NEXT: vs4r.v v16, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v12, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a2, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a2
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v16, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v24, v12, v24
+; RV32-NEXT: vand.vv v20, v12, v28
+; RV32-NEXT: vand.vx v12, v12, a1
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v12, v16, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: vmul.vv v16, v8, v4
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: vmul.vv v16, v8, v0
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: addi a0, sp, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: vmul.vv v16, v8, v24
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: vmul.vv v8, v8, v20
+; RV32-NEXT: vxor.vv v8, v12, v8
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add sp, sp, a0
+; RV32-NEXT: lw ra, 348(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s0, 344(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s1, 340(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s2, 336(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s3, 332(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s4, 328(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s5, 324(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s6, 320(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s7, 316(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s8, 312(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s9, 308(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s10, 304(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s11, 300(sp) # 4-byte Folded Reload
+; RV32-NEXT: addi sp, sp, 352
+; RV32-NEXT: ret
+;
+; RV64-LABEL: clmul_nxv4i64:
+; RV64: # %bb.0:
+; RV64-NEXT: vsetvli a0, zero, e64, m4, ta, ma
+; RV64-NEXT: vand.vi v16, v12, 2
+; RV64-NEXT: vand.vi v20, v12, 1
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v20, v16
+; RV64-NEXT: vand.vi v20, v12, 4
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vi v20, v12, 8
+; RV64-NEXT: li a0, 16
+; RV64-NEXT: li a1, 32
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a0
+; RV64-NEXT: li a0, 64
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: li a1, 128
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a0
+; RV64-NEXT: li a0, 256
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: li a1, 512
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a0
+; RV64-NEXT: li a2, 1024
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: li a0, 1
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a2
+; RV64-NEXT: slli a1, a0, 11
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: lui a1, 1
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: lui a1, 2
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: lui a1, 4
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: lui a1, 8
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: lui a1, 16
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: lui a1, 32
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: lui a1, 64
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: lui a1, 128
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: lui a1, 256
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: lui a1, 512
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: lui a1, 1024
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: lui a1, 2048
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: lui a1, 4096
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: lui a1, 8192
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: lui a1, 16384
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: lui a1, 32768
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: lui a1, 65536
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: lui a1, 131072
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: lui a1, 262144
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 31
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 32
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 33
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 34
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 35
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 36
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 37
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 38
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 39
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 40
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 41
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 42
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 43
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 44
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 45
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 46
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 47
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 48
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 49
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 50
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 51
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 52
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 53
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 54
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 55
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 56
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 57
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 58
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 59
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 60
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 61
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: li a1, -1
+; RV64-NEXT: slli a0, a0, 62
+; RV64-NEXT: slli a1, a1, 63
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a0
+; RV64-NEXT: vand.vx v12, v12, a1
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vmul.vv v8, v8, v12
+; RV64-NEXT: vxor.vv v8, v16, v8
+; RV64-NEXT: ret
+ %a = call <vscale x 4 x i64> @llvm.clmul.nxv4i64(<vscale x 4 x i64> %x, <vscale x 4 x i64> %y)
+ ret <vscale x 4 x i64> %a
+}
+
+define <vscale x 8 x i64> @clmul_nxv8i64(<vscale x 8 x i64> %x, <vscale x 8 x i64> %y) nounwind {
+; RV32-LABEL: clmul_nxv8i64:
+; RV32: # %bb.0:
+; RV32-NEXT: addi sp, sp, -352
+; RV32-NEXT: sw ra, 348(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s0, 344(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s1, 340(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s2, 336(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s3, 332(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s4, 328(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s5, 324(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s6, 320(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s7, 316(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s8, 312(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s9, 308(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s10, 304(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s11, 300(sp) # 4-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: sub sp, sp, a0
+; RV32-NEXT: lui a1, 524288
+; RV32-NEXT: li s5, 1
+; RV32-NEXT: li a3, 2
+; RV32-NEXT: li a2, 4
+; RV32-NEXT: li s10, 8
+; RV32-NEXT: li a0, 16
+; RV32-NEXT: li t6, 32
+; RV32-NEXT: li s1, 64
+; RV32-NEXT: li s3, 128
+; RV32-NEXT: li s7, 256
+; RV32-NEXT: li s4, 512
+; RV32-NEXT: li s8, 1024
+; RV32-NEXT: lui ra, 1
+; RV32-NEXT: lui s11, 2
+; RV32-NEXT: lui s9, 4
+; RV32-NEXT: lui s6, 8
+; RV32-NEXT: lui s2, 16
+; RV32-NEXT: lui s0, 32
+; RV32-NEXT: lui t5, 64
+; RV32-NEXT: lui t4, 128
+; RV32-NEXT: lui t3, 256
+; RV32-NEXT: lui t2, 512
+; RV32-NEXT: lui t1, 1024
+; RV32-NEXT: lui t0, 2048
+; RV32-NEXT: lui a7, 4096
+; RV32-NEXT: lui a6, 8192
+; RV32-NEXT: lui a5, 16384
+; RV32-NEXT: lui a4, 32768
+; RV32-NEXT: sw a1, 272(sp)
+; RV32-NEXT: sw zero, 276(sp)
+; RV32-NEXT: sw zero, 264(sp)
+; RV32-NEXT: sw s5, 268(sp)
+; RV32-NEXT: sw zero, 256(sp)
+; RV32-NEXT: sw a3, 260(sp)
+; RV32-NEXT: lui a3, 65536
+; RV32-NEXT: sw zero, 248(sp)
+; RV32-NEXT: sw a2, 252(sp)
+; RV32-NEXT: lui a2, 131072
+; RV32-NEXT: sw zero, 240(sp)
+; RV32-NEXT: sw s10, 244(sp)
+; RV32-NEXT: vsetvli s10, zero, e64, m8, ta, ma
+; RV32-NEXT: vand.vi v24, v16, 2
+; RV32-NEXT: vand.vi v0, v16, 1
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: vxor.vi v0, v0, 0
+; RV32-NEXT: vxor.vv v24, v0, v24
+; RV32-NEXT: vand.vi v0, v16, 4
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: vxor.vv v24, v24, v0
+; RV32-NEXT: vand.vi v0, v16, 8
+; RV32-NEXT: sw zero, 232(sp)
+; RV32-NEXT: sw a0, 236(sp)
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: vxor.vv v24, v24, v0
+; RV32-NEXT: vand.vx v0, v16, a0
+; RV32-NEXT: addi s10, sp, 272
+; RV32-NEXT: sw zero, 224(sp)
+; RV32-NEXT: sw t6, 228(sp)
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: vxor.vv v24, v24, v0
+; RV32-NEXT: vand.vx v0, v16, t6
+; RV32-NEXT: sw zero, 216(sp)
+; RV32-NEXT: sw s1, 220(sp)
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: vxor.vv v24, v24, v0
+; RV32-NEXT: vand.vx v0, v16, s1
+; RV32-NEXT: sw zero, 208(sp)
+; RV32-NEXT: sw s3, 212(sp)
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: vxor.vv v24, v24, v0
+; RV32-NEXT: vand.vx v0, v16, s3
+; RV32-NEXT: sw zero, 200(sp)
+; RV32-NEXT: sw s7, 204(sp)
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: vxor.vv v24, v24, v0
+; RV32-NEXT: vand.vx v0, v16, s7
+; RV32-NEXT: sw zero, 192(sp)
+; RV32-NEXT: sw s4, 196(sp)
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: vxor.vv v24, v24, v0
+; RV32-NEXT: vand.vx v0, v16, s4
+; RV32-NEXT: sw zero, 184(sp)
+; RV32-NEXT: sw s8, 188(sp)
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: vxor.vv v24, v24, v0
+; RV32-NEXT: vand.vx v0, v16, s8
+; RV32-NEXT: slli s5, s5, 11
+; RV32-NEXT: sw zero, 176(sp)
+; RV32-NEXT: sw s5, 180(sp)
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: vxor.vv v24, v24, v0
+; RV32-NEXT: vand.vx v0, v16, s5
+; RV32-NEXT: addi s5, sp, 216
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: vxor.vv v24, v24, v0
+; RV32-NEXT: vand.vx v0, v16, ra
+; RV32-NEXT: sw zero, 168(sp)
+; RV32-NEXT: sw ra, 172(sp)
+; RV32-NEXT: addi ra, sp, 208
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: vxor.vv v24, v24, v0
+; RV32-NEXT: vand.vx v0, v16, s11
+; RV32-NEXT: sw zero, 160(sp)
+; RV32-NEXT: sw s11, 164(sp)
+; RV32-NEXT: addi s11, sp, 200
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: vxor.vv v24, v24, v0
+; RV32-NEXT: vand.vx v0, v16, s9
+; RV32-NEXT: sw zero, 152(sp)
+; RV32-NEXT: sw s9, 156(sp)
+; RV32-NEXT: addi s9, sp, 192
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: vxor.vv v24, v24, v0
+; RV32-NEXT: vand.vx v0, v16, s6
+; RV32-NEXT: sw zero, 144(sp)
+; RV32-NEXT: sw s6, 148(sp)
+; RV32-NEXT: addi s6, sp, 184
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: vxor.vv v24, v24, v0
+; RV32-NEXT: vand.vx v0, v16, s2
+; RV32-NEXT: sw zero, 136(sp)
+; RV32-NEXT: sw s2, 140(sp)
+; RV32-NEXT: addi s3, sp, 176
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: vxor.vv v24, v24, v0
+; RV32-NEXT: vand.vx v0, v16, s0
+; RV32-NEXT: sw zero, 128(sp)
+; RV32-NEXT: sw s0, 132(sp)
+; RV32-NEXT: addi s4, sp, 168
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: vxor.vv v24, v24, v0
+; RV32-NEXT: vand.vx v0, v16, t5
+; RV32-NEXT: sw zero, 120(sp)
+; RV32-NEXT: sw t5, 124(sp)
+; RV32-NEXT: addi s2, sp, 160
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: vxor.vv v24, v24, v0
+; RV32-NEXT: vand.vx v0, v16, t4
+; RV32-NEXT: sw zero, 112(sp)
+; RV32-NEXT: sw t4, 116(sp)
+; RV32-NEXT: addi s1, sp, 152
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: vxor.vv v24, v24, v0
+; RV32-NEXT: vand.vx v0, v16, t3
+; RV32-NEXT: sw zero, 104(sp)
+; RV32-NEXT: sw t3, 108(sp)
+; RV32-NEXT: addi t6, sp, 144
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: vxor.vv v24, v24, v0
+; RV32-NEXT: vand.vx v0, v16, t2
+; RV32-NEXT: sw zero, 96(sp)
+; RV32-NEXT: sw t2, 100(sp)
+; RV32-NEXT: addi s0, sp, 136
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: vxor.vv v24, v24, v0
+; RV32-NEXT: vand.vx v0, v16, t1
+; RV32-NEXT: sw zero, 88(sp)
+; RV32-NEXT: sw t1, 92(sp)
+; RV32-NEXT: addi t5, sp, 128
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: vxor.vv v24, v24, v0
+; RV32-NEXT: vand.vx v0, v16, t0
+; RV32-NEXT: sw zero, 80(sp)
+; RV32-NEXT: sw t0, 84(sp)
+; RV32-NEXT: addi t4, sp, 120
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: vxor.vv v24, v24, v0
+; RV32-NEXT: vand.vx v0, v16, a7
+; RV32-NEXT: sw zero, 72(sp)
+; RV32-NEXT: sw a7, 76(sp)
+; RV32-NEXT: addi t2, sp, 112
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: vxor.vv v24, v24, v0
+; RV32-NEXT: vand.vx v0, v16, a6
+; RV32-NEXT: sw zero, 64(sp)
+; RV32-NEXT: sw a6, 68(sp)
+; RV32-NEXT: addi t3, sp, 104
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: vxor.vv v24, v24, v0
+; RV32-NEXT: vand.vx v0, v16, a5
+; RV32-NEXT: sw zero, 56(sp)
+; RV32-NEXT: sw a5, 60(sp)
+; RV32-NEXT: addi t1, sp, 96
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: vxor.vv v24, v24, v0
+; RV32-NEXT: vand.vx v0, v16, a4
+; RV32-NEXT: sw zero, 48(sp)
+; RV32-NEXT: sw a4, 52(sp)
+; RV32-NEXT: addi t0, sp, 88
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: vxor.vv v24, v24, v0
+; RV32-NEXT: vand.vx v0, v16, a3
+; RV32-NEXT: sw zero, 40(sp)
+; RV32-NEXT: sw a3, 44(sp)
+; RV32-NEXT: addi a7, sp, 80
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: vxor.vv v24, v24, v0
+; RV32-NEXT: vand.vx v0, v16, a2
+; RV32-NEXT: sw zero, 32(sp)
+; RV32-NEXT: sw a2, 36(sp)
+; RV32-NEXT: sw zero, 24(sp)
+; RV32-NEXT: lui a0, 262144
+; RV32-NEXT: sw a0, 28(sp)
+; RV32-NEXT: sw zero, 16(sp)
+; RV32-NEXT: sw a1, 20(sp)
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: vxor.vv v24, v24, v0
+; RV32-NEXT: sw t2, 4(sp) # 4-byte Folded Spill
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a1, a1, 3
+; RV32-NEXT: mv a2, a1
+; RV32-NEXT: slli a1, a1, 5
+; RV32-NEXT: add a1, a1, a2
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vs8r.v v24, (a1) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vlse64.v v24, (s10), zero
+; RV32-NEXT: addi a6, sp, 72
+; RV32-NEXT: addi a5, sp, 64
+; RV32-NEXT: addi a4, sp, 56
+; RV32-NEXT: vand.vv v24, v16, v24
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a1, a1, 8
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vs8r.v v24, (a1) # vscale x 64-byte Folded Spill
+; RV32-NEXT: addi a1, sp, 48
+; RV32-NEXT: addi s10, sp, 40
+; RV32-NEXT: addi a3, sp, 32
+; RV32-NEXT: addi a2, sp, 24
+; RV32-NEXT: addi s7, sp, 264
+; RV32-NEXT: vlse64.v v24, (s7), zero
+; RV32-NEXT: csrr t2, vlenb
+; RV32-NEXT: slli t2, t2, 4
+; RV32-NEXT: mv s7, t2
+; RV32-NEXT: slli t2, t2, 1
+; RV32-NEXT: add s7, s7, t2
+; RV32-NEXT: slli t2, t2, 1
+; RV32-NEXT: add s7, s7, t2
+; RV32-NEXT: slli t2, t2, 1
+; RV32-NEXT: add t2, t2, s7
+; RV32-NEXT: add t2, sp, t2
+; RV32-NEXT: addi t2, t2, 288
+; RV32-NEXT: vs8r.v v24, (t2) # vscale x 64-byte Folded Spill
+; RV32-NEXT: addi s7, sp, 256
+; RV32-NEXT: vlse64.v v0, (s7), zero
+; RV32-NEXT: addi s7, sp, 248
+; RV32-NEXT: vlse64.v v24, (s7), zero
+; RV32-NEXT: csrr t2, vlenb
+; RV32-NEXT: slli t2, t2, 3
+; RV32-NEXT: mv s7, t2
+; RV32-NEXT: slli t2, t2, 1
+; RV32-NEXT: add s7, s7, t2
+; RV32-NEXT: slli t2, t2, 1
+; RV32-NEXT: add s7, s7, t2
+; RV32-NEXT: slli t2, t2, 1
+; RV32-NEXT: add s7, s7, t2
+; RV32-NEXT: slli t2, t2, 1
+; RV32-NEXT: add t2, t2, s7
+; RV32-NEXT: add t2, sp, t2
+; RV32-NEXT: addi t2, t2, 288
+; RV32-NEXT: vs8r.v v24, (t2) # vscale x 64-byte Folded Spill
+; RV32-NEXT: addi s7, sp, 240
+; RV32-NEXT: vlse64.v v24, (s7), zero
+; RV32-NEXT: csrr t2, vlenb
+; RV32-NEXT: slli t2, t2, 3
+; RV32-NEXT: mv s7, t2
+; RV32-NEXT: slli t2, t2, 1
+; RV32-NEXT: add s7, s7, t2
+; RV32-NEXT: slli t2, t2, 2
+; RV32-NEXT: add s7, s7, t2
+; RV32-NEXT: slli t2, t2, 1
+; RV32-NEXT: add t2, t2, s7
+; RV32-NEXT: add t2, sp, t2
+; RV32-NEXT: addi t2, t2, 288
+; RV32-NEXT: vs8r.v v24, (t2) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr t2, vlenb
+; RV32-NEXT: slli t2, t2, 4
+; RV32-NEXT: mv s7, t2
+; RV32-NEXT: slli t2, t2, 1
+; RV32-NEXT: add s7, s7, t2
+; RV32-NEXT: slli t2, t2, 1
+; RV32-NEXT: add s7, s7, t2
+; RV32-NEXT: slli t2, t2, 1
+; RV32-NEXT: add t2, t2, s7
+; RV32-NEXT: add t2, sp, t2
+; RV32-NEXT: addi t2, t2, 288
+; RV32-NEXT: vl8r.v v24, (t2) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v24, v16, v24
+; RV32-NEXT: csrr t2, vlenb
+; RV32-NEXT: slli t2, t2, 5
+; RV32-NEXT: mv s7, t2
+; RV32-NEXT: slli t2, t2, 1
+; RV32-NEXT: add s7, s7, t2
+; RV32-NEXT: slli t2, t2, 1
+; RV32-NEXT: add t2, t2, s7
+; RV32-NEXT: add t2, sp, t2
+; RV32-NEXT: addi t2, t2, 288
+; RV32-NEXT: vs8r.v v24, (t2) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vv v24, v16, v0
+; RV32-NEXT: csrr t2, vlenb
+; RV32-NEXT: slli t2, t2, 3
+; RV32-NEXT: mv s7, t2
+; RV32-NEXT: slli t2, t2, 2
+; RV32-NEXT: add s7, s7, t2
+; RV32-NEXT: slli t2, t2, 1
+; RV32-NEXT: add s7, s7, t2
+; RV32-NEXT: slli t2, t2, 1
+; RV32-NEXT: add t2, t2, s7
+; RV32-NEXT: add t2, sp, t2
+; RV32-NEXT: addi t2, t2, 288
+; RV32-NEXT: vs8r.v v24, (t2) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr t2, vlenb
+; RV32-NEXT: slli t2, t2, 3
+; RV32-NEXT: mv s7, t2
+; RV32-NEXT: slli t2, t2, 1
+; RV32-NEXT: add s7, s7, t2
+; RV32-NEXT: slli t2, t2, 1
+; RV32-NEXT: add s7, s7, t2
+; RV32-NEXT: slli t2, t2, 1
+; RV32-NEXT: add s7, s7, t2
+; RV32-NEXT: slli t2, t2, 1
+; RV32-NEXT: add t2, t2, s7
+; RV32-NEXT: add t2, sp, t2
+; RV32-NEXT: addi t2, t2, 288
+; RV32-NEXT: vl8r.v v24, (t2) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v24, v16, v24
+; RV32-NEXT: csrr t2, vlenb
+; RV32-NEXT: slli t2, t2, 4
+; RV32-NEXT: mv s7, t2
+; RV32-NEXT: slli t2, t2, 1
+; RV32-NEXT: add s7, s7, t2
+; RV32-NEXT: slli t2, t2, 1
+; RV32-NEXT: add s7, s7, t2
+; RV32-NEXT: slli t2, t2, 1
+; RV32-NEXT: add t2, t2, s7
+; RV32-NEXT: add t2, sp, t2
+; RV32-NEXT: addi t2, t2, 288
+; RV32-NEXT: vs8r.v v24, (t2) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr t2, vlenb
+; RV32-NEXT: slli t2, t2, 3
+; RV32-NEXT: mv s7, t2
+; RV32-NEXT: slli t2, t2, 1
+; RV32-NEXT: add s7, s7, t2
+; RV32-NEXT: slli t2, t2, 2
+; RV32-NEXT: add s7, s7, t2
+; RV32-NEXT: slli t2, t2, 1
+; RV32-NEXT: add t2, t2, s7
+; RV32-NEXT: add t2, sp, t2
+; RV32-NEXT: addi t2, t2, 288
+; RV32-NEXT: vl8r.v v24, (t2) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v24, v16, v24
+; RV32-NEXT: csrr t2, vlenb
+; RV32-NEXT: slli t2, t2, 3
+; RV32-NEXT: mv s7, t2
+; RV32-NEXT: slli t2, t2, 1
+; RV32-NEXT: add s7, s7, t2
+; RV32-NEXT: slli t2, t2, 1
+; RV32-NEXT: add s7, s7, t2
+; RV32-NEXT: slli t2, t2, 1
+; RV32-NEXT: add s7, s7, t2
+; RV32-NEXT: slli t2, t2, 1
+; RV32-NEXT: add t2, t2, s7
+; RV32-NEXT: add t2, sp, t2
+; RV32-NEXT: addi t2, t2, 288
+; RV32-NEXT: vs8r.v v24, (t2) # vscale x 64-byte Folded Spill
+; RV32-NEXT: addi s7, sp, 16
+; RV32-NEXT: addi s8, sp, 232
+; RV32-NEXT: vlse64.v v24, (s8), zero
+; RV32-NEXT: csrr s8, vlenb
+; RV32-NEXT: slli s8, s8, 4
+; RV32-NEXT: mv t2, s8
+; RV32-NEXT: slli s8, s8, 2
+; RV32-NEXT: add t2, t2, s8
+; RV32-NEXT: slli s8, s8, 1
+; RV32-NEXT: add s8, s8, t2
+; RV32-NEXT: lw t2, 4(sp) # 4-byte Folded Reload
+; RV32-NEXT: add s8, sp, s8
+; RV32-NEXT: addi s8, s8, 288
+; RV32-NEXT: vs8r.v v24, (s8) # vscale x 64-byte Folded Spill
+; RV32-NEXT: addi s8, sp, 224
+; RV32-NEXT: vlse64.v v0, (s8), zero
+; RV32-NEXT: vlse64.v v24, (s5), zero
+; RV32-NEXT: csrr s5, vlenb
+; RV32-NEXT: slli s5, s5, 3
+; RV32-NEXT: mv s8, s5
+; RV32-NEXT: slli s5, s5, 1
+; RV32-NEXT: add s8, s8, s5
+; RV32-NEXT: slli s5, s5, 2
+; RV32-NEXT: add s8, s8, s5
+; RV32-NEXT: slli s5, s5, 1
+; RV32-NEXT: add s5, s5, s8
+; RV32-NEXT: add s5, sp, s5
+; RV32-NEXT: addi s5, s5, 288
+; RV32-NEXT: vs8r.v v24, (s5) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vlse64.v v24, (ra), zero
+; RV32-NEXT: csrr s5, vlenb
+; RV32-NEXT: slli s5, s5, 3
+; RV32-NEXT: mv s8, s5
+; RV32-NEXT: slli s5, s5, 3
+; RV32-NEXT: add s8, s8, s5
+; RV32-NEXT: slli s5, s5, 1
+; RV32-NEXT: add s5, s5, s8
+; RV32-NEXT: add s5, sp, s5
+; RV32-NEXT: addi s5, s5, 288
+; RV32-NEXT: vs8r.v v24, (s5) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr s5, vlenb
+; RV32-NEXT: slli s5, s5, 4
+; RV32-NEXT: mv s8, s5
+; RV32-NEXT: slli s5, s5, 2
+; RV32-NEXT: add s8, s8, s5
+; RV32-NEXT: slli s5, s5, 1
+; RV32-NEXT: add s5, s5, s8
+; RV32-NEXT: add s5, sp, s5
+; RV32-NEXT: addi s5, s5, 288
+; RV32-NEXT: vl8r.v v24, (s5) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v24, v16, v24
+; RV32-NEXT: csrr s5, vlenb
+; RV32-NEXT: slli s5, s5, 3
+; RV32-NEXT: mv s8, s5
+; RV32-NEXT: slli s5, s5, 1
+; RV32-NEXT: add s8, s8, s5
+; RV32-NEXT: slli s5, s5, 1
+; RV32-NEXT: add s5, s5, s8
+; RV32-NEXT: add s5, sp, s5
+; RV32-NEXT: addi s5, s5, 288
+; RV32-NEXT: vs8r.v v24, (s5) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vv v24, v16, v0
+; RV32-NEXT: csrr s5, vlenb
+; RV32-NEXT: slli s5, s5, 4
+; RV32-NEXT: mv s8, s5
+; RV32-NEXT: slli s5, s5, 1
+; RV32-NEXT: add s8, s8, s5
+; RV32-NEXT: slli s5, s5, 1
+; RV32-NEXT: add s5, s5, s8
+; RV32-NEXT: add s5, sp, s5
+; RV32-NEXT: addi s5, s5, 288
+; RV32-NEXT: vs8r.v v24, (s5) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr s5, vlenb
+; RV32-NEXT: slli s5, s5, 3
+; RV32-NEXT: mv s8, s5
+; RV32-NEXT: slli s5, s5, 1
+; RV32-NEXT: add s8, s8, s5
+; RV32-NEXT: slli s5, s5, 2
+; RV32-NEXT: add s8, s8, s5
+; RV32-NEXT: slli s5, s5, 1
+; RV32-NEXT: add s5, s5, s8
+; RV32-NEXT: add s5, sp, s5
+; RV32-NEXT: addi s5, s5, 288
+; RV32-NEXT: vl8r.v v24, (s5) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v24, v16, v24
+; RV32-NEXT: csrr s5, vlenb
+; RV32-NEXT: slli s5, s5, 3
+; RV32-NEXT: mv s8, s5
+; RV32-NEXT: slli s5, s5, 2
+; RV32-NEXT: add s8, s8, s5
+; RV32-NEXT: slli s5, s5, 2
+; RV32-NEXT: add s5, s5, s8
+; RV32-NEXT: add s5, sp, s5
+; RV32-NEXT: addi s5, s5, 288
+; RV32-NEXT: vs8r.v v24, (s5) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr s5, vlenb
+; RV32-NEXT: slli s5, s5, 3
+; RV32-NEXT: mv s8, s5
+; RV32-NEXT: slli s5, s5, 3
+; RV32-NEXT: add s8, s8, s5
+; RV32-NEXT: slli s5, s5, 1
+; RV32-NEXT: add s5, s5, s8
+; RV32-NEXT: add s5, sp, s5
+; RV32-NEXT: addi s5, s5, 288
+; RV32-NEXT: vl8r.v v24, (s5) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v24, v16, v24
+; RV32-NEXT: csrr s5, vlenb
+; RV32-NEXT: slli s5, s5, 3
+; RV32-NEXT: mv s8, s5
+; RV32-NEXT: slli s5, s5, 1
+; RV32-NEXT: add s8, s8, s5
+; RV32-NEXT: slli s5, s5, 2
+; RV32-NEXT: add s8, s8, s5
+; RV32-NEXT: slli s5, s5, 1
+; RV32-NEXT: add s5, s5, s8
+; RV32-NEXT: add s5, sp, s5
+; RV32-NEXT: addi s5, s5, 288
+; RV32-NEXT: vs8r.v v24, (s5) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vlse64.v v0, (s11), zero
+; RV32-NEXT: vlse64.v v24, (s9), zero
+; RV32-NEXT: csrr s5, vlenb
+; RV32-NEXT: slli s5, s5, 3
+; RV32-NEXT: mv s8, s5
+; RV32-NEXT: slli s5, s5, 3
+; RV32-NEXT: add s8, s8, s5
+; RV32-NEXT: slli s5, s5, 1
+; RV32-NEXT: add s5, s5, s8
+; RV32-NEXT: add s5, sp, s5
+; RV32-NEXT: addi s5, s5, 288
+; RV32-NEXT: vs8r.v v24, (s5) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vlse64.v v24, (s6), zero
+; RV32-NEXT: csrr s5, vlenb
+; RV32-NEXT: slli s5, s5, 4
+; RV32-NEXT: mv s6, s5
+; RV32-NEXT: slli s5, s5, 2
+; RV32-NEXT: add s6, s6, s5
+; RV32-NEXT: slli s5, s5, 1
+; RV32-NEXT: add s5, s5, s6
+; RV32-NEXT: add s5, sp, s5
+; RV32-NEXT: addi s5, s5, 288
+; RV32-NEXT: vs8r.v v24, (s5) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vlse64.v v24, (s3), zero
+; RV32-NEXT: csrr s3, vlenb
+; RV32-NEXT: slli s3, s3, 6
+; RV32-NEXT: mv s5, s3
+; RV32-NEXT: slli s3, s3, 1
+; RV32-NEXT: add s3, s3, s5
+; RV32-NEXT: add s3, sp, s3
+; RV32-NEXT: addi s3, s3, 288
+; RV32-NEXT: vs8r.v v24, (s3) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vv v0, v16, v0
+; RV32-NEXT: csrr s3, vlenb
+; RV32-NEXT: slli s3, s3, 4
+; RV32-NEXT: mv s5, s3
+; RV32-NEXT: slli s3, s3, 1
+; RV32-NEXT: add s3, s3, s5
+; RV32-NEXT: add s3, sp, s3
+; RV32-NEXT: addi s3, s3, 288
+; RV32-NEXT: vs8r.v v0, (s3) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr s3, vlenb
+; RV32-NEXT: slli s3, s3, 3
+; RV32-NEXT: mv s5, s3
+; RV32-NEXT: slli s3, s3, 3
+; RV32-NEXT: add s5, s5, s3
+; RV32-NEXT: slli s3, s3, 1
+; RV32-NEXT: add s3, s3, s5
+; RV32-NEXT: add s3, sp, s3
+; RV32-NEXT: addi s3, s3, 288
+; RV32-NEXT: vl8r.v v24, (s3) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v24, v16, v24
+; RV32-NEXT: csrr s3, vlenb
+; RV32-NEXT: slli s3, s3, 3
+; RV32-NEXT: mv s5, s3
+; RV32-NEXT: slli s3, s3, 2
+; RV32-NEXT: add s5, s5, s3
+; RV32-NEXT: slli s3, s3, 1
+; RV32-NEXT: add s3, s3, s5
+; RV32-NEXT: add s3, sp, s3
+; RV32-NEXT: addi s3, s3, 288
+; RV32-NEXT: vs8r.v v24, (s3) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr s3, vlenb
+; RV32-NEXT: slli s3, s3, 4
+; RV32-NEXT: mv s5, s3
+; RV32-NEXT: slli s3, s3, 2
+; RV32-NEXT: add s5, s5, s3
+; RV32-NEXT: slli s3, s3, 1
+; RV32-NEXT: add s3, s3, s5
+; RV32-NEXT: add s3, sp, s3
+; RV32-NEXT: addi s3, s3, 288
+; RV32-NEXT: vl8r.v v24, (s3) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v24, v16, v24
+; RV32-NEXT: csrr s3, vlenb
+; RV32-NEXT: slli s3, s3, 5
+; RV32-NEXT: mv s5, s3
+; RV32-NEXT: slli s3, s3, 2
+; RV32-NEXT: add s3, s3, s5
+; RV32-NEXT: add s3, sp, s3
+; RV32-NEXT: addi s3, s3, 288
+; RV32-NEXT: vs8r.v v24, (s3) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr s3, vlenb
+; RV32-NEXT: slli s3, s3, 6
+; RV32-NEXT: mv s5, s3
+; RV32-NEXT: slli s3, s3, 1
+; RV32-NEXT: add s3, s3, s5
+; RV32-NEXT: add s3, sp, s3
+; RV32-NEXT: addi s3, s3, 288
+; RV32-NEXT: vl8r.v v24, (s3) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v24, v16, v24
+; RV32-NEXT: csrr s3, vlenb
+; RV32-NEXT: slli s3, s3, 4
+; RV32-NEXT: mv s5, s3
+; RV32-NEXT: slli s3, s3, 2
+; RV32-NEXT: add s5, s5, s3
+; RV32-NEXT: slli s3, s3, 1
+; RV32-NEXT: add s3, s3, s5
+; RV32-NEXT: add s3, sp, s3
+; RV32-NEXT: addi s3, s3, 288
+; RV32-NEXT: vs8r.v v24, (s3) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vlse64.v v24, (s4), zero
+; RV32-NEXT: csrr s3, vlenb
+; RV32-NEXT: slli s3, s3, 6
+; RV32-NEXT: mv s4, s3
+; RV32-NEXT: slli s3, s3, 1
+; RV32-NEXT: add s3, s3, s4
+; RV32-NEXT: add s3, sp, s3
+; RV32-NEXT: addi s3, s3, 288
+; RV32-NEXT: vs8r.v v24, (s3) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vlse64.v v0, (s2), zero
+; RV32-NEXT: vlse64.v v24, (s1), zero
+; RV32-NEXT: csrr s1, vlenb
+; RV32-NEXT: slli s1, s1, 3
+; RV32-NEXT: mv s2, s1
+; RV32-NEXT: slli s1, s1, 3
+; RV32-NEXT: add s2, s2, s1
+; RV32-NEXT: slli s1, s1, 1
+; RV32-NEXT: add s1, s1, s2
+; RV32-NEXT: add s1, sp, s1
+; RV32-NEXT: addi s1, s1, 288
+; RV32-NEXT: vs8r.v v24, (s1) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vlse64.v v24, (t6), zero
+; RV32-NEXT: csrr t6, vlenb
+; RV32-NEXT: slli t6, t6, 3
+; RV32-NEXT: mv s1, t6
+; RV32-NEXT: slli t6, t6, 1
+; RV32-NEXT: add s1, s1, t6
+; RV32-NEXT: slli t6, t6, 1
+; RV32-NEXT: add s1, s1, t6
+; RV32-NEXT: slli t6, t6, 2
+; RV32-NEXT: add t6, t6, s1
+; RV32-NEXT: add t6, sp, t6
+; RV32-NEXT: addi t6, t6, 288
+; RV32-NEXT: vs8r.v v24, (t6) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr t6, vlenb
+; RV32-NEXT: slli t6, t6, 6
+; RV32-NEXT: mv s1, t6
+; RV32-NEXT: slli t6, t6, 1
+; RV32-NEXT: add t6, t6, s1
+; RV32-NEXT: add t6, sp, t6
+; RV32-NEXT: addi t6, t6, 288
+; RV32-NEXT: vl8r.v v24, (t6) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v24, v16, v24
+; RV32-NEXT: csrr t6, vlenb
+; RV32-NEXT: slli t6, t6, 3
+; RV32-NEXT: mv s1, t6
+; RV32-NEXT: slli t6, t6, 2
+; RV32-NEXT: add t6, t6, s1
+; RV32-NEXT: add t6, sp, t6
+; RV32-NEXT: addi t6, t6, 288
+; RV32-NEXT: vs8r.v v24, (t6) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vv v24, v16, v0
+; RV32-NEXT: csrr t6, vlenb
+; RV32-NEXT: slli t6, t6, 5
+; RV32-NEXT: mv s1, t6
+; RV32-NEXT: slli t6, t6, 1
+; RV32-NEXT: add t6, t6, s1
+; RV32-NEXT: add t6, sp, t6
+; RV32-NEXT: addi t6, t6, 288
+; RV32-NEXT: vs8r.v v24, (t6) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr t6, vlenb
+; RV32-NEXT: slli t6, t6, 3
+; RV32-NEXT: mv s1, t6
+; RV32-NEXT: slli t6, t6, 3
+; RV32-NEXT: add s1, s1, t6
+; RV32-NEXT: slli t6, t6, 1
+; RV32-NEXT: add t6, t6, s1
+; RV32-NEXT: add t6, sp, t6
+; RV32-NEXT: addi t6, t6, 288
+; RV32-NEXT: vl8r.v v24, (t6) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v24, v16, v24
+; RV32-NEXT: csrr t6, vlenb
+; RV32-NEXT: slli t6, t6, 3
+; RV32-NEXT: mv s1, t6
+; RV32-NEXT: slli t6, t6, 1
+; RV32-NEXT: add s1, s1, t6
+; RV32-NEXT: slli t6, t6, 3
+; RV32-NEXT: add t6, t6, s1
+; RV32-NEXT: add t6, sp, t6
+; RV32-NEXT: addi t6, t6, 288
+; RV32-NEXT: vs8r.v v24, (t6) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr t6, vlenb
+; RV32-NEXT: slli t6, t6, 3
+; RV32-NEXT: mv s1, t6
+; RV32-NEXT: slli t6, t6, 1
+; RV32-NEXT: add s1, s1, t6
+; RV32-NEXT: slli t6, t6, 1
+; RV32-NEXT: add s1, s1, t6
+; RV32-NEXT: slli t6, t6, 2
+; RV32-NEXT: add t6, t6, s1
+; RV32-NEXT: add t6, sp, t6
+; RV32-NEXT: addi t6, t6, 288
+; RV32-NEXT: vl8r.v v24, (t6) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v24, v16, v24
+; RV32-NEXT: csrr t6, vlenb
+; RV32-NEXT: slli t6, t6, 3
+; RV32-NEXT: mv s1, t6
+; RV32-NEXT: slli t6, t6, 3
+; RV32-NEXT: add s1, s1, t6
+; RV32-NEXT: slli t6, t6, 1
+; RV32-NEXT: add t6, t6, s1
+; RV32-NEXT: add t6, sp, t6
+; RV32-NEXT: addi t6, t6, 288
+; RV32-NEXT: vs8r.v v24, (t6) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vlse64.v v24, (s0), zero
+; RV32-NEXT: csrr t6, vlenb
+; RV32-NEXT: slli t6, t6, 3
+; RV32-NEXT: mv s0, t6
+; RV32-NEXT: slli t6, t6, 1
+; RV32-NEXT: add s0, s0, t6
+; RV32-NEXT: slli t6, t6, 1
+; RV32-NEXT: add s0, s0, t6
+; RV32-NEXT: slli t6, t6, 2
+; RV32-NEXT: add t6, t6, s0
+; RV32-NEXT: add t6, sp, t6
+; RV32-NEXT: addi t6, t6, 288
+; RV32-NEXT: vs8r.v v24, (t6) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vlse64.v v0, (t5), zero
+; RV32-NEXT: vlse64.v v24, (t4), zero
+; RV32-NEXT: csrr t4, vlenb
+; RV32-NEXT: slli t4, t4, 6
+; RV32-NEXT: mv t5, t4
+; RV32-NEXT: slli t4, t4, 1
+; RV32-NEXT: add t4, t4, t5
+; RV32-NEXT: add t4, sp, t4
+; RV32-NEXT: addi t4, t4, 288
+; RV32-NEXT: vs8r.v v24, (t4) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vlse64.v v24, (t2), zero
+; RV32-NEXT: csrr t2, vlenb
+; RV32-NEXT: slli t2, t2, 4
+; RV32-NEXT: mv t4, t2
+; RV32-NEXT: slli t2, t2, 1
+; RV32-NEXT: add t4, t4, t2
+; RV32-NEXT: slli t2, t2, 2
+; RV32-NEXT: add t2, t2, t4
+; RV32-NEXT: add t2, sp, t2
+; RV32-NEXT: addi t2, t2, 288
+; RV32-NEXT: vs8r.v v24, (t2) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr t2, vlenb
+; RV32-NEXT: slli t2, t2, 3
+; RV32-NEXT: mv t4, t2
+; RV32-NEXT: slli t2, t2, 1
+; RV32-NEXT: add t4, t4, t2
+; RV32-NEXT: slli t2, t2, 1
+; RV32-NEXT: add t4, t4, t2
+; RV32-NEXT: slli t2, t2, 2
+; RV32-NEXT: add t2, t2, t4
+; RV32-NEXT: add t2, sp, t2
+; RV32-NEXT: addi t2, t2, 288
+; RV32-NEXT: vl8r.v v24, (t2) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v24, v16, v24
+; RV32-NEXT: csrr t2, vlenb
+; RV32-NEXT: slli t2, t2, 5
+; RV32-NEXT: add t2, sp, t2
+; RV32-NEXT: addi t2, t2, 288
+; RV32-NEXT: vs8r.v v24, (t2) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vv v24, v16, v0
+; RV32-NEXT: csrr t2, vlenb
+; RV32-NEXT: slli t2, t2, 3
+; RV32-NEXT: mv t4, t2
+; RV32-NEXT: slli t2, t2, 1
+; RV32-NEXT: add t4, t4, t2
+; RV32-NEXT: slli t2, t2, 2
+; RV32-NEXT: add t2, t2, t4
+; RV32-NEXT: add t2, sp, t2
+; RV32-NEXT: addi t2, t2, 288
+; RV32-NEXT: vs8r.v v24, (t2) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr t2, vlenb
+; RV32-NEXT: slli t2, t2, 6
+; RV32-NEXT: mv t4, t2
+; RV32-NEXT: slli t2, t2, 1
+; RV32-NEXT: add t2, t2, t4
+; RV32-NEXT: add t2, sp, t2
+; RV32-NEXT: addi t2, t2, 288
+; RV32-NEXT: vl8r.v v24, (t2) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v24, v16, v24
+; RV32-NEXT: csrr t2, vlenb
+; RV32-NEXT: slli t2, t2, 4
+; RV32-NEXT: mv t4, t2
+; RV32-NEXT: slli t2, t2, 3
+; RV32-NEXT: add t2, t2, t4
+; RV32-NEXT: add t2, sp, t2
+; RV32-NEXT: addi t2, t2, 288
+; RV32-NEXT: vs8r.v v24, (t2) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr t2, vlenb
+; RV32-NEXT: slli t2, t2, 4
+; RV32-NEXT: mv t4, t2
+; RV32-NEXT: slli t2, t2, 1
+; RV32-NEXT: add t4, t4, t2
+; RV32-NEXT: slli t2, t2, 2
+; RV32-NEXT: add t2, t2, t4
+; RV32-NEXT: add t2, sp, t2
+; RV32-NEXT: addi t2, t2, 288
+; RV32-NEXT: vl8r.v v24, (t2) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v24, v16, v24
+; RV32-NEXT: csrr t2, vlenb
+; RV32-NEXT: slli t2, t2, 6
+; RV32-NEXT: mv t4, t2
+; RV32-NEXT: slli t2, t2, 1
+; RV32-NEXT: add t2, t2, t4
+; RV32-NEXT: add t2, sp, t2
+; RV32-NEXT: addi t2, t2, 288
+; RV32-NEXT: vs8r.v v24, (t2) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vlse64.v v24, (t3), zero
+; RV32-NEXT: csrr t2, vlenb
+; RV32-NEXT: slli t2, t2, 4
+; RV32-NEXT: mv t3, t2
+; RV32-NEXT: slli t2, t2, 1
+; RV32-NEXT: add t3, t3, t2
+; RV32-NEXT: slli t2, t2, 2
+; RV32-NEXT: add t2, t2, t3
+; RV32-NEXT: add t2, sp, t2
+; RV32-NEXT: addi t2, t2, 288
+; RV32-NEXT: vs8r.v v24, (t2) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vlse64.v v0, (t1), zero
+; RV32-NEXT: vlse64.v v24, (t0), zero
+; RV32-NEXT: csrr t0, vlenb
+; RV32-NEXT: slli t0, t0, 3
+; RV32-NEXT: mv t1, t0
+; RV32-NEXT: slli t0, t0, 1
+; RV32-NEXT: add t1, t1, t0
+; RV32-NEXT: slli t0, t0, 1
+; RV32-NEXT: add t1, t1, t0
+; RV32-NEXT: slli t0, t0, 2
+; RV32-NEXT: add t0, t0, t1
+; RV32-NEXT: add t0, sp, t0
+; RV32-NEXT: addi t0, t0, 288
+; RV32-NEXT: vs8r.v v24, (t0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vlse64.v v24, (a7), zero
+; RV32-NEXT: csrr a7, vlenb
+; RV32-NEXT: slli a7, a7, 7
+; RV32-NEXT: add a7, sp, a7
+; RV32-NEXT: addi a7, a7, 288
+; RV32-NEXT: vs8r.v v24, (a7) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a7, vlenb
+; RV32-NEXT: slli a7, a7, 4
+; RV32-NEXT: mv t0, a7
+; RV32-NEXT: slli a7, a7, 1
+; RV32-NEXT: add t0, t0, a7
+; RV32-NEXT: slli a7, a7, 2
+; RV32-NEXT: add a7, a7, t0
+; RV32-NEXT: add a7, sp, a7
+; RV32-NEXT: addi a7, a7, 288
+; RV32-NEXT: vl8r.v v24, (a7) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v24, v16, v24
+; RV32-NEXT: csrr a7, vlenb
+; RV32-NEXT: slli a7, a7, 3
+; RV32-NEXT: mv t0, a7
+; RV32-NEXT: slli a7, a7, 1
+; RV32-NEXT: add a7, a7, t0
+; RV32-NEXT: add a7, sp, a7
+; RV32-NEXT: addi a7, a7, 288
+; RV32-NEXT: vs8r.v v24, (a7) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vv v24, v16, v0
+; RV32-NEXT: csrr a7, vlenb
+; RV32-NEXT: slli a7, a7, 4
+; RV32-NEXT: mv t0, a7
+; RV32-NEXT: slli a7, a7, 2
+; RV32-NEXT: add a7, a7, t0
+; RV32-NEXT: add a7, sp, a7
+; RV32-NEXT: addi a7, a7, 288
+; RV32-NEXT: vs8r.v v24, (a7) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a7, vlenb
+; RV32-NEXT: slli a7, a7, 3
+; RV32-NEXT: mv t0, a7
+; RV32-NEXT: slli a7, a7, 1
+; RV32-NEXT: add t0, t0, a7
+; RV32-NEXT: slli a7, a7, 1
+; RV32-NEXT: add t0, t0, a7
+; RV32-NEXT: slli a7, a7, 2
+; RV32-NEXT: add a7, a7, t0
+; RV32-NEXT: add a7, sp, a7
+; RV32-NEXT: addi a7, a7, 288
+; RV32-NEXT: vl8r.v v24, (a7) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v24, v16, v24
+; RV32-NEXT: csrr a7, vlenb
+; RV32-NEXT: slli a7, a7, 3
+; RV32-NEXT: mv t0, a7
+; RV32-NEXT: slli a7, a7, 4
+; RV32-NEXT: add a7, a7, t0
+; RV32-NEXT: add a7, sp, a7
+; RV32-NEXT: addi a7, a7, 288
+; RV32-NEXT: vs8r.v v24, (a7) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a7, vlenb
+; RV32-NEXT: slli a7, a7, 7
+; RV32-NEXT: add a7, sp, a7
+; RV32-NEXT: addi a7, a7, 288
+; RV32-NEXT: vl8r.v v24, (a7) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v24, v16, v24
+; RV32-NEXT: csrr a7, vlenb
+; RV32-NEXT: slli a7, a7, 3
+; RV32-NEXT: mv t0, a7
+; RV32-NEXT: slli a7, a7, 1
+; RV32-NEXT: add t0, t0, a7
+; RV32-NEXT: slli a7, a7, 1
+; RV32-NEXT: add t0, t0, a7
+; RV32-NEXT: slli a7, a7, 2
+; RV32-NEXT: add a7, a7, t0
+; RV32-NEXT: add a7, sp, a7
+; RV32-NEXT: addi a7, a7, 288
+; RV32-NEXT: vs8r.v v24, (a7) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vlse64.v v24, (a6), zero
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 7
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 288
+; RV32-NEXT: vs8r.v v24, (a6) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vlse64.v v0, (a5), zero
+; RV32-NEXT: vlse64.v v24, (a4), zero
+; RV32-NEXT: csrr a4, vlenb
+; RV32-NEXT: slli a4, a4, 4
+; RV32-NEXT: mv a5, a4
+; RV32-NEXT: slli a4, a4, 1
+; RV32-NEXT: add a5, a5, a4
+; RV32-NEXT: slli a4, a4, 2
+; RV32-NEXT: add a4, a4, a5
+; RV32-NEXT: add a4, sp, a4
+; RV32-NEXT: addi a4, a4, 288
+; RV32-NEXT: vs8r.v v24, (a4) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vlse64.v v24, (a1), zero
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a1, a1, 3
+; RV32-NEXT: mv a4, a1
+; RV32-NEXT: slli a1, a1, 1
+; RV32-NEXT: add a4, a4, a1
+; RV32-NEXT: slli a1, a1, 1
+; RV32-NEXT: add a4, a4, a1
+; RV32-NEXT: slli a1, a1, 1
+; RV32-NEXT: add a1, a1, a4
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vs8r.v v24, (a1) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a1, a1, 7
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vl8r.v v24, (a1) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v24, v16, v24
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a1, a1, 4
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vs8r.v v24, (a1) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vv v24, v16, v0
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a1, a1, 3
+; RV32-NEXT: mv a4, a1
+; RV32-NEXT: slli a1, a1, 3
+; RV32-NEXT: add a1, a1, a4
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vs8r.v v24, (a1) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a1, a1, 4
+; RV32-NEXT: mv a4, a1
+; RV32-NEXT: slli a1, a1, 1
+; RV32-NEXT: add a4, a4, a1
+; RV32-NEXT: slli a1, a1, 2
+; RV32-NEXT: add a1, a1, a4
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vl8r.v v24, (a1) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v24, v16, v24
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a1, a1, 7
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vs8r.v v24, (a1) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a1, a1, 3
+; RV32-NEXT: mv a4, a1
+; RV32-NEXT: slli a1, a1, 1
+; RV32-NEXT: add a4, a4, a1
+; RV32-NEXT: slli a1, a1, 1
+; RV32-NEXT: add a4, a4, a1
+; RV32-NEXT: slli a1, a1, 1
+; RV32-NEXT: add a1, a1, a4
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vl8r.v v24, (a1) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v24, v16, v24
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a1, a1, 4
+; RV32-NEXT: mv a4, a1
+; RV32-NEXT: slli a1, a1, 1
+; RV32-NEXT: add a4, a4, a1
+; RV32-NEXT: slli a1, a1, 2
+; RV32-NEXT: add a1, a1, a4
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vs8r.v v24, (a1) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vlse64.v v24, (s10), zero
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a1, a1, 6
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vs8r.v v24, (a1) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vlse64.v v0, (a3), zero
+; RV32-NEXT: vlse64.v v24, (a2), zero
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a1, a1, 3
+; RV32-NEXT: mv a2, a1
+; RV32-NEXT: slli a1, a1, 1
+; RV32-NEXT: add a2, a2, a1
+; RV32-NEXT: slli a1, a1, 1
+; RV32-NEXT: add a2, a2, a1
+; RV32-NEXT: slli a1, a1, 1
+; RV32-NEXT: add a1, a1, a2
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vs8r.v v24, (a1) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vlse64.v v24, (s7), zero
+; RV32-NEXT: addi a1, sp, 288
+; RV32-NEXT: vs8r.v v24, (a1) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a1, a1, 6
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vl8r.v v24, (a1) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v24, v16, v24
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a1, a1, 3
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vs8r.v v24, (a1) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vv v24, v16, v0
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a1, a1, 6
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vs8r.v v24, (a1) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a1, a1, 3
+; RV32-NEXT: mv a2, a1
+; RV32-NEXT: slli a1, a1, 1
+; RV32-NEXT: add a2, a2, a1
+; RV32-NEXT: slli a1, a1, 1
+; RV32-NEXT: add a2, a2, a1
+; RV32-NEXT: slli a1, a1, 1
+; RV32-NEXT: add a1, a1, a2
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vl8r.v v24, (a1) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v24, v16, v24
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a1, a1, 3
+; RV32-NEXT: mv a2, a1
+; RV32-NEXT: slli a1, a1, 1
+; RV32-NEXT: add a2, a2, a1
+; RV32-NEXT: slli a1, a1, 1
+; RV32-NEXT: add a2, a2, a1
+; RV32-NEXT: slli a1, a1, 1
+; RV32-NEXT: add a1, a1, a2
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vs8r.v v24, (a1) # vscale x 64-byte Folded Spill
+; RV32-NEXT: addi a1, sp, 288
+; RV32-NEXT: vl8r.v v24, (a1) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v0, v16, v24
+; RV32-NEXT: vand.vx v16, v16, a0
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v16, v24, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 8
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vxor.vv v16, v16, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vxor.vv v16, v16, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vxor.vv v16, v16, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vxor.vv v16, v16, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vxor.vv v16, v16, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vxor.vv v16, v16, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vxor.vv v16, v16, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vxor.vv v16, v16, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vxor.vv v16, v16, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vxor.vv v16, v16, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vxor.vv v16, v16, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vxor.vv v16, v16, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vxor.vv v16, v16, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vxor.vv v16, v16, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vxor.vv v16, v16, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vxor.vv v16, v16, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vxor.vv v16, v16, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vxor.vv v16, v16, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vxor.vv v16, v16, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vxor.vv v16, v16, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vxor.vv v16, v16, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vxor.vv v16, v16, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vxor.vv v16, v16, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vxor.vv v16, v16, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vxor.vv v16, v16, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vxor.vv v16, v16, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vxor.vv v16, v16, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 7
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vxor.vv v16, v16, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vxor.vv v16, v16, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vxor.vv v16, v16, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vxor.vv v16, v16, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vxor.vv v16, v16, v24
+; RV32-NEXT: vmul.vv v8, v8, v0
+; RV32-NEXT: vxor.vv v8, v16, v8
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add sp, sp, a0
+; RV32-NEXT: lw ra, 348(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s0, 344(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s1, 340(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s2, 336(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s3, 332(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s4, 328(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s5, 324(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s6, 320(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s7, 316(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s8, 312(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s9, 308(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s10, 304(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s11, 300(sp) # 4-byte Folded Reload
+; RV32-NEXT: addi sp, sp, 352
+; RV32-NEXT: ret
+;
+; RV64-LABEL: clmul_nxv8i64:
+; RV64: # %bb.0:
+; RV64-NEXT: vsetvli a0, zero, e64, m8, ta, ma
+; RV64-NEXT: vand.vi v24, v16, 2
+; RV64-NEXT: vand.vi v0, v16, 1
+; RV64-NEXT: vmul.vv v24, v8, v24
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v0, v24
+; RV64-NEXT: vand.vi v0, v16, 4
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vi v0, v16, 8
+; RV64-NEXT: li a0, 16
+; RV64-NEXT: li a1, 32
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a0
+; RV64-NEXT: li a0, 64
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: li a1, 128
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a0
+; RV64-NEXT: li a0, 256
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: li a1, 512
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a0
+; RV64-NEXT: li a2, 1024
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: li a0, 1
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a2
+; RV64-NEXT: slli a1, a0, 11
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: lui a1, 1
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: lui a1, 2
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: lui a1, 4
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: lui a1, 8
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: lui a1, 16
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: lui a1, 32
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: lui a1, 64
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: lui a1, 128
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: lui a1, 256
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: lui a1, 512
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: lui a1, 1024
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: lui a1, 2048
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: lui a1, 4096
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: lui a1, 8192
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: lui a1, 16384
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: lui a1, 32768
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: lui a1, 65536
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: lui a1, 131072
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: lui a1, 262144
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: slli a1, a0, 31
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: slli a1, a0, 32
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: slli a1, a0, 33
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: slli a1, a0, 34
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: slli a1, a0, 35
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: slli a1, a0, 36
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: slli a1, a0, 37
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: slli a1, a0, 38
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: slli a1, a0, 39
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: slli a1, a0, 40
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: slli a1, a0, 41
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: slli a1, a0, 42
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: slli a1, a0, 43
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: slli a1, a0, 44
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: slli a1, a0, 45
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: slli a1, a0, 46
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: slli a1, a0, 47
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: slli a1, a0, 48
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: slli a1, a0, 49
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: slli a1, a0, 50
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: slli a1, a0, 51
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: slli a1, a0, 52
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: slli a1, a0, 53
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: slli a1, a0, 54
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: slli a1, a0, 55
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: slli a1, a0, 56
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: slli a1, a0, 57
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: slli a1, a0, 58
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: slli a1, a0, 59
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: slli a1, a0, 60
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: slli a1, a0, 61
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a1
+; RV64-NEXT: li a1, -1
+; RV64-NEXT: slli a0, a0, 62
+; RV64-NEXT: slli a1, a1, 63
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v0, v16, a0
+; RV64-NEXT: vand.vx v16, v16, a1
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vmul.vv v8, v8, v16
+; RV64-NEXT: vxor.vv v8, v24, v8
+; RV64-NEXT: ret
+ %a = call <vscale x 8 x i64> @llvm.clmul.nxv8i64(<vscale x 8 x i64> %x, <vscale x 8 x i64> %y)
+ ret <vscale x 8 x i64> %a
+}
+
+define <vscale x 1 x i32> @clmulr_nxv1i32(<vscale x 1 x i32> %x, <vscale x 1 x i32> %y) nounwind {
+; CHECK-LABEL: clmulr_nxv1i32:
+; CHECK: # %bb.0:
+; CHECK-NEXT: addi sp, sp, -16
+; CHECK-NEXT: csrr a0, vlenb
+; CHECK-NEXT: sub sp, sp, a0
+; CHECK-NEXT: vsetvli a0, zero, e32, mf2, ta, ma
+; CHECK-NEXT: vsrl.vi v9, v8, 8
+; CHECK-NEXT: lui a4, 16
+; CHECK-NEXT: vsrl.vi v10, v8, 24
+; CHECK-NEXT: vsll.vi v11, v8, 24
+; CHECK-NEXT: lui a0, 61681
+; CHECK-NEXT: lui a1, 209715
+; CHECK-NEXT: lui a5, 349525
+; CHECK-NEXT: li a6, 16
+; CHECK-NEXT: addi a3, a4, -256
+; CHECK-NEXT: addi a2, a0, -241
+; CHECK-NEXT: addi a1, a1, 819
+; CHECK-NEXT: addi a0, a5, 1365
+; CHECK-NEXT: vand.vx v9, v9, a3
+; CHECK-NEXT: vand.vx v8, v8, a3
+; CHECK-NEXT: vor.vv v9, v9, v10
+; CHECK-NEXT: vsll.vi v8, v8, 8
+; CHECK-NEXT: vor.vv v8, v11, v8
+; CHECK-NEXT: vor.vv v8, v8, v9
+; CHECK-NEXT: vsrl.vi v9, v8, 4
+; CHECK-NEXT: vand.vx v8, v8, a2
+; CHECK-NEXT: vand.vx v9, v9, a2
+; CHECK-NEXT: vsll.vi v8, v8, 4
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v9, v8, 2
+; CHECK-NEXT: vand.vx v8, v8, a1
+; CHECK-NEXT: vand.vx v9, v9, a1
+; CHECK-NEXT: vsll.vi v8, v8, 2
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v9, v8, 1
+; CHECK-NEXT: vand.vx v8, v8, a0
+; CHECK-NEXT: vand.vx v9, v9, a0
+; CHECK-NEXT: vadd.vv v8, v8, v8
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vand.vx v9, v8, a6
+; CHECK-NEXT: li a5, 32
+; CHECK-NEXT: vand.vx v10, v8, a5
+; CHECK-NEXT: li a5, 64
+; CHECK-NEXT: vand.vx v11, v8, a5
+; CHECK-NEXT: li a5, 128
+; CHECK-NEXT: vand.vx v12, v8, a5
+; CHECK-NEXT: li a5, 256
+; CHECK-NEXT: vand.vx v13, v8, a5
+; CHECK-NEXT: li a5, 512
+; CHECK-NEXT: vand.vx v14, v8, a5
+; CHECK-NEXT: li a5, 1024
+; CHECK-NEXT: vand.vx v15, v8, a5
+; CHECK-NEXT: li a5, 1
+; CHECK-NEXT: slli a5, a5, 11
+; CHECK-NEXT: vand.vx v16, v8, a5
+; CHECK-NEXT: lui a5, 1
+; CHECK-NEXT: vand.vx v17, v8, a5
+; CHECK-NEXT: lui a5, 2
+; CHECK-NEXT: vand.vx v18, v8, a5
+; CHECK-NEXT: lui a5, 4
+; CHECK-NEXT: vand.vx v19, v8, a5
+; CHECK-NEXT: lui a5, 8
+; CHECK-NEXT: vand.vx v20, v8, a5
+; CHECK-NEXT: lui a5, 32
+; CHECK-NEXT: vand.vx v21, v8, a4
+; CHECK-NEXT: lui a4, 64
+; CHECK-NEXT: vand.vx v22, v8, a5
+; CHECK-NEXT: lui a5, 128
+; CHECK-NEXT: vand.vx v23, v8, a4
+; CHECK-NEXT: lui a4, 256
+; CHECK-NEXT: vand.vx v24, v8, a5
+; CHECK-NEXT: lui a5, 512
+; CHECK-NEXT: vand.vx v25, v8, a4
+; CHECK-NEXT: lui a4, 1024
+; CHECK-NEXT: vand.vx v26, v8, a5
+; CHECK-NEXT: lui a5, 2048
+; CHECK-NEXT: vand.vx v27, v8, a4
+; CHECK-NEXT: lui a4, 4096
+; CHECK-NEXT: vand.vx v28, v8, a5
+; CHECK-NEXT: lui a5, 8192
+; CHECK-NEXT: vand.vx v29, v8, a4
+; CHECK-NEXT: lui a4, 16384
+; CHECK-NEXT: vand.vx v30, v8, a5
+; CHECK-NEXT: lui a5, 32768
+; CHECK-NEXT: vand.vx v31, v8, a4
+; CHECK-NEXT: lui a4, 65536
+; CHECK-NEXT: vand.vx v7, v8, a5
+; CHECK-NEXT: lui a5, 131072
+; CHECK-NEXT: vand.vx v6, v8, a4
+; CHECK-NEXT: lui a4, 262144
+; CHECK-NEXT: vand.vx v5, v8, a5
+; CHECK-NEXT: lui a5, 524288
+; CHECK-NEXT: vand.vi v4, v8, 2
+; CHECK-NEXT: vand.vi v3, v8, 1
+; CHECK-NEXT: vand.vi v2, v8, 4
+; CHECK-NEXT: vand.vi v1, v8, 8
+; CHECK-NEXT: vand.vx v0, v8, a4
+; CHECK-NEXT: vmul.vv v4, v8, v4
+; CHECK-NEXT: vmul.vv v3, v8, v3
+; CHECK-NEXT: vmul.vv v2, v8, v2
+; CHECK-NEXT: vmul.vv v1, v8, v1
+; CHECK-NEXT: vmul.vv v9, v8, v9
+; CHECK-NEXT: vmul.vv v10, v8, v10
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vmul.vv v12, v8, v12
+; CHECK-NEXT: vmul.vv v13, v8, v13
+; CHECK-NEXT: vmul.vv v14, v8, v14
+; CHECK-NEXT: vmul.vv v15, v8, v15
+; CHECK-NEXT: vmul.vv v16, v8, v16
+; CHECK-NEXT: vmul.vv v17, v8, v17
+; CHECK-NEXT: vmul.vv v18, v8, v18
+; CHECK-NEXT: vmul.vv v19, v8, v19
+; CHECK-NEXT: vmul.vv v20, v8, v20
+; CHECK-NEXT: vmul.vv v21, v8, v21
+; CHECK-NEXT: vmul.vv v22, v8, v22
+; CHECK-NEXT: vmul.vv v23, v8, v23
+; CHECK-NEXT: vmul.vv v24, v8, v24
+; CHECK-NEXT: vmul.vv v25, v8, v25
+; CHECK-NEXT: vmul.vv v26, v8, v26
+; CHECK-NEXT: vmul.vv v27, v8, v27
+; CHECK-NEXT: vmul.vv v28, v8, v28
+; CHECK-NEXT: vmul.vv v29, v8, v29
+; CHECK-NEXT: vmul.vv v30, v8, v30
+; CHECK-NEXT: vmul.vv v31, v8, v31
+; CHECK-NEXT: vmul.vv v7, v8, v7
+; CHECK-NEXT: vmul.vv v6, v8, v6
+; CHECK-NEXT: vmul.vv v5, v8, v5
+; CHECK-NEXT: vmul.vv v0, v8, v0
+; CHECK-NEXT: addi a4, sp, 16
+; CHECK-NEXT: vs1r.v v0, (a4) # vscale x 8-byte Folded Spill
+; CHECK-NEXT: vand.vx v0, v8, a5
+; CHECK-NEXT: vmul.vv v8, v8, v0
+; CHECK-NEXT: vxor.vv v4, v3, v4
+; CHECK-NEXT: vxor.vv v4, v4, v2
+; CHECK-NEXT: vxor.vv v4, v4, v1
+; CHECK-NEXT: vxor.vv v9, v4, v9
+; CHECK-NEXT: vxor.vv v9, v9, v10
+; CHECK-NEXT: vxor.vv v9, v9, v11
+; CHECK-NEXT: vxor.vv v9, v9, v12
+; CHECK-NEXT: vxor.vv v10, v9, v13
+; CHECK-NEXT: vxor.vv v10, v10, v14
+; CHECK-NEXT: vxor.vv v10, v10, v15
+; CHECK-NEXT: vxor.vv v10, v10, v16
+; CHECK-NEXT: vxor.vv v10, v10, v17
+; CHECK-NEXT: vxor.vv v10, v10, v18
+; CHECK-NEXT: vxor.vv v10, v10, v19
+; CHECK-NEXT: vxor.vv v10, v10, v20
+; CHECK-NEXT: vxor.vv v10, v10, v21
+; CHECK-NEXT: vxor.vv v10, v10, v22
+; CHECK-NEXT: vxor.vv v10, v10, v23
+; CHECK-NEXT: vxor.vv v10, v10, v24
+; CHECK-NEXT: vxor.vv v10, v10, v25
+; CHECK-NEXT: vxor.vv v10, v10, v26
+; CHECK-NEXT: vxor.vv v10, v10, v27
+; CHECK-NEXT: vxor.vv v10, v10, v28
+; CHECK-NEXT: vsll.vi v9, v9, 24
+; CHECK-NEXT: vxor.vv v11, v10, v29
+; CHECK-NEXT: vxor.vv v11, v11, v30
+; CHECK-NEXT: vand.vx v12, v10, a3
+; CHECK-NEXT: vsll.vi v12, v12, 8
+; CHECK-NEXT: vor.vv v9, v9, v12
+; CHECK-NEXT: vxor.vv v11, v11, v31
+; CHECK-NEXT: vxor.vv v11, v11, v7
+; CHECK-NEXT: vxor.vv v11, v11, v6
+; CHECK-NEXT: vxor.vv v11, v11, v5
+; CHECK-NEXT: vsrl.vi v10, v10, 8
+; CHECK-NEXT: vand.vx v10, v10, a3
+; CHECK-NEXT: addi a3, sp, 16
+; CHECK-NEXT: vl1r.v v12, (a3) # vscale x 8-byte Folded Reload
+; CHECK-NEXT: vxor.vv v11, v11, v12
+; CHECK-NEXT: vxor.vv v8, v11, v8
+; CHECK-NEXT: vsrl.vi v8, v8, 24
+; CHECK-NEXT: vor.vv v8, v10, v8
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v9, v8, 4
+; CHECK-NEXT: vand.vx v8, v8, a2
+; CHECK-NEXT: vand.vx v9, v9, a2
+; CHECK-NEXT: vsll.vi v8, v8, 4
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v9, v8, 2
+; CHECK-NEXT: vand.vx v8, v8, a1
+; CHECK-NEXT: vand.vx v9, v9, a1
+; CHECK-NEXT: vsll.vi v8, v8, 2
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v9, v8, 1
+; CHECK-NEXT: vand.vx v8, v8, a0
+; CHECK-NEXT: vand.vx v9, v9, a0
+; CHECK-NEXT: vadd.vv v8, v8, v8
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: csrr a0, vlenb
+; CHECK-NEXT: add sp, sp, a0
+; CHECK-NEXT: addi sp, sp, 16
+; CHECK-NEXT: ret
+ %a = call <vscale x 1 x i32> @llvm.clmulr.nxv1i32(<vscale x 1 x i32> %x, <vscale x 1 x i32> %y)
+ ret <vscale x 1 x i32> %a
+}
+
+define <vscale x 2 x i32> @clmulr_nxv2i32(<vscale x 2 x i32> %x, <vscale x 2 x i32> %y) nounwind {
+; CHECK-LABEL: clmulr_nxv2i32:
+; CHECK: # %bb.0:
+; CHECK-NEXT: addi sp, sp, -16
+; CHECK-NEXT: csrr a0, vlenb
+; CHECK-NEXT: sub sp, sp, a0
+; CHECK-NEXT: vsetvli a0, zero, e32, m1, ta, ma
+; CHECK-NEXT: vsrl.vi v9, v8, 8
+; CHECK-NEXT: lui a4, 16
+; CHECK-NEXT: vsrl.vi v10, v8, 24
+; CHECK-NEXT: vsll.vi v11, v8, 24
+; CHECK-NEXT: lui a0, 61681
+; CHECK-NEXT: lui a1, 209715
+; CHECK-NEXT: lui a5, 349525
+; CHECK-NEXT: li a6, 16
+; CHECK-NEXT: addi a3, a4, -256
+; CHECK-NEXT: addi a2, a0, -241
+; CHECK-NEXT: addi a1, a1, 819
+; CHECK-NEXT: addi a0, a5, 1365
+; CHECK-NEXT: vand.vx v9, v9, a3
+; CHECK-NEXT: vand.vx v8, v8, a3
+; CHECK-NEXT: vor.vv v9, v9, v10
+; CHECK-NEXT: vsll.vi v8, v8, 8
+; CHECK-NEXT: vor.vv v8, v11, v8
+; CHECK-NEXT: vor.vv v8, v8, v9
+; CHECK-NEXT: vsrl.vi v9, v8, 4
+; CHECK-NEXT: vand.vx v8, v8, a2
+; CHECK-NEXT: vand.vx v9, v9, a2
+; CHECK-NEXT: vsll.vi v8, v8, 4
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v9, v8, 2
+; CHECK-NEXT: vand.vx v8, v8, a1
+; CHECK-NEXT: vand.vx v9, v9, a1
+; CHECK-NEXT: vsll.vi v8, v8, 2
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v9, v8, 1
+; CHECK-NEXT: vand.vx v8, v8, a0
+; CHECK-NEXT: vand.vx v9, v9, a0
+; CHECK-NEXT: vadd.vv v8, v8, v8
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vand.vx v9, v8, a6
+; CHECK-NEXT: li a5, 32
+; CHECK-NEXT: vand.vx v10, v8, a5
+; CHECK-NEXT: li a5, 64
+; CHECK-NEXT: vand.vx v11, v8, a5
+; CHECK-NEXT: li a5, 128
+; CHECK-NEXT: vand.vx v12, v8, a5
+; CHECK-NEXT: li a5, 256
+; CHECK-NEXT: vand.vx v13, v8, a5
+; CHECK-NEXT: li a5, 512
+; CHECK-NEXT: vand.vx v14, v8, a5
+; CHECK-NEXT: li a5, 1024
+; CHECK-NEXT: vand.vx v15, v8, a5
+; CHECK-NEXT: li a5, 1
+; CHECK-NEXT: slli a5, a5, 11
+; CHECK-NEXT: vand.vx v16, v8, a5
+; CHECK-NEXT: lui a5, 1
+; CHECK-NEXT: vand.vx v17, v8, a5
+; CHECK-NEXT: lui a5, 2
+; CHECK-NEXT: vand.vx v18, v8, a5
+; CHECK-NEXT: lui a5, 4
+; CHECK-NEXT: vand.vx v19, v8, a5
+; CHECK-NEXT: lui a5, 8
+; CHECK-NEXT: vand.vx v20, v8, a5
+; CHECK-NEXT: lui a5, 32
+; CHECK-NEXT: vand.vx v21, v8, a4
+; CHECK-NEXT: lui a4, 64
+; CHECK-NEXT: vand.vx v22, v8, a5
+; CHECK-NEXT: lui a5, 128
+; CHECK-NEXT: vand.vx v23, v8, a4
+; CHECK-NEXT: lui a4, 256
+; CHECK-NEXT: vand.vx v24, v8, a5
+; CHECK-NEXT: lui a5, 512
+; CHECK-NEXT: vand.vx v25, v8, a4
+; CHECK-NEXT: lui a4, 1024
+; CHECK-NEXT: vand.vx v26, v8, a5
+; CHECK-NEXT: lui a5, 2048
+; CHECK-NEXT: vand.vx v27, v8, a4
+; CHECK-NEXT: lui a4, 4096
+; CHECK-NEXT: vand.vx v28, v8, a5
+; CHECK-NEXT: lui a5, 8192
+; CHECK-NEXT: vand.vx v29, v8, a4
+; CHECK-NEXT: lui a4, 16384
+; CHECK-NEXT: vand.vx v30, v8, a5
+; CHECK-NEXT: lui a5, 32768
+; CHECK-NEXT: vand.vx v31, v8, a4
+; CHECK-NEXT: lui a4, 65536
+; CHECK-NEXT: vand.vx v7, v8, a5
+; CHECK-NEXT: lui a5, 131072
+; CHECK-NEXT: vand.vx v6, v8, a4
+; CHECK-NEXT: lui a4, 262144
+; CHECK-NEXT: vand.vx v5, v8, a5
+; CHECK-NEXT: lui a5, 524288
+; CHECK-NEXT: vand.vi v4, v8, 2
+; CHECK-NEXT: vand.vi v3, v8, 1
+; CHECK-NEXT: vand.vi v2, v8, 4
+; CHECK-NEXT: vand.vi v1, v8, 8
+; CHECK-NEXT: vand.vx v0, v8, a4
+; CHECK-NEXT: vmul.vv v4, v8, v4
+; CHECK-NEXT: vmul.vv v3, v8, v3
+; CHECK-NEXT: vmul.vv v2, v8, v2
+; CHECK-NEXT: vmul.vv v1, v8, v1
+; CHECK-NEXT: vmul.vv v9, v8, v9
+; CHECK-NEXT: vmul.vv v10, v8, v10
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vmul.vv v12, v8, v12
+; CHECK-NEXT: vmul.vv v13, v8, v13
+; CHECK-NEXT: vmul.vv v14, v8, v14
+; CHECK-NEXT: vmul.vv v15, v8, v15
+; CHECK-NEXT: vmul.vv v16, v8, v16
+; CHECK-NEXT: vmul.vv v17, v8, v17
+; CHECK-NEXT: vmul.vv v18, v8, v18
+; CHECK-NEXT: vmul.vv v19, v8, v19
+; CHECK-NEXT: vmul.vv v20, v8, v20
+; CHECK-NEXT: vmul.vv v21, v8, v21
+; CHECK-NEXT: vmul.vv v22, v8, v22
+; CHECK-NEXT: vmul.vv v23, v8, v23
+; CHECK-NEXT: vmul.vv v24, v8, v24
+; CHECK-NEXT: vmul.vv v25, v8, v25
+; CHECK-NEXT: vmul.vv v26, v8, v26
+; CHECK-NEXT: vmul.vv v27, v8, v27
+; CHECK-NEXT: vmul.vv v28, v8, v28
+; CHECK-NEXT: vmul.vv v29, v8, v29
+; CHECK-NEXT: vmul.vv v30, v8, v30
+; CHECK-NEXT: vmul.vv v31, v8, v31
+; CHECK-NEXT: vmul.vv v7, v8, v7
+; CHECK-NEXT: vmul.vv v6, v8, v6
+; CHECK-NEXT: vmul.vv v5, v8, v5
+; CHECK-NEXT: vmul.vv v0, v8, v0
+; CHECK-NEXT: addi a4, sp, 16
+; CHECK-NEXT: vs1r.v v0, (a4) # vscale x 8-byte Folded Spill
+; CHECK-NEXT: vand.vx v0, v8, a5
+; CHECK-NEXT: vmul.vv v8, v8, v0
+; CHECK-NEXT: vxor.vv v4, v3, v4
+; CHECK-NEXT: vxor.vv v4, v4, v2
+; CHECK-NEXT: vxor.vv v4, v4, v1
+; CHECK-NEXT: vxor.vv v9, v4, v9
+; CHECK-NEXT: vxor.vv v9, v9, v10
+; CHECK-NEXT: vxor.vv v9, v9, v11
+; CHECK-NEXT: vxor.vv v9, v9, v12
+; CHECK-NEXT: vxor.vv v10, v9, v13
+; CHECK-NEXT: vxor.vv v10, v10, v14
+; CHECK-NEXT: vxor.vv v10, v10, v15
+; CHECK-NEXT: vxor.vv v10, v10, v16
+; CHECK-NEXT: vxor.vv v10, v10, v17
+; CHECK-NEXT: vxor.vv v10, v10, v18
+; CHECK-NEXT: vxor.vv v10, v10, v19
+; CHECK-NEXT: vxor.vv v10, v10, v20
+; CHECK-NEXT: vxor.vv v10, v10, v21
+; CHECK-NEXT: vxor.vv v10, v10, v22
+; CHECK-NEXT: vxor.vv v10, v10, v23
+; CHECK-NEXT: vxor.vv v10, v10, v24
+; CHECK-NEXT: vxor.vv v10, v10, v25
+; CHECK-NEXT: vxor.vv v10, v10, v26
+; CHECK-NEXT: vxor.vv v10, v10, v27
+; CHECK-NEXT: vxor.vv v10, v10, v28
+; CHECK-NEXT: vsll.vi v9, v9, 24
+; CHECK-NEXT: vxor.vv v11, v10, v29
+; CHECK-NEXT: vxor.vv v11, v11, v30
+; CHECK-NEXT: vand.vx v12, v10, a3
+; CHECK-NEXT: vsll.vi v12, v12, 8
+; CHECK-NEXT: vor.vv v9, v9, v12
+; CHECK-NEXT: vxor.vv v11, v11, v31
+; CHECK-NEXT: vxor.vv v11, v11, v7
+; CHECK-NEXT: vxor.vv v11, v11, v6
+; CHECK-NEXT: vxor.vv v11, v11, v5
+; CHECK-NEXT: vsrl.vi v10, v10, 8
+; CHECK-NEXT: vand.vx v10, v10, a3
+; CHECK-NEXT: addi a3, sp, 16
+; CHECK-NEXT: vl1r.v v12, (a3) # vscale x 8-byte Folded Reload
+; CHECK-NEXT: vxor.vv v11, v11, v12
+; CHECK-NEXT: vxor.vv v8, v11, v8
+; CHECK-NEXT: vsrl.vi v8, v8, 24
+; CHECK-NEXT: vor.vv v8, v10, v8
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v9, v8, 4
+; CHECK-NEXT: vand.vx v8, v8, a2
+; CHECK-NEXT: vand.vx v9, v9, a2
+; CHECK-NEXT: vsll.vi v8, v8, 4
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v9, v8, 2
+; CHECK-NEXT: vand.vx v8, v8, a1
+; CHECK-NEXT: vand.vx v9, v9, a1
+; CHECK-NEXT: vsll.vi v8, v8, 2
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v9, v8, 1
+; CHECK-NEXT: vand.vx v8, v8, a0
+; CHECK-NEXT: vand.vx v9, v9, a0
+; CHECK-NEXT: vadd.vv v8, v8, v8
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: csrr a0, vlenb
+; CHECK-NEXT: add sp, sp, a0
+; CHECK-NEXT: addi sp, sp, 16
+; CHECK-NEXT: ret
+ %a = call <vscale x 2 x i32> @llvm.clmulr.nxv2i32(<vscale x 2 x i32> %x, <vscale x 2 x i32> %y)
+ ret <vscale x 2 x i32> %a
+}
+
+define <vscale x 4 x i32> @clmulr_nxv4i32(<vscale x 4 x i32> %x, <vscale x 4 x i32> %y) nounwind {
+; RV32-LABEL: clmulr_nxv4i32:
+; RV32: # %bb.0:
+; RV32-NEXT: addi sp, sp, -64
+; RV32-NEXT: sw s0, 60(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s1, 56(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s2, 52(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s3, 48(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s4, 44(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s5, 40(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s6, 36(sp) # 4-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: sub sp, sp, a0
+; RV32-NEXT: vsetvli a0, zero, e32, m2, ta, ma
+; RV32-NEXT: vsrl.vi v10, v8, 8
+; RV32-NEXT: lui a0, 16
+; RV32-NEXT: vsrl.vi v12, v8, 24
+; RV32-NEXT: vsll.vi v14, v8, 24
+; RV32-NEXT: lui a1, 61681
+; RV32-NEXT: lui a2, 209715
+; RV32-NEXT: lui s6, 349525
+; RV32-NEXT: li t2, 16
+; RV32-NEXT: li t5, 32
+; RV32-NEXT: li s2, 64
+; RV32-NEXT: li s5, 128
+; RV32-NEXT: li s4, 256
+; RV32-NEXT: li s3, 512
+; RV32-NEXT: li s1, 1024
+; RV32-NEXT: li s0, 1
+; RV32-NEXT: lui t6, 1
+; RV32-NEXT: lui t4, 2
+; RV32-NEXT: lui t3, 4
+; RV32-NEXT: lui a5, 8
+; RV32-NEXT: lui a6, 32
+; RV32-NEXT: lui a7, 64
+; RV32-NEXT: lui t0, 128
+; RV32-NEXT: lui t1, 256
+; RV32-NEXT: addi a4, a0, -256
+; RV32-NEXT: addi a3, a1, -241
+; RV32-NEXT: addi a2, a2, 819
+; RV32-NEXT: addi a1, s6, 1365
+; RV32-NEXT: vand.vx v10, v10, a4
+; RV32-NEXT: vand.vx v8, v8, a4
+; RV32-NEXT: vor.vv v10, v10, v12
+; RV32-NEXT: vsll.vi v8, v8, 8
+; RV32-NEXT: vor.vv v8, v14, v8
+; RV32-NEXT: vor.vv v8, v8, v10
+; RV32-NEXT: vsrl.vi v10, v8, 4
+; RV32-NEXT: vand.vx v8, v8, a3
+; RV32-NEXT: vand.vx v10, v10, a3
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v10, v8
+; RV32-NEXT: vsrl.vi v10, v8, 2
+; RV32-NEXT: vand.vx v8, v8, a2
+; RV32-NEXT: vand.vx v10, v10, a2
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v8, v10, v8
+; RV32-NEXT: vsrl.vi v10, v8, 1
+; RV32-NEXT: vand.vx v8, v8, a1
+; RV32-NEXT: vand.vx v10, v10, a1
+; RV32-NEXT: vadd.vv v8, v8, v8
+; RV32-NEXT: vor.vv v8, v10, v8
+; RV32-NEXT: vand.vx v10, v8, t2
+; RV32-NEXT: lui t2, 512
+; RV32-NEXT: vand.vx v12, v8, t5
+; RV32-NEXT: lui t5, 1024
+; RV32-NEXT: vand.vx v14, v8, s2
+; RV32-NEXT: lui s2, 2048
+; RV32-NEXT: vand.vx v16, v8, s5
+; RV32-NEXT: lui s5, 4096
+; RV32-NEXT: vand.vx v26, v8, s4
+; RV32-NEXT: lui s4, 8192
+; RV32-NEXT: vand.vx v28, v8, s3
+; RV32-NEXT: lui s3, 16384
+; RV32-NEXT: vand.vx v18, v8, s1
+; RV32-NEXT: lui s1, 32768
+; RV32-NEXT: slli s0, s0, 11
+; RV32-NEXT: vand.vx v20, v8, s0
+; RV32-NEXT: lui s0, 65536
+; RV32-NEXT: vand.vx v22, v8, t6
+; RV32-NEXT: lui t6, 131072
+; RV32-NEXT: vand.vx v24, v8, t4
+; RV32-NEXT: lui t4, 262144
+; RV32-NEXT: vand.vx v30, v8, t3
+; RV32-NEXT: lui t3, 524288
+; RV32-NEXT: vand.vi v6, v8, 2
+; RV32-NEXT: vand.vi v4, v8, 1
+; RV32-NEXT: vand.vi v2, v8, 4
+; RV32-NEXT: vand.vi v0, v8, 8
+; RV32-NEXT: vmul.vv v6, v8, v6
+; RV32-NEXT: sw a0, 4(sp) # 4-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv s6, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, s6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v6, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v6, v8, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv s6, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, s6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v6, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v6, v8, v2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v6, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v6, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv s6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add s6, s6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add s6, s6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, s6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v6, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv s6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add s6, s6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, s6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v10, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv s6, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add s6, s6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, s6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v10, v8, v14
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv s6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, s6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v10, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv s6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add s6, s6, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, s6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v10, v8, v26
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv s6, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, s6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v10, v8, v28
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv s6, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, s6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v10, v8, v18
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v10, v8, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv s6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add s6, s6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, s6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v10, v8, v22
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv s6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, s6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v10, v8, v24
+; RV32-NEXT: csrr s6, vlenb
+; RV32-NEXT: slli s6, s6, 1
+; RV32-NEXT: mv a0, s6
+; RV32-NEXT: slli s6, s6, 2
+; RV32-NEXT: add s6, s6, a0
+; RV32-NEXT: lw a0, 4(sp) # 4-byte Folded Reload
+; RV32-NEXT: add s6, sp, s6
+; RV32-NEXT: addi s6, s6, 32
+; RV32-NEXT: vs2r.v v10, (s6) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v10, v8, v30
+; RV32-NEXT: csrr s6, vlenb
+; RV32-NEXT: slli s6, s6, 3
+; RV32-NEXT: add s6, sp, s6
+; RV32-NEXT: addi s6, s6, 32
+; RV32-NEXT: vs2r.v v10, (s6) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, a5
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a5, vlenb
+; RV32-NEXT: slli a5, a5, 1
+; RV32-NEXT: mv s6, a5
+; RV32-NEXT: slli a5, a5, 1
+; RV32-NEXT: add a5, a5, s6
+; RV32-NEXT: add a5, sp, a5
+; RV32-NEXT: addi a5, a5, 32
+; RV32-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, a0
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, a6
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, a7
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: addi a0, sp, 32
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, t0
+; RV32-NEXT: vmul.vv v6, v8, v10
+; RV32-NEXT: vand.vx v10, v8, t1
+; RV32-NEXT: vmul.vv v30, v8, v10
+; RV32-NEXT: vand.vx v10, v8, t2
+; RV32-NEXT: vmul.vv v28, v8, v10
+; RV32-NEXT: vand.vx v10, v8, t5
+; RV32-NEXT: vmul.vv v26, v8, v10
+; RV32-NEXT: vand.vx v10, v8, s2
+; RV32-NEXT: vmul.vv v22, v8, v10
+; RV32-NEXT: vand.vx v10, v8, s5
+; RV32-NEXT: vmul.vv v18, v8, v10
+; RV32-NEXT: vand.vx v10, v8, s4
+; RV32-NEXT: vmul.vv v16, v8, v10
+; RV32-NEXT: vand.vx v10, v8, s3
+; RV32-NEXT: vmul.vv v24, v8, v10
+; RV32-NEXT: vand.vx v10, v8, s1
+; RV32-NEXT: vmul.vv v20, v8, v10
+; RV32-NEXT: vand.vx v10, v8, s0
+; RV32-NEXT: vmul.vv v12, v8, v10
+; RV32-NEXT: vand.vx v10, v8, t6
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: vand.vx v14, v8, t4
+; RV32-NEXT: vmul.vv v14, v8, v14
+; RV32-NEXT: vand.vx v0, v8, t3
+; RV32-NEXT: vmul.vv v8, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v0, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v0, v2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v2, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v2, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v2, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v2, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v2, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v2, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v2, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v2, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v2, v4
+; RV32-NEXT: addi a0, sp, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v4, v2, v4
+; RV32-NEXT: vxor.vv v6, v4, v6
+; RV32-NEXT: vxor.vv v30, v6, v30
+; RV32-NEXT: vxor.vv v28, v30, v28
+; RV32-NEXT: vxor.vv v26, v28, v26
+; RV32-NEXT: vxor.vv v22, v26, v22
+; RV32-NEXT: vsll.vi v26, v0, 24
+; RV32-NEXT: vxor.vv v18, v22, v18
+; RV32-NEXT: vxor.vv v16, v18, v16
+; RV32-NEXT: vand.vx v18, v22, a4
+; RV32-NEXT: vsll.vi v18, v18, 8
+; RV32-NEXT: vor.vv v18, v26, v18
+; RV32-NEXT: vxor.vv v16, v16, v24
+; RV32-NEXT: vxor.vv v16, v16, v20
+; RV32-NEXT: vxor.vv v12, v16, v12
+; RV32-NEXT: vxor.vv v10, v12, v10
+; RV32-NEXT: vsrl.vi v12, v22, 8
+; RV32-NEXT: vand.vx v12, v12, a4
+; RV32-NEXT: vxor.vv v10, v10, v14
+; RV32-NEXT: vxor.vv v8, v10, v8
+; RV32-NEXT: vsrl.vi v8, v8, 24
+; RV32-NEXT: vor.vv v8, v12, v8
+; RV32-NEXT: vor.vv v8, v18, v8
+; RV32-NEXT: vsrl.vi v10, v8, 4
+; RV32-NEXT: vand.vx v8, v8, a3
+; RV32-NEXT: vand.vx v10, v10, a3
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v10, v8
+; RV32-NEXT: vsrl.vi v10, v8, 2
+; RV32-NEXT: vand.vx v8, v8, a2
+; RV32-NEXT: vand.vx v10, v10, a2
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v8, v10, v8
+; RV32-NEXT: vsrl.vi v10, v8, 1
+; RV32-NEXT: vand.vx v8, v8, a1
+; RV32-NEXT: vand.vx v10, v10, a1
+; RV32-NEXT: vadd.vv v8, v8, v8
+; RV32-NEXT: vor.vv v8, v10, v8
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add sp, sp, a0
+; RV32-NEXT: lw s0, 60(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s1, 56(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s2, 52(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s3, 48(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s4, 44(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s5, 40(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s6, 36(sp) # 4-byte Folded Reload
+; RV32-NEXT: addi sp, sp, 64
+; RV32-NEXT: ret
+;
+; RV64-LABEL: clmulr_nxv4i32:
+; RV64: # %bb.0:
+; RV64-NEXT: addi sp, sp, -96
+; RV64-NEXT: sd s0, 88(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s1, 80(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s2, 72(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s3, 64(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s4, 56(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s5, 48(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s6, 40(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: sub sp, sp, a0
+; RV64-NEXT: vsetvli a0, zero, e32, m2, ta, ma
+; RV64-NEXT: vsrl.vi v10, v8, 8
+; RV64-NEXT: lui a0, 16
+; RV64-NEXT: vsrl.vi v12, v8, 24
+; RV64-NEXT: vsll.vi v14, v8, 24
+; RV64-NEXT: lui a1, 61681
+; RV64-NEXT: lui a2, 209715
+; RV64-NEXT: lui s6, 349525
+; RV64-NEXT: li t2, 16
+; RV64-NEXT: li t5, 32
+; RV64-NEXT: li s2, 64
+; RV64-NEXT: li s5, 128
+; RV64-NEXT: li s4, 256
+; RV64-NEXT: li s3, 512
+; RV64-NEXT: li s1, 1024
+; RV64-NEXT: li s0, 1
+; RV64-NEXT: lui t6, 1
+; RV64-NEXT: lui t4, 2
+; RV64-NEXT: lui t3, 4
+; RV64-NEXT: lui a5, 8
+; RV64-NEXT: lui a6, 32
+; RV64-NEXT: lui a7, 64
+; RV64-NEXT: lui t0, 128
+; RV64-NEXT: lui t1, 256
+; RV64-NEXT: addi a4, a0, -256
+; RV64-NEXT: addi a3, a1, -241
+; RV64-NEXT: addi a2, a2, 819
+; RV64-NEXT: addi a1, s6, 1365
+; RV64-NEXT: vand.vx v10, v10, a4
+; RV64-NEXT: vand.vx v8, v8, a4
+; RV64-NEXT: vor.vv v10, v10, v12
+; RV64-NEXT: vsll.vi v8, v8, 8
+; RV64-NEXT: vor.vv v8, v14, v8
+; RV64-NEXT: vor.vv v8, v8, v10
+; RV64-NEXT: vsrl.vi v10, v8, 4
+; RV64-NEXT: vand.vx v8, v8, a3
+; RV64-NEXT: vand.vx v10, v10, a3
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v10, v8
+; RV64-NEXT: vsrl.vi v10, v8, 2
+; RV64-NEXT: vand.vx v8, v8, a2
+; RV64-NEXT: vand.vx v10, v10, a2
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v10, v8
+; RV64-NEXT: vsrl.vi v10, v8, 1
+; RV64-NEXT: vand.vx v8, v8, a1
+; RV64-NEXT: vand.vx v10, v10, a1
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v10, v8
+; RV64-NEXT: vand.vx v10, v8, t2
+; RV64-NEXT: lui t2, 512
+; RV64-NEXT: vand.vx v12, v8, t5
+; RV64-NEXT: lui t5, 1024
+; RV64-NEXT: vand.vx v14, v8, s2
+; RV64-NEXT: lui s2, 2048
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: lui s5, 4096
+; RV64-NEXT: vand.vx v26, v8, s4
+; RV64-NEXT: lui s4, 8192
+; RV64-NEXT: vand.vx v28, v8, s3
+; RV64-NEXT: lui s3, 16384
+; RV64-NEXT: vand.vx v18, v8, s1
+; RV64-NEXT: lui s1, 32768
+; RV64-NEXT: slli s0, s0, 11
+; RV64-NEXT: vand.vx v20, v8, s0
+; RV64-NEXT: lui s0, 65536
+; RV64-NEXT: vand.vx v22, v8, t6
+; RV64-NEXT: lui t6, 131072
+; RV64-NEXT: vand.vx v24, v8, t4
+; RV64-NEXT: lui t4, 262144
+; RV64-NEXT: vand.vx v30, v8, t3
+; RV64-NEXT: lui t3, 524288
+; RV64-NEXT: vand.vi v6, v8, 2
+; RV64-NEXT: vand.vi v4, v8, 1
+; RV64-NEXT: vand.vi v2, v8, 4
+; RV64-NEXT: vand.vi v0, v8, 8
+; RV64-NEXT: vmul.vv v6, v8, v6
+; RV64-NEXT: sd a0, 8(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv s6, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, s6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v6, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v6, v8, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv s6, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, a0, s6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v6, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v6, v8, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v6, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v6, v8, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv s6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add s6, s6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add s6, s6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, s6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v6, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv s6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add s6, s6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, s6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v12
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv s6, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add s6, s6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, s6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v14
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv s6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, s6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv s6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add s6, s6, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, s6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v26
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv s6, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, s6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v28
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv s6, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, s6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v18
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v20
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv s6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add s6, s6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, s6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v22
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv s6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, s6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v24
+; RV64-NEXT: csrr s6, vlenb
+; RV64-NEXT: slli s6, s6, 1
+; RV64-NEXT: mv a0, s6
+; RV64-NEXT: slli s6, s6, 2
+; RV64-NEXT: add s6, s6, a0
+; RV64-NEXT: ld a0, 8(sp) # 8-byte Folded Reload
+; RV64-NEXT: add s6, sp, s6
+; RV64-NEXT: addi s6, s6, 32
+; RV64-NEXT: vs2r.v v10, (s6) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v30
+; RV64-NEXT: csrr s6, vlenb
+; RV64-NEXT: slli s6, s6, 3
+; RV64-NEXT: add s6, sp, s6
+; RV64-NEXT: addi s6, s6, 32
+; RV64-NEXT: vs2r.v v10, (s6) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, a5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s6, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s6
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 32
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, a0
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, a6
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, a7
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: addi a0, sp, 32
+; RV64-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, t0
+; RV64-NEXT: vmul.vv v6, v8, v10
+; RV64-NEXT: vand.vx v10, v8, t1
+; RV64-NEXT: vmul.vv v30, v8, v10
+; RV64-NEXT: vand.vx v10, v8, t2
+; RV64-NEXT: vmul.vv v28, v8, v10
+; RV64-NEXT: vand.vx v10, v8, t5
+; RV64-NEXT: vmul.vv v26, v8, v10
+; RV64-NEXT: vand.vx v10, v8, s2
+; RV64-NEXT: vmul.vv v22, v8, v10
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v18, v8, v10
+; RV64-NEXT: vand.vx v10, v8, s4
+; RV64-NEXT: vmul.vv v16, v8, v10
+; RV64-NEXT: vand.vx v10, v8, s3
+; RV64-NEXT: vmul.vv v24, v8, v10
+; RV64-NEXT: vand.vx v10, v8, s1
+; RV64-NEXT: vmul.vv v20, v8, v10
+; RV64-NEXT: vand.vx v10, v8, s0
+; RV64-NEXT: vmul.vv v12, v8, v10
+; RV64-NEXT: vand.vx v10, v8, t6
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: vand.vx v14, v8, t4
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vand.vx v0, v8, t3
+; RV64-NEXT: vmul.vv v8, v8, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v0, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v4
+; RV64-NEXT: addi a0, sp, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v4, v2, v4
+; RV64-NEXT: vxor.vv v6, v4, v6
+; RV64-NEXT: vxor.vv v30, v6, v30
+; RV64-NEXT: vxor.vv v28, v30, v28
+; RV64-NEXT: vxor.vv v26, v28, v26
+; RV64-NEXT: vxor.vv v22, v26, v22
+; RV64-NEXT: vsll.vi v26, v0, 24
+; RV64-NEXT: vxor.vv v18, v22, v18
+; RV64-NEXT: vxor.vv v16, v18, v16
+; RV64-NEXT: vand.vx v18, v22, a4
+; RV64-NEXT: vsll.vi v18, v18, 8
+; RV64-NEXT: vor.vv v18, v26, v18
+; RV64-NEXT: vxor.vv v16, v16, v24
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vxor.vv v12, v16, v12
+; RV64-NEXT: vxor.vv v10, v12, v10
+; RV64-NEXT: vsrl.vi v12, v22, 8
+; RV64-NEXT: vand.vx v12, v12, a4
+; RV64-NEXT: vxor.vv v10, v10, v14
+; RV64-NEXT: vxor.vv v8, v10, v8
+; RV64-NEXT: vsrl.vi v8, v8, 24
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vor.vv v8, v18, v8
+; RV64-NEXT: vsrl.vi v10, v8, 4
+; RV64-NEXT: vand.vx v8, v8, a3
+; RV64-NEXT: vand.vx v10, v10, a3
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v10, v8
+; RV64-NEXT: vsrl.vi v10, v8, 2
+; RV64-NEXT: vand.vx v8, v8, a2
+; RV64-NEXT: vand.vx v10, v10, a2
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v10, v8
+; RV64-NEXT: vsrl.vi v10, v8, 1
+; RV64-NEXT: vand.vx v8, v8, a1
+; RV64-NEXT: vand.vx v10, v10, a1
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v10, v8
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add sp, sp, a0
+; RV64-NEXT: ld s0, 88(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s1, 80(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s2, 72(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s3, 64(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s4, 56(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s5, 48(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s6, 40(sp) # 8-byte Folded Reload
+; RV64-NEXT: addi sp, sp, 96
+; RV64-NEXT: ret
+ %a = call <vscale x 4 x i32> @llvm.clmulr.nxv4i32(<vscale x 4 x i32> %x, <vscale x 4 x i32> %y)
+ ret <vscale x 4 x i32> %a
+}
+
+define <vscale x 8 x i32> @clmulr_nxv8i32(<vscale x 8 x i32> %x, <vscale x 8 x i32> %y) nounwind {
+; RV32-LABEL: clmulr_nxv8i32:
+; RV32: # %bb.0:
+; RV32-NEXT: addi sp, sp, -80
+; RV32-NEXT: sw ra, 76(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s0, 72(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s1, 68(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s2, 64(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s3, 60(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s4, 56(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s5, 52(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s6, 48(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s7, 44(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s8, 40(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s9, 36(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s10, 32(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s11, 28(sp) # 4-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: sub sp, sp, a0
+; RV32-NEXT: vsetvli a0, zero, e32, m4, ta, ma
+; RV32-NEXT: vsrl.vi v12, v8, 8
+; RV32-NEXT: lui a5, 16
+; RV32-NEXT: vsrl.vi v16, v8, 24
+; RV32-NEXT: vsll.vi v20, v8, 24
+; RV32-NEXT: lui a1, 61681
+; RV32-NEXT: lui a2, 209715
+; RV32-NEXT: lui ra, 349525
+; RV32-NEXT: li s9, 16
+; RV32-NEXT: li s8, 32
+; RV32-NEXT: li s6, 64
+; RV32-NEXT: li a7, 512
+; RV32-NEXT: li t0, 1024
+; RV32-NEXT: li a0, 1
+; RV32-NEXT: lui t1, 1
+; RV32-NEXT: lui t2, 2
+; RV32-NEXT: lui t3, 4
+; RV32-NEXT: lui t4, 8
+; RV32-NEXT: lui t5, 32
+; RV32-NEXT: lui t6, 64
+; RV32-NEXT: lui s0, 128
+; RV32-NEXT: lui s1, 256
+; RV32-NEXT: lui s2, 512
+; RV32-NEXT: lui s3, 1024
+; RV32-NEXT: lui s4, 2048
+; RV32-NEXT: lui s5, 4096
+; RV32-NEXT: lui s7, 8192
+; RV32-NEXT: lui s10, 16384
+; RV32-NEXT: lui s11, 32768
+; RV32-NEXT: addi a4, a5, -256
+; RV32-NEXT: addi a3, a1, -241
+; RV32-NEXT: addi a2, a2, 819
+; RV32-NEXT: addi a1, ra, 1365
+; RV32-NEXT: vand.vx v12, v12, a4
+; RV32-NEXT: vand.vx v8, v8, a4
+; RV32-NEXT: vor.vv v12, v12, v16
+; RV32-NEXT: vsll.vi v8, v8, 8
+; RV32-NEXT: vor.vv v8, v20, v8
+; RV32-NEXT: vor.vv v8, v8, v12
+; RV32-NEXT: vsrl.vi v12, v8, 4
+; RV32-NEXT: vand.vx v8, v8, a3
+; RV32-NEXT: vand.vx v12, v12, a3
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v12, v8
+; RV32-NEXT: vsrl.vi v12, v8, 2
+; RV32-NEXT: vand.vx v8, v8, a2
+; RV32-NEXT: vand.vx v12, v12, a2
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v8, v12, v8
+; RV32-NEXT: vsrl.vi v12, v8, 1
+; RV32-NEXT: vand.vx v8, v8, a1
+; RV32-NEXT: vand.vx v12, v12, a1
+; RV32-NEXT: vadd.vv v8, v8, v8
+; RV32-NEXT: vor.vv v8, v12, v8
+; RV32-NEXT: vand.vx v12, v8, s9
+; RV32-NEXT: lui s9, 65536
+; RV32-NEXT: vand.vx v16, v8, s8
+; RV32-NEXT: lui s8, 131072
+; RV32-NEXT: vand.vx v20, v8, s6
+; RV32-NEXT: lui s6, 262144
+; RV32-NEXT: slli ra, a0, 11
+; RV32-NEXT: vand.vi v24, v8, 2
+; RV32-NEXT: vand.vi v28, v8, 1
+; RV32-NEXT: vand.vi v4, v8, 4
+; RV32-NEXT: vand.vi v0, v8, 8
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: sw a4, 4(sp) # 4-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a4, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a4, a4, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs4r.v v24, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vmul.vv v24, v8, v28
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a4, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a4, a4, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs4r.v v24, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vmul.vv v24, v8, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a4, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs4r.v v24, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vmul.vv v24, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a4, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a4, a4, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a4, a4, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs4r.v v24, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a4, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a4, a4, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vmul.vv v12, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a4, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a4, a4, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vmul.vv v12, v8, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a4, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: lui a0, 524288
+; RV32-NEXT: li a6, 128
+; RV32-NEXT: vand.vx v12, v8, a6
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a4, vlenb
+; RV32-NEXT: slli a4, a4, 2
+; RV32-NEXT: mv a6, a4
+; RV32-NEXT: slli a4, a4, 1
+; RV32-NEXT: add a6, a6, a4
+; RV32-NEXT: slli a4, a4, 3
+; RV32-NEXT: add a4, a4, a6
+; RV32-NEXT: add a4, sp, a4
+; RV32-NEXT: addi a4, a4, 16
+; RV32-NEXT: vs4r.v v12, (a4) # vscale x 32-byte Folded Spill
+; RV32-NEXT: li a6, 256
+; RV32-NEXT: vand.vx v12, v8, a6
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 3
+; RV32-NEXT: mv a4, a6
+; RV32-NEXT: slli a6, a6, 3
+; RV32-NEXT: add a6, a6, a4
+; RV32-NEXT: lw a4, 4(sp) # 4-byte Folded Reload
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 16
+; RV32-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, a7
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 2
+; RV32-NEXT: mv a7, a6
+; RV32-NEXT: slli a6, a6, 4
+; RV32-NEXT: add a6, a6, a7
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 16
+; RV32-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, t0
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 6
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 16
+; RV32-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, ra
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 2
+; RV32-NEXT: mv a7, a6
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: add a7, a7, a6
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: add a7, a7, a6
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: add a6, a6, a7
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 16
+; RV32-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, t1
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 3
+; RV32-NEXT: mv a7, a6
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: add a7, a7, a6
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: add a6, a6, a7
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 16
+; RV32-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, t2
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 2
+; RV32-NEXT: mv a7, a6
+; RV32-NEXT: slli a6, a6, 2
+; RV32-NEXT: add a7, a7, a6
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: add a6, a6, a7
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 16
+; RV32-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, t3
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 4
+; RV32-NEXT: mv a7, a6
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: add a6, a6, a7
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 16
+; RV32-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, t4
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 2
+; RV32-NEXT: mv a7, a6
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: add a7, a7, a6
+; RV32-NEXT: slli a6, a6, 2
+; RV32-NEXT: add a6, a6, a7
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 16
+; RV32-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, a5
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a5, vlenb
+; RV32-NEXT: slli a5, a5, 3
+; RV32-NEXT: mv a6, a5
+; RV32-NEXT: slli a5, a5, 2
+; RV32-NEXT: add a5, a5, a6
+; RV32-NEXT: add a5, sp, a5
+; RV32-NEXT: addi a5, a5, 16
+; RV32-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, t5
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a5, vlenb
+; RV32-NEXT: slli a5, a5, 2
+; RV32-NEXT: mv a6, a5
+; RV32-NEXT: slli a5, a5, 3
+; RV32-NEXT: add a5, a5, a6
+; RV32-NEXT: add a5, sp, a5
+; RV32-NEXT: addi a5, a5, 16
+; RV32-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, t6
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a5, vlenb
+; RV32-NEXT: slli a5, a5, 5
+; RV32-NEXT: add a5, sp, a5
+; RV32-NEXT: addi a5, a5, 16
+; RV32-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s0
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a5, vlenb
+; RV32-NEXT: slli a5, a5, 2
+; RV32-NEXT: mv a6, a5
+; RV32-NEXT: slli a5, a5, 1
+; RV32-NEXT: add a6, a6, a5
+; RV32-NEXT: slli a5, a5, 1
+; RV32-NEXT: add a5, a5, a6
+; RV32-NEXT: add a5, sp, a5
+; RV32-NEXT: addi a5, a5, 16
+; RV32-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s1
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a5, vlenb
+; RV32-NEXT: slli a5, a5, 3
+; RV32-NEXT: mv a6, a5
+; RV32-NEXT: slli a5, a5, 1
+; RV32-NEXT: add a5, a5, a6
+; RV32-NEXT: add a5, sp, a5
+; RV32-NEXT: addi a5, a5, 16
+; RV32-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s2
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a5, vlenb
+; RV32-NEXT: slli a5, a5, 2
+; RV32-NEXT: mv a6, a5
+; RV32-NEXT: slli a5, a5, 2
+; RV32-NEXT: add a5, a5, a6
+; RV32-NEXT: add a5, sp, a5
+; RV32-NEXT: addi a5, a5, 16
+; RV32-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s3
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a5, vlenb
+; RV32-NEXT: slli a5, a5, 4
+; RV32-NEXT: add a5, sp, a5
+; RV32-NEXT: addi a5, a5, 16
+; RV32-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s4
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a5, vlenb
+; RV32-NEXT: slli a5, a5, 3
+; RV32-NEXT: add a5, sp, a5
+; RV32-NEXT: addi a5, a5, 16
+; RV32-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s5
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: addi a5, sp, 16
+; RV32-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s7
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vand.vx v16, v8, s10
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a5, vlenb
+; RV32-NEXT: slli a5, a5, 2
+; RV32-NEXT: mv a6, a5
+; RV32-NEXT: slli a5, a5, 1
+; RV32-NEXT: add a5, a5, a6
+; RV32-NEXT: add a5, sp, a5
+; RV32-NEXT: addi a5, a5, 16
+; RV32-NEXT: vs4r.v v16, (a5) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, s11
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a5, vlenb
+; RV32-NEXT: slli a5, a5, 2
+; RV32-NEXT: add a5, sp, a5
+; RV32-NEXT: addi a5, a5, 16
+; RV32-NEXT: vs4r.v v16, (a5) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, s9
+; RV32-NEXT: vmul.vv v28, v8, v16
+; RV32-NEXT: vand.vx v16, v8, s8
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vand.vx v20, v8, s6
+; RV32-NEXT: vmul.vv v4, v8, v20
+; RV32-NEXT: vand.vx v20, v8, a0
+; RV32-NEXT: vmul.vv v20, v8, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v8, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v0, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v0, v8
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v0, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v0, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v0, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v0, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v0, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v0, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v0, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v24
+; RV32-NEXT: addi a0, sp, 16
+; RV32-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v24, v0, v24
+; RV32-NEXT: vxor.vv v12, v24, v12
+; RV32-NEXT: vsll.vi v8, v8, 24
+; RV32-NEXT: vand.vx v24, v0, a4
+; RV32-NEXT: vsll.vi v24, v24, 8
+; RV32-NEXT: vor.vv v8, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v12, v12, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v12, v12, v24
+; RV32-NEXT: vxor.vv v12, v12, v28
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: vsrl.vi v16, v0, 8
+; RV32-NEXT: vand.vx v16, v16, a4
+; RV32-NEXT: vxor.vv v12, v12, v4
+; RV32-NEXT: vxor.vv v12, v12, v20
+; RV32-NEXT: vsrl.vi v12, v12, 24
+; RV32-NEXT: vor.vv v12, v16, v12
+; RV32-NEXT: vor.vv v8, v8, v12
+; RV32-NEXT: vsrl.vi v12, v8, 4
+; RV32-NEXT: vand.vx v8, v8, a3
+; RV32-NEXT: vand.vx v12, v12, a3
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v12, v8
+; RV32-NEXT: vsrl.vi v12, v8, 2
+; RV32-NEXT: vand.vx v8, v8, a2
+; RV32-NEXT: vand.vx v12, v12, a2
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v8, v12, v8
+; RV32-NEXT: vsrl.vi v12, v8, 1
+; RV32-NEXT: vand.vx v8, v8, a1
+; RV32-NEXT: vand.vx v12, v12, a1
+; RV32-NEXT: vadd.vv v8, v8, v8
+; RV32-NEXT: vor.vv v8, v12, v8
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add sp, sp, a0
+; RV32-NEXT: lw ra, 76(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s0, 72(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s1, 68(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s2, 64(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s3, 60(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s4, 56(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s5, 52(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s6, 48(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s7, 44(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s8, 40(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s9, 36(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s10, 32(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s11, 28(sp) # 4-byte Folded Reload
+; RV32-NEXT: addi sp, sp, 80
+; RV32-NEXT: ret
+;
+; RV64-LABEL: clmulr_nxv8i32:
+; RV64: # %bb.0:
+; RV64-NEXT: addi sp, sp, -144
+; RV64-NEXT: sd ra, 136(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s0, 128(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s1, 120(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s2, 112(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s3, 104(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s4, 96(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s5, 88(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s6, 80(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s7, 72(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s8, 64(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s9, 56(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s10, 48(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s11, 40(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: sub sp, sp, a0
+; RV64-NEXT: vsetvli a0, zero, e32, m4, ta, ma
+; RV64-NEXT: vsrl.vi v12, v8, 8
+; RV64-NEXT: lui a5, 16
+; RV64-NEXT: vsrl.vi v16, v8, 24
+; RV64-NEXT: vsll.vi v20, v8, 24
+; RV64-NEXT: lui a1, 61681
+; RV64-NEXT: lui a2, 209715
+; RV64-NEXT: lui ra, 349525
+; RV64-NEXT: li s9, 16
+; RV64-NEXT: li s8, 32
+; RV64-NEXT: li s6, 64
+; RV64-NEXT: li a7, 512
+; RV64-NEXT: li t0, 1024
+; RV64-NEXT: li a0, 1
+; RV64-NEXT: lui t1, 1
+; RV64-NEXT: lui t2, 2
+; RV64-NEXT: lui t3, 4
+; RV64-NEXT: lui t4, 8
+; RV64-NEXT: lui t5, 32
+; RV64-NEXT: lui t6, 64
+; RV64-NEXT: lui s0, 128
+; RV64-NEXT: lui s1, 256
+; RV64-NEXT: lui s2, 512
+; RV64-NEXT: lui s3, 1024
+; RV64-NEXT: lui s4, 2048
+; RV64-NEXT: lui s5, 4096
+; RV64-NEXT: lui s7, 8192
+; RV64-NEXT: lui s10, 16384
+; RV64-NEXT: lui s11, 32768
+; RV64-NEXT: addi a4, a5, -256
+; RV64-NEXT: addi a3, a1, -241
+; RV64-NEXT: addi a2, a2, 819
+; RV64-NEXT: addi a1, ra, 1365
+; RV64-NEXT: vand.vx v12, v12, a4
+; RV64-NEXT: vand.vx v8, v8, a4
+; RV64-NEXT: vor.vv v12, v12, v16
+; RV64-NEXT: vsll.vi v8, v8, 8
+; RV64-NEXT: vor.vv v8, v20, v8
+; RV64-NEXT: vor.vv v8, v8, v12
+; RV64-NEXT: vsrl.vi v12, v8, 4
+; RV64-NEXT: vand.vx v8, v8, a3
+; RV64-NEXT: vand.vx v12, v12, a3
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vsrl.vi v12, v8, 2
+; RV64-NEXT: vand.vx v8, v8, a2
+; RV64-NEXT: vand.vx v12, v12, a2
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vsrl.vi v12, v8, 1
+; RV64-NEXT: vand.vx v8, v8, a1
+; RV64-NEXT: vand.vx v12, v12, a1
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vand.vx v12, v8, s9
+; RV64-NEXT: lui s9, 65536
+; RV64-NEXT: vand.vx v16, v8, s8
+; RV64-NEXT: lui s8, 131072
+; RV64-NEXT: vand.vx v20, v8, s6
+; RV64-NEXT: lui s6, 262144
+; RV64-NEXT: slli ra, a0, 11
+; RV64-NEXT: vand.vi v24, v8, 2
+; RV64-NEXT: vand.vi v28, v8, 1
+; RV64-NEXT: vand.vi v4, v8, 4
+; RV64-NEXT: vand.vi v0, v8, 8
+; RV64-NEXT: vmul.vv v24, v8, v24
+; RV64-NEXT: sd a4, 8(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a4, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a4, a4, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs4r.v v24, (a0) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vmul.vv v24, v8, v28
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a4, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a4, a4, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs4r.v v24, (a0) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vmul.vv v24, v8, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: mv a4, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs4r.v v24, (a0) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vmul.vv v24, v8, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a4, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a4, a4, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a4, a4, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs4r.v v24, (a0) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a4, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a4, a4, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vmul.vv v12, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a4, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a4, a4, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vmul.vv v12, v8, v20
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a4, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui a0, 524288
+; RV64-NEXT: li a6, 128
+; RV64-NEXT: vand.vx v12, v8, a6
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a4, vlenb
+; RV64-NEXT: slli a4, a4, 2
+; RV64-NEXT: mv a6, a4
+; RV64-NEXT: slli a4, a4, 1
+; RV64-NEXT: add a6, a6, a4
+; RV64-NEXT: slli a4, a4, 3
+; RV64-NEXT: add a4, a4, a6
+; RV64-NEXT: add a4, sp, a4
+; RV64-NEXT: addi a4, a4, 32
+; RV64-NEXT: vs4r.v v12, (a4) # vscale x 32-byte Folded Spill
+; RV64-NEXT: li a6, 256
+; RV64-NEXT: vand.vx v12, v8, a6
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a6, vlenb
+; RV64-NEXT: slli a6, a6, 3
+; RV64-NEXT: mv a4, a6
+; RV64-NEXT: slli a6, a6, 3
+; RV64-NEXT: add a6, a6, a4
+; RV64-NEXT: ld a4, 8(sp) # 8-byte Folded Reload
+; RV64-NEXT: add a6, sp, a6
+; RV64-NEXT: addi a6, a6, 32
+; RV64-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, a7
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a6, vlenb
+; RV64-NEXT: slli a6, a6, 2
+; RV64-NEXT: mv a7, a6
+; RV64-NEXT: slli a6, a6, 4
+; RV64-NEXT: add a6, a6, a7
+; RV64-NEXT: add a6, sp, a6
+; RV64-NEXT: addi a6, a6, 32
+; RV64-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t0
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a6, vlenb
+; RV64-NEXT: slli a6, a6, 6
+; RV64-NEXT: add a6, sp, a6
+; RV64-NEXT: addi a6, a6, 32
+; RV64-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, ra
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a6, vlenb
+; RV64-NEXT: slli a6, a6, 2
+; RV64-NEXT: mv a7, a6
+; RV64-NEXT: slli a6, a6, 1
+; RV64-NEXT: add a7, a7, a6
+; RV64-NEXT: slli a6, a6, 1
+; RV64-NEXT: add a7, a7, a6
+; RV64-NEXT: slli a6, a6, 1
+; RV64-NEXT: add a6, a6, a7
+; RV64-NEXT: add a6, sp, a6
+; RV64-NEXT: addi a6, a6, 32
+; RV64-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t1
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a6, vlenb
+; RV64-NEXT: slli a6, a6, 3
+; RV64-NEXT: mv a7, a6
+; RV64-NEXT: slli a6, a6, 1
+; RV64-NEXT: add a7, a7, a6
+; RV64-NEXT: slli a6, a6, 1
+; RV64-NEXT: add a6, a6, a7
+; RV64-NEXT: add a6, sp, a6
+; RV64-NEXT: addi a6, a6, 32
+; RV64-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t2
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a6, vlenb
+; RV64-NEXT: slli a6, a6, 2
+; RV64-NEXT: mv a7, a6
+; RV64-NEXT: slli a6, a6, 2
+; RV64-NEXT: add a7, a7, a6
+; RV64-NEXT: slli a6, a6, 1
+; RV64-NEXT: add a6, a6, a7
+; RV64-NEXT: add a6, sp, a6
+; RV64-NEXT: addi a6, a6, 32
+; RV64-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t3
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a6, vlenb
+; RV64-NEXT: slli a6, a6, 4
+; RV64-NEXT: mv a7, a6
+; RV64-NEXT: slli a6, a6, 1
+; RV64-NEXT: add a6, a6, a7
+; RV64-NEXT: add a6, sp, a6
+; RV64-NEXT: addi a6, a6, 32
+; RV64-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t4
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a6, vlenb
+; RV64-NEXT: slli a6, a6, 2
+; RV64-NEXT: mv a7, a6
+; RV64-NEXT: slli a6, a6, 1
+; RV64-NEXT: add a7, a7, a6
+; RV64-NEXT: slli a6, a6, 2
+; RV64-NEXT: add a6, a6, a7
+; RV64-NEXT: add a6, sp, a6
+; RV64-NEXT: addi a6, a6, 32
+; RV64-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, a5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv a6, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, a6
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 32
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv a6, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, a5, a6
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 32
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t6
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 32
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s0
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv a6, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a6, a6, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, a6
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 32
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s1
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv a6, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, a6
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 32
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s2
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv a6, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, a6
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 32
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s3
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 32
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s4
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 32
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: addi a5, sp, 32
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s7
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: vand.vx v16, v8, s10
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv a6, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, a6
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 32
+; RV64-NEXT: vs4r.v v16, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, s11
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 32
+; RV64-NEXT: vs4r.v v16, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, s9
+; RV64-NEXT: vmul.vv v28, v8, v16
+; RV64-NEXT: vand.vx v16, v8, s8
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: vand.vx v20, v8, s6
+; RV64-NEXT: vmul.vv v4, v8, v20
+; RV64-NEXT: vand.vx v20, v8, a0
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v8, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v0, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v0, v8
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v0, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v0, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v0, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v0, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v0, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v0, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v0, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v8, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v24
+; RV64-NEXT: addi a0, sp, 32
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v0, v24
+; RV64-NEXT: vxor.vv v12, v24, v12
+; RV64-NEXT: vsll.vi v8, v8, 24
+; RV64-NEXT: vand.vx v24, v0, a4
+; RV64-NEXT: vsll.vi v24, v24, 8
+; RV64-NEXT: vor.vv v8, v8, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v12, v12, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v12, v12, v24
+; RV64-NEXT: vxor.vv v12, v12, v28
+; RV64-NEXT: vxor.vv v12, v12, v16
+; RV64-NEXT: vsrl.vi v16, v0, 8
+; RV64-NEXT: vand.vx v16, v16, a4
+; RV64-NEXT: vxor.vv v12, v12, v4
+; RV64-NEXT: vxor.vv v12, v12, v20
+; RV64-NEXT: vsrl.vi v12, v12, 24
+; RV64-NEXT: vor.vv v12, v16, v12
+; RV64-NEXT: vor.vv v8, v8, v12
+; RV64-NEXT: vsrl.vi v12, v8, 4
+; RV64-NEXT: vand.vx v8, v8, a3
+; RV64-NEXT: vand.vx v12, v12, a3
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vsrl.vi v12, v8, 2
+; RV64-NEXT: vand.vx v8, v8, a2
+; RV64-NEXT: vand.vx v12, v12, a2
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vsrl.vi v12, v8, 1
+; RV64-NEXT: vand.vx v8, v8, a1
+; RV64-NEXT: vand.vx v12, v12, a1
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add sp, sp, a0
+; RV64-NEXT: ld ra, 136(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s0, 128(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s1, 120(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s2, 112(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s3, 104(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s4, 96(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s5, 88(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s6, 80(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s7, 72(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s8, 64(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s9, 56(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s10, 48(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s11, 40(sp) # 8-byte Folded Reload
+; RV64-NEXT: addi sp, sp, 144
+; RV64-NEXT: ret
+ %a = call <vscale x 8 x i32> @llvm.clmulr.nxv8i32(<vscale x 8 x i32> %x, <vscale x 8 x i32> %x)
+ ret <vscale x 8 x i32> %a
+}
+
+define <vscale x 16 x i32> @clmulr_nxv16i32(<vscale x 16 x i32> %x, <vscale x 16 x i32> %y) nounwind {
+; RV32-LABEL: clmulr_nxv16i32:
+; RV32: # %bb.0:
+; RV32-NEXT: addi sp, sp, -80
+; RV32-NEXT: sw ra, 76(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s0, 72(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s1, 68(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s2, 64(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s3, 60(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s4, 56(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s5, 52(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s6, 48(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s7, 44(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s8, 40(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s9, 36(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s10, 32(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s11, 28(sp) # 4-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: sub sp, sp, a0
+; RV32-NEXT: vsetvli a0, zero, e32, m8, ta, ma
+; RV32-NEXT: vsrl.vi v16, v8, 8
+; RV32-NEXT: lui a5, 16
+; RV32-NEXT: vsrl.vi v24, v8, 24
+; RV32-NEXT: vsll.vi v0, v8, 24
+; RV32-NEXT: lui a1, 61681
+; RV32-NEXT: lui a2, 209715
+; RV32-NEXT: lui ra, 349525
+; RV32-NEXT: li t5, 16
+; RV32-NEXT: li t2, 32
+; RV32-NEXT: li a7, 64
+; RV32-NEXT: li t0, 512
+; RV32-NEXT: li t1, 1024
+; RV32-NEXT: li a0, 1
+; RV32-NEXT: lui t3, 1
+; RV32-NEXT: lui t4, 2
+; RV32-NEXT: lui t6, 4
+; RV32-NEXT: lui s0, 8
+; RV32-NEXT: lui s1, 32
+; RV32-NEXT: lui s2, 64
+; RV32-NEXT: lui s3, 128
+; RV32-NEXT: lui s4, 256
+; RV32-NEXT: lui s5, 512
+; RV32-NEXT: lui s6, 1024
+; RV32-NEXT: lui s7, 2048
+; RV32-NEXT: lui s8, 4096
+; RV32-NEXT: lui s9, 8192
+; RV32-NEXT: lui s10, 16384
+; RV32-NEXT: lui s11, 32768
+; RV32-NEXT: addi a4, a5, -256
+; RV32-NEXT: addi a3, a1, -241
+; RV32-NEXT: addi a2, a2, 819
+; RV32-NEXT: addi a1, ra, 1365
+; RV32-NEXT: slli a0, a0, 11
+; RV32-NEXT: vand.vx v16, v16, a4
+; RV32-NEXT: vand.vx v8, v8, a4
+; RV32-NEXT: vor.vv v16, v16, v24
+; RV32-NEXT: vsll.vi v8, v8, 8
+; RV32-NEXT: vor.vv v8, v0, v8
+; RV32-NEXT: vor.vv v8, v8, v16
+; RV32-NEXT: vsrl.vi v16, v8, 4
+; RV32-NEXT: vand.vx v8, v8, a3
+; RV32-NEXT: vand.vx v16, v16, a3
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v16, v8
+; RV32-NEXT: vsrl.vi v16, v8, 2
+; RV32-NEXT: vand.vx v8, v8, a2
+; RV32-NEXT: vand.vx v16, v16, a2
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v8, v16, v8
+; RV32-NEXT: vsrl.vi v16, v8, 1
+; RV32-NEXT: vand.vx v8, v8, a1
+; RV32-NEXT: vand.vx v16, v16, a1
+; RV32-NEXT: vadd.vv v8, v8, v8
+; RV32-NEXT: vor.vv v8, v16, v8
+; RV32-NEXT: vand.vi v16, v8, 2
+; RV32-NEXT: vand.vi v24, v8, 1
+; RV32-NEXT: vand.vi v0, v8, 4
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: sw a0, 4(sp) # 4-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a6, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a6, a6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a6, a6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: vand.vi v16, v8, 8
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a6, a6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: lui ra, 65536
+; RV32-NEXT: vand.vx v16, v8, t5
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a6, a6, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a6, a6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: lui t5, 131072
+; RV32-NEXT: vand.vx v16, v8, t2
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a6, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a6, a6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: lui t2, 262144
+; RV32-NEXT: vand.vx v16, v8, a7
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a6, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a6, a6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: lui a7, 524288
+; RV32-NEXT: li a6, 128
+; RV32-NEXT: vand.vx v16, v8, a6
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: mv a6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: li a6, 256
+; RV32-NEXT: vand.vx v16, v8, a6
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 3
+; RV32-NEXT: mv a0, a6
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: add a0, a0, a6
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: add a0, a0, a6
+; RV32-NEXT: slli a6, a6, 2
+; RV32-NEXT: add a6, a6, a0
+; RV32-NEXT: lw a0, 4(sp) # 4-byte Folded Reload
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 16
+; RV32-NEXT: vs8r.v v16, (a6) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, t0
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 4
+; RV32-NEXT: mv t0, a6
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: add t0, t0, a6
+; RV32-NEXT: slli a6, a6, 2
+; RV32-NEXT: add a6, a6, t0
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 16
+; RV32-NEXT: vs8r.v v16, (a6) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, t1
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 3
+; RV32-NEXT: mv t0, a6
+; RV32-NEXT: slli a6, a6, 2
+; RV32-NEXT: add t0, t0, a6
+; RV32-NEXT: slli a6, a6, 2
+; RV32-NEXT: add a6, a6, t0
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 16
+; RV32-NEXT: vs8r.v v16, (a6) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, a0
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a6, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, t3
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a6, a6, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, t4
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a6, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, t6
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a6, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, s0
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 7
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, a5
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, s1
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, s2
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, s3
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, s4
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, s5
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, s6
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, s7
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, s8
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, s9
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, s10
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, s11
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, ra
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, t5
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, t2
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, a7
+; RV32-NEXT: vmul.vv v8, v8, v16
+; RV32-NEXT: addi a0, sp, 16
+; RV32-NEXT: vs8r.v v8, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v8, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v24, v8
+; RV32-NEXT: vxor.vv v8, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v8, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v16, v8
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 7
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v24
+; RV32-NEXT: vsll.vi v16, v16, 24
+; RV32-NEXT: vand.vx v24, v8, a4
+; RV32-NEXT: vsll.vi v24, v24, 8
+; RV32-NEXT: vor.vv v16, v16, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v24, v0, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v0, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v24, v24, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v0, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v24, v24, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v0, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v24, v24, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v0, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v24, v24, v0
+; RV32-NEXT: addi a0, sp, 16
+; RV32-NEXT: vl8r.v v0, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v24, v24, v0
+; RV32-NEXT: vsrl.vi v8, v8, 8
+; RV32-NEXT: vand.vx v8, v8, a4
+; RV32-NEXT: vsrl.vi v24, v24, 24
+; RV32-NEXT: vor.vv v8, v8, v24
+; RV32-NEXT: vor.vv v8, v16, v8
+; RV32-NEXT: vsrl.vi v16, v8, 4
+; RV32-NEXT: vand.vx v8, v8, a3
+; RV32-NEXT: vand.vx v16, v16, a3
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v16, v8
+; RV32-NEXT: vsrl.vi v16, v8, 2
+; RV32-NEXT: vand.vx v8, v8, a2
+; RV32-NEXT: vand.vx v16, v16, a2
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v8, v16, v8
+; RV32-NEXT: vsrl.vi v16, v8, 1
+; RV32-NEXT: vand.vx v8, v8, a1
+; RV32-NEXT: vand.vx v16, v16, a1
+; RV32-NEXT: vadd.vv v8, v8, v8
+; RV32-NEXT: vor.vv v8, v16, v8
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add sp, sp, a0
+; RV32-NEXT: lw ra, 76(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s0, 72(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s1, 68(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s2, 64(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s3, 60(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s4, 56(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s5, 52(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s6, 48(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s7, 44(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s8, 40(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s9, 36(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s10, 32(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s11, 28(sp) # 4-byte Folded Reload
+; RV32-NEXT: addi sp, sp, 80
+; RV32-NEXT: ret
+;
+; RV64-LABEL: clmulr_nxv16i32:
+; RV64: # %bb.0:
+; RV64-NEXT: addi sp, sp, -144
+; RV64-NEXT: sd ra, 136(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s0, 128(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s1, 120(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s2, 112(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s3, 104(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s4, 96(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s5, 88(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s6, 80(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s7, 72(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s8, 64(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s9, 56(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s10, 48(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s11, 40(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: sub sp, sp, a0
+; RV64-NEXT: vsetvli a0, zero, e32, m8, ta, ma
+; RV64-NEXT: vsrl.vi v16, v8, 8
+; RV64-NEXT: lui a5, 16
+; RV64-NEXT: vsrl.vi v24, v8, 24
+; RV64-NEXT: vsll.vi v0, v8, 24
+; RV64-NEXT: lui a1, 61681
+; RV64-NEXT: lui a2, 209715
+; RV64-NEXT: lui ra, 349525
+; RV64-NEXT: li t5, 16
+; RV64-NEXT: li t2, 32
+; RV64-NEXT: li a7, 64
+; RV64-NEXT: li t0, 512
+; RV64-NEXT: li t1, 1024
+; RV64-NEXT: li a0, 1
+; RV64-NEXT: lui t3, 1
+; RV64-NEXT: lui t4, 2
+; RV64-NEXT: lui t6, 4
+; RV64-NEXT: lui s0, 8
+; RV64-NEXT: lui s1, 32
+; RV64-NEXT: lui s2, 64
+; RV64-NEXT: lui s3, 128
+; RV64-NEXT: lui s4, 256
+; RV64-NEXT: lui s5, 512
+; RV64-NEXT: lui s6, 1024
+; RV64-NEXT: lui s7, 2048
+; RV64-NEXT: lui s8, 4096
+; RV64-NEXT: lui s9, 8192
+; RV64-NEXT: lui s10, 16384
+; RV64-NEXT: lui s11, 32768
+; RV64-NEXT: addi a4, a5, -256
+; RV64-NEXT: addi a3, a1, -241
+; RV64-NEXT: addi a2, a2, 819
+; RV64-NEXT: addi a1, ra, 1365
+; RV64-NEXT: slli a0, a0, 11
+; RV64-NEXT: vand.vx v16, v16, a4
+; RV64-NEXT: vand.vx v8, v8, a4
+; RV64-NEXT: vor.vv v16, v16, v24
+; RV64-NEXT: vsll.vi v8, v8, 8
+; RV64-NEXT: vor.vv v8, v0, v8
+; RV64-NEXT: vor.vv v8, v8, v16
+; RV64-NEXT: vsrl.vi v16, v8, 4
+; RV64-NEXT: vand.vx v8, v8, a3
+; RV64-NEXT: vand.vx v16, v16, a3
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v16, v8
+; RV64-NEXT: vsrl.vi v16, v8, 2
+; RV64-NEXT: vand.vx v8, v8, a2
+; RV64-NEXT: vand.vx v16, v16, a2
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v16, v8
+; RV64-NEXT: vsrl.vi v16, v8, 1
+; RV64-NEXT: vand.vx v8, v8, a1
+; RV64-NEXT: vand.vx v16, v16, a1
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v16, v8
+; RV64-NEXT: vand.vi v16, v8, 2
+; RV64-NEXT: vand.vi v24, v8, 1
+; RV64-NEXT: vand.vi v0, v8, 4
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: sd a0, 8(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a6, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a6, a6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a6, a6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vmul.vv v24, v8, v24
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vand.vi v16, v8, 8
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: mv a6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a6, a6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: lui ra, 65536
+; RV64-NEXT: vand.vx v16, v8, t5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a6, a6, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a6, a6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: lui t5, 131072
+; RV64-NEXT: vand.vx v16, v8, t2
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a6, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a6, a6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: lui t2, 262144
+; RV64-NEXT: vand.vx v16, v8, a7
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a6, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a6, a6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: lui a7, 524288
+; RV64-NEXT: li a6, 128
+; RV64-NEXT: vand.vx v16, v8, a6
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 6
+; RV64-NEXT: mv a6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: li a6, 256
+; RV64-NEXT: vand.vx v16, v8, a6
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a6, vlenb
+; RV64-NEXT: slli a6, a6, 3
+; RV64-NEXT: mv a0, a6
+; RV64-NEXT: slli a6, a6, 1
+; RV64-NEXT: add a0, a0, a6
+; RV64-NEXT: slli a6, a6, 1
+; RV64-NEXT: add a0, a0, a6
+; RV64-NEXT: slli a6, a6, 2
+; RV64-NEXT: add a6, a6, a0
+; RV64-NEXT: ld a0, 8(sp) # 8-byte Folded Reload
+; RV64-NEXT: add a6, sp, a6
+; RV64-NEXT: addi a6, a6, 32
+; RV64-NEXT: vs8r.v v16, (a6) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, t0
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a6, vlenb
+; RV64-NEXT: slli a6, a6, 4
+; RV64-NEXT: mv t0, a6
+; RV64-NEXT: slli a6, a6, 1
+; RV64-NEXT: add t0, t0, a6
+; RV64-NEXT: slli a6, a6, 2
+; RV64-NEXT: add a6, a6, t0
+; RV64-NEXT: add a6, sp, a6
+; RV64-NEXT: addi a6, a6, 32
+; RV64-NEXT: vs8r.v v16, (a6) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, t1
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a6, vlenb
+; RV64-NEXT: slli a6, a6, 3
+; RV64-NEXT: mv t0, a6
+; RV64-NEXT: slli a6, a6, 2
+; RV64-NEXT: add t0, t0, a6
+; RV64-NEXT: slli a6, a6, 2
+; RV64-NEXT: add a6, a6, t0
+; RV64-NEXT: add a6, sp, a6
+; RV64-NEXT: addi a6, a6, 32
+; RV64-NEXT: vs8r.v v16, (a6) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, a0
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: mv a6, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, t3
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a6, a6, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, t4
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a6, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, t6
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a6, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, a0, a6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, s0
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 7
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, a5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, s1
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, s2
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, s3
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, s4
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, s6
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, s7
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, s8
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, s9
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, s10
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, s11
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, ra
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, t5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, t2
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, a7
+; RV64-NEXT: vmul.vv v8, v8, v16
+; RV64-NEXT: addi a0, sp, 32
+; RV64-NEXT: vs8r.v v8, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v8, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v24, v8
+; RV64-NEXT: vxor.vv v8, v8, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 6
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v8, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v16, v8
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 7
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v8, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v24
+; RV64-NEXT: vsll.vi v16, v16, 24
+; RV64-NEXT: vand.vx v24, v8, a4
+; RV64-NEXT: vsll.vi v24, v24, 8
+; RV64-NEXT: vor.vv v16, v16, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v0, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v0, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v0, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v0, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v0, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: addi a0, sp, 32
+; RV64-NEXT: vl8r.v v0, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vsrl.vi v8, v8, 8
+; RV64-NEXT: vand.vx v8, v8, a4
+; RV64-NEXT: vsrl.vi v24, v24, 24
+; RV64-NEXT: vor.vv v8, v8, v24
+; RV64-NEXT: vor.vv v8, v16, v8
+; RV64-NEXT: vsrl.vi v16, v8, 4
+; RV64-NEXT: vand.vx v8, v8, a3
+; RV64-NEXT: vand.vx v16, v16, a3
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v16, v8
+; RV64-NEXT: vsrl.vi v16, v8, 2
+; RV64-NEXT: vand.vx v8, v8, a2
+; RV64-NEXT: vand.vx v16, v16, a2
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v16, v8
+; RV64-NEXT: vsrl.vi v16, v8, 1
+; RV64-NEXT: vand.vx v8, v8, a1
+; RV64-NEXT: vand.vx v16, v16, a1
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v16, v8
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add sp, sp, a0
+; RV64-NEXT: ld ra, 136(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s0, 128(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s1, 120(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s2, 112(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s3, 104(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s4, 96(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s5, 88(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s6, 80(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s7, 72(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s8, 64(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s9, 56(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s10, 48(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s11, 40(sp) # 8-byte Folded Reload
+; RV64-NEXT: addi sp, sp, 144
+; RV64-NEXT: ret
+ %a = call <vscale x 16 x i32> @llvm.clmulr.nxv16i32(<vscale x 16 x i32> %x, <vscale x 16 x i32> %y)
+ ret <vscale x 16 x i32> %a
+}
+
+define <vscale x 1 x i64> @clmulr_nxv1i64(<vscale x 1 x i64> %x, <vscale x 1 x i64> %y) nounwind {
+; RV32-LABEL: clmulr_nxv1i64:
+; RV32: # %bb.0:
+; RV32-NEXT: addi sp, sp, -352
+; RV32-NEXT: sw ra, 348(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s0, 344(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s1, 340(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s2, 336(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s3, 332(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s4, 328(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s5, 324(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s6, 320(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s7, 316(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s8, 312(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s9, 308(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s10, 304(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s11, 300(sp) # 4-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: sub sp, sp, a0
+; RV32-NEXT: lui s7, 1044480
+; RV32-NEXT: lui a7, 524288
+; RV32-NEXT: li s11, 1
+; RV32-NEXT: li s8, 2
+; RV32-NEXT: li s9, 4
+; RV32-NEXT: li s10, 8
+; RV32-NEXT: li a3, 16
+; RV32-NEXT: li a4, 32
+; RV32-NEXT: li a5, 64
+; RV32-NEXT: li a6, 128
+; RV32-NEXT: li ra, 256
+; RV32-NEXT: li a0, 512
+; RV32-NEXT: li a1, 1024
+; RV32-NEXT: lui a2, 1
+; RV32-NEXT: lui t0, 2
+; RV32-NEXT: lui t1, 4
+; RV32-NEXT: lui t2, 8
+; RV32-NEXT: lui t3, 16
+; RV32-NEXT: lui t4, 32
+; RV32-NEXT: lui t5, 64
+; RV32-NEXT: lui t6, 128
+; RV32-NEXT: lui s0, 256
+; RV32-NEXT: lui s1, 512
+; RV32-NEXT: lui s2, 1024
+; RV32-NEXT: lui s3, 2048
+; RV32-NEXT: lui s4, 4096
+; RV32-NEXT: lui s5, 8192
+; RV32-NEXT: lui s6, 16384
+; RV32-NEXT: sw s7, 272(sp)
+; RV32-NEXT: lui s7, 32768
+; RV32-NEXT: sw zero, 276(sp)
+; RV32-NEXT: sw a7, 264(sp)
+; RV32-NEXT: sw zero, 268(sp)
+; RV32-NEXT: sw zero, 256(sp)
+; RV32-NEXT: sw s11, 260(sp)
+; RV32-NEXT: sw zero, 248(sp)
+; RV32-NEXT: sw s8, 252(sp)
+; RV32-NEXT: lui s8, 65536
+; RV32-NEXT: sw zero, 240(sp)
+; RV32-NEXT: sw s9, 244(sp)
+; RV32-NEXT: lui s9, 131072
+; RV32-NEXT: sw zero, 232(sp)
+; RV32-NEXT: sw s10, 236(sp)
+; RV32-NEXT: lui s10, 262144
+; RV32-NEXT: sw zero, 224(sp)
+; RV32-NEXT: sw a3, 228(sp)
+; RV32-NEXT: sw zero, 216(sp)
+; RV32-NEXT: sw a4, 220(sp)
+; RV32-NEXT: sw zero, 208(sp)
+; RV32-NEXT: sw a5, 212(sp)
+; RV32-NEXT: sw zero, 200(sp)
+; RV32-NEXT: sw a6, 204(sp)
+; RV32-NEXT: sw zero, 192(sp)
+; RV32-NEXT: sw ra, 196(sp)
+; RV32-NEXT: sw zero, 184(sp)
+; RV32-NEXT: sw a0, 188(sp)
+; RV32-NEXT: sw zero, 176(sp)
+; RV32-NEXT: sw a1, 180(sp)
+; RV32-NEXT: slli s11, s11, 11
+; RV32-NEXT: sw zero, 168(sp)
+; RV32-NEXT: sw s11, 172(sp)
+; RV32-NEXT: sw zero, 160(sp)
+; RV32-NEXT: sw a2, 164(sp)
+; RV32-NEXT: sw zero, 152(sp)
+; RV32-NEXT: sw t0, 156(sp)
+; RV32-NEXT: sw zero, 144(sp)
+; RV32-NEXT: sw t1, 148(sp)
+; RV32-NEXT: sw zero, 136(sp)
+; RV32-NEXT: sw t2, 140(sp)
+; RV32-NEXT: sw zero, 128(sp)
+; RV32-NEXT: sw t3, 132(sp)
+; RV32-NEXT: sw zero, 120(sp)
+; RV32-NEXT: sw t4, 124(sp)
+; RV32-NEXT: sw zero, 112(sp)
+; RV32-NEXT: sw t5, 116(sp)
+; RV32-NEXT: sw zero, 104(sp)
+; RV32-NEXT: sw t6, 108(sp)
+; RV32-NEXT: sw zero, 96(sp)
+; RV32-NEXT: sw s0, 100(sp)
+; RV32-NEXT: sw zero, 88(sp)
+; RV32-NEXT: sw s1, 92(sp)
+; RV32-NEXT: sw zero, 80(sp)
+; RV32-NEXT: sw s2, 84(sp)
+; RV32-NEXT: sw zero, 72(sp)
+; RV32-NEXT: sw s3, 76(sp)
+; RV32-NEXT: sw zero, 64(sp)
+; RV32-NEXT: sw s4, 68(sp)
+; RV32-NEXT: sw zero, 56(sp)
+; RV32-NEXT: sw s5, 60(sp)
+; RV32-NEXT: sw zero, 48(sp)
+; RV32-NEXT: sw s6, 52(sp)
+; RV32-NEXT: sw zero, 40(sp)
+; RV32-NEXT: sw s7, 44(sp)
+; RV32-NEXT: sw zero, 32(sp)
+; RV32-NEXT: sw s8, 36(sp)
+; RV32-NEXT: sw zero, 24(sp)
+; RV32-NEXT: sw s9, 28(sp)
+; RV32-NEXT: sw zero, 16(sp)
+; RV32-NEXT: sw s10, 20(sp)
+; RV32-NEXT: sw zero, 8(sp)
+; RV32-NEXT: sw a7, 12(sp)
+; RV32-NEXT: lui a0, 61681
+; RV32-NEXT: addi a0, a0, -241
+; RV32-NEXT: vsetvli a1, zero, e32, m1, ta, ma
+; RV32-NEXT: vmv.v.x v3, a0
+; RV32-NEXT: lui a0, 209715
+; RV32-NEXT: addi a0, a0, 819
+; RV32-NEXT: vmv.v.x v2, a0
+; RV32-NEXT: lui a0, 349525
+; RV32-NEXT: addi a0, a0, 1365
+; RV32-NEXT: vmv.v.x v1, a0
+; RV32-NEXT: addi a0, sp, 272
+; RV32-NEXT: vsetvli a1, zero, e64, m1, ta, ma
+; RV32-NEXT: vlse64.v v0, (a0), zero
+; RV32-NEXT: addi a0, sp, 264
+; RV32-NEXT: vlse64.v v13, (a0), zero
+; RV32-NEXT: addi a0, sp, 256
+; RV32-NEXT: vlse64.v v14, (a0), zero
+; RV32-NEXT: addi a0, sp, 248
+; RV32-NEXT: vlse64.v v15, (a0), zero
+; RV32-NEXT: addi a0, sp, 240
+; RV32-NEXT: vlse64.v v16, (a0), zero
+; RV32-NEXT: addi a0, sp, 232
+; RV32-NEXT: vlse64.v v17, (a0), zero
+; RV32-NEXT: addi a0, sp, 224
+; RV32-NEXT: vlse64.v v18, (a0), zero
+; RV32-NEXT: addi a0, sp, 216
+; RV32-NEXT: vlse64.v v19, (a0), zero
+; RV32-NEXT: addi a0, sp, 208
+; RV32-NEXT: vlse64.v v20, (a0), zero
+; RV32-NEXT: addi a0, sp, 200
+; RV32-NEXT: vlse64.v v21, (a0), zero
+; RV32-NEXT: addi a0, sp, 192
+; RV32-NEXT: vlse64.v v22, (a0), zero
+; RV32-NEXT: addi a0, sp, 184
+; RV32-NEXT: vlse64.v v23, (a0), zero
+; RV32-NEXT: addi a0, sp, 176
+; RV32-NEXT: vlse64.v v24, (a0), zero
+; RV32-NEXT: addi a0, sp, 168
+; RV32-NEXT: vlse64.v v25, (a0), zero
+; RV32-NEXT: addi a0, sp, 160
+; RV32-NEXT: vlse64.v v26, (a0), zero
+; RV32-NEXT: addi a0, sp, 152
+; RV32-NEXT: vlse64.v v9, (a0), zero
+; RV32-NEXT: addi a0, sp, 144
+; RV32-NEXT: vlse64.v v10, (a0), zero
+; RV32-NEXT: addi a0, sp, 136
+; RV32-NEXT: vlse64.v v29, (a0), zero
+; RV32-NEXT: addi a0, sp, 128
+; RV32-NEXT: vlse64.v v30, (a0), zero
+; RV32-NEXT: addi a0, sp, 120
+; RV32-NEXT: vlse64.v v31, (a0), zero
+; RV32-NEXT: addi a0, sp, 112
+; RV32-NEXT: vlse64.v v11, (a0), zero
+; RV32-NEXT: addi a0, sp, 104
+; RV32-NEXT: vlse64.v v12, (a0), zero
+; RV32-NEXT: addi a0, sp, 96
+; RV32-NEXT: vlse64.v v5, (a0), zero
+; RV32-NEXT: addi a0, sp, 88
+; RV32-NEXT: vlse64.v v4, (a0), zero
+; RV32-NEXT: li a6, 56
+; RV32-NEXT: vsrl.vi v27, v8, 24
+; RV32-NEXT: vsrl.vx v28, v8, a6
+; RV32-NEXT: li ra, 40
+; RV32-NEXT: vsrl.vx v7, v8, ra
+; RV32-NEXT: vsll.vx v6, v8, a6
+; RV32-NEXT: addi a4, t3, -256
+; RV32-NEXT: vand.vx v7, v7, a4
+; RV32-NEXT: vor.vv v28, v7, v28
+; RV32-NEXT: vand.vx v7, v8, a4
+; RV32-NEXT: vsll.vx v7, v7, ra
+; RV32-NEXT: vor.vv v7, v6, v7
+; RV32-NEXT: vsrl.vi v6, v8, 8
+; RV32-NEXT: lui a5, 4080
+; RV32-NEXT: vand.vx v27, v27, a5
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v0, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v6, v6, v0
+; RV32-NEXT: vor.vv v27, v6, v27
+; RV32-NEXT: addi a3, sp, 80
+; RV32-NEXT: vlse64.v v6, (a3), zero
+; RV32-NEXT: vor.vv v27, v27, v28
+; RV32-NEXT: vand.vx v28, v8, a5
+; RV32-NEXT: vsll.vi v28, v28, 24
+; RV32-NEXT: vand.vv v8, v8, v0
+; RV32-NEXT: vsll.vi v8, v8, 8
+; RV32-NEXT: vor.vv v8, v28, v8
+; RV32-NEXT: addi a3, sp, 72
+; RV32-NEXT: vlse64.v v28, (a3), zero
+; RV32-NEXT: vor.vv v8, v7, v8
+; RV32-NEXT: addi a3, sp, 64
+; RV32-NEXT: vlse64.v v7, (a3), zero
+; RV32-NEXT: vor.vv v8, v8, v27
+; RV32-NEXT: vsrl.vi v27, v8, 4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v3, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v8, v8, v3
+; RV32-NEXT: vand.vv v27, v27, v3
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v27, v8
+; RV32-NEXT: vsrl.vi v27, v8, 2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v2, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v8, v8, v2
+; RV32-NEXT: vand.vv v27, v27, v2
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v8, v27, v8
+; RV32-NEXT: vsrl.vi v27, v8, 1
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v1, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v8, v8, v1
+; RV32-NEXT: vand.vv v27, v27, v1
+; RV32-NEXT: vadd.vv v8, v8, v8
+; RV32-NEXT: vor.vv v8, v27, v8
+; RV32-NEXT: addi a3, sp, 56
+; RV32-NEXT: vlse64.v v27, (a3), zero
+; RV32-NEXT: vand.vv v13, v8, v13
+; RV32-NEXT: vand.vv v14, v8, v14
+; RV32-NEXT: vand.vv v15, v8, v15
+; RV32-NEXT: vand.vv v16, v8, v16
+; RV32-NEXT: vand.vv v17, v8, v17
+; RV32-NEXT: vand.vv v18, v8, v18
+; RV32-NEXT: vand.vv v19, v8, v19
+; RV32-NEXT: vand.vv v20, v8, v20
+; RV32-NEXT: vand.vv v21, v8, v21
+; RV32-NEXT: vand.vv v22, v8, v22
+; RV32-NEXT: vand.vv v23, v8, v23
+; RV32-NEXT: vand.vv v24, v8, v24
+; RV32-NEXT: vand.vv v25, v8, v25
+; RV32-NEXT: vand.vv v26, v8, v26
+; RV32-NEXT: vand.vv v3, v8, v9
+; RV32-NEXT: vand.vv v2, v8, v10
+; RV32-NEXT: vand.vv v29, v8, v29
+; RV32-NEXT: vand.vv v30, v8, v30
+; RV32-NEXT: vand.vv v31, v8, v31
+; RV32-NEXT: vand.vv v0, v8, v11
+; RV32-NEXT: vand.vv v9, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v5, v8, v5
+; RV32-NEXT: vand.vv v4, v8, v4
+; RV32-NEXT: vand.vv v6, v8, v6
+; RV32-NEXT: vand.vv v9, v8, v28
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: addi a3, sp, 48
+; RV32-NEXT: addi a0, sp, 40
+; RV32-NEXT: vlse64.v v9, (a3), zero
+; RV32-NEXT: vlse64.v v10, (a0), zero
+; RV32-NEXT: vand.vv v11, v8, v7
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v11, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v11, v8, v27
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v11, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v9, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: addi a2, sp, 32
+; RV32-NEXT: addi a3, sp, 24
+; RV32-NEXT: addi a1, sp, 16
+; RV32-NEXT: addi a0, sp, 8
+; RV32-NEXT: vlse64.v v9, (a2), zero
+; RV32-NEXT: vlse64.v v10, (a3), zero
+; RV32-NEXT: vlse64.v v11, (a1), zero
+; RV32-NEXT: vlse64.v v12, (a0), zero
+; RV32-NEXT: vand.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 5
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v9, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v9, v8, v11
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 5
+; RV32-NEXT: sub a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v9, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vi v9, v8, 2
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vi v9, v8, 1
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vi v9, v8, 4
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vi v9, v8, 8
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: li a0, 16
+; RV32-NEXT: vand.vx v9, v8, a0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: li a0, 32
+; RV32-NEXT: vand.vx v9, v8, a0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: li a0, 64
+; RV32-NEXT: vand.vx v9, v8, a0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: li a0, 128
+; RV32-NEXT: vand.vx v9, v8, a0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: li a0, 256
+; RV32-NEXT: vand.vx v9, v8, a0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: li a0, 512
+; RV32-NEXT: vand.vx v9, v8, a0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: li a0, 1024
+; RV32-NEXT: vand.vx v9, v8, a0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s11
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: lui a0, 1
+; RV32-NEXT: vand.vx v9, v8, a0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, t0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 4
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, t1
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, t2
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 4
+; RV32-NEXT: sub a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, t3
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, t4
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, t5
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, t6
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s1
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 3
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s2
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s3
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 3
+; RV32-NEXT: sub a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s4
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s5
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 2
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s6
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s7
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 1
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s8
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s9
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v1, v8, s10
+; RV32-NEXT: vmul.vv v1, v8, v1
+; RV32-NEXT: vmul.vv v9, v8, v13
+; RV32-NEXT: addi a0, sp, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vmul.vv v10, v8, v14
+; RV32-NEXT: vmul.vv v11, v8, v15
+; RV32-NEXT: vmul.vv v12, v8, v16
+; RV32-NEXT: vmul.vv v13, v8, v17
+; RV32-NEXT: vmul.vv v14, v8, v18
+; RV32-NEXT: vmul.vv v15, v8, v19
+; RV32-NEXT: vmul.vv v16, v8, v20
+; RV32-NEXT: vmul.vv v17, v8, v21
+; RV32-NEXT: vmul.vv v18, v8, v22
+; RV32-NEXT: vmul.vv v19, v8, v23
+; RV32-NEXT: vmul.vv v20, v8, v24
+; RV32-NEXT: vmul.vv v21, v8, v25
+; RV32-NEXT: vmul.vv v22, v8, v26
+; RV32-NEXT: vmul.vv v23, v8, v3
+; RV32-NEXT: vmul.vv v24, v8, v2
+; RV32-NEXT: vmul.vv v25, v8, v29
+; RV32-NEXT: vmul.vv v26, v8, v30
+; RV32-NEXT: vmul.vv v27, v8, v31
+; RV32-NEXT: vmul.vv v28, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v29, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v29, v8, v29
+; RV32-NEXT: vmul.vv v30, v8, v5
+; RV32-NEXT: vmul.vv v31, v8, v4
+; RV32-NEXT: vmul.vv v7, v8, v6
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v6, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v6, v8, v6
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v5, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v5, v8, v5
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v4, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v4, v8, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v3, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v3, v8, v3
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v2, v8, v2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 5
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v0, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 5
+; RV32-NEXT: sub a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v8, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v8, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vi v8, v8, 0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 4
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 4
+; RV32-NEXT: sub a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 3
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 3
+; RV32-NEXT: sub a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 2
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 1
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: vxor.vv v8, v8, v1
+; RV32-NEXT: addi a0, sp, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: vxor.vv v8, v8, v11
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: vxor.vv v8, v8, v13
+; RV32-NEXT: vxor.vv v8, v8, v14
+; RV32-NEXT: vxor.vv v8, v8, v15
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: vxor.vv v8, v8, v17
+; RV32-NEXT: vxor.vv v8, v8, v18
+; RV32-NEXT: vxor.vv v8, v8, v19
+; RV32-NEXT: vxor.vv v8, v8, v20
+; RV32-NEXT: vxor.vv v8, v8, v21
+; RV32-NEXT: vxor.vv v8, v8, v22
+; RV32-NEXT: vxor.vv v8, v8, v23
+; RV32-NEXT: vxor.vv v8, v8, v24
+; RV32-NEXT: vxor.vv v8, v8, v25
+; RV32-NEXT: vxor.vv v8, v8, v26
+; RV32-NEXT: vxor.vv v8, v8, v27
+; RV32-NEXT: vxor.vv v8, v8, v28
+; RV32-NEXT: vxor.vv v8, v8, v29
+; RV32-NEXT: vxor.vv v8, v8, v30
+; RV32-NEXT: vxor.vv v8, v8, v31
+; RV32-NEXT: vxor.vv v8, v8, v7
+; RV32-NEXT: vxor.vv v8, v8, v6
+; RV32-NEXT: vxor.vv v8, v8, v5
+; RV32-NEXT: vxor.vv v8, v8, v4
+; RV32-NEXT: vxor.vv v8, v8, v3
+; RV32-NEXT: vxor.vv v8, v8, v2
+; RV32-NEXT: vxor.vv v8, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: vsrl.vx v9, v8, a6
+; RV32-NEXT: vsll.vx v10, v8, a6
+; RV32-NEXT: vsrl.vx v11, v8, ra
+; RV32-NEXT: vand.vx v12, v8, a4
+; RV32-NEXT: vand.vx v11, v11, a4
+; RV32-NEXT: vsrl.vi v13, v8, 24
+; RV32-NEXT: vand.vx v14, v8, a5
+; RV32-NEXT: vand.vx v13, v13, a5
+; RV32-NEXT: vsll.vx v12, v12, ra
+; RV32-NEXT: vsrl.vi v15, v8, 8
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v16, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v16
+; RV32-NEXT: vand.vv v15, v15, v16
+; RV32-NEXT: vor.vv v9, v11, v9
+; RV32-NEXT: vor.vv v11, v15, v13
+; RV32-NEXT: vsll.vi v8, v8, 8
+; RV32-NEXT: vsll.vi v13, v14, 24
+; RV32-NEXT: vor.vv v8, v13, v8
+; RV32-NEXT: vor.vv v10, v10, v12
+; RV32-NEXT: vor.vv v9, v11, v9
+; RV32-NEXT: vor.vv v8, v10, v8
+; RV32-NEXT: vor.vv v8, v8, v9
+; RV32-NEXT: vsrl.vi v9, v8, 4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v10, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v10
+; RV32-NEXT: vand.vv v9, v9, v10
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v9, v8
+; RV32-NEXT: vsrl.vi v9, v8, 2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v10, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v10
+; RV32-NEXT: vand.vv v9, v9, v10
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v8, v9, v8
+; RV32-NEXT: vsrl.vi v9, v8, 1
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v10, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v10
+; RV32-NEXT: vand.vv v9, v9, v10
+; RV32-NEXT: vadd.vv v8, v8, v8
+; RV32-NEXT: vor.vv v8, v9, v8
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add sp, sp, a0
+; RV32-NEXT: lw ra, 348(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s0, 344(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s1, 340(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s2, 336(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s3, 332(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s4, 328(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s5, 324(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s6, 320(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s7, 316(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s8, 312(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s9, 308(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s10, 304(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s11, 300(sp) # 4-byte Folded Reload
+; RV32-NEXT: addi sp, sp, 352
+; RV32-NEXT: ret
+;
+; RV64-LABEL: clmulr_nxv1i64:
+; RV64: # %bb.0:
+; RV64-NEXT: addi sp, sp, -224
+; RV64-NEXT: sd ra, 216(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s0, 208(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s1, 200(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s2, 192(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s3, 184(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s4, 176(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s5, 168(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s6, 160(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s7, 152(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s8, 144(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s9, 136(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s10, 128(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s11, 120(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: sub sp, sp, a0
+; RV64-NEXT: vsetvli a1, zero, e64, m1, ta, ma
+; RV64-NEXT: vsrl.vi v10, v8, 24
+; RV64-NEXT: vsrl.vi v9, v8, 8
+; RV64-NEXT: li t2, 255
+; RV64-NEXT: lui t6, 61681
+; RV64-NEXT: lui s0, 209715
+; RV64-NEXT: lui s1, 349525
+; RV64-NEXT: li s10, 16
+; RV64-NEXT: li s9, 32
+; RV64-NEXT: li s8, 64
+; RV64-NEXT: li s5, 128
+; RV64-NEXT: li s6, 256
+; RV64-NEXT: li t5, 512
+; RV64-NEXT: li t3, 1024
+; RV64-NEXT: li t0, 1
+; RV64-NEXT: lui s7, 1
+; RV64-NEXT: lui a1, 2
+; RV64-NEXT: lui t4, 4
+; RV64-NEXT: lui t1, 8
+; RV64-NEXT: lui a7, 32
+; RV64-NEXT: lui a6, 64
+; RV64-NEXT: lui a5, 128
+; RV64-NEXT: lui a4, 256
+; RV64-NEXT: lui a3, 512
+; RV64-NEXT: lui a2, 1024
+; RV64-NEXT: li s11, 56
+; RV64-NEXT: vsrl.vx v11, v8, s11
+; RV64-NEXT: li ra, 40
+; RV64-NEXT: vsrl.vx v12, v8, ra
+; RV64-NEXT: addi t6, t6, -241
+; RV64-NEXT: addi s2, s0, 819
+; RV64-NEXT: addi s3, s1, 1365
+; RV64-NEXT: slli s1, t6, 32
+; RV64-NEXT: add s4, t6, s1
+; RV64-NEXT: slli t6, s2, 32
+; RV64-NEXT: add s2, s2, t6
+; RV64-NEXT: slli t6, s3, 32
+; RV64-NEXT: add s3, s3, t6
+; RV64-NEXT: lui s0, 16
+; RV64-NEXT: addi s1, s0, -256
+; RV64-NEXT: lui a0, 4080
+; RV64-NEXT: vand.vx v10, v10, a0
+; RV64-NEXT: slli t6, t2, 24
+; RV64-NEXT: vand.vx v13, v8, a0
+; RV64-NEXT: vsll.vx v14, v8, s11
+; RV64-NEXT: vand.vx v12, v12, s1
+; RV64-NEXT: vand.vx v9, v9, t6
+; RV64-NEXT: vsll.vi v13, v13, 24
+; RV64-NEXT: vand.vx v15, v8, t6
+; RV64-NEXT: vand.vx v8, v8, s1
+; RV64-NEXT: vor.vv v11, v12, v11
+; RV64-NEXT: vor.vv v9, v9, v10
+; RV64-NEXT: vsll.vi v10, v15, 8
+; RV64-NEXT: vsll.vx v8, v8, ra
+; RV64-NEXT: vor.vv v9, v9, v11
+; RV64-NEXT: vor.vv v10, v13, v10
+; RV64-NEXT: vor.vv v8, v14, v8
+; RV64-NEXT: vor.vv v8, v8, v10
+; RV64-NEXT: vor.vv v8, v8, v9
+; RV64-NEXT: vsrl.vi v9, v8, 4
+; RV64-NEXT: vand.vx v8, v8, s4
+; RV64-NEXT: vand.vx v9, v9, s4
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v9, v8
+; RV64-NEXT: vsrl.vi v9, v8, 2
+; RV64-NEXT: vand.vx v8, v8, s2
+; RV64-NEXT: vand.vx v9, v9, s2
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v9, v8
+; RV64-NEXT: vsrl.vi v9, v8, 1
+; RV64-NEXT: vand.vx v8, v8, s3
+; RV64-NEXT: vand.vx v9, v9, s3
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v9, v8
+; RV64-NEXT: vand.vx v7, v8, s10
+; RV64-NEXT: lui t2, 4096
+; RV64-NEXT: vand.vx v6, v8, s9
+; RV64-NEXT: lui s9, 8192
+; RV64-NEXT: vand.vx v5, v8, s8
+; RV64-NEXT: lui s8, 16384
+; RV64-NEXT: vand.vx v4, v8, s5
+; RV64-NEXT: lui s10, 32768
+; RV64-NEXT: vand.vx v13, v8, s6
+; RV64-NEXT: lui s11, 65536
+; RV64-NEXT: vand.vx v14, v8, t5
+; RV64-NEXT: lui t5, 131072
+; RV64-NEXT: vand.vx v15, v8, t3
+; RV64-NEXT: slli t3, t0, 11
+; RV64-NEXT: vand.vx v16, v8, t3
+; RV64-NEXT: lui t3, 262144
+; RV64-NEXT: vand.vx v17, v8, s7
+; RV64-NEXT: slli a0, t0, 31
+; RV64-NEXT: sd a0, 96(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v18, v8, a1
+; RV64-NEXT: slli a0, t0, 32
+; RV64-NEXT: sd a0, 88(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v19, v8, t4
+; RV64-NEXT: slli a0, t0, 33
+; RV64-NEXT: sd a0, 80(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v20, v8, t1
+; RV64-NEXT: slli a0, t0, 34
+; RV64-NEXT: sd a0, 72(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v21, v8, s0
+; RV64-NEXT: slli a0, t0, 35
+; RV64-NEXT: sd a0, 64(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v22, v8, a7
+; RV64-NEXT: slli a0, t0, 36
+; RV64-NEXT: sd a0, 56(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v23, v8, a6
+; RV64-NEXT: slli a0, t0, 37
+; RV64-NEXT: sd a0, 48(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v24, v8, a5
+; RV64-NEXT: slli a0, t0, 38
+; RV64-NEXT: sd a0, 40(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v25, v8, a4
+; RV64-NEXT: slli a0, t0, 39
+; RV64-NEXT: sd a0, 32(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v26, v8, a3
+; RV64-NEXT: slli a0, t0, 40
+; RV64-NEXT: sd a0, 24(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v27, v8, a2
+; RV64-NEXT: slli a0, t0, 41
+; RV64-NEXT: sd a0, 16(sp) # 8-byte Folded Spill
+; RV64-NEXT: lui a0, 2048
+; RV64-NEXT: vand.vx v28, v8, a0
+; RV64-NEXT: slli s5, t0, 42
+; RV64-NEXT: vand.vx v29, v8, t2
+; RV64-NEXT: slli s6, t0, 43
+; RV64-NEXT: vand.vx v30, v8, s9
+; RV64-NEXT: slli s7, t0, 44
+; RV64-NEXT: vand.vx v10, v8, s8
+; RV64-NEXT: slli s8, t0, 45
+; RV64-NEXT: vand.vx v11, v8, s10
+; RV64-NEXT: slli s9, t0, 46
+; RV64-NEXT: vand.vx v12, v8, s11
+; RV64-NEXT: slli s10, t0, 47
+; RV64-NEXT: vand.vx v9, v8, t5
+; RV64-NEXT: slli s11, t0, 48
+; RV64-NEXT: vand.vx v31, v8, t3
+; RV64-NEXT: slli ra, t0, 49
+; RV64-NEXT: slli t5, t0, 50
+; RV64-NEXT: slli t4, t0, 51
+; RV64-NEXT: slli t3, t0, 52
+; RV64-NEXT: slli t2, t0, 53
+; RV64-NEXT: slli t1, t0, 54
+; RV64-NEXT: slli a7, t0, 55
+; RV64-NEXT: slli a6, t0, 56
+; RV64-NEXT: slli a5, t0, 57
+; RV64-NEXT: slli a4, t0, 58
+; RV64-NEXT: slli a3, t0, 59
+; RV64-NEXT: slli a2, t0, 60
+; RV64-NEXT: slli a1, t0, 61
+; RV64-NEXT: slli t0, t0, 62
+; RV64-NEXT: li a0, -1
+; RV64-NEXT: slli a0, a0, 63
+; RV64-NEXT: vand.vi v3, v8, 2
+; RV64-NEXT: vand.vi v2, v8, 1
+; RV64-NEXT: vand.vi v1, v8, 4
+; RV64-NEXT: vand.vi v0, v8, 8
+; RV64-NEXT: vmul.vv v3, v8, v3
+; RV64-NEXT: sd t6, 8(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: mv s0, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s0, s0, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add s0, s0, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s0
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v3, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v3, v8, v2
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: mv s0, t6
+; RV64-NEXT: slli t6, t6, 3
+; RV64-NEXT: add s0, s0, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s0
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v3, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v3, v8, v1
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 3
+; RV64-NEXT: mv s0, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s0
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v3, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vmul.vv v7, v8, v7
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: mv s0, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s0, s0, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s0, s0, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add t6, t6, s0
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v7, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v7, v8, v6
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: mv s0, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s0, s0, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add t6, t6, s0
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v7, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v7, v8, v5
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: mv s0, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add s0, s0, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add t6, t6, s0
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v7, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v7, v8, v4
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: mv s0, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add t6, t6, s0
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v7, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v13, v8, v13
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: mv s0, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s0, s0, t6
+; RV64-NEXT: slli t6, t6, 3
+; RV64-NEXT: add t6, t6, s0
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v13, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v13, v8, v14
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: mv s0, t6
+; RV64-NEXT: slli t6, t6, 3
+; RV64-NEXT: add t6, t6, s0
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v13, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v13, v8, v15
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli s0, t6, 4
+; RV64-NEXT: add t6, s0, t6
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v13, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v13, v8, v16
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v13, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v13, v8, v17
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli s0, t6, 4
+; RV64-NEXT: sub t6, s0, t6
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v13, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v13, v8, v18
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: mv s0, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s0, s0, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s0
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v13, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v13, v8, v19
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: mv s0, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add s0, s0, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s0
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v13, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v13, v8, v20
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: mv s0, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s0
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v13, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v13, v8, v21
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: mv s0, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s0, s0, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add t6, t6, s0
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v13, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v13, v8, v22
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: mv s0, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add t6, t6, s0
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v13, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v13, v8, v23
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli s0, t6, 3
+; RV64-NEXT: add t6, s0, t6
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v13, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v13, v8, v24
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 3
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v13, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v13, v8, v25
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli s0, t6, 3
+; RV64-NEXT: sub t6, s0, t6
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v13, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v13, v8, v26
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: mv s0, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s0
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v13, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v13, v8, v27
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli s0, t6, 2
+; RV64-NEXT: add t6, s0, t6
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v13, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v13, v8, v28
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v13, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v13, v8, v29
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli s0, t6, 1
+; RV64-NEXT: add t6, s0, t6
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v13, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v13, v8, v30
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v13, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: mv s0, t6
+; RV64-NEXT: slli t6, t6, 4
+; RV64-NEXT: add t6, t6, s0
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v10, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v11
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli s0, t6, 5
+; RV64-NEXT: add t6, s0, t6
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v10, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v12
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 5
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v10, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v9
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli s0, t6, 5
+; RV64-NEXT: sub t6, s0, t6
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v31
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: mv s0, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s0, s0, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s0, s0, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s0
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: ld s0, 96(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s0
+; RV64-NEXT: vmul.vv v9, v8, v9
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: mv s0, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add s0, s0, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s0, s0, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s0
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: ld s0, 88(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s0
+; RV64-NEXT: vmul.vv v9, v8, v9
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: mv s0, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s0, s0, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s0
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: ld s0, 80(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s0
+; RV64-NEXT: vmul.vv v9, v8, v9
+; RV64-NEXT: csrr s0, vlenb
+; RV64-NEXT: slli s0, s0, 1
+; RV64-NEXT: mv t6, s0
+; RV64-NEXT: slli s0, s0, 2
+; RV64-NEXT: add t6, t6, s0
+; RV64-NEXT: slli s0, s0, 1
+; RV64-NEXT: add s0, s0, t6
+; RV64-NEXT: ld t6, 8(sp) # 8-byte Folded Reload
+; RV64-NEXT: add s0, sp, s0
+; RV64-NEXT: addi s0, s0, 112
+; RV64-NEXT: vs1r.v v9, (s0) # vscale x 8-byte Folded Spill
+; RV64-NEXT: ld s0, 72(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s0
+; RV64-NEXT: vmul.vv v9, v8, v9
+; RV64-NEXT: csrr s0, vlenb
+; RV64-NEXT: add s0, sp, s0
+; RV64-NEXT: addi s0, s0, 112
+; RV64-NEXT: vs1r.v v9, (s0) # vscale x 8-byte Folded Spill
+; RV64-NEXT: ld s0, 64(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s0
+; RV64-NEXT: vmul.vv v9, v8, v9
+; RV64-NEXT: addi s0, sp, 112
+; RV64-NEXT: vs1r.v v9, (s0) # vscale x 8-byte Folded Spill
+; RV64-NEXT: ld s0, 56(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s0
+; RV64-NEXT: vmul.vv v4, v8, v9
+; RV64-NEXT: ld s0, 48(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s0
+; RV64-NEXT: vmul.vv v5, v8, v9
+; RV64-NEXT: ld s0, 40(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s0
+; RV64-NEXT: vmul.vv v6, v8, v9
+; RV64-NEXT: ld s0, 32(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s0
+; RV64-NEXT: vmul.vv v7, v8, v9
+; RV64-NEXT: ld s0, 24(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s0
+; RV64-NEXT: vmul.vv v31, v8, v9
+; RV64-NEXT: ld s0, 16(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s0
+; RV64-NEXT: vmul.vv v30, v8, v9
+; RV64-NEXT: vand.vx v9, v8, s5
+; RV64-NEXT: vmul.vv v29, v8, v9
+; RV64-NEXT: vand.vx v9, v8, s6
+; RV64-NEXT: vmul.vv v28, v8, v9
+; RV64-NEXT: vand.vx v9, v8, s7
+; RV64-NEXT: vmul.vv v27, v8, v9
+; RV64-NEXT: vand.vx v9, v8, s8
+; RV64-NEXT: vmul.vv v26, v8, v9
+; RV64-NEXT: vand.vx v9, v8, s9
+; RV64-NEXT: vmul.vv v25, v8, v9
+; RV64-NEXT: vand.vx v9, v8, s10
+; RV64-NEXT: vmul.vv v23, v8, v9
+; RV64-NEXT: vand.vx v9, v8, s11
+; RV64-NEXT: vmul.vv v19, v8, v9
+; RV64-NEXT: vand.vx v9, v8, ra
+; RV64-NEXT: vmul.vv v14, v8, v9
+; RV64-NEXT: vand.vx v9, v8, t5
+; RV64-NEXT: vmul.vv v9, v8, v9
+; RV64-NEXT: vand.vx v10, v8, t4
+; RV64-NEXT: vmul.vv v24, v8, v10
+; RV64-NEXT: vand.vx v10, v8, t3
+; RV64-NEXT: vmul.vv v22, v8, v10
+; RV64-NEXT: vand.vx v10, v8, t2
+; RV64-NEXT: vmul.vv v20, v8, v10
+; RV64-NEXT: vand.vx v10, v8, t1
+; RV64-NEXT: vmul.vv v15, v8, v10
+; RV64-NEXT: vand.vx v10, v8, a7
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: vand.vx v11, v8, a6
+; RV64-NEXT: vmul.vv v16, v8, v11
+; RV64-NEXT: vand.vx v11, v8, a5
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vand.vx v12, v8, a4
+; RV64-NEXT: vmul.vv v21, v8, v12
+; RV64-NEXT: vand.vx v12, v8, a3
+; RV64-NEXT: vmul.vv v17, v8, v12
+; RV64-NEXT: vand.vx v12, v8, a2
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: vand.vx v13, v8, a1
+; RV64-NEXT: vmul.vv v18, v8, v13
+; RV64-NEXT: vand.vx v13, v8, t0
+; RV64-NEXT: vmul.vv v13, v8, v13
+; RV64-NEXT: vand.vx v2, v8, a0
+; RV64-NEXT: vmul.vv v8, v8, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v1, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v1, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v1
+; RV64-NEXT: vxor.vv v2, v2, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v1, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v1
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v1, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v1
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v1, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v1
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v1, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v1
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v1, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v2, v1
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v0, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a1, a0, 4
+; RV64-NEXT: add a0, a1, a0
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v0, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v0, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a1, a0, 4
+; RV64-NEXT: sub a0, a1, a0
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v0, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v0, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v0, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v0, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v0, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v0, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a1, a0, 3
+; RV64-NEXT: add a0, a1, a0
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v0, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v0, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a1, a0, 3
+; RV64-NEXT: sub a0, a1, a0
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v0, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v0, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a1, a0, 2
+; RV64-NEXT: add a0, a1, a0
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v0, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v0, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a1, a0, 1
+; RV64-NEXT: add a0, a1, a0
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v0, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v1, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v3, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v3
+; RV64-NEXT: li a0, 56
+; RV64-NEXT: vsll.vx v2, v2, a0
+; RV64-NEXT: vand.vx v1, v1, s1
+; RV64-NEXT: li a1, 40
+; RV64-NEXT: vsll.vx v1, v1, a1
+; RV64-NEXT: vor.vv v2, v2, v1
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 4
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl1r.v v1, (a2) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v0, v1
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a3, a2, 5
+; RV64-NEXT: add a2, a3, a2
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl1r.v v0, (a2) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v0
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 5
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl1r.v v0, (a2) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v0
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a3, a2, 5
+; RV64-NEXT: sub a2, a3, a2
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl1r.v v0, (a2) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v0
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl1r.v v0, (a2) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v0
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl1r.v v0, (a2) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v0
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl1r.v v0, (a2) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v0
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl1r.v v0, (a2) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v0
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl1r.v v3, (a2) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v3
+; RV64-NEXT: addi a2, sp, 112
+; RV64-NEXT: vl1r.v v3, (a2) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v3, v1, v3
+; RV64-NEXT: vxor.vv v4, v3, v4
+; RV64-NEXT: vxor.vv v5, v4, v5
+; RV64-NEXT: vxor.vv v6, v5, v6
+; RV64-NEXT: vxor.vv v7, v6, v7
+; RV64-NEXT: vxor.vv v31, v7, v31
+; RV64-NEXT: vxor.vv v30, v31, v30
+; RV64-NEXT: vxor.vv v29, v30, v29
+; RV64-NEXT: vxor.vv v28, v29, v28
+; RV64-NEXT: vxor.vv v27, v28, v27
+; RV64-NEXT: vxor.vv v26, v27, v26
+; RV64-NEXT: vxor.vv v25, v26, v25
+; RV64-NEXT: vxor.vv v23, v25, v23
+; RV64-NEXT: vxor.vv v19, v23, v19
+; RV64-NEXT: vxor.vv v14, v19, v14
+; RV64-NEXT: vxor.vv v9, v14, v9
+; RV64-NEXT: vsrl.vi v14, v7, 8
+; RV64-NEXT: vand.vx v14, v14, t6
+; RV64-NEXT: vsrl.vi v19, v23, 24
+; RV64-NEXT: lui a2, 4080
+; RV64-NEXT: vand.vx v19, v19, a2
+; RV64-NEXT: vor.vv v14, v14, v19
+; RV64-NEXT: vxor.vv v9, v9, v24
+; RV64-NEXT: vxor.vv v9, v9, v22
+; RV64-NEXT: vxor.vv v9, v9, v20
+; RV64-NEXT: vxor.vv v9, v9, v15
+; RV64-NEXT: vxor.vv v9, v9, v10
+; RV64-NEXT: vand.vx v10, v7, a2
+; RV64-NEXT: vsll.vi v10, v10, 24
+; RV64-NEXT: vxor.vv v15, v9, v16
+; RV64-NEXT: vxor.vv v11, v15, v11
+; RV64-NEXT: vand.vx v15, v9, t6
+; RV64-NEXT: vsll.vi v15, v15, 8
+; RV64-NEXT: vor.vv v10, v10, v15
+; RV64-NEXT: vxor.vv v11, v11, v21
+; RV64-NEXT: vor.vv v10, v2, v10
+; RV64-NEXT: vxor.vv v11, v11, v17
+; RV64-NEXT: vxor.vv v11, v11, v12
+; RV64-NEXT: vsrl.vx v9, v9, a1
+; RV64-NEXT: vand.vx v9, v9, s1
+; RV64-NEXT: vxor.vv v11, v11, v18
+; RV64-NEXT: vxor.vv v11, v11, v13
+; RV64-NEXT: vxor.vv v8, v11, v8
+; RV64-NEXT: vsrl.vx v8, v8, a0
+; RV64-NEXT: vor.vv v8, v9, v8
+; RV64-NEXT: vor.vv v8, v14, v8
+; RV64-NEXT: vor.vv v8, v10, v8
+; RV64-NEXT: vsrl.vi v9, v8, 4
+; RV64-NEXT: vand.vx v8, v8, s4
+; RV64-NEXT: vand.vx v9, v9, s4
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v9, v8
+; RV64-NEXT: vsrl.vi v9, v8, 2
+; RV64-NEXT: vand.vx v8, v8, s2
+; RV64-NEXT: vand.vx v9, v9, s2
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v9, v8
+; RV64-NEXT: vsrl.vi v9, v8, 1
+; RV64-NEXT: vand.vx v8, v8, s3
+; RV64-NEXT: vand.vx v9, v9, s3
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v9, v8
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add sp, sp, a0
+; RV64-NEXT: ld ra, 216(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s0, 208(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s1, 200(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s2, 192(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s3, 184(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s4, 176(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s5, 168(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s6, 160(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s7, 152(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s8, 144(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s9, 136(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s10, 128(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s11, 120(sp) # 8-byte Folded Reload
+; RV64-NEXT: addi sp, sp, 224
+; RV64-NEXT: ret
+ %a = call <vscale x 1 x i64> @llvm.clmulr.nxv1i64(<vscale x 1 x i64> %x, <vscale x 1 x i64> %y)
+ ret <vscale x 1 x i64> %a
+}
+
+define <vscale x 2 x i64> @clmulr_nxv2i64(<vscale x 2 x i64> %x, <vscale x 2 x i64> %y) nounwind {
+; RV32-LABEL: clmulr_nxv2i64:
+; RV32: # %bb.0:
+; RV32-NEXT: addi sp, sp, -352
+; RV32-NEXT: sw ra, 348(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s0, 344(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s1, 340(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s2, 336(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s3, 332(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s4, 328(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s5, 324(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s6, 320(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s7, 316(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s8, 312(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s9, 308(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s10, 304(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s11, 300(sp) # 4-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: sub sp, sp, a0
+; RV32-NEXT: lui s7, 1044480
+; RV32-NEXT: lui a7, 524288
+; RV32-NEXT: li a1, 1
+; RV32-NEXT: li s8, 2
+; RV32-NEXT: li s9, 4
+; RV32-NEXT: li s10, 8
+; RV32-NEXT: li a3, 16
+; RV32-NEXT: li a4, 32
+; RV32-NEXT: li a5, 64
+; RV32-NEXT: li a6, 128
+; RV32-NEXT: li s11, 256
+; RV32-NEXT: li ra, 512
+; RV32-NEXT: li a0, 1024
+; RV32-NEXT: lui a2, 1
+; RV32-NEXT: lui t0, 2
+; RV32-NEXT: lui t1, 4
+; RV32-NEXT: lui t2, 8
+; RV32-NEXT: lui t3, 16
+; RV32-NEXT: lui t4, 32
+; RV32-NEXT: lui t5, 64
+; RV32-NEXT: lui t6, 128
+; RV32-NEXT: lui s0, 256
+; RV32-NEXT: lui s1, 512
+; RV32-NEXT: lui s2, 1024
+; RV32-NEXT: lui s3, 2048
+; RV32-NEXT: lui s4, 4096
+; RV32-NEXT: lui s5, 8192
+; RV32-NEXT: lui s6, 16384
+; RV32-NEXT: sw s7, 272(sp)
+; RV32-NEXT: lui s7, 32768
+; RV32-NEXT: sw zero, 276(sp)
+; RV32-NEXT: sw a7, 264(sp)
+; RV32-NEXT: sw zero, 268(sp)
+; RV32-NEXT: sw zero, 256(sp)
+; RV32-NEXT: sw a1, 260(sp)
+; RV32-NEXT: sw zero, 248(sp)
+; RV32-NEXT: sw s8, 252(sp)
+; RV32-NEXT: lui s8, 65536
+; RV32-NEXT: sw zero, 240(sp)
+; RV32-NEXT: sw s9, 244(sp)
+; RV32-NEXT: lui s9, 131072
+; RV32-NEXT: sw zero, 232(sp)
+; RV32-NEXT: sw s10, 236(sp)
+; RV32-NEXT: lui s10, 262144
+; RV32-NEXT: sw zero, 224(sp)
+; RV32-NEXT: sw a3, 228(sp)
+; RV32-NEXT: sw zero, 216(sp)
+; RV32-NEXT: sw a4, 220(sp)
+; RV32-NEXT: sw zero, 208(sp)
+; RV32-NEXT: sw a5, 212(sp)
+; RV32-NEXT: sw zero, 200(sp)
+; RV32-NEXT: sw a6, 204(sp)
+; RV32-NEXT: sw zero, 192(sp)
+; RV32-NEXT: sw s11, 196(sp)
+; RV32-NEXT: sw zero, 184(sp)
+; RV32-NEXT: sw ra, 188(sp)
+; RV32-NEXT: sw zero, 176(sp)
+; RV32-NEXT: sw a0, 180(sp)
+; RV32-NEXT: slli a5, a1, 11
+; RV32-NEXT: sw zero, 168(sp)
+; RV32-NEXT: sw a5, 172(sp)
+; RV32-NEXT: sw zero, 160(sp)
+; RV32-NEXT: sw a2, 164(sp)
+; RV32-NEXT: sw zero, 152(sp)
+; RV32-NEXT: sw t0, 156(sp)
+; RV32-NEXT: sw zero, 144(sp)
+; RV32-NEXT: sw t1, 148(sp)
+; RV32-NEXT: sw zero, 136(sp)
+; RV32-NEXT: sw t2, 140(sp)
+; RV32-NEXT: sw zero, 128(sp)
+; RV32-NEXT: sw t3, 132(sp)
+; RV32-NEXT: sw zero, 120(sp)
+; RV32-NEXT: sw t4, 124(sp)
+; RV32-NEXT: sw zero, 112(sp)
+; RV32-NEXT: sw t5, 116(sp)
+; RV32-NEXT: sw zero, 104(sp)
+; RV32-NEXT: sw t6, 108(sp)
+; RV32-NEXT: sw zero, 96(sp)
+; RV32-NEXT: sw s0, 100(sp)
+; RV32-NEXT: sw zero, 88(sp)
+; RV32-NEXT: sw s1, 92(sp)
+; RV32-NEXT: sw zero, 80(sp)
+; RV32-NEXT: sw s2, 84(sp)
+; RV32-NEXT: sw zero, 72(sp)
+; RV32-NEXT: sw s3, 76(sp)
+; RV32-NEXT: sw zero, 64(sp)
+; RV32-NEXT: sw s4, 68(sp)
+; RV32-NEXT: sw zero, 56(sp)
+; RV32-NEXT: sw s5, 60(sp)
+; RV32-NEXT: sw zero, 48(sp)
+; RV32-NEXT: sw s6, 52(sp)
+; RV32-NEXT: sw zero, 40(sp)
+; RV32-NEXT: sw s7, 44(sp)
+; RV32-NEXT: sw zero, 32(sp)
+; RV32-NEXT: sw s8, 36(sp)
+; RV32-NEXT: sw zero, 24(sp)
+; RV32-NEXT: sw s9, 28(sp)
+; RV32-NEXT: sw zero, 16(sp)
+; RV32-NEXT: sw s10, 20(sp)
+; RV32-NEXT: sw zero, 8(sp)
+; RV32-NEXT: sw a7, 12(sp)
+; RV32-NEXT: lui a0, 61681
+; RV32-NEXT: addi a0, a0, -241
+; RV32-NEXT: vsetvli a2, zero, e32, m2, ta, ma
+; RV32-NEXT: vmv.v.x v4, a0
+; RV32-NEXT: lui a0, 209715
+; RV32-NEXT: addi a0, a0, 819
+; RV32-NEXT: vmv.v.x v2, a0
+; RV32-NEXT: lui a0, 349525
+; RV32-NEXT: addi a0, a0, 1365
+; RV32-NEXT: vmv.v.x v0, a0
+; RV32-NEXT: addi a0, sp, 272
+; RV32-NEXT: vsetvli a2, zero, e64, m2, ta, ma
+; RV32-NEXT: vlse64.v v6, (a0), zero
+; RV32-NEXT: addi a0, sp, 264
+; RV32-NEXT: vlse64.v v10, (a0), zero
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 256
+; RV32-NEXT: vlse64.v v12, (a0), zero
+; RV32-NEXT: addi a0, sp, 248
+; RV32-NEXT: vlse64.v v14, (a0), zero
+; RV32-NEXT: addi a0, sp, 240
+; RV32-NEXT: vlse64.v v16, (a0), zero
+; RV32-NEXT: addi a0, sp, 232
+; RV32-NEXT: vlse64.v v18, (a0), zero
+; RV32-NEXT: addi a0, sp, 224
+; RV32-NEXT: vlse64.v v20, (a0), zero
+; RV32-NEXT: addi a0, sp, 216
+; RV32-NEXT: vlse64.v v22, (a0), zero
+; RV32-NEXT: li ra, 56
+; RV32-NEXT: vsrl.vi v24, v8, 24
+; RV32-NEXT: vsrl.vx v26, v8, ra
+; RV32-NEXT: li s11, 40
+; RV32-NEXT: vsrl.vx v28, v8, s11
+; RV32-NEXT: vsll.vx v30, v8, ra
+; RV32-NEXT: addi a4, t3, -256
+; RV32-NEXT: vand.vx v28, v28, a4
+; RV32-NEXT: vor.vv v26, v28, v26
+; RV32-NEXT: vand.vx v28, v8, a4
+; RV32-NEXT: vsll.vx v28, v28, s11
+; RV32-NEXT: vor.vv v30, v30, v28
+; RV32-NEXT: vsrl.vi v28, v8, 8
+; RV32-NEXT: lui a6, 4080
+; RV32-NEXT: vand.vx v24, v24, a6
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v6, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v28, v28, v6
+; RV32-NEXT: vor.vv v28, v28, v24
+; RV32-NEXT: addi a3, sp, 208
+; RV32-NEXT: vlse64.v v24, (a3), zero
+; RV32-NEXT: vor.vv v10, v28, v26
+; RV32-NEXT: vand.vx v26, v8, a6
+; RV32-NEXT: vsll.vi v26, v26, 24
+; RV32-NEXT: vand.vv v8, v8, v6
+; RV32-NEXT: vsll.vi v8, v8, 8
+; RV32-NEXT: vor.vv v8, v26, v8
+; RV32-NEXT: addi a3, sp, 200
+; RV32-NEXT: vlse64.v v28, (a3), zero
+; RV32-NEXT: vor.vv v8, v30, v8
+; RV32-NEXT: addi a3, sp, 192
+; RV32-NEXT: vlse64.v v26, (a3), zero
+; RV32-NEXT: vor.vv v8, v8, v10
+; RV32-NEXT: vsrl.vi v30, v8, 4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v4, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v8, v8, v4
+; RV32-NEXT: vand.vv v30, v30, v4
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v30, v8
+; RV32-NEXT: vsrl.vi v30, v8, 2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v2, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v8, v8, v2
+; RV32-NEXT: vand.vv v30, v30, v2
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v8, v30, v8
+; RV32-NEXT: vsrl.vi v30, v8, 1
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v0, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v8, v8, v0
+; RV32-NEXT: vand.vv v30, v30, v0
+; RV32-NEXT: vadd.vv v8, v8, v8
+; RV32-NEXT: vor.vv v8, v30, v8
+; RV32-NEXT: addi a3, sp, 184
+; RV32-NEXT: vlse64.v v30, (a3), zero
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vand.vv v6, v8, v10
+; RV32-NEXT: vand.vv v4, v8, v12
+; RV32-NEXT: vand.vv v2, v8, v14
+; RV32-NEXT: vand.vv v0, v8, v16
+; RV32-NEXT: vand.vv v10, v8, v18
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v22
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v28, v8, v28
+; RV32-NEXT: addi a3, sp, 176
+; RV32-NEXT: addi a0, sp, 168
+; RV32-NEXT: vlse64.v v10, (a3), zero
+; RV32-NEXT: vlse64.v v12, (a0), zero
+; RV32-NEXT: vand.vv v14, v8, v26
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v14, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v14, v8, v30
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v14, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: addi a2, sp, 160
+; RV32-NEXT: addi a3, sp, 152
+; RV32-NEXT: addi a1, sp, 144
+; RV32-NEXT: addi a0, sp, 136
+; RV32-NEXT: vlse64.v v10, (a2), zero
+; RV32-NEXT: vlse64.v v12, (a3), zero
+; RV32-NEXT: vlse64.v v14, (a1), zero
+; RV32-NEXT: vlse64.v v16, (a0), zero
+; RV32-NEXT: vand.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v14
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 128
+; RV32-NEXT: addi a1, sp, 120
+; RV32-NEXT: addi a2, sp, 112
+; RV32-NEXT: addi a3, sp, 104
+; RV32-NEXT: vlse64.v v10, (a0), zero
+; RV32-NEXT: vlse64.v v12, (a1), zero
+; RV32-NEXT: vlse64.v v14, (a2), zero
+; RV32-NEXT: vlse64.v v16, (a3), zero
+; RV32-NEXT: vand.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v14
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 96
+; RV32-NEXT: addi a1, sp, 88
+; RV32-NEXT: addi a2, sp, 80
+; RV32-NEXT: addi a3, sp, 72
+; RV32-NEXT: vlse64.v v10, (a0), zero
+; RV32-NEXT: vlse64.v v12, (a1), zero
+; RV32-NEXT: vlse64.v v14, (a2), zero
+; RV32-NEXT: vlse64.v v16, (a3), zero
+; RV32-NEXT: vand.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v14
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 64
+; RV32-NEXT: addi a1, sp, 56
+; RV32-NEXT: addi a2, sp, 48
+; RV32-NEXT: addi a3, sp, 40
+; RV32-NEXT: vlse64.v v10, (a0), zero
+; RV32-NEXT: vlse64.v v12, (a1), zero
+; RV32-NEXT: vlse64.v v14, (a2), zero
+; RV32-NEXT: vlse64.v v16, (a3), zero
+; RV32-NEXT: vand.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v14
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 32
+; RV32-NEXT: addi a1, sp, 24
+; RV32-NEXT: addi a2, sp, 16
+; RV32-NEXT: addi a3, sp, 8
+; RV32-NEXT: vlse64.v v10, (a0), zero
+; RV32-NEXT: vlse64.v v12, (a1), zero
+; RV32-NEXT: vlse64.v v14, (a2), zero
+; RV32-NEXT: vlse64.v v16, (a3), zero
+; RV32-NEXT: vand.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v14
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vi v10, v8, 2
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vi v10, v8, 1
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vi v10, v8, 4
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vi v10, v8, 8
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: li a0, 16
+; RV32-NEXT: vand.vx v10, v8, a0
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: li a0, 32
+; RV32-NEXT: vand.vx v10, v8, a0
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: li a0, 64
+; RV32-NEXT: vand.vx v10, v8, a0
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: li a0, 128
+; RV32-NEXT: vand.vx v10, v8, a0
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: li a0, 256
+; RV32-NEXT: vand.vx v10, v8, a0
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: li a0, 512
+; RV32-NEXT: vand.vx v10, v8, a0
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: li a0, 1024
+; RV32-NEXT: vand.vx v10, v8, a0
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, a5
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: lui a0, 1
+; RV32-NEXT: vand.vx v10, v8, a0
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, t0
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, t1
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, t2
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, t3
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, t4
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, t5
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, t6
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, s0
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, s1
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, s2
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, s3
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, s4
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, s5
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, s6
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, s7
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, s8
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, s9
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, s10
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: addi a0, sp, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v12, v8, v6
+; RV32-NEXT: vmul.vv v14, v8, v4
+; RV32-NEXT: vmul.vv v16, v8, v2
+; RV32-NEXT: vmul.vv v18, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v20, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v20, v8, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v22, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v22, v8, v22
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v24, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v26, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v26, v8, v26
+; RV32-NEXT: vmul.vv v28, v8, v28
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v30, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v30, v8, v30
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v6, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v6, v8, v6
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v4, v8, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v2, v8, v2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v0, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v8, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v8, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vi v8, v8, 0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: addi a0, sp, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: vxor.vv v8, v8, v14
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: vxor.vv v8, v8, v18
+; RV32-NEXT: vxor.vv v8, v8, v20
+; RV32-NEXT: vxor.vv v8, v8, v22
+; RV32-NEXT: vxor.vv v8, v8, v24
+; RV32-NEXT: vxor.vv v8, v8, v26
+; RV32-NEXT: vxor.vv v8, v8, v28
+; RV32-NEXT: vxor.vv v8, v8, v30
+; RV32-NEXT: vxor.vv v8, v8, v6
+; RV32-NEXT: vxor.vv v8, v8, v4
+; RV32-NEXT: vxor.vv v8, v8, v2
+; RV32-NEXT: vxor.vv v8, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: vsrl.vx v10, v8, ra
+; RV32-NEXT: vsll.vx v12, v8, ra
+; RV32-NEXT: vsrl.vx v14, v8, s11
+; RV32-NEXT: vand.vx v16, v8, a4
+; RV32-NEXT: vand.vx v14, v14, a4
+; RV32-NEXT: vsrl.vi v18, v8, 24
+; RV32-NEXT: vand.vx v20, v8, a6
+; RV32-NEXT: vand.vx v18, v18, a6
+; RV32-NEXT: vsll.vx v16, v16, s11
+; RV32-NEXT: vsrl.vi v22, v8, 8
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v24, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v24
+; RV32-NEXT: vand.vv v22, v22, v24
+; RV32-NEXT: vor.vv v10, v14, v10
+; RV32-NEXT: vor.vv v14, v22, v18
+; RV32-NEXT: vsll.vi v8, v8, 8
+; RV32-NEXT: vsll.vi v18, v20, 24
+; RV32-NEXT: vor.vv v8, v18, v8
+; RV32-NEXT: vor.vv v12, v12, v16
+; RV32-NEXT: vor.vv v10, v14, v10
+; RV32-NEXT: vor.vv v8, v12, v8
+; RV32-NEXT: vor.vv v8, v8, v10
+; RV32-NEXT: vsrl.vi v10, v8, 4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v12
+; RV32-NEXT: vand.vv v10, v10, v12
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v10, v8
+; RV32-NEXT: vsrl.vi v10, v8, 2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v12
+; RV32-NEXT: vand.vv v10, v10, v12
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v8, v10, v8
+; RV32-NEXT: vsrl.vi v10, v8, 1
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v12
+; RV32-NEXT: vand.vv v10, v10, v12
+; RV32-NEXT: vadd.vv v8, v8, v8
+; RV32-NEXT: vor.vv v8, v10, v8
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add sp, sp, a0
+; RV32-NEXT: lw ra, 348(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s0, 344(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s1, 340(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s2, 336(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s3, 332(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s4, 328(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s5, 324(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s6, 320(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s7, 316(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s8, 312(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s9, 308(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s10, 304(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s11, 300(sp) # 4-byte Folded Reload
+; RV32-NEXT: addi sp, sp, 352
+; RV32-NEXT: ret
+;
+; RV64-LABEL: clmulr_nxv2i64:
+; RV64: # %bb.0:
+; RV64-NEXT: addi sp, sp, -224
+; RV64-NEXT: sd ra, 216(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s0, 208(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s1, 200(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s2, 192(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s3, 184(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s4, 176(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s5, 168(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s6, 160(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s7, 152(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s8, 144(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s9, 136(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s10, 128(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s11, 120(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: sub sp, sp, a0
+; RV64-NEXT: li s3, 40
+; RV64-NEXT: lui s1, 16
+; RV64-NEXT: vsetvli a0, zero, e64, m2, ta, ma
+; RV64-NEXT: vsrl.vi v14, v8, 24
+; RV64-NEXT: vsrl.vi v10, v8, 8
+; RV64-NEXT: li t4, 255
+; RV64-NEXT: lui a5, 61681
+; RV64-NEXT: lui a6, 209715
+; RV64-NEXT: lui t6, 349525
+; RV64-NEXT: li t5, 16
+; RV64-NEXT: li t3, 32
+; RV64-NEXT: li t2, 64
+; RV64-NEXT: li t0, 128
+; RV64-NEXT: li t1, 256
+; RV64-NEXT: li a4, 512
+; RV64-NEXT: li a3, 1024
+; RV64-NEXT: li s0, 1
+; RV64-NEXT: lui a2, 1
+; RV64-NEXT: lui a1, 2
+; RV64-NEXT: lui a0, 4
+; RV64-NEXT: li a7, 56
+; RV64-NEXT: vsrl.vx v12, v8, a7
+; RV64-NEXT: vsrl.vx v18, v8, s3
+; RV64-NEXT: addi s2, s1, -256
+; RV64-NEXT: lui s1, 4080
+; RV64-NEXT: vand.vx v16, v14, s1
+; RV64-NEXT: slli t4, t4, 24
+; RV64-NEXT: vand.vx v20, v8, s1
+; RV64-NEXT: vsll.vx v14, v8, a7
+; RV64-NEXT: addi a7, a5, -241
+; RV64-NEXT: addi a6, a6, 819
+; RV64-NEXT: addi a5, t6, 1365
+; RV64-NEXT: slli t6, s0, 11
+; RV64-NEXT: slli s1, s0, 31
+; RV64-NEXT: sd s1, 96(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli s1, s0, 32
+; RV64-NEXT: sd s1, 88(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli s1, s0, 33
+; RV64-NEXT: sd s1, 80(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli s1, s0, 34
+; RV64-NEXT: sd s1, 72(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli s1, s0, 35
+; RV64-NEXT: sd s1, 64(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli s1, s0, 36
+; RV64-NEXT: sd s1, 56(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli s1, a7, 32
+; RV64-NEXT: add a7, a7, s1
+; RV64-NEXT: slli s1, a6, 32
+; RV64-NEXT: add a6, a6, s1
+; RV64-NEXT: slli s1, a5, 32
+; RV64-NEXT: add a5, a5, s1
+; RV64-NEXT: slli s1, s0, 37
+; RV64-NEXT: sd s1, 48(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v18, v18, s2
+; RV64-NEXT: vand.vx v10, v10, t4
+; RV64-NEXT: vsll.vi v20, v20, 24
+; RV64-NEXT: vand.vx v22, v8, t4
+; RV64-NEXT: vand.vx v8, v8, s2
+; RV64-NEXT: vor.vv v12, v18, v12
+; RV64-NEXT: vor.vv v10, v10, v16
+; RV64-NEXT: vsll.vi v16, v22, 8
+; RV64-NEXT: vsll.vx v8, v8, s3
+; RV64-NEXT: vor.vv v10, v10, v12
+; RV64-NEXT: vor.vv v12, v20, v16
+; RV64-NEXT: vor.vv v8, v14, v8
+; RV64-NEXT: vor.vv v8, v8, v12
+; RV64-NEXT: vor.vv v8, v8, v10
+; RV64-NEXT: vsrl.vi v10, v8, 4
+; RV64-NEXT: vand.vx v8, v8, a7
+; RV64-NEXT: vand.vx v10, v10, a7
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v10, v8
+; RV64-NEXT: vsrl.vi v10, v8, 2
+; RV64-NEXT: vand.vx v8, v8, a6
+; RV64-NEXT: vand.vx v10, v10, a6
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v10, v8
+; RV64-NEXT: vsrl.vi v10, v8, 1
+; RV64-NEXT: vand.vx v8, v8, a5
+; RV64-NEXT: vand.vx v10, v10, a5
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v10, v8
+; RV64-NEXT: vand.vx v10, v8, t5
+; RV64-NEXT: slli t5, s0, 38
+; RV64-NEXT: sd t5, 40(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t3
+; RV64-NEXT: slli t3, s0, 39
+; RV64-NEXT: sd t3, 32(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v14, v8, t2
+; RV64-NEXT: slli t2, s0, 40
+; RV64-NEXT: sd t2, 24(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v24, v8, t0
+; RV64-NEXT: slli t0, s0, 41
+; RV64-NEXT: sd t0, 16(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, t1
+; RV64-NEXT: slli s6, s0, 42
+; RV64-NEXT: vand.vx v18, v8, a4
+; RV64-NEXT: slli s7, s0, 43
+; RV64-NEXT: vand.vx v20, v8, a3
+; RV64-NEXT: slli s8, s0, 44
+; RV64-NEXT: vand.vx v22, v8, t6
+; RV64-NEXT: slli s9, s0, 45
+; RV64-NEXT: vand.vx v26, v8, a2
+; RV64-NEXT: slli s10, s0, 46
+; RV64-NEXT: vand.vx v28, v8, a1
+; RV64-NEXT: slli s11, s0, 47
+; RV64-NEXT: vand.vx v30, v8, a0
+; RV64-NEXT: slli ra, s0, 48
+; RV64-NEXT: slli s4, s0, 49
+; RV64-NEXT: slli s3, s0, 50
+; RV64-NEXT: slli s1, s0, 51
+; RV64-NEXT: slli t6, s0, 52
+; RV64-NEXT: slli t5, s0, 53
+; RV64-NEXT: slli t3, s0, 54
+; RV64-NEXT: slli t2, s0, 55
+; RV64-NEXT: slli t1, s0, 56
+; RV64-NEXT: slli t0, s0, 57
+; RV64-NEXT: slli a4, s0, 58
+; RV64-NEXT: slli a3, s0, 59
+; RV64-NEXT: slli a2, s0, 60
+; RV64-NEXT: slli a1, s0, 61
+; RV64-NEXT: slli s0, s0, 62
+; RV64-NEXT: li a0, -1
+; RV64-NEXT: slli a0, a0, 63
+; RV64-NEXT: vand.vi v6, v8, 2
+; RV64-NEXT: vand.vi v4, v8, 1
+; RV64-NEXT: vand.vi v2, v8, 4
+; RV64-NEXT: vand.vi v0, v8, 8
+; RV64-NEXT: vmul.vv v6, v8, v6
+; RV64-NEXT: sd a5, 8(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v6, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v6, v8, v4
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v6, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v6, v8, v2
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 5
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v6, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v14
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v24
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v16
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v18
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v20
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v22
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v26
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v28
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v30
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 8
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 16
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 32
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 64
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 5
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 128
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 6
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 256
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 512
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 1024
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 2048
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 4096
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 8192
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 16384
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 32768
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 65536
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 131072
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 262144
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: ld s5, 96(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: ld s5, 88(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: ld s5, 80(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: ld s5, 72(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: ld s5, 64(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: ld s5, 56(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: ld s5, 48(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: ld s5, 40(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: ld s5, 32(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: ld s5, 24(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: ld s5, 16(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 2
+; RV64-NEXT: mv a5, s5
+; RV64-NEXT: slli s5, s5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: ld a5, 8(sp) # 8-byte Folded Reload
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 112
+; RV64-NEXT: vs2r.v v10, (s5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, s6
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 3
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 112
+; RV64-NEXT: vs2r.v v10, (s5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, s7
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 4
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 112
+; RV64-NEXT: vs2r.v v10, (s5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, s8
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s6, s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 112
+; RV64-NEXT: vs2r.v v10, (s5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, s9
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 2
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 112
+; RV64-NEXT: vs2r.v v10, (s5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, s10
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 2
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 112
+; RV64-NEXT: vs2r.v v10, (s5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, s11
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 112
+; RV64-NEXT: vs2r.v v10, (s5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, ra
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 112
+; RV64-NEXT: vs2r.v v10, (s5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, s4
+; RV64-NEXT: vmul.vv v20, v8, v10
+; RV64-NEXT: vand.vx v10, v8, s3
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: vand.vx v12, v8, s1
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr s1, vlenb
+; RV64-NEXT: slli s1, s1, 3
+; RV64-NEXT: add s1, sp, s1
+; RV64-NEXT: addi s1, s1, 112
+; RV64-NEXT: vs2r.v v12, (s1) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t6
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs2r.v v12, (t6) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t5
+; RV64-NEXT: vmul.vv v6, v8, v12
+; RV64-NEXT: vand.vx v12, v8, t3
+; RV64-NEXT: vmul.vv v22, v8, v12
+; RV64-NEXT: vand.vx v12, v8, t2
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: vand.vx v14, v8, t1
+; RV64-NEXT: vmul.vv v24, v8, v14
+; RV64-NEXT: vand.vx v14, v8, t0
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vand.vx v16, v8, a4
+; RV64-NEXT: vmul.vv v4, v8, v16
+; RV64-NEXT: vand.vx v16, v8, a3
+; RV64-NEXT: vmul.vv v2, v8, v16
+; RV64-NEXT: vand.vx v16, v8, a2
+; RV64-NEXT: vmul.vv v26, v8, v16
+; RV64-NEXT: vand.vx v16, v8, a1
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: addi a1, sp, 112
+; RV64-NEXT: vs2r.v v16, (a1) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, s0
+; RV64-NEXT: vmul.vv v18, v8, v16
+; RV64-NEXT: vand.vx v16, v8, a0
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v8, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v28, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v28, v8
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v28, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v28
+; RV64-NEXT: vxor.vv v8, v8, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v28, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v28
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v28, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v28
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v28, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v28
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v28, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v28
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v28, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v8, v28
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v28, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v28
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v28, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v28
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v28, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v28
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v28, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v28
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v28, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v28
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v28, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v28
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v28, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v28
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v28, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v28
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v28, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v28
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v28, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v28
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v28, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v28
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v28, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v28
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v28, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v28
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v28, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v28
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v28, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v28
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v28, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v28, v0, v28
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v30, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v28, v28, v30
+; RV64-NEXT: li a1, 56
+; RV64-NEXT: vsll.vx v8, v8, a1
+; RV64-NEXT: vand.vx v0, v0, s2
+; RV64-NEXT: li a0, 40
+; RV64-NEXT: vsll.vx v0, v0, a0
+; RV64-NEXT: vor.vv v8, v8, v0
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl2r.v v0, (a2) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v28, v28, v0
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 4
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl2r.v v30, (a2) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v28, v28, v30
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl2r.v v30, (a2) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v28, v28, v30
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl2r.v v30, (a2) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v28, v28, v30
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl2r.v v30, (a2) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v28, v28, v30
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl2r.v v30, (a2) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v28, v28, v30
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl2r.v v30, (a2) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v28, v28, v30
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl2r.v v30, (a2) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v28, v28, v30
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 4
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl2r.v v30, (a2) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v28, v28, v30
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 5
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl2r.v v30, (a2) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v28, v28, v30
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl2r.v v30, (a2) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v28, v28, v30
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl2r.v v30, (a2) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v28, v28, v30
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl2r.v v30, (a2) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v28, v28, v30
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl2r.v v30, (a2) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v28, v28, v30
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl2r.v v30, (a2) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v28, v30
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl2r.v v30, (a2) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v30
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl2r.v v30, (a2) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v30
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 4
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl2r.v v30, (a2) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v30
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl2r.v v30, (a2) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v30
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl2r.v v30, (a2) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v30
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl2r.v v30, (a2) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v30
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl2r.v v30, (a2) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v30
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl2r.v v30, (a2) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v30, v0, v30
+; RV64-NEXT: vxor.vv v20, v30, v20
+; RV64-NEXT: vxor.vv v10, v20, v10
+; RV64-NEXT: vsrl.vi v20, v28, 8
+; RV64-NEXT: vand.vx v20, v20, t4
+; RV64-NEXT: vsrl.vi v30, v0, 24
+; RV64-NEXT: lui a2, 4080
+; RV64-NEXT: vand.vx v30, v30, a2
+; RV64-NEXT: vor.vv v20, v20, v30
+; RV64-NEXT: csrr a3, vlenb
+; RV64-NEXT: slli a3, a3, 3
+; RV64-NEXT: add a3, sp, a3
+; RV64-NEXT: addi a3, a3, 112
+; RV64-NEXT: vl2r.v v30, (a3) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v10, v10, v30
+; RV64-NEXT: csrr a3, vlenb
+; RV64-NEXT: slli a3, a3, 2
+; RV64-NEXT: add a3, sp, a3
+; RV64-NEXT: addi a3, a3, 112
+; RV64-NEXT: vl2r.v v30, (a3) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v10, v10, v30
+; RV64-NEXT: vxor.vv v10, v10, v6
+; RV64-NEXT: vxor.vv v10, v10, v22
+; RV64-NEXT: vxor.vv v10, v10, v12
+; RV64-NEXT: vand.vx v12, v28, a2
+; RV64-NEXT: vsll.vi v12, v12, 24
+; RV64-NEXT: vxor.vv v22, v10, v24
+; RV64-NEXT: vxor.vv v14, v22, v14
+; RV64-NEXT: vand.vx v22, v10, t4
+; RV64-NEXT: vsll.vi v22, v22, 8
+; RV64-NEXT: vor.vv v12, v12, v22
+; RV64-NEXT: vxor.vv v14, v14, v4
+; RV64-NEXT: vor.vv v8, v8, v12
+; RV64-NEXT: vxor.vv v12, v14, v2
+; RV64-NEXT: vxor.vv v12, v12, v26
+; RV64-NEXT: vsrl.vx v10, v10, a0
+; RV64-NEXT: vand.vx v10, v10, s2
+; RV64-NEXT: addi a0, sp, 112
+; RV64-NEXT: vl2r.v v14, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vxor.vv v12, v12, v18
+; RV64-NEXT: vxor.vv v12, v12, v16
+; RV64-NEXT: vsrl.vx v12, v12, a1
+; RV64-NEXT: vor.vv v10, v10, v12
+; RV64-NEXT: vor.vv v10, v20, v10
+; RV64-NEXT: vor.vv v8, v8, v10
+; RV64-NEXT: vsrl.vi v10, v8, 4
+; RV64-NEXT: vand.vx v8, v8, a7
+; RV64-NEXT: vand.vx v10, v10, a7
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v10, v8
+; RV64-NEXT: vsrl.vi v10, v8, 2
+; RV64-NEXT: vand.vx v8, v8, a6
+; RV64-NEXT: vand.vx v10, v10, a6
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v10, v8
+; RV64-NEXT: vsrl.vi v10, v8, 1
+; RV64-NEXT: vand.vx v8, v8, a5
+; RV64-NEXT: vand.vx v10, v10, a5
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v10, v8
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add sp, sp, a0
+; RV64-NEXT: ld ra, 216(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s0, 208(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s1, 200(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s2, 192(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s3, 184(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s4, 176(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s5, 168(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s6, 160(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s7, 152(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s8, 144(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s9, 136(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s10, 128(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s11, 120(sp) # 8-byte Folded Reload
+; RV64-NEXT: addi sp, sp, 224
+; RV64-NEXT: ret
+ %a = call <vscale x 2 x i64> @llvm.clmulr.nxv2i64(<vscale x 2 x i64> %x, <vscale x 2 x i64> %y)
+ ret <vscale x 2 x i64> %a
+}
+
+define <vscale x 4 x i64> @clmulr_nxv4i64(<vscale x 4 x i64> %x, <vscale x 4 x i64> %y) nounwind {
+; RV32-LABEL: clmulr_nxv4i64:
+; RV32: # %bb.0:
+; RV32-NEXT: addi sp, sp, -352
+; RV32-NEXT: sw ra, 348(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s0, 344(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s1, 340(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s2, 336(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s3, 332(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s4, 328(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s5, 324(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s6, 320(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s7, 316(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s8, 312(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s9, 308(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s10, 304(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s11, 300(sp) # 4-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: sub sp, sp, a0
+; RV32-NEXT: lui s11, 1044480
+; RV32-NEXT: lui t6, 524288
+; RV32-NEXT: li a0, 1
+; RV32-NEXT: li ra, 2
+; RV32-NEXT: li t4, 4
+; RV32-NEXT: li t2, 8
+; RV32-NEXT: li t5, 16
+; RV32-NEXT: li t3, 32
+; RV32-NEXT: li t1, 64
+; RV32-NEXT: li t0, 128
+; RV32-NEXT: li a7, 256
+; RV32-NEXT: li a6, 512
+; RV32-NEXT: li a3, 1024
+; RV32-NEXT: lui a2, 1
+; RV32-NEXT: lui a4, 2
+; RV32-NEXT: lui a1, 4
+; RV32-NEXT: lui a5, 8
+; RV32-NEXT: lui s0, 16
+; RV32-NEXT: lui s1, 32
+; RV32-NEXT: lui s2, 64
+; RV32-NEXT: lui s3, 128
+; RV32-NEXT: lui s4, 256
+; RV32-NEXT: lui s5, 512
+; RV32-NEXT: lui s6, 1024
+; RV32-NEXT: lui s7, 2048
+; RV32-NEXT: lui s8, 4096
+; RV32-NEXT: lui s9, 8192
+; RV32-NEXT: lui s10, 16384
+; RV32-NEXT: sw s11, 272(sp)
+; RV32-NEXT: lui s11, 32768
+; RV32-NEXT: sw zero, 276(sp)
+; RV32-NEXT: sw t6, 264(sp)
+; RV32-NEXT: sw zero, 268(sp)
+; RV32-NEXT: sw zero, 256(sp)
+; RV32-NEXT: sw a0, 260(sp)
+; RV32-NEXT: sw zero, 248(sp)
+; RV32-NEXT: sw ra, 252(sp)
+; RV32-NEXT: lui ra, 65536
+; RV32-NEXT: sw zero, 240(sp)
+; RV32-NEXT: sw t4, 244(sp)
+; RV32-NEXT: lui t4, 131072
+; RV32-NEXT: sw zero, 232(sp)
+; RV32-NEXT: sw t2, 236(sp)
+; RV32-NEXT: lui t2, 262144
+; RV32-NEXT: sw zero, 224(sp)
+; RV32-NEXT: sw t5, 228(sp)
+; RV32-NEXT: sw zero, 216(sp)
+; RV32-NEXT: sw t3, 220(sp)
+; RV32-NEXT: sw zero, 208(sp)
+; RV32-NEXT: sw t1, 212(sp)
+; RV32-NEXT: sw zero, 200(sp)
+; RV32-NEXT: sw t0, 204(sp)
+; RV32-NEXT: sw zero, 192(sp)
+; RV32-NEXT: sw a7, 196(sp)
+; RV32-NEXT: sw zero, 184(sp)
+; RV32-NEXT: sw a6, 188(sp)
+; RV32-NEXT: sw zero, 176(sp)
+; RV32-NEXT: sw a3, 180(sp)
+; RV32-NEXT: li t1, 1024
+; RV32-NEXT: slli a3, a0, 11
+; RV32-NEXT: sw zero, 168(sp)
+; RV32-NEXT: sw a3, 172(sp)
+; RV32-NEXT: sw zero, 160(sp)
+; RV32-NEXT: sw a2, 164(sp)
+; RV32-NEXT: sw zero, 152(sp)
+; RV32-NEXT: sw a4, 156(sp)
+; RV32-NEXT: lui t3, 2
+; RV32-NEXT: sw zero, 144(sp)
+; RV32-NEXT: sw a1, 148(sp)
+; RV32-NEXT: sw zero, 136(sp)
+; RV32-NEXT: sw a5, 140(sp)
+; RV32-NEXT: lui t5, 8
+; RV32-NEXT: sw zero, 128(sp)
+; RV32-NEXT: sw s0, 132(sp)
+; RV32-NEXT: sw zero, 120(sp)
+; RV32-NEXT: sw s1, 124(sp)
+; RV32-NEXT: sw zero, 112(sp)
+; RV32-NEXT: sw s2, 116(sp)
+; RV32-NEXT: sw zero, 104(sp)
+; RV32-NEXT: sw s3, 108(sp)
+; RV32-NEXT: sw zero, 96(sp)
+; RV32-NEXT: sw s4, 100(sp)
+; RV32-NEXT: sw zero, 88(sp)
+; RV32-NEXT: sw s5, 92(sp)
+; RV32-NEXT: sw zero, 80(sp)
+; RV32-NEXT: sw s6, 84(sp)
+; RV32-NEXT: sw zero, 72(sp)
+; RV32-NEXT: sw s7, 76(sp)
+; RV32-NEXT: sw zero, 64(sp)
+; RV32-NEXT: sw s8, 68(sp)
+; RV32-NEXT: sw zero, 56(sp)
+; RV32-NEXT: sw s9, 60(sp)
+; RV32-NEXT: sw zero, 48(sp)
+; RV32-NEXT: sw s10, 52(sp)
+; RV32-NEXT: sw zero, 40(sp)
+; RV32-NEXT: sw s11, 44(sp)
+; RV32-NEXT: sw zero, 32(sp)
+; RV32-NEXT: sw ra, 36(sp)
+; RV32-NEXT: sw zero, 24(sp)
+; RV32-NEXT: sw t4, 28(sp)
+; RV32-NEXT: sw zero, 16(sp)
+; RV32-NEXT: sw t2, 20(sp)
+; RV32-NEXT: sw zero, 8(sp)
+; RV32-NEXT: sw t6, 12(sp)
+; RV32-NEXT: lui a1, 61681
+; RV32-NEXT: addi a1, a1, -241
+; RV32-NEXT: vsetvli a2, zero, e32, m4, ta, ma
+; RV32-NEXT: vmv.v.x v28, a1
+; RV32-NEXT: lui a1, 209715
+; RV32-NEXT: addi a1, a1, 819
+; RV32-NEXT: vmv.v.x v4, a1
+; RV32-NEXT: addi a1, sp, 272
+; RV32-NEXT: vsetvli a2, zero, e64, m4, ta, ma
+; RV32-NEXT: vlse64.v v0, (a1), zero
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 8
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v0, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: li a6, 56
+; RV32-NEXT: vsrl.vi v20, v8, 24
+; RV32-NEXT: vsrl.vx v12, v8, a6
+; RV32-NEXT: li a5, 40
+; RV32-NEXT: vsrl.vx v16, v8, a5
+; RV32-NEXT: vsll.vx v24, v8, a6
+; RV32-NEXT: addi a2, s0, -256
+; RV32-NEXT: vand.vx v16, v16, a2
+; RV32-NEXT: vor.vv v16, v16, v12
+; RV32-NEXT: vand.vx v12, v8, a2
+; RV32-NEXT: vsll.vx v12, v12, a5
+; RV32-NEXT: vor.vv v12, v24, v12
+; RV32-NEXT: vsrl.vi v24, v8, 8
+; RV32-NEXT: lui a4, 4080
+; RV32-NEXT: vand.vx v20, v20, a4
+; RV32-NEXT: lui a7, 349525
+; RV32-NEXT: addi a7, a7, 1365
+; RV32-NEXT: vand.vv v24, v24, v0
+; RV32-NEXT: vor.vv v20, v24, v20
+; RV32-NEXT: vsetvli t0, zero, e32, m4, ta, ma
+; RV32-NEXT: vmv.v.x v24, a7
+; RV32-NEXT: vsetvli a7, zero, e64, m4, ta, ma
+; RV32-NEXT: vor.vv v16, v20, v16
+; RV32-NEXT: vand.vx v20, v8, a4
+; RV32-NEXT: vsll.vi v20, v20, 24
+; RV32-NEXT: vand.vv v8, v8, v0
+; RV32-NEXT: vsll.vi v8, v8, 8
+; RV32-NEXT: vor.vv v8, v20, v8
+; RV32-NEXT: addi a7, sp, 264
+; RV32-NEXT: vlse64.v v20, (a7), zero
+; RV32-NEXT: vor.vv v8, v12, v8
+; RV32-NEXT: addi a7, sp, 256
+; RV32-NEXT: vlse64.v v12, (a7), zero
+; RV32-NEXT: vor.vv v8, v8, v16
+; RV32-NEXT: vsrl.vi v16, v8, 4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v28, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v8, v8, v28
+; RV32-NEXT: vand.vv v16, v16, v28
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v16, v8
+; RV32-NEXT: vsrl.vi v16, v8, 2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v4, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v8, v8, v4
+; RV32-NEXT: vand.vv v16, v16, v4
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v8, v16, v8
+; RV32-NEXT: vsrl.vi v16, v8, 1
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v24, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v8, v8, v24
+; RV32-NEXT: vand.vv v16, v16, v24
+; RV32-NEXT: vadd.vv v8, v8, v8
+; RV32-NEXT: vor.vv v8, v16, v8
+; RV32-NEXT: addi a7, sp, 248
+; RV32-NEXT: vlse64.v v16, (a7), zero
+; RV32-NEXT: vand.vv v28, v8, v20
+; RV32-NEXT: addi a7, sp, 240
+; RV32-NEXT: addi t0, sp, 232
+; RV32-NEXT: vlse64.v v20, (a7), zero
+; RV32-NEXT: vlse64.v v24, (t0), zero
+; RV32-NEXT: vand.vv v4, v8, v12
+; RV32-NEXT: vand.vv v0, v8, v16
+; RV32-NEXT: vand.vv v12, v8, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: addi a7, sp, 224
+; RV32-NEXT: addi t0, sp, 216
+; RV32-NEXT: addi a1, sp, 208
+; RV32-NEXT: addi a0, sp, 200
+; RV32-NEXT: vlse64.v v12, (a7), zero
+; RV32-NEXT: vlse64.v v16, (t0), zero
+; RV32-NEXT: vlse64.v v20, (a1), zero
+; RV32-NEXT: vlse64.v v24, (a0), zero
+; RV32-NEXT: vand.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 192
+; RV32-NEXT: addi a1, sp, 184
+; RV32-NEXT: addi a7, sp, 176
+; RV32-NEXT: addi t0, sp, 168
+; RV32-NEXT: vlse64.v v12, (a0), zero
+; RV32-NEXT: vlse64.v v16, (a1), zero
+; RV32-NEXT: vlse64.v v20, (a7), zero
+; RV32-NEXT: vlse64.v v24, (t0), zero
+; RV32-NEXT: vand.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 160
+; RV32-NEXT: addi a1, sp, 152
+; RV32-NEXT: addi a7, sp, 144
+; RV32-NEXT: addi t0, sp, 136
+; RV32-NEXT: vlse64.v v12, (a0), zero
+; RV32-NEXT: vlse64.v v16, (a1), zero
+; RV32-NEXT: vlse64.v v20, (a7), zero
+; RV32-NEXT: vlse64.v v24, (t0), zero
+; RV32-NEXT: vand.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 128
+; RV32-NEXT: addi a1, sp, 120
+; RV32-NEXT: addi a7, sp, 112
+; RV32-NEXT: addi t0, sp, 104
+; RV32-NEXT: vlse64.v v12, (a0), zero
+; RV32-NEXT: vlse64.v v16, (a1), zero
+; RV32-NEXT: vlse64.v v20, (a7), zero
+; RV32-NEXT: vlse64.v v24, (t0), zero
+; RV32-NEXT: vand.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 96
+; RV32-NEXT: addi a1, sp, 88
+; RV32-NEXT: addi a7, sp, 80
+; RV32-NEXT: addi t0, sp, 72
+; RV32-NEXT: vlse64.v v12, (a0), zero
+; RV32-NEXT: vlse64.v v16, (a1), zero
+; RV32-NEXT: vlse64.v v20, (a7), zero
+; RV32-NEXT: vlse64.v v24, (t0), zero
+; RV32-NEXT: vand.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 64
+; RV32-NEXT: addi a1, sp, 56
+; RV32-NEXT: addi a7, sp, 48
+; RV32-NEXT: addi t0, sp, 40
+; RV32-NEXT: vlse64.v v12, (a0), zero
+; RV32-NEXT: vlse64.v v16, (a1), zero
+; RV32-NEXT: vlse64.v v20, (a7), zero
+; RV32-NEXT: vlse64.v v24, (t0), zero
+; RV32-NEXT: vand.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 32
+; RV32-NEXT: addi a1, sp, 24
+; RV32-NEXT: addi a7, sp, 16
+; RV32-NEXT: addi t0, sp, 8
+; RV32-NEXT: vlse64.v v12, (a0), zero
+; RV32-NEXT: vlse64.v v16, (a1), zero
+; RV32-NEXT: vlse64.v v20, (a7), zero
+; RV32-NEXT: vlse64.v v24, (t0), zero
+; RV32-NEXT: vand.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 7
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vi v12, v8, 2
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vi v12, v8, 1
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vi v12, v8, 4
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vi v12, v8, 8
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: li a0, 16
+; RV32-NEXT: vand.vx v12, v8, a0
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: li a0, 32
+; RV32-NEXT: vand.vx v12, v8, a0
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: li a0, 64
+; RV32-NEXT: vand.vx v12, v8, a0
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: li a0, 128
+; RV32-NEXT: vand.vx v12, v8, a0
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: li a0, 256
+; RV32-NEXT: vand.vx v12, v8, a0
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: li a0, 512
+; RV32-NEXT: vand.vx v12, v8, a0
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, t1
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, a3
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: lui a0, 1
+; RV32-NEXT: vand.vx v12, v8, a0
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, t3
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: lui a0, 4
+; RV32-NEXT: vand.vx v12, v8, a0
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, t5
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s0
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s1
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s2
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s3
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s4
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s5
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s6
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s7
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s8
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s9
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s10
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s11
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, ra
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, t4
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, t2
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: addi a0, sp, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vmul.vv v16, v8, v28
+; RV32-NEXT: vmul.vv v20, v8, v4
+; RV32-NEXT: vmul.vv v24, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v28, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v28, v8, v28
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v4, v8, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v0, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 7
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v8, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v8, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vi v8, v8, 0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: addi a0, sp, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: vxor.vv v8, v8, v20
+; RV32-NEXT: vxor.vv v8, v8, v24
+; RV32-NEXT: vxor.vv v8, v8, v28
+; RV32-NEXT: vxor.vv v8, v8, v4
+; RV32-NEXT: vxor.vv v8, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: vsrl.vx v12, v8, a6
+; RV32-NEXT: vsrl.vx v16, v8, a5
+; RV32-NEXT: vsrl.vi v20, v8, 24
+; RV32-NEXT: vand.vx v16, v16, a2
+; RV32-NEXT: vor.vv v12, v16, v12
+; RV32-NEXT: vsrl.vi v16, v8, 8
+; RV32-NEXT: vand.vx v20, v20, a4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 8
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vand.vv v16, v16, v24
+; RV32-NEXT: vor.vv v16, v16, v20
+; RV32-NEXT: vand.vx v20, v8, a4
+; RV32-NEXT: vand.vv v24, v8, v24
+; RV32-NEXT: vsll.vi v24, v24, 8
+; RV32-NEXT: vsll.vi v20, v20, 24
+; RV32-NEXT: vor.vv v20, v20, v24
+; RV32-NEXT: vsll.vx v24, v8, a6
+; RV32-NEXT: vand.vx v8, v8, a2
+; RV32-NEXT: vsll.vx v8, v8, a5
+; RV32-NEXT: vor.vv v8, v24, v8
+; RV32-NEXT: vor.vv v12, v16, v12
+; RV32-NEXT: vor.vv v8, v8, v20
+; RV32-NEXT: vor.vv v8, v8, v12
+; RV32-NEXT: vsrl.vi v12, v8, 4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v16
+; RV32-NEXT: vand.vv v12, v12, v16
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v12, v8
+; RV32-NEXT: vsrl.vi v12, v8, 2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v16
+; RV32-NEXT: vand.vv v12, v12, v16
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v8, v12, v8
+; RV32-NEXT: vsrl.vi v12, v8, 1
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v16
+; RV32-NEXT: vand.vv v12, v12, v16
+; RV32-NEXT: vadd.vv v8, v8, v8
+; RV32-NEXT: vor.vv v8, v12, v8
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add sp, sp, a0
+; RV32-NEXT: lw ra, 348(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s0, 344(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s1, 340(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s2, 336(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s3, 332(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s4, 328(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s5, 324(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s6, 320(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s7, 316(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s8, 312(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s9, 308(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s10, 304(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s11, 300(sp) # 4-byte Folded Reload
+; RV32-NEXT: addi sp, sp, 352
+; RV32-NEXT: ret
+;
+; RV64-LABEL: clmulr_nxv4i64:
+; RV64: # %bb.0:
+; RV64-NEXT: addi sp, sp, -240
+; RV64-NEXT: sd ra, 232(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s0, 224(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s1, 216(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s2, 208(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s3, 200(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s4, 192(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s5, 184(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s6, 176(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s7, 168(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s8, 160(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s9, 152(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s10, 144(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s11, 136(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: sub sp, sp, a0
+; RV64-NEXT: li t0, 40
+; RV64-NEXT: lui a7, 16
+; RV64-NEXT: vsetvli a0, zero, e64, m4, ta, ma
+; RV64-NEXT: vsrl.vi v20, v8, 24
+; RV64-NEXT: vsrl.vi v12, v8, 8
+; RV64-NEXT: li t2, 255
+; RV64-NEXT: lui a3, 61681
+; RV64-NEXT: lui a4, 209715
+; RV64-NEXT: lui a5, 349525
+; RV64-NEXT: li a2, 16
+; RV64-NEXT: li a1, 32
+; RV64-NEXT: li a0, 64
+; RV64-NEXT: li s9, 1
+; RV64-NEXT: li a6, 56
+; RV64-NEXT: vsrl.vx v16, v8, a6
+; RV64-NEXT: vsrl.vx v28, v8, t0
+; RV64-NEXT: addi t6, a7, -256
+; RV64-NEXT: lui a7, 4080
+; RV64-NEXT: vand.vx v24, v20, a7
+; RV64-NEXT: slli t2, t2, 24
+; RV64-NEXT: vand.vx v4, v8, a7
+; RV64-NEXT: vsll.vx v20, v8, a6
+; RV64-NEXT: addi a7, a3, -241
+; RV64-NEXT: addi a6, a4, 819
+; RV64-NEXT: addi a5, a5, 1365
+; RV64-NEXT: slli a3, s9, 11
+; RV64-NEXT: sd a3, 112(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a3, s9, 31
+; RV64-NEXT: sd a3, 104(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a3, s9, 32
+; RV64-NEXT: sd a3, 96(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a3, s9, 33
+; RV64-NEXT: sd a3, 88(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a3, s9, 34
+; RV64-NEXT: sd a3, 80(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a3, s9, 35
+; RV64-NEXT: sd a3, 72(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a3, s9, 36
+; RV64-NEXT: sd a3, 64(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a3, s9, 37
+; RV64-NEXT: sd a3, 56(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a3, s9, 38
+; RV64-NEXT: sd a3, 48(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a3, s9, 39
+; RV64-NEXT: sd a3, 40(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a3, s9, 40
+; RV64-NEXT: sd a3, 32(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a3, s9, 41
+; RV64-NEXT: sd a3, 24(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli s6, s9, 42
+; RV64-NEXT: slli s7, s9, 43
+; RV64-NEXT: slli a3, a7, 32
+; RV64-NEXT: add a7, a7, a3
+; RV64-NEXT: slli a3, a6, 32
+; RV64-NEXT: add a6, a6, a3
+; RV64-NEXT: slli a3, a5, 32
+; RV64-NEXT: add a5, a5, a3
+; RV64-NEXT: slli s8, s9, 44
+; RV64-NEXT: vand.vx v28, v28, t6
+; RV64-NEXT: vand.vx v12, v12, t2
+; RV64-NEXT: vsll.vi v4, v4, 24
+; RV64-NEXT: vand.vx v0, v8, t2
+; RV64-NEXT: vand.vx v8, v8, t6
+; RV64-NEXT: vor.vv v16, v28, v16
+; RV64-NEXT: vor.vv v12, v12, v24
+; RV64-NEXT: vsll.vi v24, v0, 8
+; RV64-NEXT: vsll.vx v8, v8, t0
+; RV64-NEXT: vor.vv v12, v12, v16
+; RV64-NEXT: vor.vv v16, v4, v24
+; RV64-NEXT: vor.vv v8, v20, v8
+; RV64-NEXT: vor.vv v8, v8, v16
+; RV64-NEXT: vor.vv v8, v8, v12
+; RV64-NEXT: vsrl.vi v12, v8, 4
+; RV64-NEXT: vand.vx v8, v8, a7
+; RV64-NEXT: vand.vx v12, v12, a7
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vsrl.vi v12, v8, 2
+; RV64-NEXT: vand.vx v8, v8, a6
+; RV64-NEXT: vand.vx v12, v12, a6
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vsrl.vi v12, v8, 1
+; RV64-NEXT: vand.vx v8, v8, a5
+; RV64-NEXT: vand.vx v12, v12, a5
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vand.vx v12, v8, a2
+; RV64-NEXT: slli s10, s9, 45
+; RV64-NEXT: vand.vx v16, v8, a1
+; RV64-NEXT: slli s11, s9, 46
+; RV64-NEXT: vand.vx v20, v8, a0
+; RV64-NEXT: slli ra, s9, 47
+; RV64-NEXT: slli s4, s9, 48
+; RV64-NEXT: slli s3, s9, 49
+; RV64-NEXT: slli s2, s9, 50
+; RV64-NEXT: slli s1, s9, 51
+; RV64-NEXT: slli s0, s9, 52
+; RV64-NEXT: slli t5, s9, 53
+; RV64-NEXT: slli t4, s9, 54
+; RV64-NEXT: slli t3, s9, 55
+; RV64-NEXT: slli t1, s9, 56
+; RV64-NEXT: slli t0, s9, 57
+; RV64-NEXT: slli a4, s9, 58
+; RV64-NEXT: slli a3, s9, 59
+; RV64-NEXT: slli a2, s9, 60
+; RV64-NEXT: slli a1, s9, 61
+; RV64-NEXT: slli s9, s9, 62
+; RV64-NEXT: li a0, -1
+; RV64-NEXT: slli a0, a0, 63
+; RV64-NEXT: vand.vi v24, v8, 2
+; RV64-NEXT: vand.vi v28, v8, 1
+; RV64-NEXT: vand.vi v4, v8, 4
+; RV64-NEXT: vand.vi v0, v8, 8
+; RV64-NEXT: vmul.vv v24, v8, v24
+; RV64-NEXT: vmul.vv v28, v8, v28
+; RV64-NEXT: sd a5, 8(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v28, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vmul.vv v28, v8, v4
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v28, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 5
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vmul.vv v12, v8, v16
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vmul.vv v12, v8, v20
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: li s5, 128
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: li s5, 256
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: li s5, 512
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: li s5, 1024
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: ld s5, 112(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 1
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 6
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 2
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 4
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 8
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 16
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 32
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 64
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 128
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 256
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 5
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 512
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 1024
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 2048
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 4096
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 8192
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 16384
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 32768
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 5
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 65536
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 7
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 131072
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 262144
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: ld s5, 104(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: ld s5, 96(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: ld s5, 88(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: ld s5, 80(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: ld s5, 72(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: ld s5, 64(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 5
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: ld s5, 56(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: ld s5, 48(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: ld s5, 40(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: ld s5, 32(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: ld s5, 24(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 2
+; RV64-NEXT: mv a5, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: slli s5, s5, 3
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: ld a5, 8(sp) # 8-byte Folded Reload
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 128
+; RV64-NEXT: vs4r.v v12, (s5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s6
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 3
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 3
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 128
+; RV64-NEXT: vs4r.v v12, (s5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s7
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 2
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 4
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 128
+; RV64-NEXT: vs4r.v v12, (s5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s8
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 128
+; RV64-NEXT: vs4r.v v12, (s5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s10
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 2
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s6, s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s6, s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 128
+; RV64-NEXT: vs4r.v v12, (s5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s11
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 3
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s6, s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 128
+; RV64-NEXT: vs4r.v v12, (s5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, ra
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 4
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 128
+; RV64-NEXT: vs4r.v v12, (s5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s4
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr s4, vlenb
+; RV64-NEXT: slli s4, s4, 3
+; RV64-NEXT: mv s5, s4
+; RV64-NEXT: slli s4, s4, 2
+; RV64-NEXT: add s4, s4, s5
+; RV64-NEXT: add s4, sp, s4
+; RV64-NEXT: addi s4, s4, 128
+; RV64-NEXT: vs4r.v v12, (s4) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s3
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr s3, vlenb
+; RV64-NEXT: slli s3, s3, 2
+; RV64-NEXT: mv s4, s3
+; RV64-NEXT: slli s3, s3, 2
+; RV64-NEXT: add s3, s3, s4
+; RV64-NEXT: add s3, sp, s3
+; RV64-NEXT: addi s3, s3, 128
+; RV64-NEXT: vs4r.v v12, (s3) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s2
+; RV64-NEXT: vmul.vv v4, v8, v12
+; RV64-NEXT: vand.vx v12, v8, s1
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr s1, vlenb
+; RV64-NEXT: slli s1, s1, 2
+; RV64-NEXT: mv s2, s1
+; RV64-NEXT: slli s1, s1, 2
+; RV64-NEXT: add s2, s2, s1
+; RV64-NEXT: slli s1, s1, 1
+; RV64-NEXT: add s1, s1, s2
+; RV64-NEXT: add s1, sp, s1
+; RV64-NEXT: addi s1, s1, 128
+; RV64-NEXT: vs4r.v v12, (s1) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s0
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr s0, vlenb
+; RV64-NEXT: slli s0, s0, 2
+; RV64-NEXT: mv s1, s0
+; RV64-NEXT: slli s0, s0, 1
+; RV64-NEXT: add s1, s1, s0
+; RV64-NEXT: slli s0, s0, 2
+; RV64-NEXT: add s0, s0, s1
+; RV64-NEXT: add s0, sp, s0
+; RV64-NEXT: addi s0, s0, 128
+; RV64-NEXT: vs4r.v v12, (s0) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr t5, vlenb
+; RV64-NEXT: slli t5, t5, 2
+; RV64-NEXT: mv s0, t5
+; RV64-NEXT: slli t5, t5, 3
+; RV64-NEXT: add t5, t5, s0
+; RV64-NEXT: add t5, sp, t5
+; RV64-NEXT: addi t5, t5, 128
+; RV64-NEXT: vs4r.v v12, (t5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t4
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr t4, vlenb
+; RV64-NEXT: slli t4, t4, 4
+; RV64-NEXT: add t4, sp, t4
+; RV64-NEXT: addi t4, t4, 128
+; RV64-NEXT: vs4r.v v12, (t4) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t3
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr t3, vlenb
+; RV64-NEXT: slli t3, t3, 2
+; RV64-NEXT: add t3, sp, t3
+; RV64-NEXT: addi t3, t3, 128
+; RV64-NEXT: vs4r.v v12, (t3) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t1
+; RV64-NEXT: vmul.vv v20, v8, v12
+; RV64-NEXT: vand.vx v12, v8, t0
+; RV64-NEXT: vmul.vv v16, v8, v12
+; RV64-NEXT: vand.vx v12, v8, a4
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a4, vlenb
+; RV64-NEXT: slli a4, a4, 5
+; RV64-NEXT: add a4, sp, a4
+; RV64-NEXT: addi a4, a4, 128
+; RV64-NEXT: vs4r.v v12, (a4) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, a3
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a3, vlenb
+; RV64-NEXT: slli a3, a3, 2
+; RV64-NEXT: mv a4, a3
+; RV64-NEXT: slli a3, a3, 1
+; RV64-NEXT: add a4, a4, a3
+; RV64-NEXT: slli a3, a3, 1
+; RV64-NEXT: add a3, a3, a4
+; RV64-NEXT: add a3, sp, a3
+; RV64-NEXT: addi a3, a3, 128
+; RV64-NEXT: vs4r.v v12, (a3) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, a2
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vs4r.v v12, (a2) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, a1
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: mv a2, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add a1, a1, a2
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs4r.v v12, (a1) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s9
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs4r.v v12, (a1) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, a0
+; RV64-NEXT: vmul.vv v8, v8, v12
+; RV64-NEXT: addi a0, sp, 128
+; RV64-NEXT: vs4r.v v8, (a0) # vscale x 32-byte Folded Spill
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v8, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v12
+; RV64-NEXT: vxor.vv v8, v8, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v12
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v12
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v12
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v12
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v12, v8, v12
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v12, v12, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v12, v12, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v12, v12, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 6
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v12, v12, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v12, v12, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v12, v12, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v12, v12, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v12, v12, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v12, v12, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v12, v12, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v12, v12, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v12, v12, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v12, v12, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v12, v12, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v12, v12, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v12, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v24
+; RV64-NEXT: li a1, 56
+; RV64-NEXT: vsll.vx v8, v8, a1
+; RV64-NEXT: vand.vx v12, v12, t6
+; RV64-NEXT: li a0, 40
+; RV64-NEXT: vsll.vx v12, v12, a0
+; RV64-NEXT: vor.vv v12, v8, v12
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 4
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v8, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v0, v8
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 5
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v24, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 7
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v24, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v24, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v24, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v24, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 4
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v24, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v24, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v24, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v24, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 5
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v24, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v24, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v24, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v24, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 4
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v24, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v8, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v24, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v24, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 4
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v24, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 6
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v24, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v24, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v24, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 4
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v24, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v24, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v0, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v28, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v24, v28
+; RV64-NEXT: vxor.vv v24, v24, v4
+; RV64-NEXT: vsrl.vi v4, v8, 8
+; RV64-NEXT: vand.vx v4, v4, t2
+; RV64-NEXT: vsrl.vi v0, v0, 24
+; RV64-NEXT: lui a2, 4080
+; RV64-NEXT: vand.vx v0, v0, a2
+; RV64-NEXT: vor.vv v4, v4, v0
+; RV64-NEXT: csrr a3, vlenb
+; RV64-NEXT: slli a3, a3, 2
+; RV64-NEXT: mv a4, a3
+; RV64-NEXT: slli a3, a3, 2
+; RV64-NEXT: add a4, a4, a3
+; RV64-NEXT: slli a3, a3, 1
+; RV64-NEXT: add a3, a3, a4
+; RV64-NEXT: add a3, sp, a3
+; RV64-NEXT: addi a3, a3, 128
+; RV64-NEXT: vl4r.v v0, (a3) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: csrr a3, vlenb
+; RV64-NEXT: slli a3, a3, 2
+; RV64-NEXT: mv a4, a3
+; RV64-NEXT: slli a3, a3, 1
+; RV64-NEXT: add a4, a4, a3
+; RV64-NEXT: slli a3, a3, 2
+; RV64-NEXT: add a3, a3, a4
+; RV64-NEXT: add a3, sp, a3
+; RV64-NEXT: addi a3, a3, 128
+; RV64-NEXT: vl4r.v v0, (a3) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: csrr a3, vlenb
+; RV64-NEXT: slli a3, a3, 2
+; RV64-NEXT: mv a4, a3
+; RV64-NEXT: slli a3, a3, 3
+; RV64-NEXT: add a3, a3, a4
+; RV64-NEXT: add a3, sp, a3
+; RV64-NEXT: addi a3, a3, 128
+; RV64-NEXT: vl4r.v v0, (a3) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: csrr a3, vlenb
+; RV64-NEXT: slli a3, a3, 4
+; RV64-NEXT: add a3, sp, a3
+; RV64-NEXT: addi a3, a3, 128
+; RV64-NEXT: vl4r.v v28, (a3) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v24, v28
+; RV64-NEXT: csrr a3, vlenb
+; RV64-NEXT: slli a3, a3, 2
+; RV64-NEXT: add a3, sp, a3
+; RV64-NEXT: addi a3, a3, 128
+; RV64-NEXT: vl4r.v v28, (a3) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v24, v28
+; RV64-NEXT: vxor.vv v20, v24, v20
+; RV64-NEXT: vxor.vv v16, v20, v16
+; RV64-NEXT: vand.vx v8, v8, a2
+; RV64-NEXT: vsll.vi v8, v8, 24
+; RV64-NEXT: vand.vx v20, v24, t2
+; RV64-NEXT: vsll.vi v20, v20, 8
+; RV64-NEXT: vor.vv v8, v8, v20
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 5
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v20, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v12, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v12, v16, v12
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v16, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v12, v12, v16
+; RV64-NEXT: vsrl.vx v16, v24, a0
+; RV64-NEXT: vand.vx v16, v16, t6
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a2, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a2
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v20, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v12, v12, v20
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v20, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v12, v12, v20
+; RV64-NEXT: addi a0, sp, 128
+; RV64-NEXT: vl4r.v v20, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v12, v12, v20
+; RV64-NEXT: vsrl.vx v12, v12, a1
+; RV64-NEXT: vor.vv v12, v16, v12
+; RV64-NEXT: vor.vv v12, v4, v12
+; RV64-NEXT: vor.vv v8, v8, v12
+; RV64-NEXT: vsrl.vi v12, v8, 4
+; RV64-NEXT: vand.vx v8, v8, a7
+; RV64-NEXT: vand.vx v12, v12, a7
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vsrl.vi v12, v8, 2
+; RV64-NEXT: vand.vx v8, v8, a6
+; RV64-NEXT: vand.vx v12, v12, a6
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vsrl.vi v12, v8, 1
+; RV64-NEXT: vand.vx v8, v8, a5
+; RV64-NEXT: vand.vx v12, v12, a5
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add sp, sp, a0
+; RV64-NEXT: ld ra, 232(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s0, 224(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s1, 216(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s2, 208(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s3, 200(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s4, 192(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s5, 184(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s6, 176(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s7, 168(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s8, 160(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s9, 152(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s10, 144(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s11, 136(sp) # 8-byte Folded Reload
+; RV64-NEXT: addi sp, sp, 240
+; RV64-NEXT: ret
+ %a = call <vscale x 4 x i64> @llvm.clmulr.nxv4i64(<vscale x 4 x i64> %x, <vscale x 4 x i64> %y)
+ ret <vscale x 4 x i64> %a
+}
+
+define <vscale x 8 x i64> @clmulr_nxv8i64(<vscale x 8 x i64> %x, <vscale x 8 x i64> %y) nounwind {
+; RV32-LABEL: clmulr_nxv8i64:
+; RV32: # %bb.0:
+; RV32-NEXT: addi sp, sp, -352
+; RV32-NEXT: sw ra, 348(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s0, 344(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s1, 340(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s2, 336(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s3, 332(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s4, 328(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s5, 324(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s6, 320(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s7, 316(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s8, 312(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s9, 308(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s10, 304(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s11, 300(sp) # 4-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: sub sp, sp, a0
+; RV32-NEXT: lui s11, 1044480
+; RV32-NEXT: lui s0, 524288
+; RV32-NEXT: li a0, 1
+; RV32-NEXT: li ra, 2
+; RV32-NEXT: li t4, 4
+; RV32-NEXT: li t2, 8
+; RV32-NEXT: li t6, 16
+; RV32-NEXT: li t5, 32
+; RV32-NEXT: li t3, 64
+; RV32-NEXT: li t1, 128
+; RV32-NEXT: li t0, 256
+; RV32-NEXT: li a7, 512
+; RV32-NEXT: li a6, 1024
+; RV32-NEXT: lui a4, 1
+; RV32-NEXT: lui a3, 2
+; RV32-NEXT: lui a2, 4
+; RV32-NEXT: lui a5, 8
+; RV32-NEXT: lui s1, 16
+; RV32-NEXT: lui a1, 32
+; RV32-NEXT: lui s2, 64
+; RV32-NEXT: lui s3, 128
+; RV32-NEXT: lui s4, 256
+; RV32-NEXT: lui s5, 512
+; RV32-NEXT: lui s6, 1024
+; RV32-NEXT: lui s7, 2048
+; RV32-NEXT: lui s8, 4096
+; RV32-NEXT: lui s9, 8192
+; RV32-NEXT: lui s10, 16384
+; RV32-NEXT: sw s11, 272(sp)
+; RV32-NEXT: lui s11, 32768
+; RV32-NEXT: sw zero, 276(sp)
+; RV32-NEXT: sw s0, 264(sp)
+; RV32-NEXT: sw zero, 268(sp)
+; RV32-NEXT: sw zero, 256(sp)
+; RV32-NEXT: sw a0, 260(sp)
+; RV32-NEXT: sw zero, 248(sp)
+; RV32-NEXT: sw ra, 252(sp)
+; RV32-NEXT: lui ra, 65536
+; RV32-NEXT: sw zero, 240(sp)
+; RV32-NEXT: sw t4, 244(sp)
+; RV32-NEXT: lui t4, 131072
+; RV32-NEXT: sw zero, 232(sp)
+; RV32-NEXT: sw t2, 236(sp)
+; RV32-NEXT: lui t2, 262144
+; RV32-NEXT: sw zero, 224(sp)
+; RV32-NEXT: sw t6, 228(sp)
+; RV32-NEXT: sw zero, 216(sp)
+; RV32-NEXT: sw t5, 220(sp)
+; RV32-NEXT: sw zero, 208(sp)
+; RV32-NEXT: sw t3, 212(sp)
+; RV32-NEXT: sw zero, 200(sp)
+; RV32-NEXT: sw t1, 204(sp)
+; RV32-NEXT: sw zero, 192(sp)
+; RV32-NEXT: sw t0, 196(sp)
+; RV32-NEXT: sw zero, 184(sp)
+; RV32-NEXT: sw a7, 188(sp)
+; RV32-NEXT: sw zero, 176(sp)
+; RV32-NEXT: sw a6, 180(sp)
+; RV32-NEXT: li t1, 1024
+; RV32-NEXT: slli t6, a0, 11
+; RV32-NEXT: sw zero, 168(sp)
+; RV32-NEXT: sw t6, 172(sp)
+; RV32-NEXT: sw zero, 160(sp)
+; RV32-NEXT: sw a4, 164(sp)
+; RV32-NEXT: sw zero, 152(sp)
+; RV32-NEXT: sw a3, 156(sp)
+; RV32-NEXT: lui t3, 2
+; RV32-NEXT: sw zero, 144(sp)
+; RV32-NEXT: sw a2, 148(sp)
+; RV32-NEXT: lui t5, 4
+; RV32-NEXT: sw zero, 136(sp)
+; RV32-NEXT: sw a5, 140(sp)
+; RV32-NEXT: lui a4, 8
+; RV32-NEXT: sw zero, 128(sp)
+; RV32-NEXT: sw s1, 132(sp)
+; RV32-NEXT: sw zero, 120(sp)
+; RV32-NEXT: sw a1, 124(sp)
+; RV32-NEXT: sw zero, 112(sp)
+; RV32-NEXT: sw s2, 116(sp)
+; RV32-NEXT: sw zero, 104(sp)
+; RV32-NEXT: sw s3, 108(sp)
+; RV32-NEXT: sw zero, 96(sp)
+; RV32-NEXT: sw s4, 100(sp)
+; RV32-NEXT: sw zero, 88(sp)
+; RV32-NEXT: sw s5, 92(sp)
+; RV32-NEXT: sw zero, 80(sp)
+; RV32-NEXT: sw s6, 84(sp)
+; RV32-NEXT: sw zero, 72(sp)
+; RV32-NEXT: sw s7, 76(sp)
+; RV32-NEXT: sw zero, 64(sp)
+; RV32-NEXT: sw s8, 68(sp)
+; RV32-NEXT: sw zero, 56(sp)
+; RV32-NEXT: sw s9, 60(sp)
+; RV32-NEXT: sw zero, 48(sp)
+; RV32-NEXT: sw s10, 52(sp)
+; RV32-NEXT: sw zero, 40(sp)
+; RV32-NEXT: sw s11, 44(sp)
+; RV32-NEXT: sw zero, 32(sp)
+; RV32-NEXT: sw ra, 36(sp)
+; RV32-NEXT: sw zero, 24(sp)
+; RV32-NEXT: sw t4, 28(sp)
+; RV32-NEXT: sw zero, 16(sp)
+; RV32-NEXT: sw t2, 20(sp)
+; RV32-NEXT: sw zero, 8(sp)
+; RV32-NEXT: sw s0, 12(sp)
+; RV32-NEXT: li a6, 56
+; RV32-NEXT: vsetvli a1, zero, e64, m8, ta, ma
+; RV32-NEXT: vsrl.vx v16, v8, a6
+; RV32-NEXT: li a5, 40
+; RV32-NEXT: vsrl.vx v24, v8, a5
+; RV32-NEXT: vsll.vx v0, v8, a6
+; RV32-NEXT: addi a2, s1, -256
+; RV32-NEXT: vand.vx v24, v24, a2
+; RV32-NEXT: vor.vv v16, v24, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v24, v8, a2
+; RV32-NEXT: vsll.vx v24, v24, a5
+; RV32-NEXT: vor.vv v16, v0, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: addi a3, sp, 272
+; RV32-NEXT: vlse64.v v24, (a3), zero
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v24, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: lui a3, 4080
+; RV32-NEXT: vsrl.vi v0, v8, 24
+; RV32-NEXT: vand.vx v16, v0, a3
+; RV32-NEXT: vsrl.vi v24, v8, 8
+; RV32-NEXT: vmv8r.v v0, v8
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v8, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v24, v24, v8
+; RV32-NEXT: vor.vv v24, v24, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v8, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vor.vv v16, v24, v8
+; RV32-NEXT: vand.vx v24, v0, a3
+; RV32-NEXT: vsll.vi v24, v24, 24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v8, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v0, v0, v8
+; RV32-NEXT: vsll.vi v0, v0, 8
+; RV32-NEXT: vor.vv v24, v24, v0
+; RV32-NEXT: lui a7, 61681
+; RV32-NEXT: addi a7, a7, -241
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v8, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vor.vv v8, v8, v24
+; RV32-NEXT: vsetvli t0, zero, e32, m8, ta, ma
+; RV32-NEXT: vmv.v.x v24, a7
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v24, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: lui a7, 209715
+; RV32-NEXT: addi a7, a7, 819
+; RV32-NEXT: vsetvli t0, zero, e64, m8, ta, ma
+; RV32-NEXT: vor.vv v8, v8, v16
+; RV32-NEXT: vsrl.vi v16, v8, 4
+; RV32-NEXT: vand.vv v8, v8, v24
+; RV32-NEXT: vand.vv v16, v16, v24
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v16, v8
+; RV32-NEXT: vsetvli t0, zero, e32, m8, ta, ma
+; RV32-NEXT: vmv.v.x v24, a7
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v24, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vsetvli a7, zero, e64, m8, ta, ma
+; RV32-NEXT: vsrl.vi v16, v8, 2
+; RV32-NEXT: vand.vv v8, v8, v24
+; RV32-NEXT: vand.vv v16, v16, v24
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v16, v16, v8
+; RV32-NEXT: lui a7, 349525
+; RV32-NEXT: addi a7, a7, 1365
+; RV32-NEXT: vsetvli t0, zero, e32, m8, ta, ma
+; RV32-NEXT: vmv.v.x v24, a7
+; RV32-NEXT: vsetvli a7, zero, e64, m8, ta, ma
+; RV32-NEXT: vsrl.vi v8, v16, 1
+; RV32-NEXT: vand.vv v16, v16, v24
+; RV32-NEXT: vmv8r.v v0, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 9
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v24, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: addi a7, sp, 264
+; RV32-NEXT: vlse64.v v24, (a7), zero
+; RV32-NEXT: vand.vv v8, v8, v0
+; RV32-NEXT: vadd.vv v16, v16, v16
+; RV32-NEXT: vor.vv v8, v8, v16
+; RV32-NEXT: vand.vv v16, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: addi a7, sp, 256
+; RV32-NEXT: addi t0, sp, 248
+; RV32-NEXT: addi a1, sp, 240
+; RV32-NEXT: addi a0, sp, 232
+; RV32-NEXT: vlse64.v v16, (a7), zero
+; RV32-NEXT: csrr a7, vlenb
+; RV32-NEXT: slli a7, a7, 4
+; RV32-NEXT: mv s0, a7
+; RV32-NEXT: slli a7, a7, 1
+; RV32-NEXT: add s0, s0, a7
+; RV32-NEXT: slli a7, a7, 1
+; RV32-NEXT: add s0, s0, a7
+; RV32-NEXT: slli a7, a7, 1
+; RV32-NEXT: add s0, s0, a7
+; RV32-NEXT: slli a7, a7, 1
+; RV32-NEXT: add a7, a7, s0
+; RV32-NEXT: add a7, sp, a7
+; RV32-NEXT: addi a7, a7, 288
+; RV32-NEXT: vs8r.v v16, (a7) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vlse64.v v24, (t0), zero
+; RV32-NEXT: vlse64.v v0, (a1), zero
+; RV32-NEXT: vlse64.v v16, (a0), zero
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 224
+; RV32-NEXT: addi a1, sp, 216
+; RV32-NEXT: addi a7, sp, 208
+; RV32-NEXT: addi t0, sp, 200
+; RV32-NEXT: vlse64.v v16, (a0), zero
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv s0, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add s0, s0, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add s0, s0, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, s0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vlse64.v v24, (a1), zero
+; RV32-NEXT: vlse64.v v0, (a7), zero
+; RV32-NEXT: vlse64.v v16, (t0), zero
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 192
+; RV32-NEXT: addi a1, sp, 184
+; RV32-NEXT: addi a7, sp, 176
+; RV32-NEXT: addi t0, sp, 168
+; RV32-NEXT: vlse64.v v16, (a0), zero
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv s0, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add s0, s0, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add s0, s0, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, s0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vlse64.v v24, (a1), zero
+; RV32-NEXT: vlse64.v v0, (a7), zero
+; RV32-NEXT: vlse64.v v16, (t0), zero
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 160
+; RV32-NEXT: addi a1, sp, 152
+; RV32-NEXT: addi a7, sp, 144
+; RV32-NEXT: addi t0, sp, 136
+; RV32-NEXT: vlse64.v v16, (a0), zero
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv s0, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add s0, s0, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, s0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vlse64.v v24, (a1), zero
+; RV32-NEXT: vlse64.v v0, (a7), zero
+; RV32-NEXT: vlse64.v v16, (t0), zero
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 7
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 128
+; RV32-NEXT: addi a1, sp, 120
+; RV32-NEXT: addi a7, sp, 112
+; RV32-NEXT: addi t0, sp, 104
+; RV32-NEXT: vlse64.v v16, (a0), zero
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv s0, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add s0, s0, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add s0, s0, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, s0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vlse64.v v24, (a1), zero
+; RV32-NEXT: vlse64.v v0, (a7), zero
+; RV32-NEXT: vlse64.v v16, (t0), zero
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 96
+; RV32-NEXT: addi a1, sp, 88
+; RV32-NEXT: addi a7, sp, 80
+; RV32-NEXT: addi t0, sp, 72
+; RV32-NEXT: vlse64.v v16, (a0), zero
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv s0, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add s0, s0, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, s0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vlse64.v v24, (a1), zero
+; RV32-NEXT: vlse64.v v0, (a7), zero
+; RV32-NEXT: vlse64.v v16, (t0), zero
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 64
+; RV32-NEXT: addi a1, sp, 56
+; RV32-NEXT: addi a7, sp, 48
+; RV32-NEXT: addi t0, sp, 40
+; RV32-NEXT: vlse64.v v16, (a0), zero
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv s0, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add s0, s0, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, s0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vlse64.v v24, (a1), zero
+; RV32-NEXT: vlse64.v v0, (a7), zero
+; RV32-NEXT: vlse64.v v16, (t0), zero
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 32
+; RV32-NEXT: addi a1, sp, 24
+; RV32-NEXT: addi a7, sp, 16
+; RV32-NEXT: addi t0, sp, 8
+; RV32-NEXT: vlse64.v v16, (a0), zero
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv s0, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, s0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vlse64.v v24, (a1), zero
+; RV32-NEXT: vlse64.v v0, (a7), zero
+; RV32-NEXT: vlse64.v v16, (t0), zero
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 8
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vi v16, v8, 2
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vi v16, v8, 1
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vi v16, v8, 4
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vi v16, v8, 8
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: li a0, 16
+; RV32-NEXT: vand.vx v16, v8, a0
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: li a0, 32
+; RV32-NEXT: vand.vx v16, v8, a0
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: li a0, 64
+; RV32-NEXT: vand.vx v16, v8, a0
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: li a0, 128
+; RV32-NEXT: vand.vx v16, v8, a0
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: li a0, 256
+; RV32-NEXT: vand.vx v16, v8, a0
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: li a0, 512
+; RV32-NEXT: vand.vx v16, v8, a0
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, t1
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, t6
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: lui a0, 1
+; RV32-NEXT: vand.vx v16, v8, a0
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, t3
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, t5
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 7
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, a4
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, s1
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: lui a0, 32
+; RV32-NEXT: vand.vx v16, v8, a0
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, s2
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, s3
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, s4
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, s5
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, s6
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, s7
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, s8
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, s9
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, s10
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, s11
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, ra
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, t4
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, t2
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: addi a0, sp, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v0, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 7
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 7
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 8
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 8
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v8, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v8, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vi v8, v8, 0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 7
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: addi a0, sp, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: vxor.vv v8, v8, v24
+; RV32-NEXT: vxor.vv v8, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 7
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 8
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: vsrl.vx v16, v8, a5
+; RV32-NEXT: vand.vx v16, v16, a2
+; RV32-NEXT: vsrl.vx v24, v8, a6
+; RV32-NEXT: vor.vv v16, v16, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vsrl.vi v24, v8, 24
+; RV32-NEXT: vand.vx v24, v24, a3
+; RV32-NEXT: vsrl.vi v0, v8, 8
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v0, v0, v16
+; RV32-NEXT: vor.vv v24, v0, v24
+; RV32-NEXT: vand.vv v0, v8, v16
+; RV32-NEXT: vsll.vi v0, v0, 8
+; RV32-NEXT: vand.vx v16, v8, a3
+; RV32-NEXT: vsll.vi v16, v16, 24
+; RV32-NEXT: vor.vv v16, v16, v0
+; RV32-NEXT: vsll.vx v0, v8, a6
+; RV32-NEXT: vand.vx v8, v8, a2
+; RV32-NEXT: vsll.vx v8, v8, a5
+; RV32-NEXT: vor.vv v8, v0, v8
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v0, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vor.vv v24, v24, v0
+; RV32-NEXT: vor.vv v8, v8, v16
+; RV32-NEXT: vor.vv v8, v8, v24
+; RV32-NEXT: vsrl.vi v16, v8, 4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v24
+; RV32-NEXT: vand.vv v16, v16, v24
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v16, v8
+; RV32-NEXT: vsrl.vi v16, v8, 2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v24
+; RV32-NEXT: vand.vv v16, v16, v24
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v8, v16, v8
+; RV32-NEXT: vsrl.vi v16, v8, 1
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 9
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v24
+; RV32-NEXT: vand.vv v16, v16, v24
+; RV32-NEXT: vadd.vv v8, v8, v8
+; RV32-NEXT: vor.vv v8, v16, v8
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add sp, sp, a0
+; RV32-NEXT: lw ra, 348(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s0, 344(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s1, 340(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s2, 336(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s3, 332(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s4, 328(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s5, 324(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s6, 320(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s7, 316(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s8, 312(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s9, 308(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s10, 304(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s11, 300(sp) # 4-byte Folded Reload
+; RV32-NEXT: addi sp, sp, 352
+; RV32-NEXT: ret
+;
+; RV64-LABEL: clmulr_nxv8i64:
+; RV64: # %bb.0:
+; RV64-NEXT: addi sp, sp, -240
+; RV64-NEXT: sd ra, 232(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s0, 224(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s1, 216(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s2, 208(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s3, 200(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s4, 192(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s5, 184(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s6, 176(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s7, 168(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s8, 160(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s9, 152(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s10, 144(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s11, 136(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: sub sp, sp, a0
+; RV64-NEXT: li a1, 56
+; RV64-NEXT: li a2, 40
+; RV64-NEXT: lui a3, 16
+; RV64-NEXT: vsetvli a0, zero, e64, m8, ta, ma
+; RV64-NEXT: vsrl.vi v24, v8, 24
+; RV64-NEXT: vsrl.vx v16, v8, a1
+; RV64-NEXT: li a5, 56
+; RV64-NEXT: vsrl.vx v0, v8, a2
+; RV64-NEXT: li s5, 40
+; RV64-NEXT: addi s4, a3, -256
+; RV64-NEXT: vand.vx v0, v0, s4
+; RV64-NEXT: vor.vv v16, v0, v16
+; RV64-NEXT: vsrl.vi v0, v8, 8
+; RV64-NEXT: li a4, 255
+; RV64-NEXT: lui a1, 61681
+; RV64-NEXT: lui a2, 209715
+; RV64-NEXT: lui a3, 349525
+; RV64-NEXT: li a0, 1
+; RV64-NEXT: lui a6, 4080
+; RV64-NEXT: vand.vx v24, v24, a6
+; RV64-NEXT: slli a4, a4, 24
+; RV64-NEXT: vand.vx v0, v0, a4
+; RV64-NEXT: vor.vv v24, v0, v24
+; RV64-NEXT: vand.vx v0, v8, a6
+; RV64-NEXT: vsll.vi v0, v0, 24
+; RV64-NEXT: vor.vv v16, v24, v16
+; RV64-NEXT: vand.vx v24, v8, a4
+; RV64-NEXT: vsll.vi v24, v24, 8
+; RV64-NEXT: vor.vv v24, v0, v24
+; RV64-NEXT: vsll.vx v0, v8, a5
+; RV64-NEXT: addi a7, a1, -241
+; RV64-NEXT: addi a6, a2, 819
+; RV64-NEXT: addi a5, a3, 1365
+; RV64-NEXT: slli a1, a0, 11
+; RV64-NEXT: sd a1, 112(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a1, a0, 31
+; RV64-NEXT: sd a1, 104(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a1, a0, 32
+; RV64-NEXT: sd a1, 96(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a1, a0, 33
+; RV64-NEXT: sd a1, 88(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a1, a0, 34
+; RV64-NEXT: sd a1, 80(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a1, a0, 35
+; RV64-NEXT: sd a1, 72(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a1, a0, 36
+; RV64-NEXT: sd a1, 64(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a1, a0, 37
+; RV64-NEXT: sd a1, 56(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a1, a0, 38
+; RV64-NEXT: sd a1, 48(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a1, a0, 39
+; RV64-NEXT: sd a1, 40(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a1, a0, 40
+; RV64-NEXT: sd a1, 32(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a1, a0, 41
+; RV64-NEXT: sd a1, 24(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli s6, a0, 42
+; RV64-NEXT: slli s7, a0, 43
+; RV64-NEXT: slli s8, a0, 44
+; RV64-NEXT: slli s9, a0, 45
+; RV64-NEXT: slli s10, a0, 46
+; RV64-NEXT: slli a1, a7, 32
+; RV64-NEXT: add a7, a7, a1
+; RV64-NEXT: slli a1, a6, 32
+; RV64-NEXT: add a6, a6, a1
+; RV64-NEXT: slli a1, a5, 32
+; RV64-NEXT: add a5, a5, a1
+; RV64-NEXT: slli s11, a0, 47
+; RV64-NEXT: slli ra, a0, 48
+; RV64-NEXT: slli s3, a0, 49
+; RV64-NEXT: slli s2, a0, 50
+; RV64-NEXT: slli s1, a0, 51
+; RV64-NEXT: slli s0, a0, 52
+; RV64-NEXT: slli t6, a0, 53
+; RV64-NEXT: slli t5, a0, 54
+; RV64-NEXT: slli t4, a0, 55
+; RV64-NEXT: slli t3, a0, 56
+; RV64-NEXT: slli t2, a0, 57
+; RV64-NEXT: slli t1, a0, 58
+; RV64-NEXT: slli t0, a0, 59
+; RV64-NEXT: slli a3, a0, 60
+; RV64-NEXT: slli a2, a0, 61
+; RV64-NEXT: slli a1, a0, 62
+; RV64-NEXT: li a0, -1
+; RV64-NEXT: slli a0, a0, 63
+; RV64-NEXT: vand.vx v8, v8, s4
+; RV64-NEXT: vsll.vx v8, v8, s5
+; RV64-NEXT: vor.vv v8, v0, v8
+; RV64-NEXT: vor.vv v8, v8, v24
+; RV64-NEXT: vor.vv v8, v8, v16
+; RV64-NEXT: vsrl.vi v16, v8, 4
+; RV64-NEXT: vand.vx v8, v8, a7
+; RV64-NEXT: vand.vx v16, v16, a7
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v16, v8
+; RV64-NEXT: vsrl.vi v16, v8, 2
+; RV64-NEXT: vand.vx v8, v8, a6
+; RV64-NEXT: vand.vx v16, v16, a6
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v16, v8
+; RV64-NEXT: vsrl.vi v16, v8, 1
+; RV64-NEXT: vand.vx v8, v8, a5
+; RV64-NEXT: vand.vx v16, v16, a5
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v16, v8
+; RV64-NEXT: vand.vi v16, v8, 2
+; RV64-NEXT: vand.vi v24, v8, 1
+; RV64-NEXT: vand.vi v0, v8, 4
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: sd a1, 8(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 2
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vmul.vv v24, v8, v24
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vand.vi v16, v8, 8
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 5
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: li s5, 16
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 2
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: li s5, 32
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 4
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 2
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: li s5, 64
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: li s5, 128
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 6
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: li s5, 256
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 2
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: li s5, 512
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 4
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 2
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: li s5, 1024
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 2
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 2
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: ld s5, 112(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 5
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 2
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: lui s5, 1
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: lui s5, 2
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 4
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: lui s5, 4
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 4
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: lui s5, 8
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 7
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: lui s5, 16
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 2
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: lui s5, 32
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 4
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 2
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: lui s5, 64
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 2
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 2
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: lui s5, 128
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 5
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 2
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: lui s5, 256
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 2
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 2
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: lui s5, 512
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 4
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 2
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 2
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: lui s5, 1024
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 2
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: lui s5, 2048
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 6
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 2
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: lui s5, 4096
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: lui s5, 8192
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 2
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: lui s5, 16384
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 4
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: lui s5, 32768
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 5
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: lui s5, 65536
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 4
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: lui s5, 131072
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 4
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 4
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: lui s5, 262144
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 5
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: ld s5, 104(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 8
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: ld s5, 96(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: ld s5, 88(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 4
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: ld s5, 80(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 2
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: ld s5, 72(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 5
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: ld s5, 64(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 2
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: ld s5, 56(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 4
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 2
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: ld s5, 48(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: ld s5, 40(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 6
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: ld s5, 32(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 2
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: ld s5, 24(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 4
+; RV64-NEXT: mv a1, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: slli s5, s5, 2
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: ld a1, 8(sp) # 8-byte Folded Reload
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 128
+; RV64-NEXT: vs8r.v v16, (s5) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, s6
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 3
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 2
+; RV64-NEXT: add s6, s6, s5
+; RV64-NEXT: slli s5, s5, 2
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 128
+; RV64-NEXT: vs8r.v v16, (s5) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, s7
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 5
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 2
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 128
+; RV64-NEXT: vs8r.v v16, (s5) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, s8
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 3
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s6, s6, s5
+; RV64-NEXT: slli s5, s5, 3
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 128
+; RV64-NEXT: vs8r.v v16, (s5) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, s9
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 4
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 3
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 128
+; RV64-NEXT: vs8r.v v16, (s5) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, s10
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 3
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 4
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 128
+; RV64-NEXT: vs8r.v v16, (s5) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, s11
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 3
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s6, s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s6, s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 128
+; RV64-NEXT: vs8r.v v16, (s5) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, ra
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 3
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 2
+; RV64-NEXT: add s6, s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 128
+; RV64-NEXT: vs8r.v v16, (s5) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, s3
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr s3, vlenb
+; RV64-NEXT: slli s3, s3, 3
+; RV64-NEXT: mv s5, s3
+; RV64-NEXT: slli s3, s3, 3
+; RV64-NEXT: add s3, s3, s5
+; RV64-NEXT: add s3, sp, s3
+; RV64-NEXT: addi s3, s3, 128
+; RV64-NEXT: vs8r.v v16, (s3) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, s2
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr s2, vlenb
+; RV64-NEXT: slli s2, s2, 4
+; RV64-NEXT: mv s3, s2
+; RV64-NEXT: slli s2, s2, 1
+; RV64-NEXT: add s2, s2, s3
+; RV64-NEXT: add s2, sp, s2
+; RV64-NEXT: addi s2, s2, 128
+; RV64-NEXT: vs8r.v v16, (s2) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, s1
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr s1, vlenb
+; RV64-NEXT: slli s1, s1, 7
+; RV64-NEXT: add s1, sp, s1
+; RV64-NEXT: addi s1, s1, 128
+; RV64-NEXT: vs8r.v v16, (s1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, s0
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr s0, vlenb
+; RV64-NEXT: slli s0, s0, 4
+; RV64-NEXT: mv s1, s0
+; RV64-NEXT: slli s0, s0, 1
+; RV64-NEXT: add s1, s1, s0
+; RV64-NEXT: slli s0, s0, 1
+; RV64-NEXT: add s0, s0, s1
+; RV64-NEXT: add s0, sp, s0
+; RV64-NEXT: addi s0, s0, 128
+; RV64-NEXT: vs8r.v v16, (s0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, t6
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 5
+; RV64-NEXT: mv s0, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s0
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 128
+; RV64-NEXT: vs8r.v v16, (t6) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, t5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr t5, vlenb
+; RV64-NEXT: slli t5, t5, 6
+; RV64-NEXT: add t5, sp, t5
+; RV64-NEXT: addi t5, t5, 128
+; RV64-NEXT: vs8r.v v16, (t5) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, t4
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr t4, vlenb
+; RV64-NEXT: slli t4, t4, 3
+; RV64-NEXT: mv t5, t4
+; RV64-NEXT: slli t4, t4, 2
+; RV64-NEXT: add t4, t4, t5
+; RV64-NEXT: add t4, sp, t4
+; RV64-NEXT: addi t4, t4, 128
+; RV64-NEXT: vs8r.v v16, (t4) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, t3
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr t3, vlenb
+; RV64-NEXT: slli t3, t3, 3
+; RV64-NEXT: mv t4, t3
+; RV64-NEXT: slli t3, t3, 1
+; RV64-NEXT: add t3, t3, t4
+; RV64-NEXT: add t3, sp, t3
+; RV64-NEXT: addi t3, t3, 128
+; RV64-NEXT: vs8r.v v16, (t3) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, t2
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr t2, vlenb
+; RV64-NEXT: slli t2, t2, 3
+; RV64-NEXT: add t2, sp, t2
+; RV64-NEXT: addi t2, t2, 128
+; RV64-NEXT: vs8r.v v16, (t2) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, t1
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr t1, vlenb
+; RV64-NEXT: slli t1, t1, 3
+; RV64-NEXT: mv t2, t1
+; RV64-NEXT: slli t1, t1, 1
+; RV64-NEXT: add t2, t2, t1
+; RV64-NEXT: slli t1, t1, 2
+; RV64-NEXT: add t1, t1, t2
+; RV64-NEXT: add t1, sp, t1
+; RV64-NEXT: addi t1, t1, 128
+; RV64-NEXT: vs8r.v v16, (t1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, t0
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr t0, vlenb
+; RV64-NEXT: slli t0, t0, 4
+; RV64-NEXT: mv t1, t0
+; RV64-NEXT: slli t0, t0, 2
+; RV64-NEXT: add t0, t0, t1
+; RV64-NEXT: add t0, sp, t0
+; RV64-NEXT: addi t0, t0, 128
+; RV64-NEXT: vs8r.v v16, (t0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, a3
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a3, vlenb
+; RV64-NEXT: slli a3, a3, 3
+; RV64-NEXT: mv t0, a3
+; RV64-NEXT: slli a3, a3, 1
+; RV64-NEXT: add t0, t0, a3
+; RV64-NEXT: slli a3, a3, 1
+; RV64-NEXT: add a3, a3, t0
+; RV64-NEXT: add a3, sp, a3
+; RV64-NEXT: addi a3, a3, 128
+; RV64-NEXT: vs8r.v v16, (a3) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, a2
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 5
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vs8r.v v16, (a2) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, a1
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 4
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, a0
+; RV64-NEXT: vmul.vv v8, v8, v16
+; RV64-NEXT: addi a0, sp, 128
+; RV64-NEXT: vs8r.v v8, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl8r.v v8, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v24, v8
+; RV64-NEXT: vxor.vv v8, v8, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 6
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v16, v16, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v16, v16, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v16, v16, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v16, v16, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v16, v16, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v16, v16, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 7
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v16, v16, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v16, v16, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v16, v16, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v16, v16, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v16, v16, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v16, v16, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v16, v16, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v16, v16, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 6
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v16, v16, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v16, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl8r.v v0, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: li a0, 56
+; RV64-NEXT: vsll.vx v8, v8, a0
+; RV64-NEXT: vand.vx v16, v16, s4
+; RV64-NEXT: li a1, 40
+; RV64-NEXT: vsll.vx v16, v16, a1
+; RV64-NEXT: vor.vv v8, v8, v16
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vs8r.v v8, (a2) # vscale x 64-byte Folded Spill
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 4
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v8, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v24, v8
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 5
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v16, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v16
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 4
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v16, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v16
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 4
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 4
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v16, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v16
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 5
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v16, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v16
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 8
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v16, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v16
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v16, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v16
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 4
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v16, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v16
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v16, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v16
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 5
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v16, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v16
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v16, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v16
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 4
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v16, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v16
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v16, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v16
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 6
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v16, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v16, v8, v16
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v8, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v16, v8
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 4
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v24, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v24, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 5
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v24, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v24, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 4
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v24, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 4
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v24, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v24, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v24, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v8, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v0, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 4
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v0, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vsrl.vi v0, v16, 8
+; RV64-NEXT: vand.vx v0, v0, a4
+; RV64-NEXT: vsrl.vi v8, v8, 24
+; RV64-NEXT: lui a2, 4080
+; RV64-NEXT: vand.vx v8, v8, a2
+; RV64-NEXT: vor.vv v8, v0, v8
+; RV64-NEXT: csrr a3, vlenb
+; RV64-NEXT: slli a3, a3, 5
+; RV64-NEXT: mv t0, a3
+; RV64-NEXT: slli a3, a3, 1
+; RV64-NEXT: add t0, t0, a3
+; RV64-NEXT: slli a3, a3, 1
+; RV64-NEXT: add t0, t0, a3
+; RV64-NEXT: slli a3, a3, 1
+; RV64-NEXT: add a3, a3, t0
+; RV64-NEXT: add a3, sp, a3
+; RV64-NEXT: addi a3, a3, 128
+; RV64-NEXT: vs8r.v v8, (a3) # vscale x 64-byte Folded Spill
+; RV64-NEXT: csrr a3, vlenb
+; RV64-NEXT: slli a3, a3, 7
+; RV64-NEXT: add a3, sp, a3
+; RV64-NEXT: addi a3, a3, 128
+; RV64-NEXT: vl8r.v v8, (a3) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v24, v8
+; RV64-NEXT: csrr a3, vlenb
+; RV64-NEXT: slli a3, a3, 4
+; RV64-NEXT: mv t0, a3
+; RV64-NEXT: slli a3, a3, 1
+; RV64-NEXT: add t0, t0, a3
+; RV64-NEXT: slli a3, a3, 1
+; RV64-NEXT: add a3, a3, t0
+; RV64-NEXT: add a3, sp, a3
+; RV64-NEXT: addi a3, a3, 128
+; RV64-NEXT: vl8r.v v24, (a3) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a3, vlenb
+; RV64-NEXT: slli a3, a3, 5
+; RV64-NEXT: mv t0, a3
+; RV64-NEXT: slli a3, a3, 1
+; RV64-NEXT: add a3, a3, t0
+; RV64-NEXT: add a3, sp, a3
+; RV64-NEXT: addi a3, a3, 128
+; RV64-NEXT: vl8r.v v24, (a3) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a3, vlenb
+; RV64-NEXT: slli a3, a3, 6
+; RV64-NEXT: add a3, sp, a3
+; RV64-NEXT: addi a3, a3, 128
+; RV64-NEXT: vl8r.v v24, (a3) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a3, vlenb
+; RV64-NEXT: slli a3, a3, 3
+; RV64-NEXT: mv t0, a3
+; RV64-NEXT: slli a3, a3, 2
+; RV64-NEXT: add a3, a3, t0
+; RV64-NEXT: add a3, sp, a3
+; RV64-NEXT: addi a3, a3, 128
+; RV64-NEXT: vl8r.v v24, (a3) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a3, vlenb
+; RV64-NEXT: slli a3, a3, 3
+; RV64-NEXT: mv t0, a3
+; RV64-NEXT: slli a3, a3, 1
+; RV64-NEXT: add a3, a3, t0
+; RV64-NEXT: add a3, sp, a3
+; RV64-NEXT: addi a3, a3, 128
+; RV64-NEXT: vl8r.v v24, (a3) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v8, v24
+; RV64-NEXT: csrr a3, vlenb
+; RV64-NEXT: slli a3, a3, 3
+; RV64-NEXT: add a3, sp, a3
+; RV64-NEXT: addi a3, a3, 128
+; RV64-NEXT: vl8r.v v0, (a3) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v16, v16, a2
+; RV64-NEXT: vsll.vi v16, v16, 24
+; RV64-NEXT: vand.vx v0, v8, a4
+; RV64-NEXT: vsll.vi v0, v0, 8
+; RV64-NEXT: vor.vv v16, v16, v0
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v0, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v0, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vor.vv v16, v0, v16
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 4
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v0, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v0, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 5
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v0, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 4
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v0, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: addi a2, sp, 128
+; RV64-NEXT: vl8r.v v0, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vsrl.vx v8, v8, a1
+; RV64-NEXT: vand.vx v8, v8, s4
+; RV64-NEXT: vsrl.vx v24, v24, a0
+; RV64-NEXT: vor.vv v8, v8, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vor.vv v8, v24, v8
+; RV64-NEXT: vor.vv v8, v16, v8
+; RV64-NEXT: vsrl.vi v16, v8, 4
+; RV64-NEXT: vand.vx v8, v8, a7
+; RV64-NEXT: vand.vx v16, v16, a7
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v16, v8
+; RV64-NEXT: vsrl.vi v16, v8, 2
+; RV64-NEXT: vand.vx v8, v8, a6
+; RV64-NEXT: vand.vx v16, v16, a6
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v16, v8
+; RV64-NEXT: vsrl.vi v16, v8, 1
+; RV64-NEXT: vand.vx v8, v8, a5
+; RV64-NEXT: vand.vx v16, v16, a5
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v16, v8
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add sp, sp, a0
+; RV64-NEXT: ld ra, 232(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s0, 224(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s1, 216(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s2, 208(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s3, 200(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s4, 192(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s5, 184(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s6, 176(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s7, 168(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s8, 160(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s9, 152(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s10, 144(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s11, 136(sp) # 8-byte Folded Reload
+; RV64-NEXT: addi sp, sp, 240
+; RV64-NEXT: ret
+ %a = call <vscale x 8 x i64> @llvm.clmulr.nxv8i64(<vscale x 8 x i64> %x, <vscale x 8 x i64> %y)
+ ret <vscale x 8 x i64> %a
+}
+
+define <vscale x 1 x i32> @clmulh_nxv1i32(<vscale x 1 x i32> %x, <vscale x 1 x i32> %y) nounwind {
+; CHECK-LABEL: clmulh_nxv1i32:
+; CHECK: # %bb.0:
+; CHECK-NEXT: addi sp, sp, -16
+; CHECK-NEXT: csrr a0, vlenb
+; CHECK-NEXT: sub sp, sp, a0
+; CHECK-NEXT: vsetvli a0, zero, e32, mf2, ta, ma
+; CHECK-NEXT: vsrl.vi v9, v8, 8
+; CHECK-NEXT: lui a4, 16
+; CHECK-NEXT: vsrl.vi v10, v8, 24
+; CHECK-NEXT: vsll.vi v11, v8, 24
+; CHECK-NEXT: lui a0, 61681
+; CHECK-NEXT: lui a1, 209715
+; CHECK-NEXT: lui a5, 349525
+; CHECK-NEXT: li a6, 16
+; CHECK-NEXT: addi a3, a4, -256
+; CHECK-NEXT: addi a2, a0, -241
+; CHECK-NEXT: addi a1, a1, 819
+; CHECK-NEXT: addi a0, a5, 1365
+; CHECK-NEXT: vand.vx v9, v9, a3
+; CHECK-NEXT: vand.vx v8, v8, a3
+; CHECK-NEXT: vor.vv v9, v9, v10
+; CHECK-NEXT: vsll.vi v8, v8, 8
+; CHECK-NEXT: vor.vv v8, v11, v8
+; CHECK-NEXT: vor.vv v8, v8, v9
+; CHECK-NEXT: vsrl.vi v9, v8, 4
+; CHECK-NEXT: vand.vx v8, v8, a2
+; CHECK-NEXT: vand.vx v9, v9, a2
+; CHECK-NEXT: vsll.vi v8, v8, 4
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v9, v8, 2
+; CHECK-NEXT: vand.vx v8, v8, a1
+; CHECK-NEXT: vand.vx v9, v9, a1
+; CHECK-NEXT: vsll.vi v8, v8, 2
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v9, v8, 1
+; CHECK-NEXT: vand.vx v8, v8, a0
+; CHECK-NEXT: vand.vx v9, v9, a0
+; CHECK-NEXT: vadd.vv v8, v8, v8
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vand.vx v9, v8, a6
+; CHECK-NEXT: li a5, 32
+; CHECK-NEXT: vand.vx v10, v8, a5
+; CHECK-NEXT: li a5, 64
+; CHECK-NEXT: vand.vx v11, v8, a5
+; CHECK-NEXT: li a5, 128
+; CHECK-NEXT: vand.vx v12, v8, a5
+; CHECK-NEXT: li a5, 256
+; CHECK-NEXT: vand.vx v13, v8, a5
+; CHECK-NEXT: li a5, 512
+; CHECK-NEXT: vand.vx v14, v8, a5
+; CHECK-NEXT: li a5, 1024
+; CHECK-NEXT: vand.vx v15, v8, a5
+; CHECK-NEXT: li a5, 1
+; CHECK-NEXT: slli a5, a5, 11
+; CHECK-NEXT: vand.vx v16, v8, a5
+; CHECK-NEXT: lui a5, 1
+; CHECK-NEXT: vand.vx v17, v8, a5
+; CHECK-NEXT: lui a5, 2
+; CHECK-NEXT: vand.vx v18, v8, a5
+; CHECK-NEXT: lui a5, 4
+; CHECK-NEXT: vand.vx v19, v8, a5
+; CHECK-NEXT: lui a5, 8
+; CHECK-NEXT: vand.vx v20, v8, a5
+; CHECK-NEXT: lui a5, 32
+; CHECK-NEXT: vand.vx v21, v8, a4
+; CHECK-NEXT: lui a4, 64
+; CHECK-NEXT: vand.vx v22, v8, a5
+; CHECK-NEXT: lui a5, 128
+; CHECK-NEXT: vand.vx v23, v8, a4
+; CHECK-NEXT: lui a4, 256
+; CHECK-NEXT: vand.vx v24, v8, a5
+; CHECK-NEXT: lui a5, 512
+; CHECK-NEXT: vand.vx v25, v8, a4
+; CHECK-NEXT: lui a4, 1024
+; CHECK-NEXT: vand.vx v26, v8, a5
+; CHECK-NEXT: lui a5, 2048
+; CHECK-NEXT: vand.vx v27, v8, a4
+; CHECK-NEXT: lui a4, 4096
+; CHECK-NEXT: vand.vx v28, v8, a5
+; CHECK-NEXT: lui a5, 8192
+; CHECK-NEXT: vand.vx v29, v8, a4
+; CHECK-NEXT: lui a4, 16384
+; CHECK-NEXT: vand.vx v30, v8, a5
+; CHECK-NEXT: lui a5, 32768
+; CHECK-NEXT: vand.vx v31, v8, a4
+; CHECK-NEXT: lui a4, 65536
+; CHECK-NEXT: vand.vx v7, v8, a5
+; CHECK-NEXT: lui a5, 131072
+; CHECK-NEXT: vand.vx v6, v8, a4
+; CHECK-NEXT: lui a4, 262144
+; CHECK-NEXT: vand.vx v5, v8, a5
+; CHECK-NEXT: lui a5, 524288
+; CHECK-NEXT: vand.vi v4, v8, 2
+; CHECK-NEXT: vand.vi v3, v8, 1
+; CHECK-NEXT: vand.vi v2, v8, 4
+; CHECK-NEXT: vand.vi v1, v8, 8
+; CHECK-NEXT: vand.vx v0, v8, a4
+; CHECK-NEXT: vmul.vv v4, v8, v4
+; CHECK-NEXT: vmul.vv v3, v8, v3
+; CHECK-NEXT: vmul.vv v2, v8, v2
+; CHECK-NEXT: vmul.vv v1, v8, v1
+; CHECK-NEXT: vmul.vv v9, v8, v9
+; CHECK-NEXT: vmul.vv v10, v8, v10
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vmul.vv v12, v8, v12
+; CHECK-NEXT: vmul.vv v13, v8, v13
+; CHECK-NEXT: vmul.vv v14, v8, v14
+; CHECK-NEXT: vmul.vv v15, v8, v15
+; CHECK-NEXT: vmul.vv v16, v8, v16
+; CHECK-NEXT: vmul.vv v17, v8, v17
+; CHECK-NEXT: vmul.vv v18, v8, v18
+; CHECK-NEXT: vmul.vv v19, v8, v19
+; CHECK-NEXT: vmul.vv v20, v8, v20
+; CHECK-NEXT: vmul.vv v21, v8, v21
+; CHECK-NEXT: vmul.vv v22, v8, v22
+; CHECK-NEXT: vmul.vv v23, v8, v23
+; CHECK-NEXT: vmul.vv v24, v8, v24
+; CHECK-NEXT: vmul.vv v25, v8, v25
+; CHECK-NEXT: vmul.vv v26, v8, v26
+; CHECK-NEXT: vmul.vv v27, v8, v27
+; CHECK-NEXT: vmul.vv v28, v8, v28
+; CHECK-NEXT: vmul.vv v29, v8, v29
+; CHECK-NEXT: vmul.vv v30, v8, v30
+; CHECK-NEXT: vmul.vv v31, v8, v31
+; CHECK-NEXT: vmul.vv v7, v8, v7
+; CHECK-NEXT: vmul.vv v6, v8, v6
+; CHECK-NEXT: vmul.vv v5, v8, v5
+; CHECK-NEXT: vmul.vv v0, v8, v0
+; CHECK-NEXT: addi a4, sp, 16
+; CHECK-NEXT: vs1r.v v0, (a4) # vscale x 8-byte Folded Spill
+; CHECK-NEXT: vand.vx v0, v8, a5
+; CHECK-NEXT: vmul.vv v8, v8, v0
+; CHECK-NEXT: vxor.vv v4, v3, v4
+; CHECK-NEXT: vxor.vv v4, v4, v2
+; CHECK-NEXT: vxor.vv v4, v4, v1
+; CHECK-NEXT: vxor.vv v9, v4, v9
+; CHECK-NEXT: vxor.vv v9, v9, v10
+; CHECK-NEXT: vxor.vv v9, v9, v11
+; CHECK-NEXT: vxor.vv v9, v9, v12
+; CHECK-NEXT: vxor.vv v10, v9, v13
+; CHECK-NEXT: vxor.vv v10, v10, v14
+; CHECK-NEXT: vxor.vv v10, v10, v15
+; CHECK-NEXT: vxor.vv v10, v10, v16
+; CHECK-NEXT: vxor.vv v10, v10, v17
+; CHECK-NEXT: vxor.vv v10, v10, v18
+; CHECK-NEXT: vxor.vv v10, v10, v19
+; CHECK-NEXT: vxor.vv v10, v10, v20
+; CHECK-NEXT: vxor.vv v10, v10, v21
+; CHECK-NEXT: vxor.vv v10, v10, v22
+; CHECK-NEXT: vxor.vv v10, v10, v23
+; CHECK-NEXT: vxor.vv v10, v10, v24
+; CHECK-NEXT: vxor.vv v10, v10, v25
+; CHECK-NEXT: vxor.vv v10, v10, v26
+; CHECK-NEXT: vxor.vv v10, v10, v27
+; CHECK-NEXT: vxor.vv v10, v10, v28
+; CHECK-NEXT: vsll.vi v9, v9, 24
+; CHECK-NEXT: vxor.vv v11, v10, v29
+; CHECK-NEXT: vxor.vv v11, v11, v30
+; CHECK-NEXT: vand.vx v12, v10, a3
+; CHECK-NEXT: vsll.vi v12, v12, 8
+; CHECK-NEXT: vor.vv v9, v9, v12
+; CHECK-NEXT: vxor.vv v11, v11, v31
+; CHECK-NEXT: vxor.vv v11, v11, v7
+; CHECK-NEXT: vxor.vv v11, v11, v6
+; CHECK-NEXT: vxor.vv v11, v11, v5
+; CHECK-NEXT: vsrl.vi v10, v10, 8
+; CHECK-NEXT: vand.vx v10, v10, a3
+; CHECK-NEXT: addi a3, sp, 16
+; CHECK-NEXT: vl1r.v v12, (a3) # vscale x 8-byte Folded Reload
+; CHECK-NEXT: vxor.vv v11, v11, v12
+; CHECK-NEXT: vxor.vv v8, v11, v8
+; CHECK-NEXT: vsrl.vi v8, v8, 24
+; CHECK-NEXT: vor.vv v8, v10, v8
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v9, v8, 4
+; CHECK-NEXT: vand.vx v8, v8, a2
+; CHECK-NEXT: vand.vx v9, v9, a2
+; CHECK-NEXT: vsll.vi v8, v8, 4
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v9, v8, 2
+; CHECK-NEXT: vand.vx v8, v8, a1
+; CHECK-NEXT: vand.vx v9, v9, a1
+; CHECK-NEXT: vsll.vi v8, v8, 2
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v9, v8, 1
+; CHECK-NEXT: vand.vx v8, v8, a0
+; CHECK-NEXT: vand.vx v9, v9, a0
+; CHECK-NEXT: vadd.vv v8, v8, v8
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v8, v8, 1
+; CHECK-NEXT: csrr a0, vlenb
+; CHECK-NEXT: add sp, sp, a0
+; CHECK-NEXT: addi sp, sp, 16
+; CHECK-NEXT: ret
+ %a = call <vscale x 1 x i32> @llvm.clmulh.nxv1i32(<vscale x 1 x i32> %x, <vscale x 1 x i32> %y)
+ ret <vscale x 1 x i32> %a
+}
+
+define <vscale x 2 x i32> @clmulh_nxv2i32(<vscale x 2 x i32> %x, <vscale x 2 x i32> %y) nounwind {
+; CHECK-LABEL: clmulh_nxv2i32:
+; CHECK: # %bb.0:
+; CHECK-NEXT: addi sp, sp, -16
+; CHECK-NEXT: csrr a0, vlenb
+; CHECK-NEXT: sub sp, sp, a0
+; CHECK-NEXT: vsetvli a0, zero, e32, m1, ta, ma
+; CHECK-NEXT: vsrl.vi v9, v8, 8
+; CHECK-NEXT: lui a4, 16
+; CHECK-NEXT: vsrl.vi v10, v8, 24
+; CHECK-NEXT: vsll.vi v11, v8, 24
+; CHECK-NEXT: lui a0, 61681
+; CHECK-NEXT: lui a1, 209715
+; CHECK-NEXT: lui a5, 349525
+; CHECK-NEXT: li a6, 16
+; CHECK-NEXT: addi a3, a4, -256
+; CHECK-NEXT: addi a2, a0, -241
+; CHECK-NEXT: addi a1, a1, 819
+; CHECK-NEXT: addi a0, a5, 1365
+; CHECK-NEXT: vand.vx v9, v9, a3
+; CHECK-NEXT: vand.vx v8, v8, a3
+; CHECK-NEXT: vor.vv v9, v9, v10
+; CHECK-NEXT: vsll.vi v8, v8, 8
+; CHECK-NEXT: vor.vv v8, v11, v8
+; CHECK-NEXT: vor.vv v8, v8, v9
+; CHECK-NEXT: vsrl.vi v9, v8, 4
+; CHECK-NEXT: vand.vx v8, v8, a2
+; CHECK-NEXT: vand.vx v9, v9, a2
+; CHECK-NEXT: vsll.vi v8, v8, 4
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v9, v8, 2
+; CHECK-NEXT: vand.vx v8, v8, a1
+; CHECK-NEXT: vand.vx v9, v9, a1
+; CHECK-NEXT: vsll.vi v8, v8, 2
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v9, v8, 1
+; CHECK-NEXT: vand.vx v8, v8, a0
+; CHECK-NEXT: vand.vx v9, v9, a0
+; CHECK-NEXT: vadd.vv v8, v8, v8
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vand.vx v9, v8, a6
+; CHECK-NEXT: li a5, 32
+; CHECK-NEXT: vand.vx v10, v8, a5
+; CHECK-NEXT: li a5, 64
+; CHECK-NEXT: vand.vx v11, v8, a5
+; CHECK-NEXT: li a5, 128
+; CHECK-NEXT: vand.vx v12, v8, a5
+; CHECK-NEXT: li a5, 256
+; CHECK-NEXT: vand.vx v13, v8, a5
+; CHECK-NEXT: li a5, 512
+; CHECK-NEXT: vand.vx v14, v8, a5
+; CHECK-NEXT: li a5, 1024
+; CHECK-NEXT: vand.vx v15, v8, a5
+; CHECK-NEXT: li a5, 1
+; CHECK-NEXT: slli a5, a5, 11
+; CHECK-NEXT: vand.vx v16, v8, a5
+; CHECK-NEXT: lui a5, 1
+; CHECK-NEXT: vand.vx v17, v8, a5
+; CHECK-NEXT: lui a5, 2
+; CHECK-NEXT: vand.vx v18, v8, a5
+; CHECK-NEXT: lui a5, 4
+; CHECK-NEXT: vand.vx v19, v8, a5
+; CHECK-NEXT: lui a5, 8
+; CHECK-NEXT: vand.vx v20, v8, a5
+; CHECK-NEXT: lui a5, 32
+; CHECK-NEXT: vand.vx v21, v8, a4
+; CHECK-NEXT: lui a4, 64
+; CHECK-NEXT: vand.vx v22, v8, a5
+; CHECK-NEXT: lui a5, 128
+; CHECK-NEXT: vand.vx v23, v8, a4
+; CHECK-NEXT: lui a4, 256
+; CHECK-NEXT: vand.vx v24, v8, a5
+; CHECK-NEXT: lui a5, 512
+; CHECK-NEXT: vand.vx v25, v8, a4
+; CHECK-NEXT: lui a4, 1024
+; CHECK-NEXT: vand.vx v26, v8, a5
+; CHECK-NEXT: lui a5, 2048
+; CHECK-NEXT: vand.vx v27, v8, a4
+; CHECK-NEXT: lui a4, 4096
+; CHECK-NEXT: vand.vx v28, v8, a5
+; CHECK-NEXT: lui a5, 8192
+; CHECK-NEXT: vand.vx v29, v8, a4
+; CHECK-NEXT: lui a4, 16384
+; CHECK-NEXT: vand.vx v30, v8, a5
+; CHECK-NEXT: lui a5, 32768
+; CHECK-NEXT: vand.vx v31, v8, a4
+; CHECK-NEXT: lui a4, 65536
+; CHECK-NEXT: vand.vx v7, v8, a5
+; CHECK-NEXT: lui a5, 131072
+; CHECK-NEXT: vand.vx v6, v8, a4
+; CHECK-NEXT: lui a4, 262144
+; CHECK-NEXT: vand.vx v5, v8, a5
+; CHECK-NEXT: lui a5, 524288
+; CHECK-NEXT: vand.vi v4, v8, 2
+; CHECK-NEXT: vand.vi v3, v8, 1
+; CHECK-NEXT: vand.vi v2, v8, 4
+; CHECK-NEXT: vand.vi v1, v8, 8
+; CHECK-NEXT: vand.vx v0, v8, a4
+; CHECK-NEXT: vmul.vv v4, v8, v4
+; CHECK-NEXT: vmul.vv v3, v8, v3
+; CHECK-NEXT: vmul.vv v2, v8, v2
+; CHECK-NEXT: vmul.vv v1, v8, v1
+; CHECK-NEXT: vmul.vv v9, v8, v9
+; CHECK-NEXT: vmul.vv v10, v8, v10
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vmul.vv v12, v8, v12
+; CHECK-NEXT: vmul.vv v13, v8, v13
+; CHECK-NEXT: vmul.vv v14, v8, v14
+; CHECK-NEXT: vmul.vv v15, v8, v15
+; CHECK-NEXT: vmul.vv v16, v8, v16
+; CHECK-NEXT: vmul.vv v17, v8, v17
+; CHECK-NEXT: vmul.vv v18, v8, v18
+; CHECK-NEXT: vmul.vv v19, v8, v19
+; CHECK-NEXT: vmul.vv v20, v8, v20
+; CHECK-NEXT: vmul.vv v21, v8, v21
+; CHECK-NEXT: vmul.vv v22, v8, v22
+; CHECK-NEXT: vmul.vv v23, v8, v23
+; CHECK-NEXT: vmul.vv v24, v8, v24
+; CHECK-NEXT: vmul.vv v25, v8, v25
+; CHECK-NEXT: vmul.vv v26, v8, v26
+; CHECK-NEXT: vmul.vv v27, v8, v27
+; CHECK-NEXT: vmul.vv v28, v8, v28
+; CHECK-NEXT: vmul.vv v29, v8, v29
+; CHECK-NEXT: vmul.vv v30, v8, v30
+; CHECK-NEXT: vmul.vv v31, v8, v31
+; CHECK-NEXT: vmul.vv v7, v8, v7
+; CHECK-NEXT: vmul.vv v6, v8, v6
+; CHECK-NEXT: vmul.vv v5, v8, v5
+; CHECK-NEXT: vmul.vv v0, v8, v0
+; CHECK-NEXT: addi a4, sp, 16
+; CHECK-NEXT: vs1r.v v0, (a4) # vscale x 8-byte Folded Spill
+; CHECK-NEXT: vand.vx v0, v8, a5
+; CHECK-NEXT: vmul.vv v8, v8, v0
+; CHECK-NEXT: vxor.vv v4, v3, v4
+; CHECK-NEXT: vxor.vv v4, v4, v2
+; CHECK-NEXT: vxor.vv v4, v4, v1
+; CHECK-NEXT: vxor.vv v9, v4, v9
+; CHECK-NEXT: vxor.vv v9, v9, v10
+; CHECK-NEXT: vxor.vv v9, v9, v11
+; CHECK-NEXT: vxor.vv v9, v9, v12
+; CHECK-NEXT: vxor.vv v10, v9, v13
+; CHECK-NEXT: vxor.vv v10, v10, v14
+; CHECK-NEXT: vxor.vv v10, v10, v15
+; CHECK-NEXT: vxor.vv v10, v10, v16
+; CHECK-NEXT: vxor.vv v10, v10, v17
+; CHECK-NEXT: vxor.vv v10, v10, v18
+; CHECK-NEXT: vxor.vv v10, v10, v19
+; CHECK-NEXT: vxor.vv v10, v10, v20
+; CHECK-NEXT: vxor.vv v10, v10, v21
+; CHECK-NEXT: vxor.vv v10, v10, v22
+; CHECK-NEXT: vxor.vv v10, v10, v23
+; CHECK-NEXT: vxor.vv v10, v10, v24
+; CHECK-NEXT: vxor.vv v10, v10, v25
+; CHECK-NEXT: vxor.vv v10, v10, v26
+; CHECK-NEXT: vxor.vv v10, v10, v27
+; CHECK-NEXT: vxor.vv v10, v10, v28
+; CHECK-NEXT: vsll.vi v9, v9, 24
+; CHECK-NEXT: vxor.vv v11, v10, v29
+; CHECK-NEXT: vxor.vv v11, v11, v30
+; CHECK-NEXT: vand.vx v12, v10, a3
+; CHECK-NEXT: vsll.vi v12, v12, 8
+; CHECK-NEXT: vor.vv v9, v9, v12
+; CHECK-NEXT: vxor.vv v11, v11, v31
+; CHECK-NEXT: vxor.vv v11, v11, v7
+; CHECK-NEXT: vxor.vv v11, v11, v6
+; CHECK-NEXT: vxor.vv v11, v11, v5
+; CHECK-NEXT: vsrl.vi v10, v10, 8
+; CHECK-NEXT: vand.vx v10, v10, a3
+; CHECK-NEXT: addi a3, sp, 16
+; CHECK-NEXT: vl1r.v v12, (a3) # vscale x 8-byte Folded Reload
+; CHECK-NEXT: vxor.vv v11, v11, v12
+; CHECK-NEXT: vxor.vv v8, v11, v8
+; CHECK-NEXT: vsrl.vi v8, v8, 24
+; CHECK-NEXT: vor.vv v8, v10, v8
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v9, v8, 4
+; CHECK-NEXT: vand.vx v8, v8, a2
+; CHECK-NEXT: vand.vx v9, v9, a2
+; CHECK-NEXT: vsll.vi v8, v8, 4
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v9, v8, 2
+; CHECK-NEXT: vand.vx v8, v8, a1
+; CHECK-NEXT: vand.vx v9, v9, a1
+; CHECK-NEXT: vsll.vi v8, v8, 2
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v9, v8, 1
+; CHECK-NEXT: vand.vx v8, v8, a0
+; CHECK-NEXT: vand.vx v9, v9, a0
+; CHECK-NEXT: vadd.vv v8, v8, v8
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v8, v8, 1
+; CHECK-NEXT: csrr a0, vlenb
+; CHECK-NEXT: add sp, sp, a0
+; CHECK-NEXT: addi sp, sp, 16
+; CHECK-NEXT: ret
+ %a = call <vscale x 2 x i32> @llvm.clmulh.nxv2i32(<vscale x 2 x i32> %x, <vscale x 2 x i32> %y)
+ ret <vscale x 2 x i32> %a
+}
+
+define <vscale x 4 x i32> @clmulh_nxv4i32(<vscale x 4 x i32> %x, <vscale x 4 x i32> %y) nounwind {
+; RV32-LABEL: clmulh_nxv4i32:
+; RV32: # %bb.0:
+; RV32-NEXT: addi sp, sp, -64
+; RV32-NEXT: sw s0, 60(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s1, 56(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s2, 52(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s3, 48(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s4, 44(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s5, 40(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s6, 36(sp) # 4-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: sub sp, sp, a0
+; RV32-NEXT: vsetvli a0, zero, e32, m2, ta, ma
+; RV32-NEXT: vsrl.vi v10, v8, 8
+; RV32-NEXT: lui a0, 16
+; RV32-NEXT: vsrl.vi v12, v8, 24
+; RV32-NEXT: vsll.vi v14, v8, 24
+; RV32-NEXT: lui a1, 61681
+; RV32-NEXT: lui a2, 209715
+; RV32-NEXT: lui s6, 349525
+; RV32-NEXT: li t2, 16
+; RV32-NEXT: li t5, 32
+; RV32-NEXT: li s2, 64
+; RV32-NEXT: li s5, 128
+; RV32-NEXT: li s4, 256
+; RV32-NEXT: li s3, 512
+; RV32-NEXT: li s1, 1024
+; RV32-NEXT: li s0, 1
+; RV32-NEXT: lui t6, 1
+; RV32-NEXT: lui t4, 2
+; RV32-NEXT: lui t3, 4
+; RV32-NEXT: lui a5, 8
+; RV32-NEXT: lui a6, 32
+; RV32-NEXT: lui a7, 64
+; RV32-NEXT: lui t0, 128
+; RV32-NEXT: lui t1, 256
+; RV32-NEXT: addi a4, a0, -256
+; RV32-NEXT: addi a3, a1, -241
+; RV32-NEXT: addi a2, a2, 819
+; RV32-NEXT: addi a1, s6, 1365
+; RV32-NEXT: vand.vx v10, v10, a4
+; RV32-NEXT: vand.vx v8, v8, a4
+; RV32-NEXT: vor.vv v10, v10, v12
+; RV32-NEXT: vsll.vi v8, v8, 8
+; RV32-NEXT: vor.vv v8, v14, v8
+; RV32-NEXT: vor.vv v8, v8, v10
+; RV32-NEXT: vsrl.vi v10, v8, 4
+; RV32-NEXT: vand.vx v8, v8, a3
+; RV32-NEXT: vand.vx v10, v10, a3
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v10, v8
+; RV32-NEXT: vsrl.vi v10, v8, 2
+; RV32-NEXT: vand.vx v8, v8, a2
+; RV32-NEXT: vand.vx v10, v10, a2
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v8, v10, v8
+; RV32-NEXT: vsrl.vi v10, v8, 1
+; RV32-NEXT: vand.vx v8, v8, a1
+; RV32-NEXT: vand.vx v10, v10, a1
+; RV32-NEXT: vadd.vv v8, v8, v8
+; RV32-NEXT: vor.vv v8, v10, v8
+; RV32-NEXT: vand.vx v10, v8, t2
+; RV32-NEXT: lui t2, 512
+; RV32-NEXT: vand.vx v12, v8, t5
+; RV32-NEXT: lui t5, 1024
+; RV32-NEXT: vand.vx v14, v8, s2
+; RV32-NEXT: lui s2, 2048
+; RV32-NEXT: vand.vx v16, v8, s5
+; RV32-NEXT: lui s5, 4096
+; RV32-NEXT: vand.vx v26, v8, s4
+; RV32-NEXT: lui s4, 8192
+; RV32-NEXT: vand.vx v28, v8, s3
+; RV32-NEXT: lui s3, 16384
+; RV32-NEXT: vand.vx v18, v8, s1
+; RV32-NEXT: lui s1, 32768
+; RV32-NEXT: slli s0, s0, 11
+; RV32-NEXT: vand.vx v20, v8, s0
+; RV32-NEXT: lui s0, 65536
+; RV32-NEXT: vand.vx v22, v8, t6
+; RV32-NEXT: lui t6, 131072
+; RV32-NEXT: vand.vx v24, v8, t4
+; RV32-NEXT: lui t4, 262144
+; RV32-NEXT: vand.vx v30, v8, t3
+; RV32-NEXT: lui t3, 524288
+; RV32-NEXT: vand.vi v6, v8, 2
+; RV32-NEXT: vand.vi v4, v8, 1
+; RV32-NEXT: vand.vi v2, v8, 4
+; RV32-NEXT: vand.vi v0, v8, 8
+; RV32-NEXT: vmul.vv v6, v8, v6
+; RV32-NEXT: sw a0, 4(sp) # 4-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv s6, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, s6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v6, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v6, v8, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv s6, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, s6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v6, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v6, v8, v2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v6, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v6, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv s6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add s6, s6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add s6, s6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, s6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v6, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv s6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add s6, s6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, s6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v10, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv s6, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add s6, s6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, s6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v10, v8, v14
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv s6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, s6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v10, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv s6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add s6, s6, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, s6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v10, v8, v26
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv s6, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, s6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v10, v8, v28
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv s6, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, s6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v10, v8, v18
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v10, v8, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv s6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add s6, s6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, s6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v10, v8, v22
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv s6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, s6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v10, v8, v24
+; RV32-NEXT: csrr s6, vlenb
+; RV32-NEXT: slli s6, s6, 1
+; RV32-NEXT: mv a0, s6
+; RV32-NEXT: slli s6, s6, 2
+; RV32-NEXT: add s6, s6, a0
+; RV32-NEXT: lw a0, 4(sp) # 4-byte Folded Reload
+; RV32-NEXT: add s6, sp, s6
+; RV32-NEXT: addi s6, s6, 32
+; RV32-NEXT: vs2r.v v10, (s6) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v10, v8, v30
+; RV32-NEXT: csrr s6, vlenb
+; RV32-NEXT: slli s6, s6, 3
+; RV32-NEXT: add s6, sp, s6
+; RV32-NEXT: addi s6, s6, 32
+; RV32-NEXT: vs2r.v v10, (s6) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, a5
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a5, vlenb
+; RV32-NEXT: slli a5, a5, 1
+; RV32-NEXT: mv s6, a5
+; RV32-NEXT: slli a5, a5, 1
+; RV32-NEXT: add a5, a5, s6
+; RV32-NEXT: add a5, sp, a5
+; RV32-NEXT: addi a5, a5, 32
+; RV32-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, a0
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, a6
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, a7
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: addi a0, sp, 32
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, t0
+; RV32-NEXT: vmul.vv v6, v8, v10
+; RV32-NEXT: vand.vx v10, v8, t1
+; RV32-NEXT: vmul.vv v30, v8, v10
+; RV32-NEXT: vand.vx v10, v8, t2
+; RV32-NEXT: vmul.vv v28, v8, v10
+; RV32-NEXT: vand.vx v10, v8, t5
+; RV32-NEXT: vmul.vv v26, v8, v10
+; RV32-NEXT: vand.vx v10, v8, s2
+; RV32-NEXT: vmul.vv v22, v8, v10
+; RV32-NEXT: vand.vx v10, v8, s5
+; RV32-NEXT: vmul.vv v18, v8, v10
+; RV32-NEXT: vand.vx v10, v8, s4
+; RV32-NEXT: vmul.vv v16, v8, v10
+; RV32-NEXT: vand.vx v10, v8, s3
+; RV32-NEXT: vmul.vv v24, v8, v10
+; RV32-NEXT: vand.vx v10, v8, s1
+; RV32-NEXT: vmul.vv v20, v8, v10
+; RV32-NEXT: vand.vx v10, v8, s0
+; RV32-NEXT: vmul.vv v12, v8, v10
+; RV32-NEXT: vand.vx v10, v8, t6
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: vand.vx v14, v8, t4
+; RV32-NEXT: vmul.vv v14, v8, v14
+; RV32-NEXT: vand.vx v0, v8, t3
+; RV32-NEXT: vmul.vv v8, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v0, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v0, v2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v2, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v2, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v2, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v2, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v2, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v2, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v2, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v2, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v2, v4
+; RV32-NEXT: addi a0, sp, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v4, v2, v4
+; RV32-NEXT: vxor.vv v6, v4, v6
+; RV32-NEXT: vxor.vv v30, v6, v30
+; RV32-NEXT: vxor.vv v28, v30, v28
+; RV32-NEXT: vxor.vv v26, v28, v26
+; RV32-NEXT: vxor.vv v22, v26, v22
+; RV32-NEXT: vsll.vi v26, v0, 24
+; RV32-NEXT: vxor.vv v18, v22, v18
+; RV32-NEXT: vxor.vv v16, v18, v16
+; RV32-NEXT: vand.vx v18, v22, a4
+; RV32-NEXT: vsll.vi v18, v18, 8
+; RV32-NEXT: vor.vv v18, v26, v18
+; RV32-NEXT: vxor.vv v16, v16, v24
+; RV32-NEXT: vxor.vv v16, v16, v20
+; RV32-NEXT: vxor.vv v12, v16, v12
+; RV32-NEXT: vxor.vv v10, v12, v10
+; RV32-NEXT: vsrl.vi v12, v22, 8
+; RV32-NEXT: vand.vx v12, v12, a4
+; RV32-NEXT: vxor.vv v10, v10, v14
+; RV32-NEXT: vxor.vv v8, v10, v8
+; RV32-NEXT: vsrl.vi v8, v8, 24
+; RV32-NEXT: vor.vv v8, v12, v8
+; RV32-NEXT: vor.vv v8, v18, v8
+; RV32-NEXT: vsrl.vi v10, v8, 4
+; RV32-NEXT: vand.vx v8, v8, a3
+; RV32-NEXT: vand.vx v10, v10, a3
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v10, v8
+; RV32-NEXT: vsrl.vi v10, v8, 2
+; RV32-NEXT: vand.vx v8, v8, a2
+; RV32-NEXT: vand.vx v10, v10, a2
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v8, v10, v8
+; RV32-NEXT: vsrl.vi v10, v8, 1
+; RV32-NEXT: vand.vx v8, v8, a1
+; RV32-NEXT: vand.vx v10, v10, a1
+; RV32-NEXT: vadd.vv v8, v8, v8
+; RV32-NEXT: vor.vv v8, v10, v8
+; RV32-NEXT: vsrl.vi v8, v8, 1
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add sp, sp, a0
+; RV32-NEXT: lw s0, 60(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s1, 56(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s2, 52(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s3, 48(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s4, 44(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s5, 40(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s6, 36(sp) # 4-byte Folded Reload
+; RV32-NEXT: addi sp, sp, 64
+; RV32-NEXT: ret
+;
+; RV64-LABEL: clmulh_nxv4i32:
+; RV64: # %bb.0:
+; RV64-NEXT: addi sp, sp, -96
+; RV64-NEXT: sd s0, 88(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s1, 80(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s2, 72(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s3, 64(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s4, 56(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s5, 48(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s6, 40(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: sub sp, sp, a0
+; RV64-NEXT: vsetvli a0, zero, e32, m2, ta, ma
+; RV64-NEXT: vsrl.vi v10, v8, 8
+; RV64-NEXT: lui a0, 16
+; RV64-NEXT: vsrl.vi v12, v8, 24
+; RV64-NEXT: vsll.vi v14, v8, 24
+; RV64-NEXT: lui a1, 61681
+; RV64-NEXT: lui a2, 209715
+; RV64-NEXT: lui s6, 349525
+; RV64-NEXT: li t2, 16
+; RV64-NEXT: li t5, 32
+; RV64-NEXT: li s2, 64
+; RV64-NEXT: li s5, 128
+; RV64-NEXT: li s4, 256
+; RV64-NEXT: li s3, 512
+; RV64-NEXT: li s1, 1024
+; RV64-NEXT: li s0, 1
+; RV64-NEXT: lui t6, 1
+; RV64-NEXT: lui t4, 2
+; RV64-NEXT: lui t3, 4
+; RV64-NEXT: lui a5, 8
+; RV64-NEXT: lui a6, 32
+; RV64-NEXT: lui a7, 64
+; RV64-NEXT: lui t0, 128
+; RV64-NEXT: lui t1, 256
+; RV64-NEXT: addi a4, a0, -256
+; RV64-NEXT: addi a3, a1, -241
+; RV64-NEXT: addi a2, a2, 819
+; RV64-NEXT: addi a1, s6, 1365
+; RV64-NEXT: vand.vx v10, v10, a4
+; RV64-NEXT: vand.vx v8, v8, a4
+; RV64-NEXT: vor.vv v10, v10, v12
+; RV64-NEXT: vsll.vi v8, v8, 8
+; RV64-NEXT: vor.vv v8, v14, v8
+; RV64-NEXT: vor.vv v8, v8, v10
+; RV64-NEXT: vsrl.vi v10, v8, 4
+; RV64-NEXT: vand.vx v8, v8, a3
+; RV64-NEXT: vand.vx v10, v10, a3
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v10, v8
+; RV64-NEXT: vsrl.vi v10, v8, 2
+; RV64-NEXT: vand.vx v8, v8, a2
+; RV64-NEXT: vand.vx v10, v10, a2
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v10, v8
+; RV64-NEXT: vsrl.vi v10, v8, 1
+; RV64-NEXT: vand.vx v8, v8, a1
+; RV64-NEXT: vand.vx v10, v10, a1
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v10, v8
+; RV64-NEXT: vand.vx v10, v8, t2
+; RV64-NEXT: lui t2, 512
+; RV64-NEXT: vand.vx v12, v8, t5
+; RV64-NEXT: lui t5, 1024
+; RV64-NEXT: vand.vx v14, v8, s2
+; RV64-NEXT: lui s2, 2048
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: lui s5, 4096
+; RV64-NEXT: vand.vx v26, v8, s4
+; RV64-NEXT: lui s4, 8192
+; RV64-NEXT: vand.vx v28, v8, s3
+; RV64-NEXT: lui s3, 16384
+; RV64-NEXT: vand.vx v18, v8, s1
+; RV64-NEXT: lui s1, 32768
+; RV64-NEXT: slli s0, s0, 11
+; RV64-NEXT: vand.vx v20, v8, s0
+; RV64-NEXT: lui s0, 65536
+; RV64-NEXT: vand.vx v22, v8, t6
+; RV64-NEXT: lui t6, 131072
+; RV64-NEXT: vand.vx v24, v8, t4
+; RV64-NEXT: lui t4, 262144
+; RV64-NEXT: vand.vx v30, v8, t3
+; RV64-NEXT: lui t3, 524288
+; RV64-NEXT: vand.vi v6, v8, 2
+; RV64-NEXT: vand.vi v4, v8, 1
+; RV64-NEXT: vand.vi v2, v8, 4
+; RV64-NEXT: vand.vi v0, v8, 8
+; RV64-NEXT: vmul.vv v6, v8, v6
+; RV64-NEXT: sd a0, 8(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv s6, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, s6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v6, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v6, v8, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv s6, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, a0, s6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v6, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v6, v8, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v6, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v6, v8, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv s6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add s6, s6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add s6, s6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, s6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v6, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv s6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add s6, s6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, s6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v12
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv s6, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add s6, s6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, s6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v14
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv s6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, s6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv s6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add s6, s6, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, s6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v26
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv s6, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, s6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v28
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv s6, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, s6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v18
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v20
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv s6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add s6, s6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, s6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v22
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv s6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, s6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v24
+; RV64-NEXT: csrr s6, vlenb
+; RV64-NEXT: slli s6, s6, 1
+; RV64-NEXT: mv a0, s6
+; RV64-NEXT: slli s6, s6, 2
+; RV64-NEXT: add s6, s6, a0
+; RV64-NEXT: ld a0, 8(sp) # 8-byte Folded Reload
+; RV64-NEXT: add s6, sp, s6
+; RV64-NEXT: addi s6, s6, 32
+; RV64-NEXT: vs2r.v v10, (s6) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v30
+; RV64-NEXT: csrr s6, vlenb
+; RV64-NEXT: slli s6, s6, 3
+; RV64-NEXT: add s6, sp, s6
+; RV64-NEXT: addi s6, s6, 32
+; RV64-NEXT: vs2r.v v10, (s6) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, a5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s6, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s6
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 32
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, a0
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, a6
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, a7
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: addi a0, sp, 32
+; RV64-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, t0
+; RV64-NEXT: vmul.vv v6, v8, v10
+; RV64-NEXT: vand.vx v10, v8, t1
+; RV64-NEXT: vmul.vv v30, v8, v10
+; RV64-NEXT: vand.vx v10, v8, t2
+; RV64-NEXT: vmul.vv v28, v8, v10
+; RV64-NEXT: vand.vx v10, v8, t5
+; RV64-NEXT: vmul.vv v26, v8, v10
+; RV64-NEXT: vand.vx v10, v8, s2
+; RV64-NEXT: vmul.vv v22, v8, v10
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v18, v8, v10
+; RV64-NEXT: vand.vx v10, v8, s4
+; RV64-NEXT: vmul.vv v16, v8, v10
+; RV64-NEXT: vand.vx v10, v8, s3
+; RV64-NEXT: vmul.vv v24, v8, v10
+; RV64-NEXT: vand.vx v10, v8, s1
+; RV64-NEXT: vmul.vv v20, v8, v10
+; RV64-NEXT: vand.vx v10, v8, s0
+; RV64-NEXT: vmul.vv v12, v8, v10
+; RV64-NEXT: vand.vx v10, v8, t6
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: vand.vx v14, v8, t4
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vand.vx v0, v8, t3
+; RV64-NEXT: vmul.vv v8, v8, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v0, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v4
+; RV64-NEXT: addi a0, sp, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v4, v2, v4
+; RV64-NEXT: vxor.vv v6, v4, v6
+; RV64-NEXT: vxor.vv v30, v6, v30
+; RV64-NEXT: vxor.vv v28, v30, v28
+; RV64-NEXT: vxor.vv v26, v28, v26
+; RV64-NEXT: vxor.vv v22, v26, v22
+; RV64-NEXT: vsll.vi v26, v0, 24
+; RV64-NEXT: vxor.vv v18, v22, v18
+; RV64-NEXT: vxor.vv v16, v18, v16
+; RV64-NEXT: vand.vx v18, v22, a4
+; RV64-NEXT: vsll.vi v18, v18, 8
+; RV64-NEXT: vor.vv v18, v26, v18
+; RV64-NEXT: vxor.vv v16, v16, v24
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vxor.vv v12, v16, v12
+; RV64-NEXT: vxor.vv v10, v12, v10
+; RV64-NEXT: vsrl.vi v12, v22, 8
+; RV64-NEXT: vand.vx v12, v12, a4
+; RV64-NEXT: vxor.vv v10, v10, v14
+; RV64-NEXT: vxor.vv v8, v10, v8
+; RV64-NEXT: vsrl.vi v8, v8, 24
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vor.vv v8, v18, v8
+; RV64-NEXT: vsrl.vi v10, v8, 4
+; RV64-NEXT: vand.vx v8, v8, a3
+; RV64-NEXT: vand.vx v10, v10, a3
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v10, v8
+; RV64-NEXT: vsrl.vi v10, v8, 2
+; RV64-NEXT: vand.vx v8, v8, a2
+; RV64-NEXT: vand.vx v10, v10, a2
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v10, v8
+; RV64-NEXT: vsrl.vi v10, v8, 1
+; RV64-NEXT: vand.vx v8, v8, a1
+; RV64-NEXT: vand.vx v10, v10, a1
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v10, v8
+; RV64-NEXT: vsrl.vi v8, v8, 1
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add sp, sp, a0
+; RV64-NEXT: ld s0, 88(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s1, 80(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s2, 72(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s3, 64(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s4, 56(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s5, 48(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s6, 40(sp) # 8-byte Folded Reload
+; RV64-NEXT: addi sp, sp, 96
+; RV64-NEXT: ret
+ %a = call <vscale x 4 x i32> @llvm.clmulh.nxv4i32(<vscale x 4 x i32> %x, <vscale x 4 x i32> %y)
+ ret <vscale x 4 x i32> %a
+}
+
+define <vscale x 8 x i32> @clmulh_nxv8i32(<vscale x 8 x i32> %x, <vscale x 8 x i32> %y) nounwind {
+; RV32-LABEL: clmulh_nxv8i32:
+; RV32: # %bb.0:
+; RV32-NEXT: addi sp, sp, -80
+; RV32-NEXT: sw ra, 76(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s0, 72(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s1, 68(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s2, 64(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s3, 60(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s4, 56(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s5, 52(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s6, 48(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s7, 44(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s8, 40(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s9, 36(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s10, 32(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s11, 28(sp) # 4-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: sub sp, sp, a0
+; RV32-NEXT: vsetvli a0, zero, e32, m4, ta, ma
+; RV32-NEXT: vsrl.vi v12, v8, 8
+; RV32-NEXT: lui a5, 16
+; RV32-NEXT: vsrl.vi v16, v8, 24
+; RV32-NEXT: vsll.vi v20, v8, 24
+; RV32-NEXT: lui a1, 61681
+; RV32-NEXT: lui a2, 209715
+; RV32-NEXT: lui ra, 349525
+; RV32-NEXT: li s9, 16
+; RV32-NEXT: li s8, 32
+; RV32-NEXT: li s6, 64
+; RV32-NEXT: li a7, 512
+; RV32-NEXT: li t0, 1024
+; RV32-NEXT: li a0, 1
+; RV32-NEXT: lui t1, 1
+; RV32-NEXT: lui t2, 2
+; RV32-NEXT: lui t3, 4
+; RV32-NEXT: lui t4, 8
+; RV32-NEXT: lui t5, 32
+; RV32-NEXT: lui t6, 64
+; RV32-NEXT: lui s0, 128
+; RV32-NEXT: lui s1, 256
+; RV32-NEXT: lui s2, 512
+; RV32-NEXT: lui s3, 1024
+; RV32-NEXT: lui s4, 2048
+; RV32-NEXT: lui s5, 4096
+; RV32-NEXT: lui s7, 8192
+; RV32-NEXT: lui s10, 16384
+; RV32-NEXT: lui s11, 32768
+; RV32-NEXT: addi a4, a5, -256
+; RV32-NEXT: addi a3, a1, -241
+; RV32-NEXT: addi a2, a2, 819
+; RV32-NEXT: addi a1, ra, 1365
+; RV32-NEXT: vand.vx v12, v12, a4
+; RV32-NEXT: vand.vx v8, v8, a4
+; RV32-NEXT: vor.vv v12, v12, v16
+; RV32-NEXT: vsll.vi v8, v8, 8
+; RV32-NEXT: vor.vv v8, v20, v8
+; RV32-NEXT: vor.vv v8, v8, v12
+; RV32-NEXT: vsrl.vi v12, v8, 4
+; RV32-NEXT: vand.vx v8, v8, a3
+; RV32-NEXT: vand.vx v12, v12, a3
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v12, v8
+; RV32-NEXT: vsrl.vi v12, v8, 2
+; RV32-NEXT: vand.vx v8, v8, a2
+; RV32-NEXT: vand.vx v12, v12, a2
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v8, v12, v8
+; RV32-NEXT: vsrl.vi v12, v8, 1
+; RV32-NEXT: vand.vx v8, v8, a1
+; RV32-NEXT: vand.vx v12, v12, a1
+; RV32-NEXT: vadd.vv v8, v8, v8
+; RV32-NEXT: vor.vv v8, v12, v8
+; RV32-NEXT: vand.vx v12, v8, s9
+; RV32-NEXT: lui s9, 65536
+; RV32-NEXT: vand.vx v16, v8, s8
+; RV32-NEXT: lui s8, 131072
+; RV32-NEXT: vand.vx v20, v8, s6
+; RV32-NEXT: lui s6, 262144
+; RV32-NEXT: slli ra, a0, 11
+; RV32-NEXT: vand.vi v24, v8, 2
+; RV32-NEXT: vand.vi v28, v8, 1
+; RV32-NEXT: vand.vi v4, v8, 4
+; RV32-NEXT: vand.vi v0, v8, 8
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: sw a4, 4(sp) # 4-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a4, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a4, a4, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs4r.v v24, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vmul.vv v24, v8, v28
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a4, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a4, a4, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs4r.v v24, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vmul.vv v24, v8, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a4, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs4r.v v24, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vmul.vv v24, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a4, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a4, a4, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a4, a4, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs4r.v v24, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a4, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a4, a4, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vmul.vv v12, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a4, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a4, a4, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vmul.vv v12, v8, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a4, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: lui a0, 524288
+; RV32-NEXT: li a6, 128
+; RV32-NEXT: vand.vx v12, v8, a6
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a4, vlenb
+; RV32-NEXT: slli a4, a4, 2
+; RV32-NEXT: mv a6, a4
+; RV32-NEXT: slli a4, a4, 1
+; RV32-NEXT: add a6, a6, a4
+; RV32-NEXT: slli a4, a4, 3
+; RV32-NEXT: add a4, a4, a6
+; RV32-NEXT: add a4, sp, a4
+; RV32-NEXT: addi a4, a4, 16
+; RV32-NEXT: vs4r.v v12, (a4) # vscale x 32-byte Folded Spill
+; RV32-NEXT: li a6, 256
+; RV32-NEXT: vand.vx v12, v8, a6
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 3
+; RV32-NEXT: mv a4, a6
+; RV32-NEXT: slli a6, a6, 3
+; RV32-NEXT: add a6, a6, a4
+; RV32-NEXT: lw a4, 4(sp) # 4-byte Folded Reload
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 16
+; RV32-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, a7
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 2
+; RV32-NEXT: mv a7, a6
+; RV32-NEXT: slli a6, a6, 4
+; RV32-NEXT: add a6, a6, a7
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 16
+; RV32-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, t0
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 6
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 16
+; RV32-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, ra
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 2
+; RV32-NEXT: mv a7, a6
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: add a7, a7, a6
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: add a7, a7, a6
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: add a6, a6, a7
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 16
+; RV32-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, t1
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 3
+; RV32-NEXT: mv a7, a6
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: add a7, a7, a6
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: add a6, a6, a7
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 16
+; RV32-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, t2
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 2
+; RV32-NEXT: mv a7, a6
+; RV32-NEXT: slli a6, a6, 2
+; RV32-NEXT: add a7, a7, a6
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: add a6, a6, a7
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 16
+; RV32-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, t3
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 4
+; RV32-NEXT: mv a7, a6
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: add a6, a6, a7
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 16
+; RV32-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, t4
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 2
+; RV32-NEXT: mv a7, a6
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: add a7, a7, a6
+; RV32-NEXT: slli a6, a6, 2
+; RV32-NEXT: add a6, a6, a7
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 16
+; RV32-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, a5
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a5, vlenb
+; RV32-NEXT: slli a5, a5, 3
+; RV32-NEXT: mv a6, a5
+; RV32-NEXT: slli a5, a5, 2
+; RV32-NEXT: add a5, a5, a6
+; RV32-NEXT: add a5, sp, a5
+; RV32-NEXT: addi a5, a5, 16
+; RV32-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, t5
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a5, vlenb
+; RV32-NEXT: slli a5, a5, 2
+; RV32-NEXT: mv a6, a5
+; RV32-NEXT: slli a5, a5, 3
+; RV32-NEXT: add a5, a5, a6
+; RV32-NEXT: add a5, sp, a5
+; RV32-NEXT: addi a5, a5, 16
+; RV32-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, t6
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a5, vlenb
+; RV32-NEXT: slli a5, a5, 5
+; RV32-NEXT: add a5, sp, a5
+; RV32-NEXT: addi a5, a5, 16
+; RV32-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s0
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a5, vlenb
+; RV32-NEXT: slli a5, a5, 2
+; RV32-NEXT: mv a6, a5
+; RV32-NEXT: slli a5, a5, 1
+; RV32-NEXT: add a6, a6, a5
+; RV32-NEXT: slli a5, a5, 1
+; RV32-NEXT: add a5, a5, a6
+; RV32-NEXT: add a5, sp, a5
+; RV32-NEXT: addi a5, a5, 16
+; RV32-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s1
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a5, vlenb
+; RV32-NEXT: slli a5, a5, 3
+; RV32-NEXT: mv a6, a5
+; RV32-NEXT: slli a5, a5, 1
+; RV32-NEXT: add a5, a5, a6
+; RV32-NEXT: add a5, sp, a5
+; RV32-NEXT: addi a5, a5, 16
+; RV32-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s2
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a5, vlenb
+; RV32-NEXT: slli a5, a5, 2
+; RV32-NEXT: mv a6, a5
+; RV32-NEXT: slli a5, a5, 2
+; RV32-NEXT: add a5, a5, a6
+; RV32-NEXT: add a5, sp, a5
+; RV32-NEXT: addi a5, a5, 16
+; RV32-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s3
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a5, vlenb
+; RV32-NEXT: slli a5, a5, 4
+; RV32-NEXT: add a5, sp, a5
+; RV32-NEXT: addi a5, a5, 16
+; RV32-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s4
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a5, vlenb
+; RV32-NEXT: slli a5, a5, 3
+; RV32-NEXT: add a5, sp, a5
+; RV32-NEXT: addi a5, a5, 16
+; RV32-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s5
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: addi a5, sp, 16
+; RV32-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s7
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vand.vx v16, v8, s10
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a5, vlenb
+; RV32-NEXT: slli a5, a5, 2
+; RV32-NEXT: mv a6, a5
+; RV32-NEXT: slli a5, a5, 1
+; RV32-NEXT: add a5, a5, a6
+; RV32-NEXT: add a5, sp, a5
+; RV32-NEXT: addi a5, a5, 16
+; RV32-NEXT: vs4r.v v16, (a5) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, s11
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a5, vlenb
+; RV32-NEXT: slli a5, a5, 2
+; RV32-NEXT: add a5, sp, a5
+; RV32-NEXT: addi a5, a5, 16
+; RV32-NEXT: vs4r.v v16, (a5) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, s9
+; RV32-NEXT: vmul.vv v28, v8, v16
+; RV32-NEXT: vand.vx v16, v8, s8
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vand.vx v20, v8, s6
+; RV32-NEXT: vmul.vv v4, v8, v20
+; RV32-NEXT: vand.vx v20, v8, a0
+; RV32-NEXT: vmul.vv v20, v8, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v8, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v0, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v0, v8
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v0, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v0, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v0, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v0, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v0, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v0, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v0, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v24
+; RV32-NEXT: addi a0, sp, 16
+; RV32-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v24, v0, v24
+; RV32-NEXT: vxor.vv v12, v24, v12
+; RV32-NEXT: vsll.vi v8, v8, 24
+; RV32-NEXT: vand.vx v24, v0, a4
+; RV32-NEXT: vsll.vi v24, v24, 8
+; RV32-NEXT: vor.vv v8, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v12, v12, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v12, v12, v24
+; RV32-NEXT: vxor.vv v12, v12, v28
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: vsrl.vi v16, v0, 8
+; RV32-NEXT: vand.vx v16, v16, a4
+; RV32-NEXT: vxor.vv v12, v12, v4
+; RV32-NEXT: vxor.vv v12, v12, v20
+; RV32-NEXT: vsrl.vi v12, v12, 24
+; RV32-NEXT: vor.vv v12, v16, v12
+; RV32-NEXT: vor.vv v8, v8, v12
+; RV32-NEXT: vsrl.vi v12, v8, 4
+; RV32-NEXT: vand.vx v8, v8, a3
+; RV32-NEXT: vand.vx v12, v12, a3
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v12, v8
+; RV32-NEXT: vsrl.vi v12, v8, 2
+; RV32-NEXT: vand.vx v8, v8, a2
+; RV32-NEXT: vand.vx v12, v12, a2
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v8, v12, v8
+; RV32-NEXT: vsrl.vi v12, v8, 1
+; RV32-NEXT: vand.vx v8, v8, a1
+; RV32-NEXT: vand.vx v12, v12, a1
+; RV32-NEXT: vadd.vv v8, v8, v8
+; RV32-NEXT: vor.vv v8, v12, v8
+; RV32-NEXT: vsrl.vi v8, v8, 1
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add sp, sp, a0
+; RV32-NEXT: lw ra, 76(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s0, 72(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s1, 68(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s2, 64(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s3, 60(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s4, 56(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s5, 52(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s6, 48(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s7, 44(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s8, 40(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s9, 36(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s10, 32(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s11, 28(sp) # 4-byte Folded Reload
+; RV32-NEXT: addi sp, sp, 80
+; RV32-NEXT: ret
+;
+; RV64-LABEL: clmulh_nxv8i32:
+; RV64: # %bb.0:
+; RV64-NEXT: addi sp, sp, -144
+; RV64-NEXT: sd ra, 136(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s0, 128(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s1, 120(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s2, 112(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s3, 104(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s4, 96(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s5, 88(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s6, 80(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s7, 72(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s8, 64(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s9, 56(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s10, 48(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s11, 40(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: sub sp, sp, a0
+; RV64-NEXT: vsetvli a0, zero, e32, m4, ta, ma
+; RV64-NEXT: vsrl.vi v12, v8, 8
+; RV64-NEXT: lui a5, 16
+; RV64-NEXT: vsrl.vi v16, v8, 24
+; RV64-NEXT: vsll.vi v20, v8, 24
+; RV64-NEXT: lui a1, 61681
+; RV64-NEXT: lui a2, 209715
+; RV64-NEXT: lui ra, 349525
+; RV64-NEXT: li s9, 16
+; RV64-NEXT: li s8, 32
+; RV64-NEXT: li s6, 64
+; RV64-NEXT: li a7, 512
+; RV64-NEXT: li t0, 1024
+; RV64-NEXT: li a0, 1
+; RV64-NEXT: lui t1, 1
+; RV64-NEXT: lui t2, 2
+; RV64-NEXT: lui t3, 4
+; RV64-NEXT: lui t4, 8
+; RV64-NEXT: lui t5, 32
+; RV64-NEXT: lui t6, 64
+; RV64-NEXT: lui s0, 128
+; RV64-NEXT: lui s1, 256
+; RV64-NEXT: lui s2, 512
+; RV64-NEXT: lui s3, 1024
+; RV64-NEXT: lui s4, 2048
+; RV64-NEXT: lui s5, 4096
+; RV64-NEXT: lui s7, 8192
+; RV64-NEXT: lui s10, 16384
+; RV64-NEXT: lui s11, 32768
+; RV64-NEXT: addi a4, a5, -256
+; RV64-NEXT: addi a3, a1, -241
+; RV64-NEXT: addi a2, a2, 819
+; RV64-NEXT: addi a1, ra, 1365
+; RV64-NEXT: vand.vx v12, v12, a4
+; RV64-NEXT: vand.vx v8, v8, a4
+; RV64-NEXT: vor.vv v12, v12, v16
+; RV64-NEXT: vsll.vi v8, v8, 8
+; RV64-NEXT: vor.vv v8, v20, v8
+; RV64-NEXT: vor.vv v8, v8, v12
+; RV64-NEXT: vsrl.vi v12, v8, 4
+; RV64-NEXT: vand.vx v8, v8, a3
+; RV64-NEXT: vand.vx v12, v12, a3
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vsrl.vi v12, v8, 2
+; RV64-NEXT: vand.vx v8, v8, a2
+; RV64-NEXT: vand.vx v12, v12, a2
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vsrl.vi v12, v8, 1
+; RV64-NEXT: vand.vx v8, v8, a1
+; RV64-NEXT: vand.vx v12, v12, a1
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vand.vx v12, v8, s9
+; RV64-NEXT: lui s9, 65536
+; RV64-NEXT: vand.vx v16, v8, s8
+; RV64-NEXT: lui s8, 131072
+; RV64-NEXT: vand.vx v20, v8, s6
+; RV64-NEXT: lui s6, 262144
+; RV64-NEXT: slli ra, a0, 11
+; RV64-NEXT: vand.vi v24, v8, 2
+; RV64-NEXT: vand.vi v28, v8, 1
+; RV64-NEXT: vand.vi v4, v8, 4
+; RV64-NEXT: vand.vi v0, v8, 8
+; RV64-NEXT: vmul.vv v24, v8, v24
+; RV64-NEXT: sd a4, 8(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a4, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a4, a4, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs4r.v v24, (a0) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vmul.vv v24, v8, v28
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a4, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a4, a4, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs4r.v v24, (a0) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vmul.vv v24, v8, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: mv a4, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs4r.v v24, (a0) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vmul.vv v24, v8, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a4, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a4, a4, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a4, a4, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs4r.v v24, (a0) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a4, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a4, a4, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vmul.vv v12, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a4, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a4, a4, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vmul.vv v12, v8, v20
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a4, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui a0, 524288
+; RV64-NEXT: li a6, 128
+; RV64-NEXT: vand.vx v12, v8, a6
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a4, vlenb
+; RV64-NEXT: slli a4, a4, 2
+; RV64-NEXT: mv a6, a4
+; RV64-NEXT: slli a4, a4, 1
+; RV64-NEXT: add a6, a6, a4
+; RV64-NEXT: slli a4, a4, 3
+; RV64-NEXT: add a4, a4, a6
+; RV64-NEXT: add a4, sp, a4
+; RV64-NEXT: addi a4, a4, 32
+; RV64-NEXT: vs4r.v v12, (a4) # vscale x 32-byte Folded Spill
+; RV64-NEXT: li a6, 256
+; RV64-NEXT: vand.vx v12, v8, a6
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a6, vlenb
+; RV64-NEXT: slli a6, a6, 3
+; RV64-NEXT: mv a4, a6
+; RV64-NEXT: slli a6, a6, 3
+; RV64-NEXT: add a6, a6, a4
+; RV64-NEXT: ld a4, 8(sp) # 8-byte Folded Reload
+; RV64-NEXT: add a6, sp, a6
+; RV64-NEXT: addi a6, a6, 32
+; RV64-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, a7
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a6, vlenb
+; RV64-NEXT: slli a6, a6, 2
+; RV64-NEXT: mv a7, a6
+; RV64-NEXT: slli a6, a6, 4
+; RV64-NEXT: add a6, a6, a7
+; RV64-NEXT: add a6, sp, a6
+; RV64-NEXT: addi a6, a6, 32
+; RV64-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t0
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a6, vlenb
+; RV64-NEXT: slli a6, a6, 6
+; RV64-NEXT: add a6, sp, a6
+; RV64-NEXT: addi a6, a6, 32
+; RV64-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, ra
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a6, vlenb
+; RV64-NEXT: slli a6, a6, 2
+; RV64-NEXT: mv a7, a6
+; RV64-NEXT: slli a6, a6, 1
+; RV64-NEXT: add a7, a7, a6
+; RV64-NEXT: slli a6, a6, 1
+; RV64-NEXT: add a7, a7, a6
+; RV64-NEXT: slli a6, a6, 1
+; RV64-NEXT: add a6, a6, a7
+; RV64-NEXT: add a6, sp, a6
+; RV64-NEXT: addi a6, a6, 32
+; RV64-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t1
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a6, vlenb
+; RV64-NEXT: slli a6, a6, 3
+; RV64-NEXT: mv a7, a6
+; RV64-NEXT: slli a6, a6, 1
+; RV64-NEXT: add a7, a7, a6
+; RV64-NEXT: slli a6, a6, 1
+; RV64-NEXT: add a6, a6, a7
+; RV64-NEXT: add a6, sp, a6
+; RV64-NEXT: addi a6, a6, 32
+; RV64-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t2
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a6, vlenb
+; RV64-NEXT: slli a6, a6, 2
+; RV64-NEXT: mv a7, a6
+; RV64-NEXT: slli a6, a6, 2
+; RV64-NEXT: add a7, a7, a6
+; RV64-NEXT: slli a6, a6, 1
+; RV64-NEXT: add a6, a6, a7
+; RV64-NEXT: add a6, sp, a6
+; RV64-NEXT: addi a6, a6, 32
+; RV64-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t3
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a6, vlenb
+; RV64-NEXT: slli a6, a6, 4
+; RV64-NEXT: mv a7, a6
+; RV64-NEXT: slli a6, a6, 1
+; RV64-NEXT: add a6, a6, a7
+; RV64-NEXT: add a6, sp, a6
+; RV64-NEXT: addi a6, a6, 32
+; RV64-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t4
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a6, vlenb
+; RV64-NEXT: slli a6, a6, 2
+; RV64-NEXT: mv a7, a6
+; RV64-NEXT: slli a6, a6, 1
+; RV64-NEXT: add a7, a7, a6
+; RV64-NEXT: slli a6, a6, 2
+; RV64-NEXT: add a6, a6, a7
+; RV64-NEXT: add a6, sp, a6
+; RV64-NEXT: addi a6, a6, 32
+; RV64-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, a5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv a6, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, a6
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 32
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv a6, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, a5, a6
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 32
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t6
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 32
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s0
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv a6, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a6, a6, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, a6
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 32
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s1
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv a6, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, a6
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 32
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s2
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv a6, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, a6
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 32
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s3
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 32
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s4
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 32
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: addi a5, sp, 32
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s7
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: vand.vx v16, v8, s10
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv a6, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, a6
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 32
+; RV64-NEXT: vs4r.v v16, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, s11
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 32
+; RV64-NEXT: vs4r.v v16, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, s9
+; RV64-NEXT: vmul.vv v28, v8, v16
+; RV64-NEXT: vand.vx v16, v8, s8
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: vand.vx v20, v8, s6
+; RV64-NEXT: vmul.vv v4, v8, v20
+; RV64-NEXT: vand.vx v20, v8, a0
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v8, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v0, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v0, v8
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v0, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v0, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v0, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v0, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v0, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v0, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v0, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v8, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v24
+; RV64-NEXT: addi a0, sp, 32
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v0, v24
+; RV64-NEXT: vxor.vv v12, v24, v12
+; RV64-NEXT: vsll.vi v8, v8, 24
+; RV64-NEXT: vand.vx v24, v0, a4
+; RV64-NEXT: vsll.vi v24, v24, 8
+; RV64-NEXT: vor.vv v8, v8, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v12, v12, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v12, v12, v24
+; RV64-NEXT: vxor.vv v12, v12, v28
+; RV64-NEXT: vxor.vv v12, v12, v16
+; RV64-NEXT: vsrl.vi v16, v0, 8
+; RV64-NEXT: vand.vx v16, v16, a4
+; RV64-NEXT: vxor.vv v12, v12, v4
+; RV64-NEXT: vxor.vv v12, v12, v20
+; RV64-NEXT: vsrl.vi v12, v12, 24
+; RV64-NEXT: vor.vv v12, v16, v12
+; RV64-NEXT: vor.vv v8, v8, v12
+; RV64-NEXT: vsrl.vi v12, v8, 4
+; RV64-NEXT: vand.vx v8, v8, a3
+; RV64-NEXT: vand.vx v12, v12, a3
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vsrl.vi v12, v8, 2
+; RV64-NEXT: vand.vx v8, v8, a2
+; RV64-NEXT: vand.vx v12, v12, a2
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vsrl.vi v12, v8, 1
+; RV64-NEXT: vand.vx v8, v8, a1
+; RV64-NEXT: vand.vx v12, v12, a1
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vsrl.vi v8, v8, 1
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add sp, sp, a0
+; RV64-NEXT: ld ra, 136(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s0, 128(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s1, 120(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s2, 112(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s3, 104(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s4, 96(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s5, 88(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s6, 80(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s7, 72(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s8, 64(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s9, 56(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s10, 48(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s11, 40(sp) # 8-byte Folded Reload
+; RV64-NEXT: addi sp, sp, 144
+; RV64-NEXT: ret
+ %a = call <vscale x 8 x i32> @llvm.clmulh.nxv8i32(<vscale x 8 x i32> %x, <vscale x 8 x i32> %x)
+ ret <vscale x 8 x i32> %a
+}
+
+define <vscale x 16 x i32> @clmulh_nxv16i32(<vscale x 16 x i32> %x, <vscale x 16 x i32> %y) nounwind {
+; RV32-LABEL: clmulh_nxv16i32:
+; RV32: # %bb.0:
+; RV32-NEXT: addi sp, sp, -80
+; RV32-NEXT: sw ra, 76(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s0, 72(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s1, 68(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s2, 64(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s3, 60(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s4, 56(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s5, 52(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s6, 48(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s7, 44(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s8, 40(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s9, 36(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s10, 32(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s11, 28(sp) # 4-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: sub sp, sp, a0
+; RV32-NEXT: vsetvli a0, zero, e32, m8, ta, ma
+; RV32-NEXT: vsrl.vi v16, v8, 8
+; RV32-NEXT: lui a5, 16
+; RV32-NEXT: vsrl.vi v24, v8, 24
+; RV32-NEXT: vsll.vi v0, v8, 24
+; RV32-NEXT: lui a1, 61681
+; RV32-NEXT: lui a2, 209715
+; RV32-NEXT: lui ra, 349525
+; RV32-NEXT: li t5, 16
+; RV32-NEXT: li t2, 32
+; RV32-NEXT: li a7, 64
+; RV32-NEXT: li t0, 512
+; RV32-NEXT: li t1, 1024
+; RV32-NEXT: li a0, 1
+; RV32-NEXT: lui t3, 1
+; RV32-NEXT: lui t4, 2
+; RV32-NEXT: lui t6, 4
+; RV32-NEXT: lui s0, 8
+; RV32-NEXT: lui s1, 32
+; RV32-NEXT: lui s2, 64
+; RV32-NEXT: lui s3, 128
+; RV32-NEXT: lui s4, 256
+; RV32-NEXT: lui s5, 512
+; RV32-NEXT: lui s6, 1024
+; RV32-NEXT: lui s7, 2048
+; RV32-NEXT: lui s8, 4096
+; RV32-NEXT: lui s9, 8192
+; RV32-NEXT: lui s10, 16384
+; RV32-NEXT: lui s11, 32768
+; RV32-NEXT: addi a4, a5, -256
+; RV32-NEXT: addi a3, a1, -241
+; RV32-NEXT: addi a2, a2, 819
+; RV32-NEXT: addi a1, ra, 1365
+; RV32-NEXT: slli a0, a0, 11
+; RV32-NEXT: vand.vx v16, v16, a4
+; RV32-NEXT: vand.vx v8, v8, a4
+; RV32-NEXT: vor.vv v16, v16, v24
+; RV32-NEXT: vsll.vi v8, v8, 8
+; RV32-NEXT: vor.vv v8, v0, v8
+; RV32-NEXT: vor.vv v8, v8, v16
+; RV32-NEXT: vsrl.vi v16, v8, 4
+; RV32-NEXT: vand.vx v8, v8, a3
+; RV32-NEXT: vand.vx v16, v16, a3
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v16, v8
+; RV32-NEXT: vsrl.vi v16, v8, 2
+; RV32-NEXT: vand.vx v8, v8, a2
+; RV32-NEXT: vand.vx v16, v16, a2
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v8, v16, v8
+; RV32-NEXT: vsrl.vi v16, v8, 1
+; RV32-NEXT: vand.vx v8, v8, a1
+; RV32-NEXT: vand.vx v16, v16, a1
+; RV32-NEXT: vadd.vv v8, v8, v8
+; RV32-NEXT: vor.vv v8, v16, v8
+; RV32-NEXT: vand.vi v16, v8, 2
+; RV32-NEXT: vand.vi v24, v8, 1
+; RV32-NEXT: vand.vi v0, v8, 4
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: sw a0, 4(sp) # 4-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a6, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a6, a6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a6, a6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: vand.vi v16, v8, 8
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a6, a6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: lui ra, 65536
+; RV32-NEXT: vand.vx v16, v8, t5
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a6, a6, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a6, a6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: lui t5, 131072
+; RV32-NEXT: vand.vx v16, v8, t2
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a6, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a6, a6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: lui t2, 262144
+; RV32-NEXT: vand.vx v16, v8, a7
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a6, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a6, a6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: lui a7, 524288
+; RV32-NEXT: li a6, 128
+; RV32-NEXT: vand.vx v16, v8, a6
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: mv a6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: li a6, 256
+; RV32-NEXT: vand.vx v16, v8, a6
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 3
+; RV32-NEXT: mv a0, a6
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: add a0, a0, a6
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: add a0, a0, a6
+; RV32-NEXT: slli a6, a6, 2
+; RV32-NEXT: add a6, a6, a0
+; RV32-NEXT: lw a0, 4(sp) # 4-byte Folded Reload
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 16
+; RV32-NEXT: vs8r.v v16, (a6) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, t0
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 4
+; RV32-NEXT: mv t0, a6
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: add t0, t0, a6
+; RV32-NEXT: slli a6, a6, 2
+; RV32-NEXT: add a6, a6, t0
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 16
+; RV32-NEXT: vs8r.v v16, (a6) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, t1
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 3
+; RV32-NEXT: mv t0, a6
+; RV32-NEXT: slli a6, a6, 2
+; RV32-NEXT: add t0, t0, a6
+; RV32-NEXT: slli a6, a6, 2
+; RV32-NEXT: add a6, a6, t0
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 16
+; RV32-NEXT: vs8r.v v16, (a6) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, a0
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a6, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, t3
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a6, a6, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, t4
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a6, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, t6
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a6, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, s0
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 7
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, a5
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, s1
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, s2
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, s3
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, s4
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, s5
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, s6
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, s7
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, s8
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, s9
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, s10
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, s11
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, ra
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, t5
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, t2
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, a7
+; RV32-NEXT: vmul.vv v8, v8, v16
+; RV32-NEXT: addi a0, sp, 16
+; RV32-NEXT: vs8r.v v8, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v8, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v24, v8
+; RV32-NEXT: vxor.vv v8, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v8, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v16, v8
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 7
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v24
+; RV32-NEXT: vsll.vi v16, v16, 24
+; RV32-NEXT: vand.vx v24, v8, a4
+; RV32-NEXT: vsll.vi v24, v24, 8
+; RV32-NEXT: vor.vv v16, v16, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v24, v0, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v0, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v24, v24, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v0, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v24, v24, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v0, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v24, v24, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl8r.v v0, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v24, v24, v0
+; RV32-NEXT: addi a0, sp, 16
+; RV32-NEXT: vl8r.v v0, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v24, v24, v0
+; RV32-NEXT: vsrl.vi v8, v8, 8
+; RV32-NEXT: vand.vx v8, v8, a4
+; RV32-NEXT: vsrl.vi v24, v24, 24
+; RV32-NEXT: vor.vv v8, v8, v24
+; RV32-NEXT: vor.vv v8, v16, v8
+; RV32-NEXT: vsrl.vi v16, v8, 4
+; RV32-NEXT: vand.vx v8, v8, a3
+; RV32-NEXT: vand.vx v16, v16, a3
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v16, v8
+; RV32-NEXT: vsrl.vi v16, v8, 2
+; RV32-NEXT: vand.vx v8, v8, a2
+; RV32-NEXT: vand.vx v16, v16, a2
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v8, v16, v8
+; RV32-NEXT: vsrl.vi v16, v8, 1
+; RV32-NEXT: vand.vx v8, v8, a1
+; RV32-NEXT: vand.vx v16, v16, a1
+; RV32-NEXT: vadd.vv v8, v8, v8
+; RV32-NEXT: vor.vv v8, v16, v8
+; RV32-NEXT: vsrl.vi v8, v8, 1
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add sp, sp, a0
+; RV32-NEXT: lw ra, 76(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s0, 72(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s1, 68(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s2, 64(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s3, 60(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s4, 56(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s5, 52(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s6, 48(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s7, 44(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s8, 40(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s9, 36(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s10, 32(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s11, 28(sp) # 4-byte Folded Reload
+; RV32-NEXT: addi sp, sp, 80
+; RV32-NEXT: ret
+;
+; RV64-LABEL: clmulh_nxv16i32:
+; RV64: # %bb.0:
+; RV64-NEXT: addi sp, sp, -144
+; RV64-NEXT: sd ra, 136(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s0, 128(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s1, 120(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s2, 112(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s3, 104(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s4, 96(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s5, 88(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s6, 80(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s7, 72(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s8, 64(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s9, 56(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s10, 48(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s11, 40(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: sub sp, sp, a0
+; RV64-NEXT: vsetvli a0, zero, e32, m8, ta, ma
+; RV64-NEXT: vsrl.vi v16, v8, 8
+; RV64-NEXT: lui a5, 16
+; RV64-NEXT: vsrl.vi v24, v8, 24
+; RV64-NEXT: vsll.vi v0, v8, 24
+; RV64-NEXT: lui a1, 61681
+; RV64-NEXT: lui a2, 209715
+; RV64-NEXT: lui ra, 349525
+; RV64-NEXT: li t5, 16
+; RV64-NEXT: li t2, 32
+; RV64-NEXT: li a7, 64
+; RV64-NEXT: li t0, 512
+; RV64-NEXT: li t1, 1024
+; RV64-NEXT: li a0, 1
+; RV64-NEXT: lui t3, 1
+; RV64-NEXT: lui t4, 2
+; RV64-NEXT: lui t6, 4
+; RV64-NEXT: lui s0, 8
+; RV64-NEXT: lui s1, 32
+; RV64-NEXT: lui s2, 64
+; RV64-NEXT: lui s3, 128
+; RV64-NEXT: lui s4, 256
+; RV64-NEXT: lui s5, 512
+; RV64-NEXT: lui s6, 1024
+; RV64-NEXT: lui s7, 2048
+; RV64-NEXT: lui s8, 4096
+; RV64-NEXT: lui s9, 8192
+; RV64-NEXT: lui s10, 16384
+; RV64-NEXT: lui s11, 32768
+; RV64-NEXT: addi a4, a5, -256
+; RV64-NEXT: addi a3, a1, -241
+; RV64-NEXT: addi a2, a2, 819
+; RV64-NEXT: addi a1, ra, 1365
+; RV64-NEXT: slli a0, a0, 11
+; RV64-NEXT: vand.vx v16, v16, a4
+; RV64-NEXT: vand.vx v8, v8, a4
+; RV64-NEXT: vor.vv v16, v16, v24
+; RV64-NEXT: vsll.vi v8, v8, 8
+; RV64-NEXT: vor.vv v8, v0, v8
+; RV64-NEXT: vor.vv v8, v8, v16
+; RV64-NEXT: vsrl.vi v16, v8, 4
+; RV64-NEXT: vand.vx v8, v8, a3
+; RV64-NEXT: vand.vx v16, v16, a3
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v16, v8
+; RV64-NEXT: vsrl.vi v16, v8, 2
+; RV64-NEXT: vand.vx v8, v8, a2
+; RV64-NEXT: vand.vx v16, v16, a2
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v16, v8
+; RV64-NEXT: vsrl.vi v16, v8, 1
+; RV64-NEXT: vand.vx v8, v8, a1
+; RV64-NEXT: vand.vx v16, v16, a1
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v16, v8
+; RV64-NEXT: vand.vi v16, v8, 2
+; RV64-NEXT: vand.vi v24, v8, 1
+; RV64-NEXT: vand.vi v0, v8, 4
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: sd a0, 8(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a6, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a6, a6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a6, a6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vmul.vv v24, v8, v24
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vand.vi v16, v8, 8
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: mv a6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a6, a6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: lui ra, 65536
+; RV64-NEXT: vand.vx v16, v8, t5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a6, a6, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a6, a6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: lui t5, 131072
+; RV64-NEXT: vand.vx v16, v8, t2
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a6, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a6, a6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: lui t2, 262144
+; RV64-NEXT: vand.vx v16, v8, a7
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a6, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a6, a6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: lui a7, 524288
+; RV64-NEXT: li a6, 128
+; RV64-NEXT: vand.vx v16, v8, a6
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 6
+; RV64-NEXT: mv a6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: li a6, 256
+; RV64-NEXT: vand.vx v16, v8, a6
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a6, vlenb
+; RV64-NEXT: slli a6, a6, 3
+; RV64-NEXT: mv a0, a6
+; RV64-NEXT: slli a6, a6, 1
+; RV64-NEXT: add a0, a0, a6
+; RV64-NEXT: slli a6, a6, 1
+; RV64-NEXT: add a0, a0, a6
+; RV64-NEXT: slli a6, a6, 2
+; RV64-NEXT: add a6, a6, a0
+; RV64-NEXT: ld a0, 8(sp) # 8-byte Folded Reload
+; RV64-NEXT: add a6, sp, a6
+; RV64-NEXT: addi a6, a6, 32
+; RV64-NEXT: vs8r.v v16, (a6) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, t0
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a6, vlenb
+; RV64-NEXT: slli a6, a6, 4
+; RV64-NEXT: mv t0, a6
+; RV64-NEXT: slli a6, a6, 1
+; RV64-NEXT: add t0, t0, a6
+; RV64-NEXT: slli a6, a6, 2
+; RV64-NEXT: add a6, a6, t0
+; RV64-NEXT: add a6, sp, a6
+; RV64-NEXT: addi a6, a6, 32
+; RV64-NEXT: vs8r.v v16, (a6) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, t1
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a6, vlenb
+; RV64-NEXT: slli a6, a6, 3
+; RV64-NEXT: mv t0, a6
+; RV64-NEXT: slli a6, a6, 2
+; RV64-NEXT: add t0, t0, a6
+; RV64-NEXT: slli a6, a6, 2
+; RV64-NEXT: add a6, a6, t0
+; RV64-NEXT: add a6, sp, a6
+; RV64-NEXT: addi a6, a6, 32
+; RV64-NEXT: vs8r.v v16, (a6) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, a0
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: mv a6, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, t3
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a6, a6, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, t4
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a6, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, t6
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a6, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, a0, a6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, s0
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 7
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, a5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, s1
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, s2
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, s3
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, s4
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, s6
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, s7
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, s8
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, s9
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, s10
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, s11
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, ra
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, t5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, t2
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, a7
+; RV64-NEXT: vmul.vv v8, v8, v16
+; RV64-NEXT: addi a0, sp, 32
+; RV64-NEXT: vs8r.v v8, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v8, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v24, v8
+; RV64-NEXT: vxor.vv v8, v8, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 6
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v8, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v16, v8
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 7
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v8, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v24
+; RV64-NEXT: vsll.vi v16, v16, 24
+; RV64-NEXT: vand.vx v24, v8, a4
+; RV64-NEXT: vsll.vi v24, v24, 8
+; RV64-NEXT: vor.vv v16, v16, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v0, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v0, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v0, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v0, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl8r.v v0, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: addi a0, sp, 32
+; RV64-NEXT: vl8r.v v0, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vsrl.vi v8, v8, 8
+; RV64-NEXT: vand.vx v8, v8, a4
+; RV64-NEXT: vsrl.vi v24, v24, 24
+; RV64-NEXT: vor.vv v8, v8, v24
+; RV64-NEXT: vor.vv v8, v16, v8
+; RV64-NEXT: vsrl.vi v16, v8, 4
+; RV64-NEXT: vand.vx v8, v8, a3
+; RV64-NEXT: vand.vx v16, v16, a3
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v16, v8
+; RV64-NEXT: vsrl.vi v16, v8, 2
+; RV64-NEXT: vand.vx v8, v8, a2
+; RV64-NEXT: vand.vx v16, v16, a2
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v16, v8
+; RV64-NEXT: vsrl.vi v16, v8, 1
+; RV64-NEXT: vand.vx v8, v8, a1
+; RV64-NEXT: vand.vx v16, v16, a1
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v16, v8
+; RV64-NEXT: vsrl.vi v8, v8, 1
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add sp, sp, a0
+; RV64-NEXT: ld ra, 136(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s0, 128(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s1, 120(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s2, 112(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s3, 104(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s4, 96(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s5, 88(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s6, 80(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s7, 72(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s8, 64(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s9, 56(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s10, 48(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s11, 40(sp) # 8-byte Folded Reload
+; RV64-NEXT: addi sp, sp, 144
+; RV64-NEXT: ret
+ %a = call <vscale x 16 x i32> @llvm.clmulh.nxv16i32(<vscale x 16 x i32> %x, <vscale x 16 x i32> %y)
+ ret <vscale x 16 x i32> %a
+}
+
+define <vscale x 1 x i64> @clmulh_nxv1i64(<vscale x 1 x i64> %x, <vscale x 1 x i64> %y) nounwind {
+; RV32-LABEL: clmulh_nxv1i64:
+; RV32: # %bb.0:
+; RV32-NEXT: addi sp, sp, -352
+; RV32-NEXT: sw ra, 348(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s0, 344(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s1, 340(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s2, 336(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s3, 332(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s4, 328(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s5, 324(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s6, 320(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s7, 316(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s8, 312(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s9, 308(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s10, 304(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s11, 300(sp) # 4-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: sub sp, sp, a0
+; RV32-NEXT: lui s7, 1044480
+; RV32-NEXT: lui a7, 524288
+; RV32-NEXT: li s11, 1
+; RV32-NEXT: li s8, 2
+; RV32-NEXT: li s9, 4
+; RV32-NEXT: li s10, 8
+; RV32-NEXT: li a3, 16
+; RV32-NEXT: li a4, 32
+; RV32-NEXT: li a5, 64
+; RV32-NEXT: li a6, 128
+; RV32-NEXT: li ra, 256
+; RV32-NEXT: li a0, 512
+; RV32-NEXT: li a1, 1024
+; RV32-NEXT: lui a2, 1
+; RV32-NEXT: lui t0, 2
+; RV32-NEXT: lui t1, 4
+; RV32-NEXT: lui t2, 8
+; RV32-NEXT: lui t3, 16
+; RV32-NEXT: lui t4, 32
+; RV32-NEXT: lui t5, 64
+; RV32-NEXT: lui t6, 128
+; RV32-NEXT: lui s0, 256
+; RV32-NEXT: lui s1, 512
+; RV32-NEXT: lui s2, 1024
+; RV32-NEXT: lui s3, 2048
+; RV32-NEXT: lui s4, 4096
+; RV32-NEXT: lui s5, 8192
+; RV32-NEXT: lui s6, 16384
+; RV32-NEXT: sw s7, 272(sp)
+; RV32-NEXT: lui s7, 32768
+; RV32-NEXT: sw zero, 276(sp)
+; RV32-NEXT: sw a7, 264(sp)
+; RV32-NEXT: sw zero, 268(sp)
+; RV32-NEXT: sw zero, 256(sp)
+; RV32-NEXT: sw s11, 260(sp)
+; RV32-NEXT: sw zero, 248(sp)
+; RV32-NEXT: sw s8, 252(sp)
+; RV32-NEXT: lui s8, 65536
+; RV32-NEXT: sw zero, 240(sp)
+; RV32-NEXT: sw s9, 244(sp)
+; RV32-NEXT: lui s9, 131072
+; RV32-NEXT: sw zero, 232(sp)
+; RV32-NEXT: sw s10, 236(sp)
+; RV32-NEXT: lui s10, 262144
+; RV32-NEXT: sw zero, 224(sp)
+; RV32-NEXT: sw a3, 228(sp)
+; RV32-NEXT: sw zero, 216(sp)
+; RV32-NEXT: sw a4, 220(sp)
+; RV32-NEXT: sw zero, 208(sp)
+; RV32-NEXT: sw a5, 212(sp)
+; RV32-NEXT: sw zero, 200(sp)
+; RV32-NEXT: sw a6, 204(sp)
+; RV32-NEXT: sw zero, 192(sp)
+; RV32-NEXT: sw ra, 196(sp)
+; RV32-NEXT: sw zero, 184(sp)
+; RV32-NEXT: sw a0, 188(sp)
+; RV32-NEXT: sw zero, 176(sp)
+; RV32-NEXT: sw a1, 180(sp)
+; RV32-NEXT: slli s11, s11, 11
+; RV32-NEXT: sw zero, 168(sp)
+; RV32-NEXT: sw s11, 172(sp)
+; RV32-NEXT: sw zero, 160(sp)
+; RV32-NEXT: sw a2, 164(sp)
+; RV32-NEXT: sw zero, 152(sp)
+; RV32-NEXT: sw t0, 156(sp)
+; RV32-NEXT: sw zero, 144(sp)
+; RV32-NEXT: sw t1, 148(sp)
+; RV32-NEXT: sw zero, 136(sp)
+; RV32-NEXT: sw t2, 140(sp)
+; RV32-NEXT: sw zero, 128(sp)
+; RV32-NEXT: sw t3, 132(sp)
+; RV32-NEXT: sw zero, 120(sp)
+; RV32-NEXT: sw t4, 124(sp)
+; RV32-NEXT: sw zero, 112(sp)
+; RV32-NEXT: sw t5, 116(sp)
+; RV32-NEXT: sw zero, 104(sp)
+; RV32-NEXT: sw t6, 108(sp)
+; RV32-NEXT: sw zero, 96(sp)
+; RV32-NEXT: sw s0, 100(sp)
+; RV32-NEXT: sw zero, 88(sp)
+; RV32-NEXT: sw s1, 92(sp)
+; RV32-NEXT: sw zero, 80(sp)
+; RV32-NEXT: sw s2, 84(sp)
+; RV32-NEXT: sw zero, 72(sp)
+; RV32-NEXT: sw s3, 76(sp)
+; RV32-NEXT: sw zero, 64(sp)
+; RV32-NEXT: sw s4, 68(sp)
+; RV32-NEXT: sw zero, 56(sp)
+; RV32-NEXT: sw s5, 60(sp)
+; RV32-NEXT: sw zero, 48(sp)
+; RV32-NEXT: sw s6, 52(sp)
+; RV32-NEXT: sw zero, 40(sp)
+; RV32-NEXT: sw s7, 44(sp)
+; RV32-NEXT: sw zero, 32(sp)
+; RV32-NEXT: sw s8, 36(sp)
+; RV32-NEXT: sw zero, 24(sp)
+; RV32-NEXT: sw s9, 28(sp)
+; RV32-NEXT: sw zero, 16(sp)
+; RV32-NEXT: sw s10, 20(sp)
+; RV32-NEXT: sw zero, 8(sp)
+; RV32-NEXT: sw a7, 12(sp)
+; RV32-NEXT: lui a0, 61681
+; RV32-NEXT: addi a0, a0, -241
+; RV32-NEXT: vsetvli a1, zero, e32, m1, ta, ma
+; RV32-NEXT: vmv.v.x v3, a0
+; RV32-NEXT: lui a0, 209715
+; RV32-NEXT: addi a0, a0, 819
+; RV32-NEXT: vmv.v.x v2, a0
+; RV32-NEXT: lui a0, 349525
+; RV32-NEXT: addi a0, a0, 1365
+; RV32-NEXT: vmv.v.x v1, a0
+; RV32-NEXT: addi a0, sp, 272
+; RV32-NEXT: vsetvli a1, zero, e64, m1, ta, ma
+; RV32-NEXT: vlse64.v v0, (a0), zero
+; RV32-NEXT: addi a0, sp, 264
+; RV32-NEXT: vlse64.v v13, (a0), zero
+; RV32-NEXT: addi a0, sp, 256
+; RV32-NEXT: vlse64.v v14, (a0), zero
+; RV32-NEXT: addi a0, sp, 248
+; RV32-NEXT: vlse64.v v15, (a0), zero
+; RV32-NEXT: addi a0, sp, 240
+; RV32-NEXT: vlse64.v v16, (a0), zero
+; RV32-NEXT: addi a0, sp, 232
+; RV32-NEXT: vlse64.v v17, (a0), zero
+; RV32-NEXT: addi a0, sp, 224
+; RV32-NEXT: vlse64.v v18, (a0), zero
+; RV32-NEXT: addi a0, sp, 216
+; RV32-NEXT: vlse64.v v19, (a0), zero
+; RV32-NEXT: addi a0, sp, 208
+; RV32-NEXT: vlse64.v v20, (a0), zero
+; RV32-NEXT: addi a0, sp, 200
+; RV32-NEXT: vlse64.v v21, (a0), zero
+; RV32-NEXT: addi a0, sp, 192
+; RV32-NEXT: vlse64.v v22, (a0), zero
+; RV32-NEXT: addi a0, sp, 184
+; RV32-NEXT: vlse64.v v23, (a0), zero
+; RV32-NEXT: addi a0, sp, 176
+; RV32-NEXT: vlse64.v v24, (a0), zero
+; RV32-NEXT: addi a0, sp, 168
+; RV32-NEXT: vlse64.v v25, (a0), zero
+; RV32-NEXT: addi a0, sp, 160
+; RV32-NEXT: vlse64.v v26, (a0), zero
+; RV32-NEXT: addi a0, sp, 152
+; RV32-NEXT: vlse64.v v9, (a0), zero
+; RV32-NEXT: addi a0, sp, 144
+; RV32-NEXT: vlse64.v v10, (a0), zero
+; RV32-NEXT: addi a0, sp, 136
+; RV32-NEXT: vlse64.v v29, (a0), zero
+; RV32-NEXT: addi a0, sp, 128
+; RV32-NEXT: vlse64.v v30, (a0), zero
+; RV32-NEXT: addi a0, sp, 120
+; RV32-NEXT: vlse64.v v31, (a0), zero
+; RV32-NEXT: addi a0, sp, 112
+; RV32-NEXT: vlse64.v v11, (a0), zero
+; RV32-NEXT: addi a0, sp, 104
+; RV32-NEXT: vlse64.v v12, (a0), zero
+; RV32-NEXT: addi a0, sp, 96
+; RV32-NEXT: vlse64.v v5, (a0), zero
+; RV32-NEXT: addi a0, sp, 88
+; RV32-NEXT: vlse64.v v4, (a0), zero
+; RV32-NEXT: li a6, 56
+; RV32-NEXT: vsrl.vi v27, v8, 24
+; RV32-NEXT: vsrl.vx v28, v8, a6
+; RV32-NEXT: li ra, 40
+; RV32-NEXT: vsrl.vx v7, v8, ra
+; RV32-NEXT: vsll.vx v6, v8, a6
+; RV32-NEXT: addi a4, t3, -256
+; RV32-NEXT: vand.vx v7, v7, a4
+; RV32-NEXT: vor.vv v28, v7, v28
+; RV32-NEXT: vand.vx v7, v8, a4
+; RV32-NEXT: vsll.vx v7, v7, ra
+; RV32-NEXT: vor.vv v7, v6, v7
+; RV32-NEXT: vsrl.vi v6, v8, 8
+; RV32-NEXT: lui a5, 4080
+; RV32-NEXT: vand.vx v27, v27, a5
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v0, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v6, v6, v0
+; RV32-NEXT: vor.vv v27, v6, v27
+; RV32-NEXT: addi a3, sp, 80
+; RV32-NEXT: vlse64.v v6, (a3), zero
+; RV32-NEXT: vor.vv v27, v27, v28
+; RV32-NEXT: vand.vx v28, v8, a5
+; RV32-NEXT: vsll.vi v28, v28, 24
+; RV32-NEXT: vand.vv v8, v8, v0
+; RV32-NEXT: vsll.vi v8, v8, 8
+; RV32-NEXT: vor.vv v8, v28, v8
+; RV32-NEXT: addi a3, sp, 72
+; RV32-NEXT: vlse64.v v28, (a3), zero
+; RV32-NEXT: vor.vv v8, v7, v8
+; RV32-NEXT: addi a3, sp, 64
+; RV32-NEXT: vlse64.v v7, (a3), zero
+; RV32-NEXT: vor.vv v8, v8, v27
+; RV32-NEXT: vsrl.vi v27, v8, 4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v3, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v8, v8, v3
+; RV32-NEXT: vand.vv v27, v27, v3
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v27, v8
+; RV32-NEXT: vsrl.vi v27, v8, 2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v2, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v8, v8, v2
+; RV32-NEXT: vand.vv v27, v27, v2
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v8, v27, v8
+; RV32-NEXT: vsrl.vi v27, v8, 1
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v1, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v8, v8, v1
+; RV32-NEXT: vand.vv v27, v27, v1
+; RV32-NEXT: vadd.vv v8, v8, v8
+; RV32-NEXT: vor.vv v8, v27, v8
+; RV32-NEXT: addi a3, sp, 56
+; RV32-NEXT: vlse64.v v27, (a3), zero
+; RV32-NEXT: vand.vv v13, v8, v13
+; RV32-NEXT: vand.vv v14, v8, v14
+; RV32-NEXT: vand.vv v15, v8, v15
+; RV32-NEXT: vand.vv v16, v8, v16
+; RV32-NEXT: vand.vv v17, v8, v17
+; RV32-NEXT: vand.vv v18, v8, v18
+; RV32-NEXT: vand.vv v19, v8, v19
+; RV32-NEXT: vand.vv v20, v8, v20
+; RV32-NEXT: vand.vv v21, v8, v21
+; RV32-NEXT: vand.vv v22, v8, v22
+; RV32-NEXT: vand.vv v23, v8, v23
+; RV32-NEXT: vand.vv v24, v8, v24
+; RV32-NEXT: vand.vv v25, v8, v25
+; RV32-NEXT: vand.vv v26, v8, v26
+; RV32-NEXT: vand.vv v3, v8, v9
+; RV32-NEXT: vand.vv v2, v8, v10
+; RV32-NEXT: vand.vv v29, v8, v29
+; RV32-NEXT: vand.vv v30, v8, v30
+; RV32-NEXT: vand.vv v31, v8, v31
+; RV32-NEXT: vand.vv v0, v8, v11
+; RV32-NEXT: vand.vv v9, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v5, v8, v5
+; RV32-NEXT: vand.vv v4, v8, v4
+; RV32-NEXT: vand.vv v6, v8, v6
+; RV32-NEXT: vand.vv v9, v8, v28
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: addi a3, sp, 48
+; RV32-NEXT: addi a0, sp, 40
+; RV32-NEXT: vlse64.v v9, (a3), zero
+; RV32-NEXT: vlse64.v v10, (a0), zero
+; RV32-NEXT: vand.vv v11, v8, v7
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v11, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v11, v8, v27
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v11, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v9, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: addi a2, sp, 32
+; RV32-NEXT: addi a3, sp, 24
+; RV32-NEXT: addi a1, sp, 16
+; RV32-NEXT: addi a0, sp, 8
+; RV32-NEXT: vlse64.v v9, (a2), zero
+; RV32-NEXT: vlse64.v v10, (a3), zero
+; RV32-NEXT: vlse64.v v11, (a1), zero
+; RV32-NEXT: vlse64.v v12, (a0), zero
+; RV32-NEXT: vand.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 5
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v9, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v9, v8, v11
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 5
+; RV32-NEXT: sub a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v9, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vi v9, v8, 2
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vi v9, v8, 1
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vi v9, v8, 4
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vi v9, v8, 8
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: li a0, 16
+; RV32-NEXT: vand.vx v9, v8, a0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: li a0, 32
+; RV32-NEXT: vand.vx v9, v8, a0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: li a0, 64
+; RV32-NEXT: vand.vx v9, v8, a0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: li a0, 128
+; RV32-NEXT: vand.vx v9, v8, a0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: li a0, 256
+; RV32-NEXT: vand.vx v9, v8, a0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: li a0, 512
+; RV32-NEXT: vand.vx v9, v8, a0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: li a0, 1024
+; RV32-NEXT: vand.vx v9, v8, a0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s11
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: lui a0, 1
+; RV32-NEXT: vand.vx v9, v8, a0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, t0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 4
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, t1
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, t2
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 4
+; RV32-NEXT: sub a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, t3
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, t4
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, t5
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, t6
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s1
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 3
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s2
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s3
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 3
+; RV32-NEXT: sub a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s4
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s5
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 2
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s6
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s7
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 1
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s8
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s9
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v1, v8, s10
+; RV32-NEXT: vmul.vv v1, v8, v1
+; RV32-NEXT: vmul.vv v9, v8, v13
+; RV32-NEXT: addi a0, sp, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vmul.vv v10, v8, v14
+; RV32-NEXT: vmul.vv v11, v8, v15
+; RV32-NEXT: vmul.vv v12, v8, v16
+; RV32-NEXT: vmul.vv v13, v8, v17
+; RV32-NEXT: vmul.vv v14, v8, v18
+; RV32-NEXT: vmul.vv v15, v8, v19
+; RV32-NEXT: vmul.vv v16, v8, v20
+; RV32-NEXT: vmul.vv v17, v8, v21
+; RV32-NEXT: vmul.vv v18, v8, v22
+; RV32-NEXT: vmul.vv v19, v8, v23
+; RV32-NEXT: vmul.vv v20, v8, v24
+; RV32-NEXT: vmul.vv v21, v8, v25
+; RV32-NEXT: vmul.vv v22, v8, v26
+; RV32-NEXT: vmul.vv v23, v8, v3
+; RV32-NEXT: vmul.vv v24, v8, v2
+; RV32-NEXT: vmul.vv v25, v8, v29
+; RV32-NEXT: vmul.vv v26, v8, v30
+; RV32-NEXT: vmul.vv v27, v8, v31
+; RV32-NEXT: vmul.vv v28, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v29, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v29, v8, v29
+; RV32-NEXT: vmul.vv v30, v8, v5
+; RV32-NEXT: vmul.vv v31, v8, v4
+; RV32-NEXT: vmul.vv v7, v8, v6
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v6, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v6, v8, v6
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v5, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v5, v8, v5
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v4, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v4, v8, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v3, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v3, v8, v3
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v2, v8, v2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 5
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v0, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 5
+; RV32-NEXT: sub a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v8, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v8, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vi v8, v8, 0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 4
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 4
+; RV32-NEXT: sub a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 3
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 3
+; RV32-NEXT: sub a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 2
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 1
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: vxor.vv v8, v8, v1
+; RV32-NEXT: addi a0, sp, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: vxor.vv v8, v8, v11
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: vxor.vv v8, v8, v13
+; RV32-NEXT: vxor.vv v8, v8, v14
+; RV32-NEXT: vxor.vv v8, v8, v15
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: vxor.vv v8, v8, v17
+; RV32-NEXT: vxor.vv v8, v8, v18
+; RV32-NEXT: vxor.vv v8, v8, v19
+; RV32-NEXT: vxor.vv v8, v8, v20
+; RV32-NEXT: vxor.vv v8, v8, v21
+; RV32-NEXT: vxor.vv v8, v8, v22
+; RV32-NEXT: vxor.vv v8, v8, v23
+; RV32-NEXT: vxor.vv v8, v8, v24
+; RV32-NEXT: vxor.vv v8, v8, v25
+; RV32-NEXT: vxor.vv v8, v8, v26
+; RV32-NEXT: vxor.vv v8, v8, v27
+; RV32-NEXT: vxor.vv v8, v8, v28
+; RV32-NEXT: vxor.vv v8, v8, v29
+; RV32-NEXT: vxor.vv v8, v8, v30
+; RV32-NEXT: vxor.vv v8, v8, v31
+; RV32-NEXT: vxor.vv v8, v8, v7
+; RV32-NEXT: vxor.vv v8, v8, v6
+; RV32-NEXT: vxor.vv v8, v8, v5
+; RV32-NEXT: vxor.vv v8, v8, v4
+; RV32-NEXT: vxor.vv v8, v8, v3
+; RV32-NEXT: vxor.vv v8, v8, v2
+; RV32-NEXT: vxor.vv v8, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: vsrl.vx v9, v8, a6
+; RV32-NEXT: vsll.vx v10, v8, a6
+; RV32-NEXT: vsrl.vx v11, v8, ra
+; RV32-NEXT: vand.vx v12, v8, a4
+; RV32-NEXT: vand.vx v11, v11, a4
+; RV32-NEXT: vsrl.vi v13, v8, 24
+; RV32-NEXT: vand.vx v14, v8, a5
+; RV32-NEXT: vand.vx v13, v13, a5
+; RV32-NEXT: vsll.vx v12, v12, ra
+; RV32-NEXT: vsrl.vi v15, v8, 8
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v16, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v16
+; RV32-NEXT: vand.vv v15, v15, v16
+; RV32-NEXT: vor.vv v9, v11, v9
+; RV32-NEXT: vor.vv v11, v15, v13
+; RV32-NEXT: vsll.vi v8, v8, 8
+; RV32-NEXT: vsll.vi v13, v14, 24
+; RV32-NEXT: vor.vv v8, v13, v8
+; RV32-NEXT: vor.vv v10, v10, v12
+; RV32-NEXT: vor.vv v9, v11, v9
+; RV32-NEXT: vor.vv v8, v10, v8
+; RV32-NEXT: vor.vv v8, v8, v9
+; RV32-NEXT: vsrl.vi v9, v8, 4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v10, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v10
+; RV32-NEXT: vand.vv v9, v9, v10
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v9, v8
+; RV32-NEXT: vsrl.vi v9, v8, 2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v10, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v10
+; RV32-NEXT: vand.vv v9, v9, v10
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v8, v9, v8
+; RV32-NEXT: vsrl.vi v9, v8, 1
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v10, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v10
+; RV32-NEXT: vand.vv v9, v9, v10
+; RV32-NEXT: vadd.vv v8, v8, v8
+; RV32-NEXT: vor.vv v8, v9, v8
+; RV32-NEXT: vsrl.vi v8, v8, 1
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add sp, sp, a0
+; RV32-NEXT: lw ra, 348(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s0, 344(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s1, 340(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s2, 336(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s3, 332(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s4, 328(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s5, 324(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s6, 320(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s7, 316(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s8, 312(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s9, 308(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s10, 304(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s11, 300(sp) # 4-byte Folded Reload
+; RV32-NEXT: addi sp, sp, 352
+; RV32-NEXT: ret
+;
+; RV64-LABEL: clmulh_nxv1i64:
+; RV64: # %bb.0:
+; RV64-NEXT: addi sp, sp, -224
+; RV64-NEXT: sd ra, 216(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s0, 208(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s1, 200(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s2, 192(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s3, 184(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s4, 176(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s5, 168(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s6, 160(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s7, 152(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s8, 144(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s9, 136(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s10, 128(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s11, 120(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: sub sp, sp, a0
+; RV64-NEXT: vsetvli a1, zero, e64, m1, ta, ma
+; RV64-NEXT: vsrl.vi v10, v8, 24
+; RV64-NEXT: vsrl.vi v9, v8, 8
+; RV64-NEXT: li t2, 255
+; RV64-NEXT: lui t6, 61681
+; RV64-NEXT: lui s0, 209715
+; RV64-NEXT: lui s1, 349525
+; RV64-NEXT: li s10, 16
+; RV64-NEXT: li s9, 32
+; RV64-NEXT: li s8, 64
+; RV64-NEXT: li s5, 128
+; RV64-NEXT: li s6, 256
+; RV64-NEXT: li t5, 512
+; RV64-NEXT: li t3, 1024
+; RV64-NEXT: li t0, 1
+; RV64-NEXT: lui s7, 1
+; RV64-NEXT: lui a1, 2
+; RV64-NEXT: lui t4, 4
+; RV64-NEXT: lui t1, 8
+; RV64-NEXT: lui a7, 32
+; RV64-NEXT: lui a6, 64
+; RV64-NEXT: lui a5, 128
+; RV64-NEXT: lui a4, 256
+; RV64-NEXT: lui a3, 512
+; RV64-NEXT: lui a2, 1024
+; RV64-NEXT: li s11, 56
+; RV64-NEXT: vsrl.vx v11, v8, s11
+; RV64-NEXT: li ra, 40
+; RV64-NEXT: vsrl.vx v12, v8, ra
+; RV64-NEXT: addi t6, t6, -241
+; RV64-NEXT: addi s2, s0, 819
+; RV64-NEXT: addi s3, s1, 1365
+; RV64-NEXT: slli s1, t6, 32
+; RV64-NEXT: add s4, t6, s1
+; RV64-NEXT: slli t6, s2, 32
+; RV64-NEXT: add s2, s2, t6
+; RV64-NEXT: slli t6, s3, 32
+; RV64-NEXT: add s3, s3, t6
+; RV64-NEXT: lui s0, 16
+; RV64-NEXT: addi s1, s0, -256
+; RV64-NEXT: lui a0, 4080
+; RV64-NEXT: vand.vx v10, v10, a0
+; RV64-NEXT: slli t6, t2, 24
+; RV64-NEXT: vand.vx v13, v8, a0
+; RV64-NEXT: vsll.vx v14, v8, s11
+; RV64-NEXT: vand.vx v12, v12, s1
+; RV64-NEXT: vand.vx v9, v9, t6
+; RV64-NEXT: vsll.vi v13, v13, 24
+; RV64-NEXT: vand.vx v15, v8, t6
+; RV64-NEXT: vand.vx v8, v8, s1
+; RV64-NEXT: vor.vv v11, v12, v11
+; RV64-NEXT: vor.vv v9, v9, v10
+; RV64-NEXT: vsll.vi v10, v15, 8
+; RV64-NEXT: vsll.vx v8, v8, ra
+; RV64-NEXT: vor.vv v9, v9, v11
+; RV64-NEXT: vor.vv v10, v13, v10
+; RV64-NEXT: vor.vv v8, v14, v8
+; RV64-NEXT: vor.vv v8, v8, v10
+; RV64-NEXT: vor.vv v8, v8, v9
+; RV64-NEXT: vsrl.vi v9, v8, 4
+; RV64-NEXT: vand.vx v8, v8, s4
+; RV64-NEXT: vand.vx v9, v9, s4
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v9, v8
+; RV64-NEXT: vsrl.vi v9, v8, 2
+; RV64-NEXT: vand.vx v8, v8, s2
+; RV64-NEXT: vand.vx v9, v9, s2
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v9, v8
+; RV64-NEXT: vsrl.vi v9, v8, 1
+; RV64-NEXT: vand.vx v8, v8, s3
+; RV64-NEXT: vand.vx v9, v9, s3
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v9, v8
+; RV64-NEXT: vand.vx v7, v8, s10
+; RV64-NEXT: lui t2, 4096
+; RV64-NEXT: vand.vx v6, v8, s9
+; RV64-NEXT: lui s9, 8192
+; RV64-NEXT: vand.vx v5, v8, s8
+; RV64-NEXT: lui s8, 16384
+; RV64-NEXT: vand.vx v4, v8, s5
+; RV64-NEXT: lui s10, 32768
+; RV64-NEXT: vand.vx v13, v8, s6
+; RV64-NEXT: lui s11, 65536
+; RV64-NEXT: vand.vx v14, v8, t5
+; RV64-NEXT: lui t5, 131072
+; RV64-NEXT: vand.vx v15, v8, t3
+; RV64-NEXT: slli t3, t0, 11
+; RV64-NEXT: vand.vx v16, v8, t3
+; RV64-NEXT: lui t3, 262144
+; RV64-NEXT: vand.vx v17, v8, s7
+; RV64-NEXT: slli a0, t0, 31
+; RV64-NEXT: sd a0, 96(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v18, v8, a1
+; RV64-NEXT: slli a0, t0, 32
+; RV64-NEXT: sd a0, 88(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v19, v8, t4
+; RV64-NEXT: slli a0, t0, 33
+; RV64-NEXT: sd a0, 80(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v20, v8, t1
+; RV64-NEXT: slli a0, t0, 34
+; RV64-NEXT: sd a0, 72(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v21, v8, s0
+; RV64-NEXT: slli a0, t0, 35
+; RV64-NEXT: sd a0, 64(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v22, v8, a7
+; RV64-NEXT: slli a0, t0, 36
+; RV64-NEXT: sd a0, 56(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v23, v8, a6
+; RV64-NEXT: slli a0, t0, 37
+; RV64-NEXT: sd a0, 48(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v24, v8, a5
+; RV64-NEXT: slli a0, t0, 38
+; RV64-NEXT: sd a0, 40(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v25, v8, a4
+; RV64-NEXT: slli a0, t0, 39
+; RV64-NEXT: sd a0, 32(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v26, v8, a3
+; RV64-NEXT: slli a0, t0, 40
+; RV64-NEXT: sd a0, 24(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v27, v8, a2
+; RV64-NEXT: slli a0, t0, 41
+; RV64-NEXT: sd a0, 16(sp) # 8-byte Folded Spill
+; RV64-NEXT: lui a0, 2048
+; RV64-NEXT: vand.vx v28, v8, a0
+; RV64-NEXT: slli s5, t0, 42
+; RV64-NEXT: vand.vx v29, v8, t2
+; RV64-NEXT: slli s6, t0, 43
+; RV64-NEXT: vand.vx v30, v8, s9
+; RV64-NEXT: slli s7, t0, 44
+; RV64-NEXT: vand.vx v10, v8, s8
+; RV64-NEXT: slli s8, t0, 45
+; RV64-NEXT: vand.vx v11, v8, s10
+; RV64-NEXT: slli s9, t0, 46
+; RV64-NEXT: vand.vx v12, v8, s11
+; RV64-NEXT: slli s10, t0, 47
+; RV64-NEXT: vand.vx v9, v8, t5
+; RV64-NEXT: slli s11, t0, 48
+; RV64-NEXT: vand.vx v31, v8, t3
+; RV64-NEXT: slli ra, t0, 49
+; RV64-NEXT: slli t5, t0, 50
+; RV64-NEXT: slli t4, t0, 51
+; RV64-NEXT: slli t3, t0, 52
+; RV64-NEXT: slli t2, t0, 53
+; RV64-NEXT: slli t1, t0, 54
+; RV64-NEXT: slli a7, t0, 55
+; RV64-NEXT: slli a6, t0, 56
+; RV64-NEXT: slli a5, t0, 57
+; RV64-NEXT: slli a4, t0, 58
+; RV64-NEXT: slli a3, t0, 59
+; RV64-NEXT: slli a2, t0, 60
+; RV64-NEXT: slli a1, t0, 61
+; RV64-NEXT: slli t0, t0, 62
+; RV64-NEXT: li a0, -1
+; RV64-NEXT: slli a0, a0, 63
+; RV64-NEXT: vand.vi v3, v8, 2
+; RV64-NEXT: vand.vi v2, v8, 1
+; RV64-NEXT: vand.vi v1, v8, 4
+; RV64-NEXT: vand.vi v0, v8, 8
+; RV64-NEXT: vmul.vv v3, v8, v3
+; RV64-NEXT: sd t6, 8(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: mv s0, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s0, s0, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add s0, s0, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s0
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v3, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v3, v8, v2
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: mv s0, t6
+; RV64-NEXT: slli t6, t6, 3
+; RV64-NEXT: add s0, s0, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s0
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v3, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v3, v8, v1
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 3
+; RV64-NEXT: mv s0, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s0
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v3, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vmul.vv v7, v8, v7
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: mv s0, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s0, s0, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s0, s0, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add t6, t6, s0
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v7, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v7, v8, v6
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: mv s0, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s0, s0, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add t6, t6, s0
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v7, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v7, v8, v5
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: mv s0, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add s0, s0, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add t6, t6, s0
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v7, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v7, v8, v4
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: mv s0, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add t6, t6, s0
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v7, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v13, v8, v13
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: mv s0, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s0, s0, t6
+; RV64-NEXT: slli t6, t6, 3
+; RV64-NEXT: add t6, t6, s0
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v13, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v13, v8, v14
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: mv s0, t6
+; RV64-NEXT: slli t6, t6, 3
+; RV64-NEXT: add t6, t6, s0
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v13, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v13, v8, v15
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli s0, t6, 4
+; RV64-NEXT: add t6, s0, t6
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v13, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v13, v8, v16
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v13, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v13, v8, v17
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli s0, t6, 4
+; RV64-NEXT: sub t6, s0, t6
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v13, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v13, v8, v18
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: mv s0, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s0, s0, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s0
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v13, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v13, v8, v19
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: mv s0, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add s0, s0, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s0
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v13, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v13, v8, v20
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: mv s0, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s0
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v13, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v13, v8, v21
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: mv s0, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s0, s0, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add t6, t6, s0
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v13, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v13, v8, v22
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: mv s0, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add t6, t6, s0
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v13, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v13, v8, v23
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli s0, t6, 3
+; RV64-NEXT: add t6, s0, t6
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v13, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v13, v8, v24
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 3
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v13, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v13, v8, v25
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli s0, t6, 3
+; RV64-NEXT: sub t6, s0, t6
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v13, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v13, v8, v26
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: mv s0, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s0
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v13, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v13, v8, v27
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli s0, t6, 2
+; RV64-NEXT: add t6, s0, t6
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v13, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v13, v8, v28
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v13, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v13, v8, v29
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli s0, t6, 1
+; RV64-NEXT: add t6, s0, t6
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v13, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v13, v8, v30
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v13, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: mv s0, t6
+; RV64-NEXT: slli t6, t6, 4
+; RV64-NEXT: add t6, t6, s0
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v10, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v11
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli s0, t6, 5
+; RV64-NEXT: add t6, s0, t6
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v10, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v12
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 5
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v10, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v9
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli s0, t6, 5
+; RV64-NEXT: sub t6, s0, t6
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v31
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: mv s0, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s0, s0, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s0, s0, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s0
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: ld s0, 96(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s0
+; RV64-NEXT: vmul.vv v9, v8, v9
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: mv s0, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add s0, s0, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s0, s0, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s0
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: ld s0, 88(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s0
+; RV64-NEXT: vmul.vv v9, v8, v9
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: mv s0, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s0, s0, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s0
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: ld s0, 80(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s0
+; RV64-NEXT: vmul.vv v9, v8, v9
+; RV64-NEXT: csrr s0, vlenb
+; RV64-NEXT: slli s0, s0, 1
+; RV64-NEXT: mv t6, s0
+; RV64-NEXT: slli s0, s0, 2
+; RV64-NEXT: add t6, t6, s0
+; RV64-NEXT: slli s0, s0, 1
+; RV64-NEXT: add s0, s0, t6
+; RV64-NEXT: ld t6, 8(sp) # 8-byte Folded Reload
+; RV64-NEXT: add s0, sp, s0
+; RV64-NEXT: addi s0, s0, 112
+; RV64-NEXT: vs1r.v v9, (s0) # vscale x 8-byte Folded Spill
+; RV64-NEXT: ld s0, 72(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s0
+; RV64-NEXT: vmul.vv v9, v8, v9
+; RV64-NEXT: csrr s0, vlenb
+; RV64-NEXT: add s0, sp, s0
+; RV64-NEXT: addi s0, s0, 112
+; RV64-NEXT: vs1r.v v9, (s0) # vscale x 8-byte Folded Spill
+; RV64-NEXT: ld s0, 64(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s0
+; RV64-NEXT: vmul.vv v9, v8, v9
+; RV64-NEXT: addi s0, sp, 112
+; RV64-NEXT: vs1r.v v9, (s0) # vscale x 8-byte Folded Spill
+; RV64-NEXT: ld s0, 56(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s0
+; RV64-NEXT: vmul.vv v4, v8, v9
+; RV64-NEXT: ld s0, 48(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s0
+; RV64-NEXT: vmul.vv v5, v8, v9
+; RV64-NEXT: ld s0, 40(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s0
+; RV64-NEXT: vmul.vv v6, v8, v9
+; RV64-NEXT: ld s0, 32(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s0
+; RV64-NEXT: vmul.vv v7, v8, v9
+; RV64-NEXT: ld s0, 24(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s0
+; RV64-NEXT: vmul.vv v31, v8, v9
+; RV64-NEXT: ld s0, 16(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s0
+; RV64-NEXT: vmul.vv v30, v8, v9
+; RV64-NEXT: vand.vx v9, v8, s5
+; RV64-NEXT: vmul.vv v29, v8, v9
+; RV64-NEXT: vand.vx v9, v8, s6
+; RV64-NEXT: vmul.vv v28, v8, v9
+; RV64-NEXT: vand.vx v9, v8, s7
+; RV64-NEXT: vmul.vv v27, v8, v9
+; RV64-NEXT: vand.vx v9, v8, s8
+; RV64-NEXT: vmul.vv v26, v8, v9
+; RV64-NEXT: vand.vx v9, v8, s9
+; RV64-NEXT: vmul.vv v25, v8, v9
+; RV64-NEXT: vand.vx v9, v8, s10
+; RV64-NEXT: vmul.vv v23, v8, v9
+; RV64-NEXT: vand.vx v9, v8, s11
+; RV64-NEXT: vmul.vv v19, v8, v9
+; RV64-NEXT: vand.vx v9, v8, ra
+; RV64-NEXT: vmul.vv v14, v8, v9
+; RV64-NEXT: vand.vx v9, v8, t5
+; RV64-NEXT: vmul.vv v9, v8, v9
+; RV64-NEXT: vand.vx v10, v8, t4
+; RV64-NEXT: vmul.vv v24, v8, v10
+; RV64-NEXT: vand.vx v10, v8, t3
+; RV64-NEXT: vmul.vv v22, v8, v10
+; RV64-NEXT: vand.vx v10, v8, t2
+; RV64-NEXT: vmul.vv v20, v8, v10
+; RV64-NEXT: vand.vx v10, v8, t1
+; RV64-NEXT: vmul.vv v15, v8, v10
+; RV64-NEXT: vand.vx v10, v8, a7
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: vand.vx v11, v8, a6
+; RV64-NEXT: vmul.vv v16, v8, v11
+; RV64-NEXT: vand.vx v11, v8, a5
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vand.vx v12, v8, a4
+; RV64-NEXT: vmul.vv v21, v8, v12
+; RV64-NEXT: vand.vx v12, v8, a3
+; RV64-NEXT: vmul.vv v17, v8, v12
+; RV64-NEXT: vand.vx v12, v8, a2
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: vand.vx v13, v8, a1
+; RV64-NEXT: vmul.vv v18, v8, v13
+; RV64-NEXT: vand.vx v13, v8, t0
+; RV64-NEXT: vmul.vv v13, v8, v13
+; RV64-NEXT: vand.vx v2, v8, a0
+; RV64-NEXT: vmul.vv v8, v8, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v1, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v1, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v1
+; RV64-NEXT: vxor.vv v2, v2, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v1, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v1
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v1, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v1
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v1, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v1
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v1, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v1
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v1, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v2, v1
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v0, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a1, a0, 4
+; RV64-NEXT: add a0, a1, a0
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v0, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v0, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a1, a0, 4
+; RV64-NEXT: sub a0, a1, a0
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v0, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v0, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v0, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v0, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v0, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v0, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a1, a0, 3
+; RV64-NEXT: add a0, a1, a0
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v0, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v0, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a1, a0, 3
+; RV64-NEXT: sub a0, a1, a0
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v0, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v0, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a1, a0, 2
+; RV64-NEXT: add a0, a1, a0
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v0, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v0, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a1, a0, 1
+; RV64-NEXT: add a0, a1, a0
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v0, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v1, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v3, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v3
+; RV64-NEXT: li a0, 56
+; RV64-NEXT: vsll.vx v2, v2, a0
+; RV64-NEXT: vand.vx v1, v1, s1
+; RV64-NEXT: li a1, 40
+; RV64-NEXT: vsll.vx v1, v1, a1
+; RV64-NEXT: vor.vv v2, v2, v1
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 4
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl1r.v v1, (a2) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v0, v1
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a3, a2, 5
+; RV64-NEXT: add a2, a3, a2
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl1r.v v0, (a2) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v0
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 5
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl1r.v v0, (a2) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v0
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a3, a2, 5
+; RV64-NEXT: sub a2, a3, a2
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl1r.v v0, (a2) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v0
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl1r.v v0, (a2) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v0
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl1r.v v0, (a2) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v0
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl1r.v v0, (a2) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v0
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl1r.v v0, (a2) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v0
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl1r.v v3, (a2) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v3
+; RV64-NEXT: addi a2, sp, 112
+; RV64-NEXT: vl1r.v v3, (a2) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v3, v1, v3
+; RV64-NEXT: vxor.vv v4, v3, v4
+; RV64-NEXT: vxor.vv v5, v4, v5
+; RV64-NEXT: vxor.vv v6, v5, v6
+; RV64-NEXT: vxor.vv v7, v6, v7
+; RV64-NEXT: vxor.vv v31, v7, v31
+; RV64-NEXT: vxor.vv v30, v31, v30
+; RV64-NEXT: vxor.vv v29, v30, v29
+; RV64-NEXT: vxor.vv v28, v29, v28
+; RV64-NEXT: vxor.vv v27, v28, v27
+; RV64-NEXT: vxor.vv v26, v27, v26
+; RV64-NEXT: vxor.vv v25, v26, v25
+; RV64-NEXT: vxor.vv v23, v25, v23
+; RV64-NEXT: vxor.vv v19, v23, v19
+; RV64-NEXT: vxor.vv v14, v19, v14
+; RV64-NEXT: vxor.vv v9, v14, v9
+; RV64-NEXT: vsrl.vi v14, v7, 8
+; RV64-NEXT: vand.vx v14, v14, t6
+; RV64-NEXT: vsrl.vi v19, v23, 24
+; RV64-NEXT: lui a2, 4080
+; RV64-NEXT: vand.vx v19, v19, a2
+; RV64-NEXT: vor.vv v14, v14, v19
+; RV64-NEXT: vxor.vv v9, v9, v24
+; RV64-NEXT: vxor.vv v9, v9, v22
+; RV64-NEXT: vxor.vv v9, v9, v20
+; RV64-NEXT: vxor.vv v9, v9, v15
+; RV64-NEXT: vxor.vv v9, v9, v10
+; RV64-NEXT: vand.vx v10, v7, a2
+; RV64-NEXT: vsll.vi v10, v10, 24
+; RV64-NEXT: vxor.vv v15, v9, v16
+; RV64-NEXT: vxor.vv v11, v15, v11
+; RV64-NEXT: vand.vx v15, v9, t6
+; RV64-NEXT: vsll.vi v15, v15, 8
+; RV64-NEXT: vor.vv v10, v10, v15
+; RV64-NEXT: vxor.vv v11, v11, v21
+; RV64-NEXT: vor.vv v10, v2, v10
+; RV64-NEXT: vxor.vv v11, v11, v17
+; RV64-NEXT: vxor.vv v11, v11, v12
+; RV64-NEXT: vsrl.vx v9, v9, a1
+; RV64-NEXT: vand.vx v9, v9, s1
+; RV64-NEXT: vxor.vv v11, v11, v18
+; RV64-NEXT: vxor.vv v11, v11, v13
+; RV64-NEXT: vxor.vv v8, v11, v8
+; RV64-NEXT: vsrl.vx v8, v8, a0
+; RV64-NEXT: vor.vv v8, v9, v8
+; RV64-NEXT: vor.vv v8, v14, v8
+; RV64-NEXT: vor.vv v8, v10, v8
+; RV64-NEXT: vsrl.vi v9, v8, 4
+; RV64-NEXT: vand.vx v8, v8, s4
+; RV64-NEXT: vand.vx v9, v9, s4
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v9, v8
+; RV64-NEXT: vsrl.vi v9, v8, 2
+; RV64-NEXT: vand.vx v8, v8, s2
+; RV64-NEXT: vand.vx v9, v9, s2
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v9, v8
+; RV64-NEXT: vsrl.vi v9, v8, 1
+; RV64-NEXT: vand.vx v8, v8, s3
+; RV64-NEXT: vand.vx v9, v9, s3
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v9, v8
+; RV64-NEXT: vsrl.vi v8, v8, 1
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add sp, sp, a0
+; RV64-NEXT: ld ra, 216(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s0, 208(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s1, 200(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s2, 192(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s3, 184(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s4, 176(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s5, 168(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s6, 160(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s7, 152(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s8, 144(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s9, 136(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s10, 128(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s11, 120(sp) # 8-byte Folded Reload
+; RV64-NEXT: addi sp, sp, 224
+; RV64-NEXT: ret
+ %a = call <vscale x 1 x i64> @llvm.clmulh.nxv1i64(<vscale x 1 x i64> %x, <vscale x 1 x i64> %y)
+ ret <vscale x 1 x i64> %a
+}
+
+define <vscale x 2 x i64> @clmulh_nxv2i64(<vscale x 2 x i64> %x, <vscale x 2 x i64> %y) nounwind {
+; RV32-LABEL: clmulh_nxv2i64:
+; RV32: # %bb.0:
+; RV32-NEXT: addi sp, sp, -352
+; RV32-NEXT: sw ra, 348(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s0, 344(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s1, 340(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s2, 336(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s3, 332(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s4, 328(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s5, 324(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s6, 320(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s7, 316(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s8, 312(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s9, 308(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s10, 304(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s11, 300(sp) # 4-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: sub sp, sp, a0
+; RV32-NEXT: lui s7, 1044480
+; RV32-NEXT: lui a7, 524288
+; RV32-NEXT: li a1, 1
+; RV32-NEXT: li s8, 2
+; RV32-NEXT: li s9, 4
+; RV32-NEXT: li s10, 8
+; RV32-NEXT: li a3, 16
+; RV32-NEXT: li a4, 32
+; RV32-NEXT: li a5, 64
+; RV32-NEXT: li a6, 128
+; RV32-NEXT: li s11, 256
+; RV32-NEXT: li ra, 512
+; RV32-NEXT: li a0, 1024
+; RV32-NEXT: lui a2, 1
+; RV32-NEXT: lui t0, 2
+; RV32-NEXT: lui t1, 4
+; RV32-NEXT: lui t2, 8
+; RV32-NEXT: lui t3, 16
+; RV32-NEXT: lui t4, 32
+; RV32-NEXT: lui t5, 64
+; RV32-NEXT: lui t6, 128
+; RV32-NEXT: lui s0, 256
+; RV32-NEXT: lui s1, 512
+; RV32-NEXT: lui s2, 1024
+; RV32-NEXT: lui s3, 2048
+; RV32-NEXT: lui s4, 4096
+; RV32-NEXT: lui s5, 8192
+; RV32-NEXT: lui s6, 16384
+; RV32-NEXT: sw s7, 272(sp)
+; RV32-NEXT: lui s7, 32768
+; RV32-NEXT: sw zero, 276(sp)
+; RV32-NEXT: sw a7, 264(sp)
+; RV32-NEXT: sw zero, 268(sp)
+; RV32-NEXT: sw zero, 256(sp)
+; RV32-NEXT: sw a1, 260(sp)
+; RV32-NEXT: sw zero, 248(sp)
+; RV32-NEXT: sw s8, 252(sp)
+; RV32-NEXT: lui s8, 65536
+; RV32-NEXT: sw zero, 240(sp)
+; RV32-NEXT: sw s9, 244(sp)
+; RV32-NEXT: lui s9, 131072
+; RV32-NEXT: sw zero, 232(sp)
+; RV32-NEXT: sw s10, 236(sp)
+; RV32-NEXT: lui s10, 262144
+; RV32-NEXT: sw zero, 224(sp)
+; RV32-NEXT: sw a3, 228(sp)
+; RV32-NEXT: sw zero, 216(sp)
+; RV32-NEXT: sw a4, 220(sp)
+; RV32-NEXT: sw zero, 208(sp)
+; RV32-NEXT: sw a5, 212(sp)
+; RV32-NEXT: sw zero, 200(sp)
+; RV32-NEXT: sw a6, 204(sp)
+; RV32-NEXT: sw zero, 192(sp)
+; RV32-NEXT: sw s11, 196(sp)
+; RV32-NEXT: sw zero, 184(sp)
+; RV32-NEXT: sw ra, 188(sp)
+; RV32-NEXT: sw zero, 176(sp)
+; RV32-NEXT: sw a0, 180(sp)
+; RV32-NEXT: slli a5, a1, 11
+; RV32-NEXT: sw zero, 168(sp)
+; RV32-NEXT: sw a5, 172(sp)
+; RV32-NEXT: sw zero, 160(sp)
+; RV32-NEXT: sw a2, 164(sp)
+; RV32-NEXT: sw zero, 152(sp)
+; RV32-NEXT: sw t0, 156(sp)
+; RV32-NEXT: sw zero, 144(sp)
+; RV32-NEXT: sw t1, 148(sp)
+; RV32-NEXT: sw zero, 136(sp)
+; RV32-NEXT: sw t2, 140(sp)
+; RV32-NEXT: sw zero, 128(sp)
+; RV32-NEXT: sw t3, 132(sp)
+; RV32-NEXT: sw zero, 120(sp)
+; RV32-NEXT: sw t4, 124(sp)
+; RV32-NEXT: sw zero, 112(sp)
+; RV32-NEXT: sw t5, 116(sp)
+; RV32-NEXT: sw zero, 104(sp)
+; RV32-NEXT: sw t6, 108(sp)
+; RV32-NEXT: sw zero, 96(sp)
+; RV32-NEXT: sw s0, 100(sp)
+; RV32-NEXT: sw zero, 88(sp)
+; RV32-NEXT: sw s1, 92(sp)
+; RV32-NEXT: sw zero, 80(sp)
+; RV32-NEXT: sw s2, 84(sp)
+; RV32-NEXT: sw zero, 72(sp)
+; RV32-NEXT: sw s3, 76(sp)
+; RV32-NEXT: sw zero, 64(sp)
+; RV32-NEXT: sw s4, 68(sp)
+; RV32-NEXT: sw zero, 56(sp)
+; RV32-NEXT: sw s5, 60(sp)
+; RV32-NEXT: sw zero, 48(sp)
+; RV32-NEXT: sw s6, 52(sp)
+; RV32-NEXT: sw zero, 40(sp)
+; RV32-NEXT: sw s7, 44(sp)
+; RV32-NEXT: sw zero, 32(sp)
+; RV32-NEXT: sw s8, 36(sp)
+; RV32-NEXT: sw zero, 24(sp)
+; RV32-NEXT: sw s9, 28(sp)
+; RV32-NEXT: sw zero, 16(sp)
+; RV32-NEXT: sw s10, 20(sp)
+; RV32-NEXT: sw zero, 8(sp)
+; RV32-NEXT: sw a7, 12(sp)
+; RV32-NEXT: lui a0, 61681
+; RV32-NEXT: addi a0, a0, -241
+; RV32-NEXT: vsetvli a2, zero, e32, m2, ta, ma
+; RV32-NEXT: vmv.v.x v4, a0
+; RV32-NEXT: lui a0, 209715
+; RV32-NEXT: addi a0, a0, 819
+; RV32-NEXT: vmv.v.x v2, a0
+; RV32-NEXT: lui a0, 349525
+; RV32-NEXT: addi a0, a0, 1365
+; RV32-NEXT: vmv.v.x v0, a0
+; RV32-NEXT: addi a0, sp, 272
+; RV32-NEXT: vsetvli a2, zero, e64, m2, ta, ma
+; RV32-NEXT: vlse64.v v6, (a0), zero
+; RV32-NEXT: addi a0, sp, 264
+; RV32-NEXT: vlse64.v v10, (a0), zero
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 256
+; RV32-NEXT: vlse64.v v12, (a0), zero
+; RV32-NEXT: addi a0, sp, 248
+; RV32-NEXT: vlse64.v v14, (a0), zero
+; RV32-NEXT: addi a0, sp, 240
+; RV32-NEXT: vlse64.v v16, (a0), zero
+; RV32-NEXT: addi a0, sp, 232
+; RV32-NEXT: vlse64.v v18, (a0), zero
+; RV32-NEXT: addi a0, sp, 224
+; RV32-NEXT: vlse64.v v20, (a0), zero
+; RV32-NEXT: addi a0, sp, 216
+; RV32-NEXT: vlse64.v v22, (a0), zero
+; RV32-NEXT: li ra, 56
+; RV32-NEXT: vsrl.vi v24, v8, 24
+; RV32-NEXT: vsrl.vx v26, v8, ra
+; RV32-NEXT: li s11, 40
+; RV32-NEXT: vsrl.vx v28, v8, s11
+; RV32-NEXT: vsll.vx v30, v8, ra
+; RV32-NEXT: addi a4, t3, -256
+; RV32-NEXT: vand.vx v28, v28, a4
+; RV32-NEXT: vor.vv v26, v28, v26
+; RV32-NEXT: vand.vx v28, v8, a4
+; RV32-NEXT: vsll.vx v28, v28, s11
+; RV32-NEXT: vor.vv v30, v30, v28
+; RV32-NEXT: vsrl.vi v28, v8, 8
+; RV32-NEXT: lui a6, 4080
+; RV32-NEXT: vand.vx v24, v24, a6
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v6, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v28, v28, v6
+; RV32-NEXT: vor.vv v28, v28, v24
+; RV32-NEXT: addi a3, sp, 208
+; RV32-NEXT: vlse64.v v24, (a3), zero
+; RV32-NEXT: vor.vv v10, v28, v26
+; RV32-NEXT: vand.vx v26, v8, a6
+; RV32-NEXT: vsll.vi v26, v26, 24
+; RV32-NEXT: vand.vv v8, v8, v6
+; RV32-NEXT: vsll.vi v8, v8, 8
+; RV32-NEXT: vor.vv v8, v26, v8
+; RV32-NEXT: addi a3, sp, 200
+; RV32-NEXT: vlse64.v v28, (a3), zero
+; RV32-NEXT: vor.vv v8, v30, v8
+; RV32-NEXT: addi a3, sp, 192
+; RV32-NEXT: vlse64.v v26, (a3), zero
+; RV32-NEXT: vor.vv v8, v8, v10
+; RV32-NEXT: vsrl.vi v30, v8, 4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v4, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v8, v8, v4
+; RV32-NEXT: vand.vv v30, v30, v4
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v30, v8
+; RV32-NEXT: vsrl.vi v30, v8, 2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v2, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v8, v8, v2
+; RV32-NEXT: vand.vv v30, v30, v2
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v8, v30, v8
+; RV32-NEXT: vsrl.vi v30, v8, 1
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v0, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v8, v8, v0
+; RV32-NEXT: vand.vv v30, v30, v0
+; RV32-NEXT: vadd.vv v8, v8, v8
+; RV32-NEXT: vor.vv v8, v30, v8
+; RV32-NEXT: addi a3, sp, 184
+; RV32-NEXT: vlse64.v v30, (a3), zero
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vand.vv v6, v8, v10
+; RV32-NEXT: vand.vv v4, v8, v12
+; RV32-NEXT: vand.vv v2, v8, v14
+; RV32-NEXT: vand.vv v0, v8, v16
+; RV32-NEXT: vand.vv v10, v8, v18
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v22
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v28, v8, v28
+; RV32-NEXT: addi a3, sp, 176
+; RV32-NEXT: addi a0, sp, 168
+; RV32-NEXT: vlse64.v v10, (a3), zero
+; RV32-NEXT: vlse64.v v12, (a0), zero
+; RV32-NEXT: vand.vv v14, v8, v26
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v14, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v14, v8, v30
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v14, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: addi a2, sp, 160
+; RV32-NEXT: addi a3, sp, 152
+; RV32-NEXT: addi a1, sp, 144
+; RV32-NEXT: addi a0, sp, 136
+; RV32-NEXT: vlse64.v v10, (a2), zero
+; RV32-NEXT: vlse64.v v12, (a3), zero
+; RV32-NEXT: vlse64.v v14, (a1), zero
+; RV32-NEXT: vlse64.v v16, (a0), zero
+; RV32-NEXT: vand.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v14
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 128
+; RV32-NEXT: addi a1, sp, 120
+; RV32-NEXT: addi a2, sp, 112
+; RV32-NEXT: addi a3, sp, 104
+; RV32-NEXT: vlse64.v v10, (a0), zero
+; RV32-NEXT: vlse64.v v12, (a1), zero
+; RV32-NEXT: vlse64.v v14, (a2), zero
+; RV32-NEXT: vlse64.v v16, (a3), zero
+; RV32-NEXT: vand.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v14
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 96
+; RV32-NEXT: addi a1, sp, 88
+; RV32-NEXT: addi a2, sp, 80
+; RV32-NEXT: addi a3, sp, 72
+; RV32-NEXT: vlse64.v v10, (a0), zero
+; RV32-NEXT: vlse64.v v12, (a1), zero
+; RV32-NEXT: vlse64.v v14, (a2), zero
+; RV32-NEXT: vlse64.v v16, (a3), zero
+; RV32-NEXT: vand.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v14
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 64
+; RV32-NEXT: addi a1, sp, 56
+; RV32-NEXT: addi a2, sp, 48
+; RV32-NEXT: addi a3, sp, 40
+; RV32-NEXT: vlse64.v v10, (a0), zero
+; RV32-NEXT: vlse64.v v12, (a1), zero
+; RV32-NEXT: vlse64.v v14, (a2), zero
+; RV32-NEXT: vlse64.v v16, (a3), zero
+; RV32-NEXT: vand.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v14
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 32
+; RV32-NEXT: addi a1, sp, 24
+; RV32-NEXT: addi a2, sp, 16
+; RV32-NEXT: addi a3, sp, 8
+; RV32-NEXT: vlse64.v v10, (a0), zero
+; RV32-NEXT: vlse64.v v12, (a1), zero
+; RV32-NEXT: vlse64.v v14, (a2), zero
+; RV32-NEXT: vlse64.v v16, (a3), zero
+; RV32-NEXT: vand.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v14
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vi v10, v8, 2
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vi v10, v8, 1
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vi v10, v8, 4
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vi v10, v8, 8
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: li a0, 16
+; RV32-NEXT: vand.vx v10, v8, a0
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: li a0, 32
+; RV32-NEXT: vand.vx v10, v8, a0
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: li a0, 64
+; RV32-NEXT: vand.vx v10, v8, a0
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: li a0, 128
+; RV32-NEXT: vand.vx v10, v8, a0
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: li a0, 256
+; RV32-NEXT: vand.vx v10, v8, a0
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: li a0, 512
+; RV32-NEXT: vand.vx v10, v8, a0
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: li a0, 1024
+; RV32-NEXT: vand.vx v10, v8, a0
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, a5
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: lui a0, 1
+; RV32-NEXT: vand.vx v10, v8, a0
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, t0
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, t1
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, t2
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, t3
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, t4
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, t5
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, t6
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, s0
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, s1
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, s2
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, s3
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, s4
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, s5
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, s6
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, s7
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, s8
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, s9
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, s10
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: addi a0, sp, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v12, v8, v6
+; RV32-NEXT: vmul.vv v14, v8, v4
+; RV32-NEXT: vmul.vv v16, v8, v2
+; RV32-NEXT: vmul.vv v18, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v20, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v20, v8, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v22, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v22, v8, v22
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v24, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v26, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v26, v8, v26
+; RV32-NEXT: vmul.vv v28, v8, v28
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v30, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v30, v8, v30
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v6, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v6, v8, v6
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v4, v8, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v2, v8, v2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v0, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v8, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v8, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vi v8, v8, 0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: addi a0, sp, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: vxor.vv v8, v8, v14
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: vxor.vv v8, v8, v18
+; RV32-NEXT: vxor.vv v8, v8, v20
+; RV32-NEXT: vxor.vv v8, v8, v22
+; RV32-NEXT: vxor.vv v8, v8, v24
+; RV32-NEXT: vxor.vv v8, v8, v26
+; RV32-NEXT: vxor.vv v8, v8, v28
+; RV32-NEXT: vxor.vv v8, v8, v30
+; RV32-NEXT: vxor.vv v8, v8, v6
+; RV32-NEXT: vxor.vv v8, v8, v4
+; RV32-NEXT: vxor.vv v8, v8, v2
+; RV32-NEXT: vxor.vv v8, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: vsrl.vx v10, v8, ra
+; RV32-NEXT: vsll.vx v12, v8, ra
+; RV32-NEXT: vsrl.vx v14, v8, s11
+; RV32-NEXT: vand.vx v16, v8, a4
+; RV32-NEXT: vand.vx v14, v14, a4
+; RV32-NEXT: vsrl.vi v18, v8, 24
+; RV32-NEXT: vand.vx v20, v8, a6
+; RV32-NEXT: vand.vx v18, v18, a6
+; RV32-NEXT: vsll.vx v16, v16, s11
+; RV32-NEXT: vsrl.vi v22, v8, 8
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v24, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v24
+; RV32-NEXT: vand.vv v22, v22, v24
+; RV32-NEXT: vor.vv v10, v14, v10
+; RV32-NEXT: vor.vv v14, v22, v18
+; RV32-NEXT: vsll.vi v8, v8, 8
+; RV32-NEXT: vsll.vi v18, v20, 24
+; RV32-NEXT: vor.vv v8, v18, v8
+; RV32-NEXT: vor.vv v12, v12, v16
+; RV32-NEXT: vor.vv v10, v14, v10
+; RV32-NEXT: vor.vv v8, v12, v8
+; RV32-NEXT: vor.vv v8, v8, v10
+; RV32-NEXT: vsrl.vi v10, v8, 4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v12
+; RV32-NEXT: vand.vv v10, v10, v12
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v10, v8
+; RV32-NEXT: vsrl.vi v10, v8, 2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v12
+; RV32-NEXT: vand.vv v10, v10, v12
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v8, v10, v8
+; RV32-NEXT: vsrl.vi v10, v8, 1
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v12
+; RV32-NEXT: vand.vv v10, v10, v12
+; RV32-NEXT: vadd.vv v8, v8, v8
+; RV32-NEXT: vor.vv v8, v10, v8
+; RV32-NEXT: vsrl.vi v8, v8, 1
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add sp, sp, a0
+; RV32-NEXT: lw ra, 348(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s0, 344(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s1, 340(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s2, 336(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s3, 332(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s4, 328(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s5, 324(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s6, 320(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s7, 316(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s8, 312(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s9, 308(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s10, 304(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s11, 300(sp) # 4-byte Folded Reload
+; RV32-NEXT: addi sp, sp, 352
+; RV32-NEXT: ret
+;
+; RV64-LABEL: clmulh_nxv2i64:
+; RV64: # %bb.0:
+; RV64-NEXT: addi sp, sp, -224
+; RV64-NEXT: sd ra, 216(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s0, 208(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s1, 200(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s2, 192(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s3, 184(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s4, 176(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s5, 168(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s6, 160(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s7, 152(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s8, 144(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s9, 136(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s10, 128(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s11, 120(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: sub sp, sp, a0
+; RV64-NEXT: li s3, 40
+; RV64-NEXT: lui s1, 16
+; RV64-NEXT: vsetvli a0, zero, e64, m2, ta, ma
+; RV64-NEXT: vsrl.vi v14, v8, 24
+; RV64-NEXT: vsrl.vi v10, v8, 8
+; RV64-NEXT: li t4, 255
+; RV64-NEXT: lui a5, 61681
+; RV64-NEXT: lui a6, 209715
+; RV64-NEXT: lui t6, 349525
+; RV64-NEXT: li t5, 16
+; RV64-NEXT: li t3, 32
+; RV64-NEXT: li t2, 64
+; RV64-NEXT: li t0, 128
+; RV64-NEXT: li t1, 256
+; RV64-NEXT: li a4, 512
+; RV64-NEXT: li a3, 1024
+; RV64-NEXT: li s0, 1
+; RV64-NEXT: lui a2, 1
+; RV64-NEXT: lui a1, 2
+; RV64-NEXT: lui a0, 4
+; RV64-NEXT: li a7, 56
+; RV64-NEXT: vsrl.vx v12, v8, a7
+; RV64-NEXT: vsrl.vx v18, v8, s3
+; RV64-NEXT: addi s2, s1, -256
+; RV64-NEXT: lui s1, 4080
+; RV64-NEXT: vand.vx v16, v14, s1
+; RV64-NEXT: slli t4, t4, 24
+; RV64-NEXT: vand.vx v20, v8, s1
+; RV64-NEXT: vsll.vx v14, v8, a7
+; RV64-NEXT: addi a7, a5, -241
+; RV64-NEXT: addi a6, a6, 819
+; RV64-NEXT: addi a5, t6, 1365
+; RV64-NEXT: slli t6, s0, 11
+; RV64-NEXT: slli s1, s0, 31
+; RV64-NEXT: sd s1, 96(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli s1, s0, 32
+; RV64-NEXT: sd s1, 88(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli s1, s0, 33
+; RV64-NEXT: sd s1, 80(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli s1, s0, 34
+; RV64-NEXT: sd s1, 72(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli s1, s0, 35
+; RV64-NEXT: sd s1, 64(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli s1, s0, 36
+; RV64-NEXT: sd s1, 56(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli s1, a7, 32
+; RV64-NEXT: add a7, a7, s1
+; RV64-NEXT: slli s1, a6, 32
+; RV64-NEXT: add a6, a6, s1
+; RV64-NEXT: slli s1, a5, 32
+; RV64-NEXT: add a5, a5, s1
+; RV64-NEXT: slli s1, s0, 37
+; RV64-NEXT: sd s1, 48(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v18, v18, s2
+; RV64-NEXT: vand.vx v10, v10, t4
+; RV64-NEXT: vsll.vi v20, v20, 24
+; RV64-NEXT: vand.vx v22, v8, t4
+; RV64-NEXT: vand.vx v8, v8, s2
+; RV64-NEXT: vor.vv v12, v18, v12
+; RV64-NEXT: vor.vv v10, v10, v16
+; RV64-NEXT: vsll.vi v16, v22, 8
+; RV64-NEXT: vsll.vx v8, v8, s3
+; RV64-NEXT: vor.vv v10, v10, v12
+; RV64-NEXT: vor.vv v12, v20, v16
+; RV64-NEXT: vor.vv v8, v14, v8
+; RV64-NEXT: vor.vv v8, v8, v12
+; RV64-NEXT: vor.vv v8, v8, v10
+; RV64-NEXT: vsrl.vi v10, v8, 4
+; RV64-NEXT: vand.vx v8, v8, a7
+; RV64-NEXT: vand.vx v10, v10, a7
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v10, v8
+; RV64-NEXT: vsrl.vi v10, v8, 2
+; RV64-NEXT: vand.vx v8, v8, a6
+; RV64-NEXT: vand.vx v10, v10, a6
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v10, v8
+; RV64-NEXT: vsrl.vi v10, v8, 1
+; RV64-NEXT: vand.vx v8, v8, a5
+; RV64-NEXT: vand.vx v10, v10, a5
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v10, v8
+; RV64-NEXT: vand.vx v10, v8, t5
+; RV64-NEXT: slli t5, s0, 38
+; RV64-NEXT: sd t5, 40(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t3
+; RV64-NEXT: slli t3, s0, 39
+; RV64-NEXT: sd t3, 32(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v14, v8, t2
+; RV64-NEXT: slli t2, s0, 40
+; RV64-NEXT: sd t2, 24(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v24, v8, t0
+; RV64-NEXT: slli t0, s0, 41
+; RV64-NEXT: sd t0, 16(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, t1
+; RV64-NEXT: slli s6, s0, 42
+; RV64-NEXT: vand.vx v18, v8, a4
+; RV64-NEXT: slli s7, s0, 43
+; RV64-NEXT: vand.vx v20, v8, a3
+; RV64-NEXT: slli s8, s0, 44
+; RV64-NEXT: vand.vx v22, v8, t6
+; RV64-NEXT: slli s9, s0, 45
+; RV64-NEXT: vand.vx v26, v8, a2
+; RV64-NEXT: slli s10, s0, 46
+; RV64-NEXT: vand.vx v28, v8, a1
+; RV64-NEXT: slli s11, s0, 47
+; RV64-NEXT: vand.vx v30, v8, a0
+; RV64-NEXT: slli ra, s0, 48
+; RV64-NEXT: slli s4, s0, 49
+; RV64-NEXT: slli s3, s0, 50
+; RV64-NEXT: slli s1, s0, 51
+; RV64-NEXT: slli t6, s0, 52
+; RV64-NEXT: slli t5, s0, 53
+; RV64-NEXT: slli t3, s0, 54
+; RV64-NEXT: slli t2, s0, 55
+; RV64-NEXT: slli t1, s0, 56
+; RV64-NEXT: slli t0, s0, 57
+; RV64-NEXT: slli a4, s0, 58
+; RV64-NEXT: slli a3, s0, 59
+; RV64-NEXT: slli a2, s0, 60
+; RV64-NEXT: slli a1, s0, 61
+; RV64-NEXT: slli s0, s0, 62
+; RV64-NEXT: li a0, -1
+; RV64-NEXT: slli a0, a0, 63
+; RV64-NEXT: vand.vi v6, v8, 2
+; RV64-NEXT: vand.vi v4, v8, 1
+; RV64-NEXT: vand.vi v2, v8, 4
+; RV64-NEXT: vand.vi v0, v8, 8
+; RV64-NEXT: vmul.vv v6, v8, v6
+; RV64-NEXT: sd a5, 8(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v6, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v6, v8, v4
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v6, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v6, v8, v2
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 5
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v6, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v14
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v24
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v16
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v18
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v20
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v22
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v26
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v28
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v30
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 8
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 16
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 32
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 64
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 5
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 128
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 6
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 256
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 512
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 1024
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 2048
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 4096
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 8192
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 16384
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 32768
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 65536
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 131072
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 262144
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: ld s5, 96(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: ld s5, 88(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: ld s5, 80(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: ld s5, 72(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: ld s5, 64(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: ld s5, 56(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: ld s5, 48(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: ld s5, 40(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: ld s5, 32(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: ld s5, 24(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: ld s5, 16(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 2
+; RV64-NEXT: mv a5, s5
+; RV64-NEXT: slli s5, s5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: ld a5, 8(sp) # 8-byte Folded Reload
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 112
+; RV64-NEXT: vs2r.v v10, (s5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, s6
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 3
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 112
+; RV64-NEXT: vs2r.v v10, (s5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, s7
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 4
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 112
+; RV64-NEXT: vs2r.v v10, (s5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, s8
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s6, s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 112
+; RV64-NEXT: vs2r.v v10, (s5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, s9
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 2
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 112
+; RV64-NEXT: vs2r.v v10, (s5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, s10
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 2
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 112
+; RV64-NEXT: vs2r.v v10, (s5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, s11
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 112
+; RV64-NEXT: vs2r.v v10, (s5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, ra
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 112
+; RV64-NEXT: vs2r.v v10, (s5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, s4
+; RV64-NEXT: vmul.vv v20, v8, v10
+; RV64-NEXT: vand.vx v10, v8, s3
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: vand.vx v12, v8, s1
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr s1, vlenb
+; RV64-NEXT: slli s1, s1, 3
+; RV64-NEXT: add s1, sp, s1
+; RV64-NEXT: addi s1, s1, 112
+; RV64-NEXT: vs2r.v v12, (s1) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t6
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs2r.v v12, (t6) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t5
+; RV64-NEXT: vmul.vv v6, v8, v12
+; RV64-NEXT: vand.vx v12, v8, t3
+; RV64-NEXT: vmul.vv v22, v8, v12
+; RV64-NEXT: vand.vx v12, v8, t2
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: vand.vx v14, v8, t1
+; RV64-NEXT: vmul.vv v24, v8, v14
+; RV64-NEXT: vand.vx v14, v8, t0
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vand.vx v16, v8, a4
+; RV64-NEXT: vmul.vv v4, v8, v16
+; RV64-NEXT: vand.vx v16, v8, a3
+; RV64-NEXT: vmul.vv v2, v8, v16
+; RV64-NEXT: vand.vx v16, v8, a2
+; RV64-NEXT: vmul.vv v26, v8, v16
+; RV64-NEXT: vand.vx v16, v8, a1
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: addi a1, sp, 112
+; RV64-NEXT: vs2r.v v16, (a1) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, s0
+; RV64-NEXT: vmul.vv v18, v8, v16
+; RV64-NEXT: vand.vx v16, v8, a0
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v8, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v28, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v28, v8
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v28, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v28
+; RV64-NEXT: vxor.vv v8, v8, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v28, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v28
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v28, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v28
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v28, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v28
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v28, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v28
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v28, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v8, v28
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v28, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v28
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v28, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v28
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v28, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v28
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v28, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v28
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v28, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v28
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v28, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v28
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v28, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v28
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v28, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v28
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v28, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v28
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v28, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v28
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v28, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v28
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v28, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v28
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v28, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v28
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v28, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v28
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v28, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v28
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v28, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v28, v0, v28
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v30, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v28, v28, v30
+; RV64-NEXT: li a1, 56
+; RV64-NEXT: vsll.vx v8, v8, a1
+; RV64-NEXT: vand.vx v0, v0, s2
+; RV64-NEXT: li a0, 40
+; RV64-NEXT: vsll.vx v0, v0, a0
+; RV64-NEXT: vor.vv v8, v8, v0
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl2r.v v0, (a2) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v28, v28, v0
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 4
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl2r.v v30, (a2) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v28, v28, v30
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl2r.v v30, (a2) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v28, v28, v30
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl2r.v v30, (a2) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v28, v28, v30
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl2r.v v30, (a2) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v28, v28, v30
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl2r.v v30, (a2) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v28, v28, v30
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl2r.v v30, (a2) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v28, v28, v30
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl2r.v v30, (a2) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v28, v28, v30
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 4
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl2r.v v30, (a2) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v28, v28, v30
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 5
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl2r.v v30, (a2) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v28, v28, v30
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl2r.v v30, (a2) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v28, v28, v30
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl2r.v v30, (a2) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v28, v28, v30
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl2r.v v30, (a2) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v28, v28, v30
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl2r.v v30, (a2) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v28, v28, v30
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl2r.v v30, (a2) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v28, v30
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl2r.v v30, (a2) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v30
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl2r.v v30, (a2) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v30
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 4
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl2r.v v30, (a2) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v30
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl2r.v v30, (a2) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v30
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl2r.v v30, (a2) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v30
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl2r.v v30, (a2) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v30
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl2r.v v30, (a2) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v30
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 112
+; RV64-NEXT: vl2r.v v30, (a2) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v30, v0, v30
+; RV64-NEXT: vxor.vv v20, v30, v20
+; RV64-NEXT: vxor.vv v10, v20, v10
+; RV64-NEXT: vsrl.vi v20, v28, 8
+; RV64-NEXT: vand.vx v20, v20, t4
+; RV64-NEXT: vsrl.vi v30, v0, 24
+; RV64-NEXT: lui a2, 4080
+; RV64-NEXT: vand.vx v30, v30, a2
+; RV64-NEXT: vor.vv v20, v20, v30
+; RV64-NEXT: csrr a3, vlenb
+; RV64-NEXT: slli a3, a3, 3
+; RV64-NEXT: add a3, sp, a3
+; RV64-NEXT: addi a3, a3, 112
+; RV64-NEXT: vl2r.v v30, (a3) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v10, v10, v30
+; RV64-NEXT: csrr a3, vlenb
+; RV64-NEXT: slli a3, a3, 2
+; RV64-NEXT: add a3, sp, a3
+; RV64-NEXT: addi a3, a3, 112
+; RV64-NEXT: vl2r.v v30, (a3) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v10, v10, v30
+; RV64-NEXT: vxor.vv v10, v10, v6
+; RV64-NEXT: vxor.vv v10, v10, v22
+; RV64-NEXT: vxor.vv v10, v10, v12
+; RV64-NEXT: vand.vx v12, v28, a2
+; RV64-NEXT: vsll.vi v12, v12, 24
+; RV64-NEXT: vxor.vv v22, v10, v24
+; RV64-NEXT: vxor.vv v14, v22, v14
+; RV64-NEXT: vand.vx v22, v10, t4
+; RV64-NEXT: vsll.vi v22, v22, 8
+; RV64-NEXT: vor.vv v12, v12, v22
+; RV64-NEXT: vxor.vv v14, v14, v4
+; RV64-NEXT: vor.vv v8, v8, v12
+; RV64-NEXT: vxor.vv v12, v14, v2
+; RV64-NEXT: vxor.vv v12, v12, v26
+; RV64-NEXT: vsrl.vx v10, v10, a0
+; RV64-NEXT: vand.vx v10, v10, s2
+; RV64-NEXT: addi a0, sp, 112
+; RV64-NEXT: vl2r.v v14, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vxor.vv v12, v12, v18
+; RV64-NEXT: vxor.vv v12, v12, v16
+; RV64-NEXT: vsrl.vx v12, v12, a1
+; RV64-NEXT: vor.vv v10, v10, v12
+; RV64-NEXT: vor.vv v10, v20, v10
+; RV64-NEXT: vor.vv v8, v8, v10
+; RV64-NEXT: vsrl.vi v10, v8, 4
+; RV64-NEXT: vand.vx v8, v8, a7
+; RV64-NEXT: vand.vx v10, v10, a7
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v10, v8
+; RV64-NEXT: vsrl.vi v10, v8, 2
+; RV64-NEXT: vand.vx v8, v8, a6
+; RV64-NEXT: vand.vx v10, v10, a6
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v10, v8
+; RV64-NEXT: vsrl.vi v10, v8, 1
+; RV64-NEXT: vand.vx v8, v8, a5
+; RV64-NEXT: vand.vx v10, v10, a5
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v10, v8
+; RV64-NEXT: vsrl.vi v8, v8, 1
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add sp, sp, a0
+; RV64-NEXT: ld ra, 216(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s0, 208(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s1, 200(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s2, 192(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s3, 184(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s4, 176(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s5, 168(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s6, 160(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s7, 152(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s8, 144(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s9, 136(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s10, 128(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s11, 120(sp) # 8-byte Folded Reload
+; RV64-NEXT: addi sp, sp, 224
+; RV64-NEXT: ret
+ %a = call <vscale x 2 x i64> @llvm.clmulh.nxv2i64(<vscale x 2 x i64> %x, <vscale x 2 x i64> %y)
+ ret <vscale x 2 x i64> %a
+}
+
+define <vscale x 4 x i64> @clmulh_nxv4i64(<vscale x 4 x i64> %x, <vscale x 4 x i64> %y) nounwind {
+; RV32-LABEL: clmulh_nxv4i64:
+; RV32: # %bb.0:
+; RV32-NEXT: addi sp, sp, -352
+; RV32-NEXT: sw ra, 348(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s0, 344(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s1, 340(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s2, 336(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s3, 332(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s4, 328(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s5, 324(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s6, 320(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s7, 316(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s8, 312(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s9, 308(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s10, 304(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s11, 300(sp) # 4-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: sub sp, sp, a0
+; RV32-NEXT: lui s11, 1044480
+; RV32-NEXT: lui t6, 524288
+; RV32-NEXT: li a0, 1
+; RV32-NEXT: li ra, 2
+; RV32-NEXT: li t4, 4
+; RV32-NEXT: li t2, 8
+; RV32-NEXT: li t5, 16
+; RV32-NEXT: li t3, 32
+; RV32-NEXT: li t1, 64
+; RV32-NEXT: li t0, 128
+; RV32-NEXT: li a7, 256
+; RV32-NEXT: li a6, 512
+; RV32-NEXT: li a3, 1024
+; RV32-NEXT: lui a2, 1
+; RV32-NEXT: lui a4, 2
+; RV32-NEXT: lui a1, 4
+; RV32-NEXT: lui a5, 8
+; RV32-NEXT: lui s0, 16
+; RV32-NEXT: lui s1, 32
+; RV32-NEXT: lui s2, 64
+; RV32-NEXT: lui s3, 128
+; RV32-NEXT: lui s4, 256
+; RV32-NEXT: lui s5, 512
+; RV32-NEXT: lui s6, 1024
+; RV32-NEXT: lui s7, 2048
+; RV32-NEXT: lui s8, 4096
+; RV32-NEXT: lui s9, 8192
+; RV32-NEXT: lui s10, 16384
+; RV32-NEXT: sw s11, 272(sp)
+; RV32-NEXT: lui s11, 32768
+; RV32-NEXT: sw zero, 276(sp)
+; RV32-NEXT: sw t6, 264(sp)
+; RV32-NEXT: sw zero, 268(sp)
+; RV32-NEXT: sw zero, 256(sp)
+; RV32-NEXT: sw a0, 260(sp)
+; RV32-NEXT: sw zero, 248(sp)
+; RV32-NEXT: sw ra, 252(sp)
+; RV32-NEXT: lui ra, 65536
+; RV32-NEXT: sw zero, 240(sp)
+; RV32-NEXT: sw t4, 244(sp)
+; RV32-NEXT: lui t4, 131072
+; RV32-NEXT: sw zero, 232(sp)
+; RV32-NEXT: sw t2, 236(sp)
+; RV32-NEXT: lui t2, 262144
+; RV32-NEXT: sw zero, 224(sp)
+; RV32-NEXT: sw t5, 228(sp)
+; RV32-NEXT: sw zero, 216(sp)
+; RV32-NEXT: sw t3, 220(sp)
+; RV32-NEXT: sw zero, 208(sp)
+; RV32-NEXT: sw t1, 212(sp)
+; RV32-NEXT: sw zero, 200(sp)
+; RV32-NEXT: sw t0, 204(sp)
+; RV32-NEXT: sw zero, 192(sp)
+; RV32-NEXT: sw a7, 196(sp)
+; RV32-NEXT: sw zero, 184(sp)
+; RV32-NEXT: sw a6, 188(sp)
+; RV32-NEXT: sw zero, 176(sp)
+; RV32-NEXT: sw a3, 180(sp)
+; RV32-NEXT: li t1, 1024
+; RV32-NEXT: slli a3, a0, 11
+; RV32-NEXT: sw zero, 168(sp)
+; RV32-NEXT: sw a3, 172(sp)
+; RV32-NEXT: sw zero, 160(sp)
+; RV32-NEXT: sw a2, 164(sp)
+; RV32-NEXT: sw zero, 152(sp)
+; RV32-NEXT: sw a4, 156(sp)
+; RV32-NEXT: lui t3, 2
+; RV32-NEXT: sw zero, 144(sp)
+; RV32-NEXT: sw a1, 148(sp)
+; RV32-NEXT: sw zero, 136(sp)
+; RV32-NEXT: sw a5, 140(sp)
+; RV32-NEXT: lui t5, 8
+; RV32-NEXT: sw zero, 128(sp)
+; RV32-NEXT: sw s0, 132(sp)
+; RV32-NEXT: sw zero, 120(sp)
+; RV32-NEXT: sw s1, 124(sp)
+; RV32-NEXT: sw zero, 112(sp)
+; RV32-NEXT: sw s2, 116(sp)
+; RV32-NEXT: sw zero, 104(sp)
+; RV32-NEXT: sw s3, 108(sp)
+; RV32-NEXT: sw zero, 96(sp)
+; RV32-NEXT: sw s4, 100(sp)
+; RV32-NEXT: sw zero, 88(sp)
+; RV32-NEXT: sw s5, 92(sp)
+; RV32-NEXT: sw zero, 80(sp)
+; RV32-NEXT: sw s6, 84(sp)
+; RV32-NEXT: sw zero, 72(sp)
+; RV32-NEXT: sw s7, 76(sp)
+; RV32-NEXT: sw zero, 64(sp)
+; RV32-NEXT: sw s8, 68(sp)
+; RV32-NEXT: sw zero, 56(sp)
+; RV32-NEXT: sw s9, 60(sp)
+; RV32-NEXT: sw zero, 48(sp)
+; RV32-NEXT: sw s10, 52(sp)
+; RV32-NEXT: sw zero, 40(sp)
+; RV32-NEXT: sw s11, 44(sp)
+; RV32-NEXT: sw zero, 32(sp)
+; RV32-NEXT: sw ra, 36(sp)
+; RV32-NEXT: sw zero, 24(sp)
+; RV32-NEXT: sw t4, 28(sp)
+; RV32-NEXT: sw zero, 16(sp)
+; RV32-NEXT: sw t2, 20(sp)
+; RV32-NEXT: sw zero, 8(sp)
+; RV32-NEXT: sw t6, 12(sp)
+; RV32-NEXT: lui a1, 61681
+; RV32-NEXT: addi a1, a1, -241
+; RV32-NEXT: vsetvli a2, zero, e32, m4, ta, ma
+; RV32-NEXT: vmv.v.x v28, a1
+; RV32-NEXT: lui a1, 209715
+; RV32-NEXT: addi a1, a1, 819
+; RV32-NEXT: vmv.v.x v4, a1
+; RV32-NEXT: addi a1, sp, 272
+; RV32-NEXT: vsetvli a2, zero, e64, m4, ta, ma
+; RV32-NEXT: vlse64.v v0, (a1), zero
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 8
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v0, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: li a6, 56
+; RV32-NEXT: vsrl.vi v20, v8, 24
+; RV32-NEXT: vsrl.vx v12, v8, a6
+; RV32-NEXT: li a5, 40
+; RV32-NEXT: vsrl.vx v16, v8, a5
+; RV32-NEXT: vsll.vx v24, v8, a6
+; RV32-NEXT: addi a2, s0, -256
+; RV32-NEXT: vand.vx v16, v16, a2
+; RV32-NEXT: vor.vv v16, v16, v12
+; RV32-NEXT: vand.vx v12, v8, a2
+; RV32-NEXT: vsll.vx v12, v12, a5
+; RV32-NEXT: vor.vv v12, v24, v12
+; RV32-NEXT: vsrl.vi v24, v8, 8
+; RV32-NEXT: lui a4, 4080
+; RV32-NEXT: vand.vx v20, v20, a4
+; RV32-NEXT: lui a7, 349525
+; RV32-NEXT: addi a7, a7, 1365
+; RV32-NEXT: vand.vv v24, v24, v0
+; RV32-NEXT: vor.vv v20, v24, v20
+; RV32-NEXT: vsetvli t0, zero, e32, m4, ta, ma
+; RV32-NEXT: vmv.v.x v24, a7
+; RV32-NEXT: vsetvli a7, zero, e64, m4, ta, ma
+; RV32-NEXT: vor.vv v16, v20, v16
+; RV32-NEXT: vand.vx v20, v8, a4
+; RV32-NEXT: vsll.vi v20, v20, 24
+; RV32-NEXT: vand.vv v8, v8, v0
+; RV32-NEXT: vsll.vi v8, v8, 8
+; RV32-NEXT: vor.vv v8, v20, v8
+; RV32-NEXT: addi a7, sp, 264
+; RV32-NEXT: vlse64.v v20, (a7), zero
+; RV32-NEXT: vor.vv v8, v12, v8
+; RV32-NEXT: addi a7, sp, 256
+; RV32-NEXT: vlse64.v v12, (a7), zero
+; RV32-NEXT: vor.vv v8, v8, v16
+; RV32-NEXT: vsrl.vi v16, v8, 4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v28, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v8, v8, v28
+; RV32-NEXT: vand.vv v16, v16, v28
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v16, v8
+; RV32-NEXT: vsrl.vi v16, v8, 2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v4, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v8, v8, v4
+; RV32-NEXT: vand.vv v16, v16, v4
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v8, v16, v8
+; RV32-NEXT: vsrl.vi v16, v8, 1
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v24, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v8, v8, v24
+; RV32-NEXT: vand.vv v16, v16, v24
+; RV32-NEXT: vadd.vv v8, v8, v8
+; RV32-NEXT: vor.vv v8, v16, v8
+; RV32-NEXT: addi a7, sp, 248
+; RV32-NEXT: vlse64.v v16, (a7), zero
+; RV32-NEXT: vand.vv v28, v8, v20
+; RV32-NEXT: addi a7, sp, 240
+; RV32-NEXT: addi t0, sp, 232
+; RV32-NEXT: vlse64.v v20, (a7), zero
+; RV32-NEXT: vlse64.v v24, (t0), zero
+; RV32-NEXT: vand.vv v4, v8, v12
+; RV32-NEXT: vand.vv v0, v8, v16
+; RV32-NEXT: vand.vv v12, v8, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: addi a7, sp, 224
+; RV32-NEXT: addi t0, sp, 216
+; RV32-NEXT: addi a1, sp, 208
+; RV32-NEXT: addi a0, sp, 200
+; RV32-NEXT: vlse64.v v12, (a7), zero
+; RV32-NEXT: vlse64.v v16, (t0), zero
+; RV32-NEXT: vlse64.v v20, (a1), zero
+; RV32-NEXT: vlse64.v v24, (a0), zero
+; RV32-NEXT: vand.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 192
+; RV32-NEXT: addi a1, sp, 184
+; RV32-NEXT: addi a7, sp, 176
+; RV32-NEXT: addi t0, sp, 168
+; RV32-NEXT: vlse64.v v12, (a0), zero
+; RV32-NEXT: vlse64.v v16, (a1), zero
+; RV32-NEXT: vlse64.v v20, (a7), zero
+; RV32-NEXT: vlse64.v v24, (t0), zero
+; RV32-NEXT: vand.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 160
+; RV32-NEXT: addi a1, sp, 152
+; RV32-NEXT: addi a7, sp, 144
+; RV32-NEXT: addi t0, sp, 136
+; RV32-NEXT: vlse64.v v12, (a0), zero
+; RV32-NEXT: vlse64.v v16, (a1), zero
+; RV32-NEXT: vlse64.v v20, (a7), zero
+; RV32-NEXT: vlse64.v v24, (t0), zero
+; RV32-NEXT: vand.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 128
+; RV32-NEXT: addi a1, sp, 120
+; RV32-NEXT: addi a7, sp, 112
+; RV32-NEXT: addi t0, sp, 104
+; RV32-NEXT: vlse64.v v12, (a0), zero
+; RV32-NEXT: vlse64.v v16, (a1), zero
+; RV32-NEXT: vlse64.v v20, (a7), zero
+; RV32-NEXT: vlse64.v v24, (t0), zero
+; RV32-NEXT: vand.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 96
+; RV32-NEXT: addi a1, sp, 88
+; RV32-NEXT: addi a7, sp, 80
+; RV32-NEXT: addi t0, sp, 72
+; RV32-NEXT: vlse64.v v12, (a0), zero
+; RV32-NEXT: vlse64.v v16, (a1), zero
+; RV32-NEXT: vlse64.v v20, (a7), zero
+; RV32-NEXT: vlse64.v v24, (t0), zero
+; RV32-NEXT: vand.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 64
+; RV32-NEXT: addi a1, sp, 56
+; RV32-NEXT: addi a7, sp, 48
+; RV32-NEXT: addi t0, sp, 40
+; RV32-NEXT: vlse64.v v12, (a0), zero
+; RV32-NEXT: vlse64.v v16, (a1), zero
+; RV32-NEXT: vlse64.v v20, (a7), zero
+; RV32-NEXT: vlse64.v v24, (t0), zero
+; RV32-NEXT: vand.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 32
+; RV32-NEXT: addi a1, sp, 24
+; RV32-NEXT: addi a7, sp, 16
+; RV32-NEXT: addi t0, sp, 8
+; RV32-NEXT: vlse64.v v12, (a0), zero
+; RV32-NEXT: vlse64.v v16, (a1), zero
+; RV32-NEXT: vlse64.v v20, (a7), zero
+; RV32-NEXT: vlse64.v v24, (t0), zero
+; RV32-NEXT: vand.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 7
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vi v12, v8, 2
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vi v12, v8, 1
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vi v12, v8, 4
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vi v12, v8, 8
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: li a0, 16
+; RV32-NEXT: vand.vx v12, v8, a0
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: li a0, 32
+; RV32-NEXT: vand.vx v12, v8, a0
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: li a0, 64
+; RV32-NEXT: vand.vx v12, v8, a0
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: li a0, 128
+; RV32-NEXT: vand.vx v12, v8, a0
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: li a0, 256
+; RV32-NEXT: vand.vx v12, v8, a0
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: li a0, 512
+; RV32-NEXT: vand.vx v12, v8, a0
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, t1
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, a3
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: lui a0, 1
+; RV32-NEXT: vand.vx v12, v8, a0
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, t3
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: lui a0, 4
+; RV32-NEXT: vand.vx v12, v8, a0
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, t5
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s0
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s1
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s2
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s3
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s4
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s5
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s6
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s7
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s8
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s9
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s10
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s11
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, ra
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, t4
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, t2
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: addi a0, sp, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vmul.vv v16, v8, v28
+; RV32-NEXT: vmul.vv v20, v8, v4
+; RV32-NEXT: vmul.vv v24, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v28, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v28, v8, v28
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v4, v8, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v0, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 7
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v8, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v8, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vi v8, v8, 0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: addi a0, sp, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: vxor.vv v8, v8, v20
+; RV32-NEXT: vxor.vv v8, v8, v24
+; RV32-NEXT: vxor.vv v8, v8, v28
+; RV32-NEXT: vxor.vv v8, v8, v4
+; RV32-NEXT: vxor.vv v8, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: vsrl.vx v12, v8, a6
+; RV32-NEXT: vsrl.vx v16, v8, a5
+; RV32-NEXT: vsrl.vi v20, v8, 24
+; RV32-NEXT: vand.vx v16, v16, a2
+; RV32-NEXT: vor.vv v12, v16, v12
+; RV32-NEXT: vsrl.vi v16, v8, 8
+; RV32-NEXT: vand.vx v20, v20, a4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 8
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vand.vv v16, v16, v24
+; RV32-NEXT: vor.vv v16, v16, v20
+; RV32-NEXT: vand.vx v20, v8, a4
+; RV32-NEXT: vand.vv v24, v8, v24
+; RV32-NEXT: vsll.vi v24, v24, 8
+; RV32-NEXT: vsll.vi v20, v20, 24
+; RV32-NEXT: vor.vv v20, v20, v24
+; RV32-NEXT: vsll.vx v24, v8, a6
+; RV32-NEXT: vand.vx v8, v8, a2
+; RV32-NEXT: vsll.vx v8, v8, a5
+; RV32-NEXT: vor.vv v8, v24, v8
+; RV32-NEXT: vor.vv v12, v16, v12
+; RV32-NEXT: vor.vv v8, v8, v20
+; RV32-NEXT: vor.vv v8, v8, v12
+; RV32-NEXT: vsrl.vi v12, v8, 4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v16
+; RV32-NEXT: vand.vv v12, v12, v16
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v12, v8
+; RV32-NEXT: vsrl.vi v12, v8, 2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v16
+; RV32-NEXT: vand.vv v12, v12, v16
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v8, v12, v8
+; RV32-NEXT: vsrl.vi v12, v8, 1
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v16
+; RV32-NEXT: vand.vv v12, v12, v16
+; RV32-NEXT: vadd.vv v8, v8, v8
+; RV32-NEXT: vor.vv v8, v12, v8
+; RV32-NEXT: vsrl.vi v8, v8, 1
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add sp, sp, a0
+; RV32-NEXT: lw ra, 348(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s0, 344(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s1, 340(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s2, 336(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s3, 332(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s4, 328(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s5, 324(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s6, 320(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s7, 316(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s8, 312(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s9, 308(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s10, 304(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s11, 300(sp) # 4-byte Folded Reload
+; RV32-NEXT: addi sp, sp, 352
+; RV32-NEXT: ret
+;
+; RV64-LABEL: clmulh_nxv4i64:
+; RV64: # %bb.0:
+; RV64-NEXT: addi sp, sp, -240
+; RV64-NEXT: sd ra, 232(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s0, 224(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s1, 216(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s2, 208(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s3, 200(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s4, 192(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s5, 184(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s6, 176(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s7, 168(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s8, 160(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s9, 152(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s10, 144(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s11, 136(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: sub sp, sp, a0
+; RV64-NEXT: li t0, 40
+; RV64-NEXT: lui a7, 16
+; RV64-NEXT: vsetvli a0, zero, e64, m4, ta, ma
+; RV64-NEXT: vsrl.vi v20, v8, 24
+; RV64-NEXT: vsrl.vi v12, v8, 8
+; RV64-NEXT: li t2, 255
+; RV64-NEXT: lui a3, 61681
+; RV64-NEXT: lui a4, 209715
+; RV64-NEXT: lui a5, 349525
+; RV64-NEXT: li a2, 16
+; RV64-NEXT: li a1, 32
+; RV64-NEXT: li a0, 64
+; RV64-NEXT: li s9, 1
+; RV64-NEXT: li a6, 56
+; RV64-NEXT: vsrl.vx v16, v8, a6
+; RV64-NEXT: vsrl.vx v28, v8, t0
+; RV64-NEXT: addi t6, a7, -256
+; RV64-NEXT: lui a7, 4080
+; RV64-NEXT: vand.vx v24, v20, a7
+; RV64-NEXT: slli t2, t2, 24
+; RV64-NEXT: vand.vx v4, v8, a7
+; RV64-NEXT: vsll.vx v20, v8, a6
+; RV64-NEXT: addi a7, a3, -241
+; RV64-NEXT: addi a6, a4, 819
+; RV64-NEXT: addi a5, a5, 1365
+; RV64-NEXT: slli a3, s9, 11
+; RV64-NEXT: sd a3, 112(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a3, s9, 31
+; RV64-NEXT: sd a3, 104(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a3, s9, 32
+; RV64-NEXT: sd a3, 96(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a3, s9, 33
+; RV64-NEXT: sd a3, 88(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a3, s9, 34
+; RV64-NEXT: sd a3, 80(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a3, s9, 35
+; RV64-NEXT: sd a3, 72(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a3, s9, 36
+; RV64-NEXT: sd a3, 64(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a3, s9, 37
+; RV64-NEXT: sd a3, 56(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a3, s9, 38
+; RV64-NEXT: sd a3, 48(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a3, s9, 39
+; RV64-NEXT: sd a3, 40(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a3, s9, 40
+; RV64-NEXT: sd a3, 32(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a3, s9, 41
+; RV64-NEXT: sd a3, 24(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli s6, s9, 42
+; RV64-NEXT: slli s7, s9, 43
+; RV64-NEXT: slli a3, a7, 32
+; RV64-NEXT: add a7, a7, a3
+; RV64-NEXT: slli a3, a6, 32
+; RV64-NEXT: add a6, a6, a3
+; RV64-NEXT: slli a3, a5, 32
+; RV64-NEXT: add a5, a5, a3
+; RV64-NEXT: slli s8, s9, 44
+; RV64-NEXT: vand.vx v28, v28, t6
+; RV64-NEXT: vand.vx v12, v12, t2
+; RV64-NEXT: vsll.vi v4, v4, 24
+; RV64-NEXT: vand.vx v0, v8, t2
+; RV64-NEXT: vand.vx v8, v8, t6
+; RV64-NEXT: vor.vv v16, v28, v16
+; RV64-NEXT: vor.vv v12, v12, v24
+; RV64-NEXT: vsll.vi v24, v0, 8
+; RV64-NEXT: vsll.vx v8, v8, t0
+; RV64-NEXT: vor.vv v12, v12, v16
+; RV64-NEXT: vor.vv v16, v4, v24
+; RV64-NEXT: vor.vv v8, v20, v8
+; RV64-NEXT: vor.vv v8, v8, v16
+; RV64-NEXT: vor.vv v8, v8, v12
+; RV64-NEXT: vsrl.vi v12, v8, 4
+; RV64-NEXT: vand.vx v8, v8, a7
+; RV64-NEXT: vand.vx v12, v12, a7
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vsrl.vi v12, v8, 2
+; RV64-NEXT: vand.vx v8, v8, a6
+; RV64-NEXT: vand.vx v12, v12, a6
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vsrl.vi v12, v8, 1
+; RV64-NEXT: vand.vx v8, v8, a5
+; RV64-NEXT: vand.vx v12, v12, a5
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vand.vx v12, v8, a2
+; RV64-NEXT: slli s10, s9, 45
+; RV64-NEXT: vand.vx v16, v8, a1
+; RV64-NEXT: slli s11, s9, 46
+; RV64-NEXT: vand.vx v20, v8, a0
+; RV64-NEXT: slli ra, s9, 47
+; RV64-NEXT: slli s4, s9, 48
+; RV64-NEXT: slli s3, s9, 49
+; RV64-NEXT: slli s2, s9, 50
+; RV64-NEXT: slli s1, s9, 51
+; RV64-NEXT: slli s0, s9, 52
+; RV64-NEXT: slli t5, s9, 53
+; RV64-NEXT: slli t4, s9, 54
+; RV64-NEXT: slli t3, s9, 55
+; RV64-NEXT: slli t1, s9, 56
+; RV64-NEXT: slli t0, s9, 57
+; RV64-NEXT: slli a4, s9, 58
+; RV64-NEXT: slli a3, s9, 59
+; RV64-NEXT: slli a2, s9, 60
+; RV64-NEXT: slli a1, s9, 61
+; RV64-NEXT: slli s9, s9, 62
+; RV64-NEXT: li a0, -1
+; RV64-NEXT: slli a0, a0, 63
+; RV64-NEXT: vand.vi v24, v8, 2
+; RV64-NEXT: vand.vi v28, v8, 1
+; RV64-NEXT: vand.vi v4, v8, 4
+; RV64-NEXT: vand.vi v0, v8, 8
+; RV64-NEXT: vmul.vv v24, v8, v24
+; RV64-NEXT: vmul.vv v28, v8, v28
+; RV64-NEXT: sd a5, 8(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v28, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vmul.vv v28, v8, v4
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v28, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 5
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vmul.vv v12, v8, v16
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vmul.vv v12, v8, v20
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: li s5, 128
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: li s5, 256
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: li s5, 512
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: li s5, 1024
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: ld s5, 112(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 1
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 6
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 2
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 4
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 8
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 16
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 32
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 64
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 128
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 256
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 5
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 512
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 1024
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 2048
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 4096
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 8192
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 16384
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 32768
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 5
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 65536
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 7
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 131072
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 262144
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: ld s5, 104(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: ld s5, 96(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: ld s5, 88(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: ld s5, 80(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: ld s5, 72(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: ld s5, 64(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 5
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: ld s5, 56(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: ld s5, 48(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: ld s5, 40(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: ld s5, 32(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: ld s5, 24(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 2
+; RV64-NEXT: mv a5, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: slli s5, s5, 3
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: ld a5, 8(sp) # 8-byte Folded Reload
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 128
+; RV64-NEXT: vs4r.v v12, (s5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s6
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 3
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 3
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 128
+; RV64-NEXT: vs4r.v v12, (s5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s7
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 2
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 4
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 128
+; RV64-NEXT: vs4r.v v12, (s5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s8
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 128
+; RV64-NEXT: vs4r.v v12, (s5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s10
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 2
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s6, s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s6, s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 128
+; RV64-NEXT: vs4r.v v12, (s5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s11
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 3
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s6, s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 128
+; RV64-NEXT: vs4r.v v12, (s5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, ra
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 4
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 128
+; RV64-NEXT: vs4r.v v12, (s5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s4
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr s4, vlenb
+; RV64-NEXT: slli s4, s4, 3
+; RV64-NEXT: mv s5, s4
+; RV64-NEXT: slli s4, s4, 2
+; RV64-NEXT: add s4, s4, s5
+; RV64-NEXT: add s4, sp, s4
+; RV64-NEXT: addi s4, s4, 128
+; RV64-NEXT: vs4r.v v12, (s4) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s3
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr s3, vlenb
+; RV64-NEXT: slli s3, s3, 2
+; RV64-NEXT: mv s4, s3
+; RV64-NEXT: slli s3, s3, 2
+; RV64-NEXT: add s3, s3, s4
+; RV64-NEXT: add s3, sp, s3
+; RV64-NEXT: addi s3, s3, 128
+; RV64-NEXT: vs4r.v v12, (s3) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s2
+; RV64-NEXT: vmul.vv v4, v8, v12
+; RV64-NEXT: vand.vx v12, v8, s1
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr s1, vlenb
+; RV64-NEXT: slli s1, s1, 2
+; RV64-NEXT: mv s2, s1
+; RV64-NEXT: slli s1, s1, 2
+; RV64-NEXT: add s2, s2, s1
+; RV64-NEXT: slli s1, s1, 1
+; RV64-NEXT: add s1, s1, s2
+; RV64-NEXT: add s1, sp, s1
+; RV64-NEXT: addi s1, s1, 128
+; RV64-NEXT: vs4r.v v12, (s1) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s0
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr s0, vlenb
+; RV64-NEXT: slli s0, s0, 2
+; RV64-NEXT: mv s1, s0
+; RV64-NEXT: slli s0, s0, 1
+; RV64-NEXT: add s1, s1, s0
+; RV64-NEXT: slli s0, s0, 2
+; RV64-NEXT: add s0, s0, s1
+; RV64-NEXT: add s0, sp, s0
+; RV64-NEXT: addi s0, s0, 128
+; RV64-NEXT: vs4r.v v12, (s0) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr t5, vlenb
+; RV64-NEXT: slli t5, t5, 2
+; RV64-NEXT: mv s0, t5
+; RV64-NEXT: slli t5, t5, 3
+; RV64-NEXT: add t5, t5, s0
+; RV64-NEXT: add t5, sp, t5
+; RV64-NEXT: addi t5, t5, 128
+; RV64-NEXT: vs4r.v v12, (t5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t4
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr t4, vlenb
+; RV64-NEXT: slli t4, t4, 4
+; RV64-NEXT: add t4, sp, t4
+; RV64-NEXT: addi t4, t4, 128
+; RV64-NEXT: vs4r.v v12, (t4) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t3
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr t3, vlenb
+; RV64-NEXT: slli t3, t3, 2
+; RV64-NEXT: add t3, sp, t3
+; RV64-NEXT: addi t3, t3, 128
+; RV64-NEXT: vs4r.v v12, (t3) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t1
+; RV64-NEXT: vmul.vv v20, v8, v12
+; RV64-NEXT: vand.vx v12, v8, t0
+; RV64-NEXT: vmul.vv v16, v8, v12
+; RV64-NEXT: vand.vx v12, v8, a4
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a4, vlenb
+; RV64-NEXT: slli a4, a4, 5
+; RV64-NEXT: add a4, sp, a4
+; RV64-NEXT: addi a4, a4, 128
+; RV64-NEXT: vs4r.v v12, (a4) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, a3
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a3, vlenb
+; RV64-NEXT: slli a3, a3, 2
+; RV64-NEXT: mv a4, a3
+; RV64-NEXT: slli a3, a3, 1
+; RV64-NEXT: add a4, a4, a3
+; RV64-NEXT: slli a3, a3, 1
+; RV64-NEXT: add a3, a3, a4
+; RV64-NEXT: add a3, sp, a3
+; RV64-NEXT: addi a3, a3, 128
+; RV64-NEXT: vs4r.v v12, (a3) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, a2
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vs4r.v v12, (a2) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, a1
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: mv a2, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add a1, a1, a2
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs4r.v v12, (a1) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s9
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs4r.v v12, (a1) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, a0
+; RV64-NEXT: vmul.vv v8, v8, v12
+; RV64-NEXT: addi a0, sp, 128
+; RV64-NEXT: vs4r.v v8, (a0) # vscale x 32-byte Folded Spill
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v8, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v12
+; RV64-NEXT: vxor.vv v8, v8, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v12
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v12
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v12
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v12
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v12, v8, v12
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v12, v12, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v12, v12, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v12, v12, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 6
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v12, v12, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v12, v12, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v12, v12, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v12, v12, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v12, v12, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v12, v12, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v12, v12, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v12, v12, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v12, v12, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v12, v12, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v12, v12, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v12, v12, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v12, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v24
+; RV64-NEXT: li a1, 56
+; RV64-NEXT: vsll.vx v8, v8, a1
+; RV64-NEXT: vand.vx v12, v12, t6
+; RV64-NEXT: li a0, 40
+; RV64-NEXT: vsll.vx v12, v12, a0
+; RV64-NEXT: vor.vv v12, v8, v12
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 4
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v8, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v0, v8
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 5
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v24, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 7
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v24, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v24, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v24, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v24, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 4
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v24, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v24, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v24, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v24, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 5
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v24, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v24, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v24, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v24, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 4
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v24, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v8, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v24, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v24, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 4
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v24, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 6
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v24, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v24, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v24, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 4
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v24, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v24, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v0, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v28, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v24, v28
+; RV64-NEXT: vxor.vv v24, v24, v4
+; RV64-NEXT: vsrl.vi v4, v8, 8
+; RV64-NEXT: vand.vx v4, v4, t2
+; RV64-NEXT: vsrl.vi v0, v0, 24
+; RV64-NEXT: lui a2, 4080
+; RV64-NEXT: vand.vx v0, v0, a2
+; RV64-NEXT: vor.vv v4, v4, v0
+; RV64-NEXT: csrr a3, vlenb
+; RV64-NEXT: slli a3, a3, 2
+; RV64-NEXT: mv a4, a3
+; RV64-NEXT: slli a3, a3, 2
+; RV64-NEXT: add a4, a4, a3
+; RV64-NEXT: slli a3, a3, 1
+; RV64-NEXT: add a3, a3, a4
+; RV64-NEXT: add a3, sp, a3
+; RV64-NEXT: addi a3, a3, 128
+; RV64-NEXT: vl4r.v v0, (a3) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: csrr a3, vlenb
+; RV64-NEXT: slli a3, a3, 2
+; RV64-NEXT: mv a4, a3
+; RV64-NEXT: slli a3, a3, 1
+; RV64-NEXT: add a4, a4, a3
+; RV64-NEXT: slli a3, a3, 2
+; RV64-NEXT: add a3, a3, a4
+; RV64-NEXT: add a3, sp, a3
+; RV64-NEXT: addi a3, a3, 128
+; RV64-NEXT: vl4r.v v0, (a3) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: csrr a3, vlenb
+; RV64-NEXT: slli a3, a3, 2
+; RV64-NEXT: mv a4, a3
+; RV64-NEXT: slli a3, a3, 3
+; RV64-NEXT: add a3, a3, a4
+; RV64-NEXT: add a3, sp, a3
+; RV64-NEXT: addi a3, a3, 128
+; RV64-NEXT: vl4r.v v0, (a3) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: csrr a3, vlenb
+; RV64-NEXT: slli a3, a3, 4
+; RV64-NEXT: add a3, sp, a3
+; RV64-NEXT: addi a3, a3, 128
+; RV64-NEXT: vl4r.v v28, (a3) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v24, v28
+; RV64-NEXT: csrr a3, vlenb
+; RV64-NEXT: slli a3, a3, 2
+; RV64-NEXT: add a3, sp, a3
+; RV64-NEXT: addi a3, a3, 128
+; RV64-NEXT: vl4r.v v28, (a3) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v24, v28
+; RV64-NEXT: vxor.vv v20, v24, v20
+; RV64-NEXT: vxor.vv v16, v20, v16
+; RV64-NEXT: vand.vx v8, v8, a2
+; RV64-NEXT: vsll.vi v8, v8, 24
+; RV64-NEXT: vand.vx v20, v24, t2
+; RV64-NEXT: vsll.vi v20, v20, 8
+; RV64-NEXT: vor.vv v8, v8, v20
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 5
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v20, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v12, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v12, v16, v12
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl4r.v v16, (a2) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v12, v12, v16
+; RV64-NEXT: vsrl.vx v16, v24, a0
+; RV64-NEXT: vand.vx v16, v16, t6
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a2, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a2
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v20, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v12, v12, v20
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v20, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v12, v12, v20
+; RV64-NEXT: addi a0, sp, 128
+; RV64-NEXT: vl4r.v v20, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v12, v12, v20
+; RV64-NEXT: vsrl.vx v12, v12, a1
+; RV64-NEXT: vor.vv v12, v16, v12
+; RV64-NEXT: vor.vv v12, v4, v12
+; RV64-NEXT: vor.vv v8, v8, v12
+; RV64-NEXT: vsrl.vi v12, v8, 4
+; RV64-NEXT: vand.vx v8, v8, a7
+; RV64-NEXT: vand.vx v12, v12, a7
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vsrl.vi v12, v8, 2
+; RV64-NEXT: vand.vx v8, v8, a6
+; RV64-NEXT: vand.vx v12, v12, a6
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vsrl.vi v12, v8, 1
+; RV64-NEXT: vand.vx v8, v8, a5
+; RV64-NEXT: vand.vx v12, v12, a5
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vsrl.vi v8, v8, 1
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add sp, sp, a0
+; RV64-NEXT: ld ra, 232(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s0, 224(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s1, 216(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s2, 208(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s3, 200(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s4, 192(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s5, 184(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s6, 176(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s7, 168(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s8, 160(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s9, 152(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s10, 144(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s11, 136(sp) # 8-byte Folded Reload
+; RV64-NEXT: addi sp, sp, 240
+; RV64-NEXT: ret
+ %a = call <vscale x 4 x i64> @llvm.clmulh.nxv4i64(<vscale x 4 x i64> %x, <vscale x 4 x i64> %y)
+ ret <vscale x 4 x i64> %a
+}
+
+define <vscale x 8 x i64> @clmulh_nxv8i64(<vscale x 8 x i64> %x, <vscale x 8 x i64> %y) nounwind {
+; RV32-LABEL: clmulh_nxv8i64:
+; RV32: # %bb.0:
+; RV32-NEXT: addi sp, sp, -352
+; RV32-NEXT: sw ra, 348(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s0, 344(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s1, 340(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s2, 336(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s3, 332(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s4, 328(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s5, 324(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s6, 320(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s7, 316(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s8, 312(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s9, 308(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s10, 304(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s11, 300(sp) # 4-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: sub sp, sp, a0
+; RV32-NEXT: lui s11, 1044480
+; RV32-NEXT: lui s0, 524288
+; RV32-NEXT: li a0, 1
+; RV32-NEXT: li ra, 2
+; RV32-NEXT: li t4, 4
+; RV32-NEXT: li t2, 8
+; RV32-NEXT: li t6, 16
+; RV32-NEXT: li t5, 32
+; RV32-NEXT: li t3, 64
+; RV32-NEXT: li t1, 128
+; RV32-NEXT: li t0, 256
+; RV32-NEXT: li a7, 512
+; RV32-NEXT: li a6, 1024
+; RV32-NEXT: lui a4, 1
+; RV32-NEXT: lui a3, 2
+; RV32-NEXT: lui a2, 4
+; RV32-NEXT: lui a5, 8
+; RV32-NEXT: lui s1, 16
+; RV32-NEXT: lui a1, 32
+; RV32-NEXT: lui s2, 64
+; RV32-NEXT: lui s3, 128
+; RV32-NEXT: lui s4, 256
+; RV32-NEXT: lui s5, 512
+; RV32-NEXT: lui s6, 1024
+; RV32-NEXT: lui s7, 2048
+; RV32-NEXT: lui s8, 4096
+; RV32-NEXT: lui s9, 8192
+; RV32-NEXT: lui s10, 16384
+; RV32-NEXT: sw s11, 272(sp)
+; RV32-NEXT: lui s11, 32768
+; RV32-NEXT: sw zero, 276(sp)
+; RV32-NEXT: sw s0, 264(sp)
+; RV32-NEXT: sw zero, 268(sp)
+; RV32-NEXT: sw zero, 256(sp)
+; RV32-NEXT: sw a0, 260(sp)
+; RV32-NEXT: sw zero, 248(sp)
+; RV32-NEXT: sw ra, 252(sp)
+; RV32-NEXT: lui ra, 65536
+; RV32-NEXT: sw zero, 240(sp)
+; RV32-NEXT: sw t4, 244(sp)
+; RV32-NEXT: lui t4, 131072
+; RV32-NEXT: sw zero, 232(sp)
+; RV32-NEXT: sw t2, 236(sp)
+; RV32-NEXT: lui t2, 262144
+; RV32-NEXT: sw zero, 224(sp)
+; RV32-NEXT: sw t6, 228(sp)
+; RV32-NEXT: sw zero, 216(sp)
+; RV32-NEXT: sw t5, 220(sp)
+; RV32-NEXT: sw zero, 208(sp)
+; RV32-NEXT: sw t3, 212(sp)
+; RV32-NEXT: sw zero, 200(sp)
+; RV32-NEXT: sw t1, 204(sp)
+; RV32-NEXT: sw zero, 192(sp)
+; RV32-NEXT: sw t0, 196(sp)
+; RV32-NEXT: sw zero, 184(sp)
+; RV32-NEXT: sw a7, 188(sp)
+; RV32-NEXT: sw zero, 176(sp)
+; RV32-NEXT: sw a6, 180(sp)
+; RV32-NEXT: li t1, 1024
+; RV32-NEXT: slli t6, a0, 11
+; RV32-NEXT: sw zero, 168(sp)
+; RV32-NEXT: sw t6, 172(sp)
+; RV32-NEXT: sw zero, 160(sp)
+; RV32-NEXT: sw a4, 164(sp)
+; RV32-NEXT: sw zero, 152(sp)
+; RV32-NEXT: sw a3, 156(sp)
+; RV32-NEXT: lui t3, 2
+; RV32-NEXT: sw zero, 144(sp)
+; RV32-NEXT: sw a2, 148(sp)
+; RV32-NEXT: lui t5, 4
+; RV32-NEXT: sw zero, 136(sp)
+; RV32-NEXT: sw a5, 140(sp)
+; RV32-NEXT: lui a4, 8
+; RV32-NEXT: sw zero, 128(sp)
+; RV32-NEXT: sw s1, 132(sp)
+; RV32-NEXT: sw zero, 120(sp)
+; RV32-NEXT: sw a1, 124(sp)
+; RV32-NEXT: sw zero, 112(sp)
+; RV32-NEXT: sw s2, 116(sp)
+; RV32-NEXT: sw zero, 104(sp)
+; RV32-NEXT: sw s3, 108(sp)
+; RV32-NEXT: sw zero, 96(sp)
+; RV32-NEXT: sw s4, 100(sp)
+; RV32-NEXT: sw zero, 88(sp)
+; RV32-NEXT: sw s5, 92(sp)
+; RV32-NEXT: sw zero, 80(sp)
+; RV32-NEXT: sw s6, 84(sp)
+; RV32-NEXT: sw zero, 72(sp)
+; RV32-NEXT: sw s7, 76(sp)
+; RV32-NEXT: sw zero, 64(sp)
+; RV32-NEXT: sw s8, 68(sp)
+; RV32-NEXT: sw zero, 56(sp)
+; RV32-NEXT: sw s9, 60(sp)
+; RV32-NEXT: sw zero, 48(sp)
+; RV32-NEXT: sw s10, 52(sp)
+; RV32-NEXT: sw zero, 40(sp)
+; RV32-NEXT: sw s11, 44(sp)
+; RV32-NEXT: sw zero, 32(sp)
+; RV32-NEXT: sw ra, 36(sp)
+; RV32-NEXT: sw zero, 24(sp)
+; RV32-NEXT: sw t4, 28(sp)
+; RV32-NEXT: sw zero, 16(sp)
+; RV32-NEXT: sw t2, 20(sp)
+; RV32-NEXT: sw zero, 8(sp)
+; RV32-NEXT: sw s0, 12(sp)
+; RV32-NEXT: li a6, 56
+; RV32-NEXT: vsetvli a1, zero, e64, m8, ta, ma
+; RV32-NEXT: vsrl.vx v16, v8, a6
+; RV32-NEXT: li a5, 40
+; RV32-NEXT: vsrl.vx v24, v8, a5
+; RV32-NEXT: vsll.vx v0, v8, a6
+; RV32-NEXT: addi a2, s1, -256
+; RV32-NEXT: vand.vx v24, v24, a2
+; RV32-NEXT: vor.vv v16, v24, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v24, v8, a2
+; RV32-NEXT: vsll.vx v24, v24, a5
+; RV32-NEXT: vor.vv v16, v0, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: addi a3, sp, 272
+; RV32-NEXT: vlse64.v v24, (a3), zero
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v24, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: lui a3, 4080
+; RV32-NEXT: vsrl.vi v0, v8, 24
+; RV32-NEXT: vand.vx v16, v0, a3
+; RV32-NEXT: vsrl.vi v24, v8, 8
+; RV32-NEXT: vmv8r.v v0, v8
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v8, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v24, v24, v8
+; RV32-NEXT: vor.vv v24, v24, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v8, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vor.vv v16, v24, v8
+; RV32-NEXT: vand.vx v24, v0, a3
+; RV32-NEXT: vsll.vi v24, v24, 24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v8, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v0, v0, v8
+; RV32-NEXT: vsll.vi v0, v0, 8
+; RV32-NEXT: vor.vv v24, v24, v0
+; RV32-NEXT: lui a7, 61681
+; RV32-NEXT: addi a7, a7, -241
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v8, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vor.vv v8, v8, v24
+; RV32-NEXT: vsetvli t0, zero, e32, m8, ta, ma
+; RV32-NEXT: vmv.v.x v24, a7
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v24, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: lui a7, 209715
+; RV32-NEXT: addi a7, a7, 819
+; RV32-NEXT: vsetvli t0, zero, e64, m8, ta, ma
+; RV32-NEXT: vor.vv v8, v8, v16
+; RV32-NEXT: vsrl.vi v16, v8, 4
+; RV32-NEXT: vand.vv v8, v8, v24
+; RV32-NEXT: vand.vv v16, v16, v24
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v16, v8
+; RV32-NEXT: vsetvli t0, zero, e32, m8, ta, ma
+; RV32-NEXT: vmv.v.x v24, a7
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v24, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vsetvli a7, zero, e64, m8, ta, ma
+; RV32-NEXT: vsrl.vi v16, v8, 2
+; RV32-NEXT: vand.vv v8, v8, v24
+; RV32-NEXT: vand.vv v16, v16, v24
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v16, v16, v8
+; RV32-NEXT: lui a7, 349525
+; RV32-NEXT: addi a7, a7, 1365
+; RV32-NEXT: vsetvli t0, zero, e32, m8, ta, ma
+; RV32-NEXT: vmv.v.x v24, a7
+; RV32-NEXT: vsetvli a7, zero, e64, m8, ta, ma
+; RV32-NEXT: vsrl.vi v8, v16, 1
+; RV32-NEXT: vand.vv v16, v16, v24
+; RV32-NEXT: vmv8r.v v0, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 9
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v24, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: addi a7, sp, 264
+; RV32-NEXT: vlse64.v v24, (a7), zero
+; RV32-NEXT: vand.vv v8, v8, v0
+; RV32-NEXT: vadd.vv v16, v16, v16
+; RV32-NEXT: vor.vv v8, v8, v16
+; RV32-NEXT: vand.vv v16, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: addi a7, sp, 256
+; RV32-NEXT: addi t0, sp, 248
+; RV32-NEXT: addi a1, sp, 240
+; RV32-NEXT: addi a0, sp, 232
+; RV32-NEXT: vlse64.v v16, (a7), zero
+; RV32-NEXT: csrr a7, vlenb
+; RV32-NEXT: slli a7, a7, 4
+; RV32-NEXT: mv s0, a7
+; RV32-NEXT: slli a7, a7, 1
+; RV32-NEXT: add s0, s0, a7
+; RV32-NEXT: slli a7, a7, 1
+; RV32-NEXT: add s0, s0, a7
+; RV32-NEXT: slli a7, a7, 1
+; RV32-NEXT: add s0, s0, a7
+; RV32-NEXT: slli a7, a7, 1
+; RV32-NEXT: add a7, a7, s0
+; RV32-NEXT: add a7, sp, a7
+; RV32-NEXT: addi a7, a7, 288
+; RV32-NEXT: vs8r.v v16, (a7) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vlse64.v v24, (t0), zero
+; RV32-NEXT: vlse64.v v0, (a1), zero
+; RV32-NEXT: vlse64.v v16, (a0), zero
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 224
+; RV32-NEXT: addi a1, sp, 216
+; RV32-NEXT: addi a7, sp, 208
+; RV32-NEXT: addi t0, sp, 200
+; RV32-NEXT: vlse64.v v16, (a0), zero
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv s0, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add s0, s0, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add s0, s0, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, s0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vlse64.v v24, (a1), zero
+; RV32-NEXT: vlse64.v v0, (a7), zero
+; RV32-NEXT: vlse64.v v16, (t0), zero
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 192
+; RV32-NEXT: addi a1, sp, 184
+; RV32-NEXT: addi a7, sp, 176
+; RV32-NEXT: addi t0, sp, 168
+; RV32-NEXT: vlse64.v v16, (a0), zero
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv s0, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add s0, s0, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add s0, s0, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, s0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vlse64.v v24, (a1), zero
+; RV32-NEXT: vlse64.v v0, (a7), zero
+; RV32-NEXT: vlse64.v v16, (t0), zero
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 160
+; RV32-NEXT: addi a1, sp, 152
+; RV32-NEXT: addi a7, sp, 144
+; RV32-NEXT: addi t0, sp, 136
+; RV32-NEXT: vlse64.v v16, (a0), zero
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv s0, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add s0, s0, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, s0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vlse64.v v24, (a1), zero
+; RV32-NEXT: vlse64.v v0, (a7), zero
+; RV32-NEXT: vlse64.v v16, (t0), zero
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 7
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 128
+; RV32-NEXT: addi a1, sp, 120
+; RV32-NEXT: addi a7, sp, 112
+; RV32-NEXT: addi t0, sp, 104
+; RV32-NEXT: vlse64.v v16, (a0), zero
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv s0, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add s0, s0, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add s0, s0, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, s0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vlse64.v v24, (a1), zero
+; RV32-NEXT: vlse64.v v0, (a7), zero
+; RV32-NEXT: vlse64.v v16, (t0), zero
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 96
+; RV32-NEXT: addi a1, sp, 88
+; RV32-NEXT: addi a7, sp, 80
+; RV32-NEXT: addi t0, sp, 72
+; RV32-NEXT: vlse64.v v16, (a0), zero
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv s0, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add s0, s0, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, s0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vlse64.v v24, (a1), zero
+; RV32-NEXT: vlse64.v v0, (a7), zero
+; RV32-NEXT: vlse64.v v16, (t0), zero
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 64
+; RV32-NEXT: addi a1, sp, 56
+; RV32-NEXT: addi a7, sp, 48
+; RV32-NEXT: addi t0, sp, 40
+; RV32-NEXT: vlse64.v v16, (a0), zero
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv s0, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add s0, s0, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, s0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vlse64.v v24, (a1), zero
+; RV32-NEXT: vlse64.v v0, (a7), zero
+; RV32-NEXT: vlse64.v v16, (t0), zero
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 32
+; RV32-NEXT: addi a1, sp, 24
+; RV32-NEXT: addi a7, sp, 16
+; RV32-NEXT: addi t0, sp, 8
+; RV32-NEXT: vlse64.v v16, (a0), zero
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv s0, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, s0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vlse64.v v24, (a1), zero
+; RV32-NEXT: vlse64.v v0, (a7), zero
+; RV32-NEXT: vlse64.v v16, (t0), zero
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 8
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vi v16, v8, 2
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vi v16, v8, 1
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vi v16, v8, 4
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vi v16, v8, 8
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: li a0, 16
+; RV32-NEXT: vand.vx v16, v8, a0
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: li a0, 32
+; RV32-NEXT: vand.vx v16, v8, a0
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: li a0, 64
+; RV32-NEXT: vand.vx v16, v8, a0
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: li a0, 128
+; RV32-NEXT: vand.vx v16, v8, a0
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: li a0, 256
+; RV32-NEXT: vand.vx v16, v8, a0
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: li a0, 512
+; RV32-NEXT: vand.vx v16, v8, a0
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, t1
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, t6
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: lui a0, 1
+; RV32-NEXT: vand.vx v16, v8, a0
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, t3
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, t5
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 7
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, a4
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, s1
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: lui a0, 32
+; RV32-NEXT: vand.vx v16, v8, a0
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, s2
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, s3
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, s4
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, s5
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, s6
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, s7
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, s8
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, s9
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, s10
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, s11
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, ra
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, t4
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vand.vx v16, v8, t2
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: addi a0, sp, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v0, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 7
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 7
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 8
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vmul.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 8
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v8, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v8, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vi v8, v8, 0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 7
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: addi a0, sp, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: vxor.vv v8, v8, v24
+; RV32-NEXT: vxor.vv v8, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 7
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 8
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: vsrl.vx v16, v8, a5
+; RV32-NEXT: vand.vx v16, v16, a2
+; RV32-NEXT: vsrl.vx v24, v8, a6
+; RV32-NEXT: vor.vv v16, v16, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs8r.v v16, (a0) # vscale x 64-byte Folded Spill
+; RV32-NEXT: vsrl.vi v24, v8, 24
+; RV32-NEXT: vand.vx v24, v24, a3
+; RV32-NEXT: vsrl.vi v0, v8, 8
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v0, v0, v16
+; RV32-NEXT: vor.vv v24, v0, v24
+; RV32-NEXT: vand.vv v0, v8, v16
+; RV32-NEXT: vsll.vi v0, v0, 8
+; RV32-NEXT: vand.vx v16, v8, a3
+; RV32-NEXT: vsll.vi v16, v16, 24
+; RV32-NEXT: vor.vv v16, v16, v0
+; RV32-NEXT: vsll.vx v0, v8, a6
+; RV32-NEXT: vand.vx v8, v8, a2
+; RV32-NEXT: vsll.vx v8, v8, a5
+; RV32-NEXT: vor.vv v8, v0, v8
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v0, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vor.vv v24, v24, v0
+; RV32-NEXT: vor.vv v8, v8, v16
+; RV32-NEXT: vor.vv v8, v8, v24
+; RV32-NEXT: vsrl.vi v16, v8, 4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v24
+; RV32-NEXT: vand.vv v16, v16, v24
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v16, v8
+; RV32-NEXT: vsrl.vi v16, v8, 2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v24
+; RV32-NEXT: vand.vv v16, v16, v24
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v8, v16, v8
+; RV32-NEXT: vsrl.vi v16, v8, 1
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 9
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v24
+; RV32-NEXT: vand.vv v16, v16, v24
+; RV32-NEXT: vadd.vv v8, v8, v8
+; RV32-NEXT: vor.vv v8, v16, v8
+; RV32-NEXT: vsrl.vi v8, v8, 1
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add sp, sp, a0
+; RV32-NEXT: lw ra, 348(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s0, 344(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s1, 340(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s2, 336(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s3, 332(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s4, 328(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s5, 324(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s6, 320(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s7, 316(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s8, 312(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s9, 308(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s10, 304(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s11, 300(sp) # 4-byte Folded Reload
+; RV32-NEXT: addi sp, sp, 352
+; RV32-NEXT: ret
+;
+; RV64-LABEL: clmulh_nxv8i64:
+; RV64: # %bb.0:
+; RV64-NEXT: addi sp, sp, -240
+; RV64-NEXT: sd ra, 232(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s0, 224(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s1, 216(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s2, 208(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s3, 200(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s4, 192(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s5, 184(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s6, 176(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s7, 168(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s8, 160(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s9, 152(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s10, 144(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s11, 136(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: sub sp, sp, a0
+; RV64-NEXT: li a1, 56
+; RV64-NEXT: li a2, 40
+; RV64-NEXT: lui a3, 16
+; RV64-NEXT: vsetvli a0, zero, e64, m8, ta, ma
+; RV64-NEXT: vsrl.vi v24, v8, 24
+; RV64-NEXT: vsrl.vx v16, v8, a1
+; RV64-NEXT: li a5, 56
+; RV64-NEXT: vsrl.vx v0, v8, a2
+; RV64-NEXT: li s5, 40
+; RV64-NEXT: addi s4, a3, -256
+; RV64-NEXT: vand.vx v0, v0, s4
+; RV64-NEXT: vor.vv v16, v0, v16
+; RV64-NEXT: vsrl.vi v0, v8, 8
+; RV64-NEXT: li a4, 255
+; RV64-NEXT: lui a1, 61681
+; RV64-NEXT: lui a2, 209715
+; RV64-NEXT: lui a3, 349525
+; RV64-NEXT: li a0, 1
+; RV64-NEXT: lui a6, 4080
+; RV64-NEXT: vand.vx v24, v24, a6
+; RV64-NEXT: slli a4, a4, 24
+; RV64-NEXT: vand.vx v0, v0, a4
+; RV64-NEXT: vor.vv v24, v0, v24
+; RV64-NEXT: vand.vx v0, v8, a6
+; RV64-NEXT: vsll.vi v0, v0, 24
+; RV64-NEXT: vor.vv v16, v24, v16
+; RV64-NEXT: vand.vx v24, v8, a4
+; RV64-NEXT: vsll.vi v24, v24, 8
+; RV64-NEXT: vor.vv v24, v0, v24
+; RV64-NEXT: vsll.vx v0, v8, a5
+; RV64-NEXT: addi a7, a1, -241
+; RV64-NEXT: addi a6, a2, 819
+; RV64-NEXT: addi a5, a3, 1365
+; RV64-NEXT: slli a1, a0, 11
+; RV64-NEXT: sd a1, 112(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a1, a0, 31
+; RV64-NEXT: sd a1, 104(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a1, a0, 32
+; RV64-NEXT: sd a1, 96(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a1, a0, 33
+; RV64-NEXT: sd a1, 88(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a1, a0, 34
+; RV64-NEXT: sd a1, 80(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a1, a0, 35
+; RV64-NEXT: sd a1, 72(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a1, a0, 36
+; RV64-NEXT: sd a1, 64(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a1, a0, 37
+; RV64-NEXT: sd a1, 56(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a1, a0, 38
+; RV64-NEXT: sd a1, 48(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a1, a0, 39
+; RV64-NEXT: sd a1, 40(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a1, a0, 40
+; RV64-NEXT: sd a1, 32(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a1, a0, 41
+; RV64-NEXT: sd a1, 24(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli s6, a0, 42
+; RV64-NEXT: slli s7, a0, 43
+; RV64-NEXT: slli s8, a0, 44
+; RV64-NEXT: slli s9, a0, 45
+; RV64-NEXT: slli s10, a0, 46
+; RV64-NEXT: slli a1, a7, 32
+; RV64-NEXT: add a7, a7, a1
+; RV64-NEXT: slli a1, a6, 32
+; RV64-NEXT: add a6, a6, a1
+; RV64-NEXT: slli a1, a5, 32
+; RV64-NEXT: add a5, a5, a1
+; RV64-NEXT: slli s11, a0, 47
+; RV64-NEXT: slli ra, a0, 48
+; RV64-NEXT: slli s3, a0, 49
+; RV64-NEXT: slli s2, a0, 50
+; RV64-NEXT: slli s1, a0, 51
+; RV64-NEXT: slli s0, a0, 52
+; RV64-NEXT: slli t6, a0, 53
+; RV64-NEXT: slli t5, a0, 54
+; RV64-NEXT: slli t4, a0, 55
+; RV64-NEXT: slli t3, a0, 56
+; RV64-NEXT: slli t2, a0, 57
+; RV64-NEXT: slli t1, a0, 58
+; RV64-NEXT: slli t0, a0, 59
+; RV64-NEXT: slli a3, a0, 60
+; RV64-NEXT: slli a2, a0, 61
+; RV64-NEXT: slli a1, a0, 62
+; RV64-NEXT: li a0, -1
+; RV64-NEXT: slli a0, a0, 63
+; RV64-NEXT: vand.vx v8, v8, s4
+; RV64-NEXT: vsll.vx v8, v8, s5
+; RV64-NEXT: vor.vv v8, v0, v8
+; RV64-NEXT: vor.vv v8, v8, v24
+; RV64-NEXT: vor.vv v8, v8, v16
+; RV64-NEXT: vsrl.vi v16, v8, 4
+; RV64-NEXT: vand.vx v8, v8, a7
+; RV64-NEXT: vand.vx v16, v16, a7
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v16, v8
+; RV64-NEXT: vsrl.vi v16, v8, 2
+; RV64-NEXT: vand.vx v8, v8, a6
+; RV64-NEXT: vand.vx v16, v16, a6
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v16, v8
+; RV64-NEXT: vsrl.vi v16, v8, 1
+; RV64-NEXT: vand.vx v8, v8, a5
+; RV64-NEXT: vand.vx v16, v16, a5
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v16, v8
+; RV64-NEXT: vand.vi v16, v8, 2
+; RV64-NEXT: vand.vi v24, v8, 1
+; RV64-NEXT: vand.vi v0, v8, 4
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: sd a1, 8(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 2
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vmul.vv v24, v8, v24
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vand.vi v16, v8, 8
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 5
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: li s5, 16
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 2
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: li s5, 32
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 4
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 2
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: li s5, 64
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: li s5, 128
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 6
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: li s5, 256
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 2
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: li s5, 512
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 4
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 2
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: li s5, 1024
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 2
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 2
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: ld s5, 112(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 5
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 2
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: lui s5, 1
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: lui s5, 2
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 4
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: lui s5, 4
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 4
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: lui s5, 8
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 7
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: lui s5, 16
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 2
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: lui s5, 32
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 4
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 2
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: lui s5, 64
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 2
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 2
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: lui s5, 128
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 5
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 2
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: lui s5, 256
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 2
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 2
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: lui s5, 512
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 4
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 2
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 2
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: lui s5, 1024
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 2
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: lui s5, 2048
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 6
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 2
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: lui s5, 4096
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: lui s5, 8192
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 2
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: lui s5, 16384
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 4
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: lui s5, 32768
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 5
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: lui s5, 65536
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 4
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: lui s5, 131072
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 4
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 4
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: lui s5, 262144
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 5
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: ld s5, 104(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 8
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: ld s5, 96(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: ld s5, 88(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 4
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: ld s5, 80(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 2
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: ld s5, 72(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 5
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: ld s5, 64(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 2
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: ld s5, 56(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 4
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 2
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: ld s5, 48(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: ld s5, 40(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 6
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: ld s5, 32(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 3
+; RV64-NEXT: mv s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 1
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: slli a1, a1, 2
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: ld s5, 24(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 4
+; RV64-NEXT: mv a1, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add a1, a1, s5
+; RV64-NEXT: slli s5, s5, 2
+; RV64-NEXT: add s5, s5, a1
+; RV64-NEXT: ld a1, 8(sp) # 8-byte Folded Reload
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 128
+; RV64-NEXT: vs8r.v v16, (s5) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, s6
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 3
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 2
+; RV64-NEXT: add s6, s6, s5
+; RV64-NEXT: slli s5, s5, 2
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 128
+; RV64-NEXT: vs8r.v v16, (s5) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, s7
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 5
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 2
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 128
+; RV64-NEXT: vs8r.v v16, (s5) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, s8
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 3
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s6, s6, s5
+; RV64-NEXT: slli s5, s5, 3
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 128
+; RV64-NEXT: vs8r.v v16, (s5) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, s9
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 4
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 3
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 128
+; RV64-NEXT: vs8r.v v16, (s5) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, s10
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 3
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 4
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 128
+; RV64-NEXT: vs8r.v v16, (s5) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, s11
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 3
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s6, s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s6, s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 128
+; RV64-NEXT: vs8r.v v16, (s5) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, ra
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 3
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 2
+; RV64-NEXT: add s6, s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 128
+; RV64-NEXT: vs8r.v v16, (s5) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, s3
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr s3, vlenb
+; RV64-NEXT: slli s3, s3, 3
+; RV64-NEXT: mv s5, s3
+; RV64-NEXT: slli s3, s3, 3
+; RV64-NEXT: add s3, s3, s5
+; RV64-NEXT: add s3, sp, s3
+; RV64-NEXT: addi s3, s3, 128
+; RV64-NEXT: vs8r.v v16, (s3) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, s2
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr s2, vlenb
+; RV64-NEXT: slli s2, s2, 4
+; RV64-NEXT: mv s3, s2
+; RV64-NEXT: slli s2, s2, 1
+; RV64-NEXT: add s2, s2, s3
+; RV64-NEXT: add s2, sp, s2
+; RV64-NEXT: addi s2, s2, 128
+; RV64-NEXT: vs8r.v v16, (s2) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, s1
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr s1, vlenb
+; RV64-NEXT: slli s1, s1, 7
+; RV64-NEXT: add s1, sp, s1
+; RV64-NEXT: addi s1, s1, 128
+; RV64-NEXT: vs8r.v v16, (s1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, s0
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr s0, vlenb
+; RV64-NEXT: slli s0, s0, 4
+; RV64-NEXT: mv s1, s0
+; RV64-NEXT: slli s0, s0, 1
+; RV64-NEXT: add s1, s1, s0
+; RV64-NEXT: slli s0, s0, 1
+; RV64-NEXT: add s0, s0, s1
+; RV64-NEXT: add s0, sp, s0
+; RV64-NEXT: addi s0, s0, 128
+; RV64-NEXT: vs8r.v v16, (s0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, t6
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 5
+; RV64-NEXT: mv s0, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s0
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 128
+; RV64-NEXT: vs8r.v v16, (t6) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, t5
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr t5, vlenb
+; RV64-NEXT: slli t5, t5, 6
+; RV64-NEXT: add t5, sp, t5
+; RV64-NEXT: addi t5, t5, 128
+; RV64-NEXT: vs8r.v v16, (t5) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, t4
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr t4, vlenb
+; RV64-NEXT: slli t4, t4, 3
+; RV64-NEXT: mv t5, t4
+; RV64-NEXT: slli t4, t4, 2
+; RV64-NEXT: add t4, t4, t5
+; RV64-NEXT: add t4, sp, t4
+; RV64-NEXT: addi t4, t4, 128
+; RV64-NEXT: vs8r.v v16, (t4) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, t3
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr t3, vlenb
+; RV64-NEXT: slli t3, t3, 3
+; RV64-NEXT: mv t4, t3
+; RV64-NEXT: slli t3, t3, 1
+; RV64-NEXT: add t3, t3, t4
+; RV64-NEXT: add t3, sp, t3
+; RV64-NEXT: addi t3, t3, 128
+; RV64-NEXT: vs8r.v v16, (t3) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, t2
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr t2, vlenb
+; RV64-NEXT: slli t2, t2, 3
+; RV64-NEXT: add t2, sp, t2
+; RV64-NEXT: addi t2, t2, 128
+; RV64-NEXT: vs8r.v v16, (t2) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, t1
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr t1, vlenb
+; RV64-NEXT: slli t1, t1, 3
+; RV64-NEXT: mv t2, t1
+; RV64-NEXT: slli t1, t1, 1
+; RV64-NEXT: add t2, t2, t1
+; RV64-NEXT: slli t1, t1, 2
+; RV64-NEXT: add t1, t1, t2
+; RV64-NEXT: add t1, sp, t1
+; RV64-NEXT: addi t1, t1, 128
+; RV64-NEXT: vs8r.v v16, (t1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, t0
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr t0, vlenb
+; RV64-NEXT: slli t0, t0, 4
+; RV64-NEXT: mv t1, t0
+; RV64-NEXT: slli t0, t0, 2
+; RV64-NEXT: add t0, t0, t1
+; RV64-NEXT: add t0, sp, t0
+; RV64-NEXT: addi t0, t0, 128
+; RV64-NEXT: vs8r.v v16, (t0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, a3
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a3, vlenb
+; RV64-NEXT: slli a3, a3, 3
+; RV64-NEXT: mv t0, a3
+; RV64-NEXT: slli a3, a3, 1
+; RV64-NEXT: add t0, t0, a3
+; RV64-NEXT: slli a3, a3, 1
+; RV64-NEXT: add a3, a3, t0
+; RV64-NEXT: add a3, sp, a3
+; RV64-NEXT: addi a3, a3, 128
+; RV64-NEXT: vs8r.v v16, (a3) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, a2
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 5
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vs8r.v v16, (a2) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, a1
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: csrr a1, vlenb
+; RV64-NEXT: slli a1, a1, 4
+; RV64-NEXT: add a1, sp, a1
+; RV64-NEXT: addi a1, a1, 128
+; RV64-NEXT: vs8r.v v16, (a1) # vscale x 64-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, a0
+; RV64-NEXT: vmul.vv v8, v8, v16
+; RV64-NEXT: addi a0, sp, 128
+; RV64-NEXT: vs8r.v v8, (a0) # vscale x 64-byte Folded Spill
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl8r.v v8, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v24, v8
+; RV64-NEXT: vxor.vv v8, v8, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 6
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl8r.v v16, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v16, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v16, v16, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v16, v16, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v16, v16, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v16, v16, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v16, v16, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v16, v16, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 7
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v16, v16, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v16, v16, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v16, v16, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v16, v16, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v16, v16, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v16, v16, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v16, v16, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v16, v16, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 6
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v16, v16, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v16, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl8r.v v0, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: li a0, 56
+; RV64-NEXT: vsll.vx v8, v8, a0
+; RV64-NEXT: vand.vx v16, v16, s4
+; RV64-NEXT: li a1, 40
+; RV64-NEXT: vsll.vx v16, v16, a1
+; RV64-NEXT: vor.vv v8, v8, v16
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vs8r.v v8, (a2) # vscale x 64-byte Folded Spill
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 4
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v8, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v24, v8
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 5
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v16, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v16
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 4
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v16, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v16
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 4
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 4
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v16, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v16
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 5
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v16, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v16
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 8
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v16, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v16
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v16, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v16
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 4
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v16, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v16
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v16, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v16
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 5
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v16, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v16
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v16, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v16
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 4
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v16, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v16
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v16, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v16
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 6
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v16, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v16, v8, v16
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v8, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v16, v8
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 4
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v24, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v24, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 5
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v24, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v24, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 4
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v24, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 4
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v24, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v24, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v24, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v8, v24
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v0, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 4
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v0, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vsrl.vi v0, v16, 8
+; RV64-NEXT: vand.vx v0, v0, a4
+; RV64-NEXT: vsrl.vi v8, v8, 24
+; RV64-NEXT: lui a2, 4080
+; RV64-NEXT: vand.vx v8, v8, a2
+; RV64-NEXT: vor.vv v8, v0, v8
+; RV64-NEXT: csrr a3, vlenb
+; RV64-NEXT: slli a3, a3, 5
+; RV64-NEXT: mv t0, a3
+; RV64-NEXT: slli a3, a3, 1
+; RV64-NEXT: add t0, t0, a3
+; RV64-NEXT: slli a3, a3, 1
+; RV64-NEXT: add t0, t0, a3
+; RV64-NEXT: slli a3, a3, 1
+; RV64-NEXT: add a3, a3, t0
+; RV64-NEXT: add a3, sp, a3
+; RV64-NEXT: addi a3, a3, 128
+; RV64-NEXT: vs8r.v v8, (a3) # vscale x 64-byte Folded Spill
+; RV64-NEXT: csrr a3, vlenb
+; RV64-NEXT: slli a3, a3, 7
+; RV64-NEXT: add a3, sp, a3
+; RV64-NEXT: addi a3, a3, 128
+; RV64-NEXT: vl8r.v v8, (a3) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v24, v8
+; RV64-NEXT: csrr a3, vlenb
+; RV64-NEXT: slli a3, a3, 4
+; RV64-NEXT: mv t0, a3
+; RV64-NEXT: slli a3, a3, 1
+; RV64-NEXT: add t0, t0, a3
+; RV64-NEXT: slli a3, a3, 1
+; RV64-NEXT: add a3, a3, t0
+; RV64-NEXT: add a3, sp, a3
+; RV64-NEXT: addi a3, a3, 128
+; RV64-NEXT: vl8r.v v24, (a3) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a3, vlenb
+; RV64-NEXT: slli a3, a3, 5
+; RV64-NEXT: mv t0, a3
+; RV64-NEXT: slli a3, a3, 1
+; RV64-NEXT: add a3, a3, t0
+; RV64-NEXT: add a3, sp, a3
+; RV64-NEXT: addi a3, a3, 128
+; RV64-NEXT: vl8r.v v24, (a3) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a3, vlenb
+; RV64-NEXT: slli a3, a3, 6
+; RV64-NEXT: add a3, sp, a3
+; RV64-NEXT: addi a3, a3, 128
+; RV64-NEXT: vl8r.v v24, (a3) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a3, vlenb
+; RV64-NEXT: slli a3, a3, 3
+; RV64-NEXT: mv t0, a3
+; RV64-NEXT: slli a3, a3, 2
+; RV64-NEXT: add a3, a3, t0
+; RV64-NEXT: add a3, sp, a3
+; RV64-NEXT: addi a3, a3, 128
+; RV64-NEXT: vl8r.v v24, (a3) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v8, v8, v24
+; RV64-NEXT: csrr a3, vlenb
+; RV64-NEXT: slli a3, a3, 3
+; RV64-NEXT: mv t0, a3
+; RV64-NEXT: slli a3, a3, 1
+; RV64-NEXT: add a3, a3, t0
+; RV64-NEXT: add a3, sp, a3
+; RV64-NEXT: addi a3, a3, 128
+; RV64-NEXT: vl8r.v v24, (a3) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v8, v24
+; RV64-NEXT: csrr a3, vlenb
+; RV64-NEXT: slli a3, a3, 3
+; RV64-NEXT: add a3, sp, a3
+; RV64-NEXT: addi a3, a3, 128
+; RV64-NEXT: vl8r.v v0, (a3) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vand.vx v16, v16, a2
+; RV64-NEXT: vsll.vi v16, v16, 24
+; RV64-NEXT: vand.vx v0, v8, a4
+; RV64-NEXT: vsll.vi v0, v0, 8
+; RV64-NEXT: vor.vv v16, v16, v0
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v0, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v0, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vor.vv v16, v0, v16
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 4
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 2
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v0, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 3
+; RV64-NEXT: mv a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a3, a3, a2
+; RV64-NEXT: slli a2, a2, 1
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v0, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 5
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v0, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: csrr a2, vlenb
+; RV64-NEXT: slli a2, a2, 4
+; RV64-NEXT: add a2, sp, a2
+; RV64-NEXT: addi a2, a2, 128
+; RV64-NEXT: vl8r.v v0, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: addi a2, sp, 128
+; RV64-NEXT: vl8r.v v0, (a2) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vxor.vv v24, v24, v0
+; RV64-NEXT: vsrl.vx v8, v8, a1
+; RV64-NEXT: vand.vx v8, v8, s4
+; RV64-NEXT: vsrl.vx v24, v24, a0
+; RV64-NEXT: vor.vv v8, v8, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
+; RV64-NEXT: vor.vv v8, v24, v8
+; RV64-NEXT: vor.vv v8, v16, v8
+; RV64-NEXT: vsrl.vi v16, v8, 4
+; RV64-NEXT: vand.vx v8, v8, a7
+; RV64-NEXT: vand.vx v16, v16, a7
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v16, v8
+; RV64-NEXT: vsrl.vi v16, v8, 2
+; RV64-NEXT: vand.vx v8, v8, a6
+; RV64-NEXT: vand.vx v16, v16, a6
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v16, v8
+; RV64-NEXT: vsrl.vi v16, v8, 1
+; RV64-NEXT: vand.vx v8, v8, a5
+; RV64-NEXT: vand.vx v16, v16, a5
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v16, v8
+; RV64-NEXT: vsrl.vi v8, v8, 1
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add sp, sp, a0
+; RV64-NEXT: ld ra, 232(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s0, 224(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s1, 216(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s2, 208(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s3, 200(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s4, 192(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s5, 184(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s6, 176(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s7, 168(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s8, 160(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s9, 152(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s10, 144(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s11, 136(sp) # 8-byte Folded Reload
+; RV64-NEXT: addi sp, sp, 240
+; RV64-NEXT: ret
+ %a = call <vscale x 8 x i64> @llvm.clmulh.nxv8i64(<vscale x 8 x i64> %x, <vscale x 8 x i64> %y)
+ ret <vscale x 8 x i64> %a
+}
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-clmul.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-clmul.ll
new file mode 100644
index 0000000000000..d1893856cb88a
--- /dev/null
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-clmul.ll
@@ -0,0 +1,34118 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=riscv32 -verify-machineinstrs -mattr=+v < %s | FileCheck %s --check-prefixes=CHECK,RV32
+; RUN: llc -mtriple=riscv64 -verify-machineinstrs -mattr=+v < %s | FileCheck %s --check-prefixes=CHECK,RV64
+
+define <1 x i32> @clmul_v1i32(<1 x i32> %x, <1 x i32> %y) nounwind {
+; CHECK-LABEL: clmul_v1i32:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetivli zero, 1, e32, mf2, ta, ma
+; CHECK-NEXT: vand.vi v10, v9, 2
+; CHECK-NEXT: vand.vi v11, v9, 1
+; CHECK-NEXT: vmul.vv v10, v8, v10
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v11, v10
+; CHECK-NEXT: vand.vi v11, v9, 4
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vi v11, v9, 8
+; CHECK-NEXT: li a0, 16
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: li a0, 32
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: li a0, 64
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: li a0, 128
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: li a0, 256
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: li a0, 512
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: li a0, 1024
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: li a0, 1
+; CHECK-NEXT: slli a0, a0, 11
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 1
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 2
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 4
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 8
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 16
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 32
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 64
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 128
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 256
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 512
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 1024
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 2048
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 4096
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 8192
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 16384
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 32768
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 65536
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 131072
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 262144
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 524288
+; CHECK-NEXT: vand.vx v9, v9, a0
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vmul.vv v8, v8, v9
+; CHECK-NEXT: vxor.vv v8, v10, v8
+; CHECK-NEXT: ret
+ %a = call <1 x i32> @llvm.clmul.v1i32(<1 x i32> %x, <1 x i32> %y)
+ ret <1 x i32> %a
+}
+
+define <2 x i32> @clmul_v2i32(<2 x i32> %x, <2 x i32> %y) nounwind {
+; CHECK-LABEL: clmul_v2i32:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetivli zero, 2, e32, mf2, ta, ma
+; CHECK-NEXT: vand.vi v10, v9, 2
+; CHECK-NEXT: vand.vi v11, v9, 1
+; CHECK-NEXT: vmul.vv v10, v8, v10
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v11, v10
+; CHECK-NEXT: vand.vi v11, v9, 4
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vi v11, v9, 8
+; CHECK-NEXT: li a0, 16
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: li a0, 32
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: li a0, 64
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: li a0, 128
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: li a0, 256
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: li a0, 512
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: li a0, 1024
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: li a0, 1
+; CHECK-NEXT: slli a0, a0, 11
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 1
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 2
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 4
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 8
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 16
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 32
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 64
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 128
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 256
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 512
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 1024
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 2048
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 4096
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 8192
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 16384
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 32768
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 65536
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 131072
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 262144
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 524288
+; CHECK-NEXT: vand.vx v9, v9, a0
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vmul.vv v8, v8, v9
+; CHECK-NEXT: vxor.vv v8, v10, v8
+; CHECK-NEXT: ret
+ %a = call <2 x i32> @llvm.clmul.v2i32(<2 x i32> %x, <2 x i32> %y)
+ ret <2 x i32> %a
+}
+
+define <4 x i32> @clmul_v4i32(<4 x i32> %x, <4 x i32> %y) nounwind {
+; CHECK-LABEL: clmul_v4i32:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetivli zero, 4, e32, m1, ta, ma
+; CHECK-NEXT: vand.vi v10, v9, 2
+; CHECK-NEXT: vand.vi v11, v9, 1
+; CHECK-NEXT: vmul.vv v10, v8, v10
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v11, v10
+; CHECK-NEXT: vand.vi v11, v9, 4
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vi v11, v9, 8
+; CHECK-NEXT: li a0, 16
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: li a0, 32
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: li a0, 64
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: li a0, 128
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: li a0, 256
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: li a0, 512
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: li a0, 1024
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: li a0, 1
+; CHECK-NEXT: slli a0, a0, 11
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 1
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 2
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 4
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 8
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 16
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 32
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 64
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 128
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 256
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 512
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 1024
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 2048
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 4096
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 8192
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 16384
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 32768
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 65536
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 131072
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 262144
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vand.vx v11, v9, a0
+; CHECK-NEXT: lui a0, 524288
+; CHECK-NEXT: vand.vx v9, v9, a0
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vxor.vv v10, v10, v11
+; CHECK-NEXT: vmul.vv v8, v8, v9
+; CHECK-NEXT: vxor.vv v8, v10, v8
+; CHECK-NEXT: ret
+ %a = call <4 x i32> @llvm.clmul.v4i32(<4 x i32> %x, <4 x i32> %y)
+ ret <4 x i32> %a
+}
+
+define <8 x i32> @clmul_v8i32(<8 x i32> %x, <8 x i32> %y) nounwind {
+; CHECK-LABEL: clmul_v8i32:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetivli zero, 8, e32, m2, ta, ma
+; CHECK-NEXT: vand.vi v10, v8, 2
+; CHECK-NEXT: vand.vi v12, v8, 1
+; CHECK-NEXT: vmul.vv v10, v8, v10
+; CHECK-NEXT: vmul.vv v12, v8, v12
+; CHECK-NEXT: vxor.vv v10, v12, v10
+; CHECK-NEXT: vand.vi v12, v8, 4
+; CHECK-NEXT: vmul.vv v12, v8, v12
+; CHECK-NEXT: vxor.vv v10, v10, v12
+; CHECK-NEXT: vand.vi v12, v8, 8
+; CHECK-NEXT: li a0, 16
+; CHECK-NEXT: vmul.vv v12, v8, v12
+; CHECK-NEXT: vxor.vv v10, v10, v12
+; CHECK-NEXT: vand.vx v12, v8, a0
+; CHECK-NEXT: li a0, 32
+; CHECK-NEXT: vmul.vv v12, v8, v12
+; CHECK-NEXT: vxor.vv v10, v10, v12
+; CHECK-NEXT: vand.vx v12, v8, a0
+; CHECK-NEXT: li a0, 64
+; CHECK-NEXT: vmul.vv v12, v8, v12
+; CHECK-NEXT: vxor.vv v10, v10, v12
+; CHECK-NEXT: vand.vx v12, v8, a0
+; CHECK-NEXT: li a0, 128
+; CHECK-NEXT: vmul.vv v12, v8, v12
+; CHECK-NEXT: vxor.vv v10, v10, v12
+; CHECK-NEXT: vand.vx v12, v8, a0
+; CHECK-NEXT: li a0, 256
+; CHECK-NEXT: vmul.vv v12, v8, v12
+; CHECK-NEXT: vxor.vv v10, v10, v12
+; CHECK-NEXT: vand.vx v12, v8, a0
+; CHECK-NEXT: li a0, 512
+; CHECK-NEXT: vmul.vv v12, v8, v12
+; CHECK-NEXT: vxor.vv v10, v10, v12
+; CHECK-NEXT: vand.vx v12, v8, a0
+; CHECK-NEXT: li a0, 1024
+; CHECK-NEXT: vmul.vv v12, v8, v12
+; CHECK-NEXT: vxor.vv v10, v10, v12
+; CHECK-NEXT: vand.vx v12, v8, a0
+; CHECK-NEXT: li a0, 1
+; CHECK-NEXT: slli a0, a0, 11
+; CHECK-NEXT: vmul.vv v12, v8, v12
+; CHECK-NEXT: vxor.vv v10, v10, v12
+; CHECK-NEXT: vand.vx v12, v8, a0
+; CHECK-NEXT: lui a0, 1
+; CHECK-NEXT: vmul.vv v12, v8, v12
+; CHECK-NEXT: vxor.vv v10, v10, v12
+; CHECK-NEXT: vand.vx v12, v8, a0
+; CHECK-NEXT: lui a0, 2
+; CHECK-NEXT: vmul.vv v12, v8, v12
+; CHECK-NEXT: vxor.vv v10, v10, v12
+; CHECK-NEXT: vand.vx v12, v8, a0
+; CHECK-NEXT: lui a0, 4
+; CHECK-NEXT: vmul.vv v12, v8, v12
+; CHECK-NEXT: vxor.vv v10, v10, v12
+; CHECK-NEXT: vand.vx v12, v8, a0
+; CHECK-NEXT: lui a0, 8
+; CHECK-NEXT: vmul.vv v12, v8, v12
+; CHECK-NEXT: vxor.vv v10, v10, v12
+; CHECK-NEXT: vand.vx v12, v8, a0
+; CHECK-NEXT: lui a0, 16
+; CHECK-NEXT: vmul.vv v12, v8, v12
+; CHECK-NEXT: vxor.vv v10, v10, v12
+; CHECK-NEXT: vand.vx v12, v8, a0
+; CHECK-NEXT: lui a0, 32
+; CHECK-NEXT: vmul.vv v12, v8, v12
+; CHECK-NEXT: vxor.vv v10, v10, v12
+; CHECK-NEXT: vand.vx v12, v8, a0
+; CHECK-NEXT: lui a0, 64
+; CHECK-NEXT: vmul.vv v12, v8, v12
+; CHECK-NEXT: vxor.vv v10, v10, v12
+; CHECK-NEXT: vand.vx v12, v8, a0
+; CHECK-NEXT: lui a0, 128
+; CHECK-NEXT: vmul.vv v12, v8, v12
+; CHECK-NEXT: vxor.vv v10, v10, v12
+; CHECK-NEXT: vand.vx v12, v8, a0
+; CHECK-NEXT: lui a0, 256
+; CHECK-NEXT: vmul.vv v12, v8, v12
+; CHECK-NEXT: vxor.vv v10, v10, v12
+; CHECK-NEXT: vand.vx v12, v8, a0
+; CHECK-NEXT: lui a0, 512
+; CHECK-NEXT: vmul.vv v12, v8, v12
+; CHECK-NEXT: vxor.vv v10, v10, v12
+; CHECK-NEXT: vand.vx v12, v8, a0
+; CHECK-NEXT: lui a0, 1024
+; CHECK-NEXT: vmul.vv v12, v8, v12
+; CHECK-NEXT: vxor.vv v10, v10, v12
+; CHECK-NEXT: vand.vx v12, v8, a0
+; CHECK-NEXT: lui a0, 2048
+; CHECK-NEXT: vmul.vv v12, v8, v12
+; CHECK-NEXT: vxor.vv v10, v10, v12
+; CHECK-NEXT: vand.vx v12, v8, a0
+; CHECK-NEXT: lui a0, 4096
+; CHECK-NEXT: vmul.vv v12, v8, v12
+; CHECK-NEXT: vxor.vv v10, v10, v12
+; CHECK-NEXT: vand.vx v12, v8, a0
+; CHECK-NEXT: lui a0, 8192
+; CHECK-NEXT: vmul.vv v12, v8, v12
+; CHECK-NEXT: vxor.vv v10, v10, v12
+; CHECK-NEXT: vand.vx v12, v8, a0
+; CHECK-NEXT: lui a0, 16384
+; CHECK-NEXT: vmul.vv v12, v8, v12
+; CHECK-NEXT: vxor.vv v10, v10, v12
+; CHECK-NEXT: vand.vx v12, v8, a0
+; CHECK-NEXT: lui a0, 32768
+; CHECK-NEXT: vmul.vv v12, v8, v12
+; CHECK-NEXT: vxor.vv v10, v10, v12
+; CHECK-NEXT: vand.vx v12, v8, a0
+; CHECK-NEXT: lui a0, 65536
+; CHECK-NEXT: vmul.vv v12, v8, v12
+; CHECK-NEXT: vxor.vv v10, v10, v12
+; CHECK-NEXT: vand.vx v12, v8, a0
+; CHECK-NEXT: lui a0, 131072
+; CHECK-NEXT: vmul.vv v12, v8, v12
+; CHECK-NEXT: vxor.vv v10, v10, v12
+; CHECK-NEXT: vand.vx v12, v8, a0
+; CHECK-NEXT: lui a0, 262144
+; CHECK-NEXT: vmul.vv v12, v8, v12
+; CHECK-NEXT: vxor.vv v10, v10, v12
+; CHECK-NEXT: vand.vx v12, v8, a0
+; CHECK-NEXT: lui a0, 524288
+; CHECK-NEXT: vmul.vv v12, v8, v12
+; CHECK-NEXT: vxor.vv v10, v10, v12
+; CHECK-NEXT: vand.vx v12, v8, a0
+; CHECK-NEXT: vmul.vv v8, v8, v12
+; CHECK-NEXT: vxor.vv v8, v10, v8
+; CHECK-NEXT: ret
+ %a = call <8 x i32> @llvm.clmul.v8i32(<8 x i32> %x, <8 x i32> %x)
+ ret <8 x i32> %a
+}
+
+define <16 x i32> @clmul_v16i32(<16 x i32> %x, <16 x i32> %y) nounwind {
+; CHECK-LABEL: clmul_v16i32:
+; CHECK: # %bb.0:
+; CHECK-NEXT: vsetivli zero, 16, e32, m4, ta, ma
+; CHECK-NEXT: vand.vi v16, v12, 2
+; CHECK-NEXT: vand.vi v20, v12, 1
+; CHECK-NEXT: vmul.vv v16, v8, v16
+; CHECK-NEXT: vmul.vv v20, v8, v20
+; CHECK-NEXT: vxor.vv v16, v20, v16
+; CHECK-NEXT: vand.vi v20, v12, 4
+; CHECK-NEXT: vmul.vv v20, v8, v20
+; CHECK-NEXT: vxor.vv v16, v16, v20
+; CHECK-NEXT: vand.vi v20, v12, 8
+; CHECK-NEXT: li a0, 16
+; CHECK-NEXT: vmul.vv v20, v8, v20
+; CHECK-NEXT: vxor.vv v16, v16, v20
+; CHECK-NEXT: vand.vx v20, v12, a0
+; CHECK-NEXT: li a0, 32
+; CHECK-NEXT: vmul.vv v20, v8, v20
+; CHECK-NEXT: vxor.vv v16, v16, v20
+; CHECK-NEXT: vand.vx v20, v12, a0
+; CHECK-NEXT: li a0, 64
+; CHECK-NEXT: vmul.vv v20, v8, v20
+; CHECK-NEXT: vxor.vv v16, v16, v20
+; CHECK-NEXT: vand.vx v20, v12, a0
+; CHECK-NEXT: li a0, 128
+; CHECK-NEXT: vmul.vv v20, v8, v20
+; CHECK-NEXT: vxor.vv v16, v16, v20
+; CHECK-NEXT: vand.vx v20, v12, a0
+; CHECK-NEXT: li a0, 256
+; CHECK-NEXT: vmul.vv v20, v8, v20
+; CHECK-NEXT: vxor.vv v16, v16, v20
+; CHECK-NEXT: vand.vx v20, v12, a0
+; CHECK-NEXT: li a0, 512
+; CHECK-NEXT: vmul.vv v20, v8, v20
+; CHECK-NEXT: vxor.vv v16, v16, v20
+; CHECK-NEXT: vand.vx v20, v12, a0
+; CHECK-NEXT: li a0, 1024
+; CHECK-NEXT: vmul.vv v20, v8, v20
+; CHECK-NEXT: vxor.vv v16, v16, v20
+; CHECK-NEXT: vand.vx v20, v12, a0
+; CHECK-NEXT: li a0, 1
+; CHECK-NEXT: slli a0, a0, 11
+; CHECK-NEXT: vmul.vv v20, v8, v20
+; CHECK-NEXT: vxor.vv v16, v16, v20
+; CHECK-NEXT: vand.vx v20, v12, a0
+; CHECK-NEXT: lui a0, 1
+; CHECK-NEXT: vmul.vv v20, v8, v20
+; CHECK-NEXT: vxor.vv v16, v16, v20
+; CHECK-NEXT: vand.vx v20, v12, a0
+; CHECK-NEXT: lui a0, 2
+; CHECK-NEXT: vmul.vv v20, v8, v20
+; CHECK-NEXT: vxor.vv v16, v16, v20
+; CHECK-NEXT: vand.vx v20, v12, a0
+; CHECK-NEXT: lui a0, 4
+; CHECK-NEXT: vmul.vv v20, v8, v20
+; CHECK-NEXT: vxor.vv v16, v16, v20
+; CHECK-NEXT: vand.vx v20, v12, a0
+; CHECK-NEXT: lui a0, 8
+; CHECK-NEXT: vmul.vv v20, v8, v20
+; CHECK-NEXT: vxor.vv v16, v16, v20
+; CHECK-NEXT: vand.vx v20, v12, a0
+; CHECK-NEXT: lui a0, 16
+; CHECK-NEXT: vmul.vv v20, v8, v20
+; CHECK-NEXT: vxor.vv v16, v16, v20
+; CHECK-NEXT: vand.vx v20, v12, a0
+; CHECK-NEXT: lui a0, 32
+; CHECK-NEXT: vmul.vv v20, v8, v20
+; CHECK-NEXT: vxor.vv v16, v16, v20
+; CHECK-NEXT: vand.vx v20, v12, a0
+; CHECK-NEXT: lui a0, 64
+; CHECK-NEXT: vmul.vv v20, v8, v20
+; CHECK-NEXT: vxor.vv v16, v16, v20
+; CHECK-NEXT: vand.vx v20, v12, a0
+; CHECK-NEXT: lui a0, 128
+; CHECK-NEXT: vmul.vv v20, v8, v20
+; CHECK-NEXT: vxor.vv v16, v16, v20
+; CHECK-NEXT: vand.vx v20, v12, a0
+; CHECK-NEXT: lui a0, 256
+; CHECK-NEXT: vmul.vv v20, v8, v20
+; CHECK-NEXT: vxor.vv v16, v16, v20
+; CHECK-NEXT: vand.vx v20, v12, a0
+; CHECK-NEXT: lui a0, 512
+; CHECK-NEXT: vmul.vv v20, v8, v20
+; CHECK-NEXT: vxor.vv v16, v16, v20
+; CHECK-NEXT: vand.vx v20, v12, a0
+; CHECK-NEXT: lui a0, 1024
+; CHECK-NEXT: vmul.vv v20, v8, v20
+; CHECK-NEXT: vxor.vv v16, v16, v20
+; CHECK-NEXT: vand.vx v20, v12, a0
+; CHECK-NEXT: lui a0, 2048
+; CHECK-NEXT: vmul.vv v20, v8, v20
+; CHECK-NEXT: vxor.vv v16, v16, v20
+; CHECK-NEXT: vand.vx v20, v12, a0
+; CHECK-NEXT: lui a0, 4096
+; CHECK-NEXT: vmul.vv v20, v8, v20
+; CHECK-NEXT: vxor.vv v16, v16, v20
+; CHECK-NEXT: vand.vx v20, v12, a0
+; CHECK-NEXT: lui a0, 8192
+; CHECK-NEXT: vmul.vv v20, v8, v20
+; CHECK-NEXT: vxor.vv v16, v16, v20
+; CHECK-NEXT: vand.vx v20, v12, a0
+; CHECK-NEXT: lui a0, 16384
+; CHECK-NEXT: vmul.vv v20, v8, v20
+; CHECK-NEXT: vxor.vv v16, v16, v20
+; CHECK-NEXT: vand.vx v20, v12, a0
+; CHECK-NEXT: lui a0, 32768
+; CHECK-NEXT: vmul.vv v20, v8, v20
+; CHECK-NEXT: vxor.vv v16, v16, v20
+; CHECK-NEXT: vand.vx v20, v12, a0
+; CHECK-NEXT: lui a0, 65536
+; CHECK-NEXT: vmul.vv v20, v8, v20
+; CHECK-NEXT: vxor.vv v16, v16, v20
+; CHECK-NEXT: vand.vx v20, v12, a0
+; CHECK-NEXT: lui a0, 131072
+; CHECK-NEXT: vmul.vv v20, v8, v20
+; CHECK-NEXT: vxor.vv v16, v16, v20
+; CHECK-NEXT: vand.vx v20, v12, a0
+; CHECK-NEXT: lui a0, 262144
+; CHECK-NEXT: vmul.vv v20, v8, v20
+; CHECK-NEXT: vxor.vv v16, v16, v20
+; CHECK-NEXT: vand.vx v20, v12, a0
+; CHECK-NEXT: lui a0, 524288
+; CHECK-NEXT: vand.vx v12, v12, a0
+; CHECK-NEXT: vmul.vv v20, v8, v20
+; CHECK-NEXT: vxor.vv v16, v16, v20
+; CHECK-NEXT: vmul.vv v8, v8, v12
+; CHECK-NEXT: vxor.vv v8, v16, v8
+; CHECK-NEXT: ret
+ %a = call <16 x i32> @llvm.clmul.v16i32(<16 x i32> %x, <16 x i32> %y)
+ ret <16 x i32> %a
+}
+
+define <1 x i64> @clmul_v1i64(<1 x i64> %x, <1 x i64> %y) nounwind {
+; RV32-LABEL: clmul_v1i64:
+; RV32: # %bb.0:
+; RV32-NEXT: addi sp, sp, -352
+; RV32-NEXT: sw ra, 348(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s0, 344(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s1, 340(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s2, 336(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s3, 332(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s4, 328(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s5, 324(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s6, 320(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s7, 316(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s8, 312(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s9, 308(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s10, 304(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s11, 300(sp) # 4-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 3
+; RV32-NEXT: sub a0, a1, a0
+; RV32-NEXT: sub sp, sp, a0
+; RV32-NEXT: lui a1, 524288
+; RV32-NEXT: li t5, 1
+; RV32-NEXT: li a4, 2
+; RV32-NEXT: li a2, 4
+; RV32-NEXT: li s11, 8
+; RV32-NEXT: li a0, 16
+; RV32-NEXT: li ra, 32
+; RV32-NEXT: li s10, 64
+; RV32-NEXT: li s9, 128
+; RV32-NEXT: li s8, 256
+; RV32-NEXT: li s7, 512
+; RV32-NEXT: li s1, 1024
+; RV32-NEXT: lui s6, 1
+; RV32-NEXT: lui s5, 2
+; RV32-NEXT: lui s4, 4
+; RV32-NEXT: lui s3, 8
+; RV32-NEXT: lui s2, 16
+; RV32-NEXT: lui s0, 32
+; RV32-NEXT: lui t6, 64
+; RV32-NEXT: lui t4, 128
+; RV32-NEXT: lui t3, 256
+; RV32-NEXT: lui t2, 512
+; RV32-NEXT: lui t1, 1024
+; RV32-NEXT: lui t0, 2048
+; RV32-NEXT: lui a7, 4096
+; RV32-NEXT: lui a6, 8192
+; RV32-NEXT: lui a5, 16384
+; RV32-NEXT: lui a3, 32768
+; RV32-NEXT: sw a1, 272(sp)
+; RV32-NEXT: sw zero, 276(sp)
+; RV32-NEXT: sw zero, 264(sp)
+; RV32-NEXT: sw t5, 268(sp)
+; RV32-NEXT: sw zero, 256(sp)
+; RV32-NEXT: sw a4, 260(sp)
+; RV32-NEXT: lui a4, 65536
+; RV32-NEXT: sw zero, 248(sp)
+; RV32-NEXT: sw a2, 252(sp)
+; RV32-NEXT: lui a2, 131072
+; RV32-NEXT: sw zero, 240(sp)
+; RV32-NEXT: sw s11, 244(sp)
+; RV32-NEXT: vsetivli zero, 1, e64, m1, ta, ma
+; RV32-NEXT: vand.vi v13, v9, 2
+; RV32-NEXT: vand.vi v14, v9, 1
+; RV32-NEXT: vand.vi v12, v9, 4
+; RV32-NEXT: vand.vi v11, v9, 8
+; RV32-NEXT: sw zero, 232(sp)
+; RV32-NEXT: sw a0, 236(sp)
+; RV32-NEXT: vand.vx v10, v9, a0
+; RV32-NEXT: addi s11, sp, 272
+; RV32-NEXT: sw zero, 224(sp)
+; RV32-NEXT: sw ra, 228(sp)
+; RV32-NEXT: vand.vx v15, v9, ra
+; RV32-NEXT: addi ra, sp, 264
+; RV32-NEXT: sw zero, 216(sp)
+; RV32-NEXT: sw s10, 220(sp)
+; RV32-NEXT: vand.vx v16, v9, s10
+; RV32-NEXT: addi s10, sp, 256
+; RV32-NEXT: sw zero, 208(sp)
+; RV32-NEXT: sw s9, 212(sp)
+; RV32-NEXT: vand.vx v17, v9, s9
+; RV32-NEXT: addi s9, sp, 248
+; RV32-NEXT: sw zero, 200(sp)
+; RV32-NEXT: sw s8, 204(sp)
+; RV32-NEXT: vand.vx v18, v9, s8
+; RV32-NEXT: addi s8, sp, 240
+; RV32-NEXT: sw zero, 192(sp)
+; RV32-NEXT: sw s7, 196(sp)
+; RV32-NEXT: vand.vx v19, v9, s7
+; RV32-NEXT: addi s7, sp, 232
+; RV32-NEXT: sw zero, 184(sp)
+; RV32-NEXT: sw s1, 188(sp)
+; RV32-NEXT: vand.vx v20, v9, s1
+; RV32-NEXT: slli t5, t5, 11
+; RV32-NEXT: vand.vx v21, v9, s6
+; RV32-NEXT: sw zero, 176(sp)
+; RV32-NEXT: sw t5, 180(sp)
+; RV32-NEXT: sw zero, 168(sp)
+; RV32-NEXT: sw s6, 172(sp)
+; RV32-NEXT: addi s6, sp, 216
+; RV32-NEXT: vand.vx v22, v9, s5
+; RV32-NEXT: sw zero, 160(sp)
+; RV32-NEXT: sw s5, 164(sp)
+; RV32-NEXT: addi s5, sp, 208
+; RV32-NEXT: vand.vx v23, v9, s4
+; RV32-NEXT: sw zero, 152(sp)
+; RV32-NEXT: sw s4, 156(sp)
+; RV32-NEXT: addi s4, sp, 200
+; RV32-NEXT: vand.vx v24, v9, s3
+; RV32-NEXT: sw zero, 144(sp)
+; RV32-NEXT: sw s3, 148(sp)
+; RV32-NEXT: addi s3, sp, 192
+; RV32-NEXT: vand.vx v25, v9, s2
+; RV32-NEXT: sw zero, 136(sp)
+; RV32-NEXT: sw s2, 140(sp)
+; RV32-NEXT: addi s2, sp, 184
+; RV32-NEXT: vand.vx v26, v9, s0
+; RV32-NEXT: sw zero, 128(sp)
+; RV32-NEXT: sw s0, 132(sp)
+; RV32-NEXT: addi s1, sp, 176
+; RV32-NEXT: vand.vx v27, v9, t6
+; RV32-NEXT: sw zero, 120(sp)
+; RV32-NEXT: sw t6, 124(sp)
+; RV32-NEXT: addi s0, sp, 168
+; RV32-NEXT: vand.vx v28, v9, t4
+; RV32-NEXT: sw zero, 112(sp)
+; RV32-NEXT: sw t4, 116(sp)
+; RV32-NEXT: addi t6, sp, 160
+; RV32-NEXT: vand.vx v29, v9, t3
+; RV32-NEXT: sw zero, 104(sp)
+; RV32-NEXT: sw t3, 108(sp)
+; RV32-NEXT: addi t4, sp, 152
+; RV32-NEXT: vand.vx v30, v9, t2
+; RV32-NEXT: sw zero, 96(sp)
+; RV32-NEXT: sw t2, 100(sp)
+; RV32-NEXT: addi t3, sp, 144
+; RV32-NEXT: vand.vx v31, v9, t1
+; RV32-NEXT: sw zero, 88(sp)
+; RV32-NEXT: sw t1, 92(sp)
+; RV32-NEXT: addi t2, sp, 136
+; RV32-NEXT: vand.vx v7, v9, t0
+; RV32-NEXT: sw zero, 80(sp)
+; RV32-NEXT: sw t0, 84(sp)
+; RV32-NEXT: addi t1, sp, 128
+; RV32-NEXT: vand.vx v6, v9, a7
+; RV32-NEXT: sw zero, 72(sp)
+; RV32-NEXT: sw a7, 76(sp)
+; RV32-NEXT: addi t0, sp, 120
+; RV32-NEXT: vand.vx v5, v9, a6
+; RV32-NEXT: sw zero, 64(sp)
+; RV32-NEXT: sw a6, 68(sp)
+; RV32-NEXT: addi a7, sp, 112
+; RV32-NEXT: vand.vx v4, v9, a5
+; RV32-NEXT: sw zero, 56(sp)
+; RV32-NEXT: sw a5, 60(sp)
+; RV32-NEXT: addi a6, sp, 104
+; RV32-NEXT: vand.vx v3, v9, a3
+; RV32-NEXT: sw zero, 48(sp)
+; RV32-NEXT: sw a3, 52(sp)
+; RV32-NEXT: addi a5, sp, 96
+; RV32-NEXT: vand.vx v2, v9, a4
+; RV32-NEXT: sw zero, 40(sp)
+; RV32-NEXT: sw a4, 44(sp)
+; RV32-NEXT: addi a4, sp, 88
+; RV32-NEXT: vand.vx v1, v9, a2
+; RV32-NEXT: sw zero, 32(sp)
+; RV32-NEXT: sw a2, 36(sp)
+; RV32-NEXT: addi a3, sp, 80
+; RV32-NEXT: sw zero, 24(sp)
+; RV32-NEXT: lui a0, 262144
+; RV32-NEXT: sw a0, 28(sp)
+; RV32-NEXT: sw zero, 16(sp)
+; RV32-NEXT: sw a1, 20(sp)
+; RV32-NEXT: addi a2, sp, 72
+; RV32-NEXT: vand.vx v0, v9, t5
+; RV32-NEXT: addi a1, sp, 64
+; RV32-NEXT: vmul.vv v13, v8, v13
+; RV32-NEXT: vmul.vv v14, v8, v14
+; RV32-NEXT: vxor.vi v14, v14, 0
+; RV32-NEXT: vxor.vv v14, v14, v13
+; RV32-NEXT: vlse64.v v13, (s11), zero
+; RV32-NEXT: addi s11, sp, 56
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vxor.vv v14, v14, v12
+; RV32-NEXT: vlse64.v v12, (ra), zero
+; RV32-NEXT: csrr t5, vlenb
+; RV32-NEXT: slli t5, t5, 1
+; RV32-NEXT: mv ra, t5
+; RV32-NEXT: slli t5, t5, 1
+; RV32-NEXT: add t5, t5, ra
+; RV32-NEXT: add t5, sp, t5
+; RV32-NEXT: addi t5, t5, 288
+; RV32-NEXT: vs1r.v v12, (t5) # vscale x 8-byte Folded Spill
+; RV32-NEXT: addi ra, sp, 48
+; RV32-NEXT: vmul.vv v11, v8, v11
+; RV32-NEXT: vxor.vv v14, v14, v11
+; RV32-NEXT: vlse64.v v11, (s10), zero
+; RV32-NEXT: csrr t5, vlenb
+; RV32-NEXT: slli s10, t5, 2
+; RV32-NEXT: add t5, s10, t5
+; RV32-NEXT: add t5, sp, t5
+; RV32-NEXT: addi t5, t5, 288
+; RV32-NEXT: vs1r.v v11, (t5) # vscale x 8-byte Folded Spill
+; RV32-NEXT: addi s10, sp, 40
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: vxor.vv v14, v14, v10
+; RV32-NEXT: vlse64.v v10, (s9), zero
+; RV32-NEXT: csrr t5, vlenb
+; RV32-NEXT: slli t5, t5, 2
+; RV32-NEXT: add t5, sp, t5
+; RV32-NEXT: addi t5, t5, 288
+; RV32-NEXT: vs1r.v v10, (t5) # vscale x 8-byte Folded Spill
+; RV32-NEXT: addi t5, sp, 32
+; RV32-NEXT: vmul.vv v15, v8, v15
+; RV32-NEXT: vxor.vv v15, v14, v15
+; RV32-NEXT: vlse64.v v10, (s8), zero
+; RV32-NEXT: csrr s8, vlenb
+; RV32-NEXT: slli s9, s8, 1
+; RV32-NEXT: add s8, s9, s8
+; RV32-NEXT: add s8, sp, s8
+; RV32-NEXT: addi s8, s8, 288
+; RV32-NEXT: vs1r.v v10, (s8) # vscale x 8-byte Folded Spill
+; RV32-NEXT: addi s8, sp, 24
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v16, v15, v16
+; RV32-NEXT: vlse64.v v10, (s7), zero
+; RV32-NEXT: csrr s7, vlenb
+; RV32-NEXT: slli s7, s7, 1
+; RV32-NEXT: add s7, sp, s7
+; RV32-NEXT: addi s7, s7, 288
+; RV32-NEXT: vs1r.v v10, (s7) # vscale x 8-byte Folded Spill
+; RV32-NEXT: addi s7, sp, 16
+; RV32-NEXT: vmul.vv v17, v8, v17
+; RV32-NEXT: vmul.vv v18, v8, v18
+; RV32-NEXT: vmul.vv v19, v8, v19
+; RV32-NEXT: vmul.vv v20, v8, v20
+; RV32-NEXT: vmul.vv v21, v8, v21
+; RV32-NEXT: vmul.vv v22, v8, v22
+; RV32-NEXT: vmul.vv v23, v8, v23
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vmul.vv v25, v8, v25
+; RV32-NEXT: vmul.vv v26, v8, v26
+; RV32-NEXT: vmul.vv v27, v8, v27
+; RV32-NEXT: vmul.vv v28, v8, v28
+; RV32-NEXT: vmul.vv v29, v8, v29
+; RV32-NEXT: vmul.vv v30, v8, v30
+; RV32-NEXT: vmul.vv v31, v8, v31
+; RV32-NEXT: vmul.vv v7, v8, v7
+; RV32-NEXT: vmul.vv v6, v8, v6
+; RV32-NEXT: vmul.vv v5, v8, v5
+; RV32-NEXT: vmul.vv v4, v8, v4
+; RV32-NEXT: vmul.vv v3, v8, v3
+; RV32-NEXT: vmul.vv v2, v8, v2
+; RV32-NEXT: vmul.vv v1, v8, v1
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: vxor.vv v16, v16, v17
+; RV32-NEXT: addi s9, sp, 224
+; RV32-NEXT: vlse64.v v11, (s9), zero
+; RV32-NEXT: vxor.vv v16, v16, v18
+; RV32-NEXT: vlse64.v v10, (s6), zero
+; RV32-NEXT: csrr s6, vlenb
+; RV32-NEXT: add s6, sp, s6
+; RV32-NEXT: addi s6, s6, 288
+; RV32-NEXT: vs1r.v v10, (s6) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vxor.vv v16, v16, v19
+; RV32-NEXT: vlse64.v v10, (s5), zero
+; RV32-NEXT: addi s5, sp, 288
+; RV32-NEXT: vs1r.v v10, (s5) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vxor.vv v16, v16, v20
+; RV32-NEXT: vlse64.v v12, (s4), zero
+; RV32-NEXT: vxor.vv v16, v16, v0
+; RV32-NEXT: vlse64.v v0, (s3), zero
+; RV32-NEXT: vxor.vv v16, v16, v21
+; RV32-NEXT: vlse64.v v21, (s2), zero
+; RV32-NEXT: vxor.vv v16, v16, v22
+; RV32-NEXT: vlse64.v v22, (s1), zero
+; RV32-NEXT: vxor.vv v16, v16, v23
+; RV32-NEXT: vlse64.v v23, (s0), zero
+; RV32-NEXT: vxor.vv v16, v16, v24
+; RV32-NEXT: vlse64.v v24, (t6), zero
+; RV32-NEXT: vxor.vv v16, v16, v25
+; RV32-NEXT: vlse64.v v25, (t4), zero
+; RV32-NEXT: vxor.vv v16, v16, v26
+; RV32-NEXT: vlse64.v v26, (t3), zero
+; RV32-NEXT: vxor.vv v16, v16, v27
+; RV32-NEXT: vlse64.v v27, (t2), zero
+; RV32-NEXT: vxor.vv v16, v16, v28
+; RV32-NEXT: vlse64.v v28, (t1), zero
+; RV32-NEXT: vxor.vv v16, v16, v29
+; RV32-NEXT: vlse64.v v29, (t0), zero
+; RV32-NEXT: vxor.vv v16, v16, v30
+; RV32-NEXT: vlse64.v v30, (a7), zero
+; RV32-NEXT: vxor.vv v16, v16, v31
+; RV32-NEXT: vlse64.v v31, (a6), zero
+; RV32-NEXT: vxor.vv v16, v16, v7
+; RV32-NEXT: vlse64.v v7, (a5), zero
+; RV32-NEXT: vxor.vv v16, v16, v6
+; RV32-NEXT: vlse64.v v6, (a4), zero
+; RV32-NEXT: vxor.vv v16, v16, v5
+; RV32-NEXT: vlse64.v v5, (a3), zero
+; RV32-NEXT: vxor.vv v16, v16, v4
+; RV32-NEXT: vlse64.v v4, (a2), zero
+; RV32-NEXT: vxor.vv v16, v16, v3
+; RV32-NEXT: vlse64.v v3, (a1), zero
+; RV32-NEXT: vxor.vv v16, v16, v2
+; RV32-NEXT: vlse64.v v2, (s11), zero
+; RV32-NEXT: vxor.vv v1, v16, v1
+; RV32-NEXT: vlse64.v v10, (ra), zero
+; RV32-NEXT: vand.vv v13, v9, v13
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a1, a1, 1
+; RV32-NEXT: mv a2, a1
+; RV32-NEXT: slli a1, a1, 1
+; RV32-NEXT: add a1, a1, a2
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vl1r.v v14, (a1) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vand.vv v14, v9, v14
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a2, a1, 2
+; RV32-NEXT: add a1, a2, a1
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vl1r.v v15, (a1) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vand.vv v15, v9, v15
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a1, a1, 2
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vl1r.v v16, (a1) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vand.vv v16, v9, v16
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a2, a1, 1
+; RV32-NEXT: add a1, a2, a1
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vl1r.v v17, (a1) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vand.vv v17, v9, v17
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a1, a1, 1
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vl1r.v v18, (a1) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vand.vv v18, v9, v18
+; RV32-NEXT: vand.vv v19, v9, v11
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vl1r.v v11, (a1) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vand.vv v20, v9, v11
+; RV32-NEXT: addi a1, sp, 288
+; RV32-NEXT: vl1r.v v11, (a1) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vand.vv v11, v9, v11
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a1, a1, 1
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vs1r.v v11, (a1) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v11, v9, v12
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a2, a1, 1
+; RV32-NEXT: add a1, a2, a1
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vs1r.v v11, (a1) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v0, v9, v0
+; RV32-NEXT: vand.vv v21, v9, v21
+; RV32-NEXT: vand.vv v22, v9, v22
+; RV32-NEXT: vand.vv v23, v9, v23
+; RV32-NEXT: vand.vv v24, v9, v24
+; RV32-NEXT: vand.vv v25, v9, v25
+; RV32-NEXT: vand.vv v26, v9, v26
+; RV32-NEXT: vand.vv v27, v9, v27
+; RV32-NEXT: vand.vv v28, v9, v28
+; RV32-NEXT: vand.vv v29, v9, v29
+; RV32-NEXT: vand.vv v30, v9, v30
+; RV32-NEXT: vand.vv v31, v9, v31
+; RV32-NEXT: vand.vv v7, v9, v7
+; RV32-NEXT: vand.vv v6, v9, v6
+; RV32-NEXT: vand.vv v5, v9, v5
+; RV32-NEXT: vand.vv v4, v9, v4
+; RV32-NEXT: vand.vv v11, v9, v3
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a1, a1, 2
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vs1r.v v11, (a1) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v2, v9, v2
+; RV32-NEXT: vand.vv v10, v9, v10
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a1, a1, 1
+; RV32-NEXT: mv a2, a1
+; RV32-NEXT: slli a1, a1, 1
+; RV32-NEXT: add a1, a1, a2
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vs1r.v v10, (a1) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vlse64.v v10, (s10), zero
+; RV32-NEXT: vlse64.v v3, (t5), zero
+; RV32-NEXT: vlse64.v v11, (s8), zero
+; RV32-NEXT: vlse64.v v12, (s7), zero
+; RV32-NEXT: vand.vv v10, v9, v10
+; RV32-NEXT: vand.vv v3, v9, v3
+; RV32-NEXT: vand.vv v11, v9, v11
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a2, a1, 2
+; RV32-NEXT: add a1, a2, a1
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vs1r.v v11, (a1) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v9, v12
+; RV32-NEXT: vand.vx v9, v9, a0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: vxor.vv v9, v1, v9
+; RV32-NEXT: vmul.vv v11, v8, v13
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v14
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v15
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v16
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v17
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v18
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v19
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v20
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v11, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v11, v8, v11
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 1
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v11, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v11, v8, v11
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v0
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v21
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v22
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v23
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v24
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v25
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v26
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v27
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v28
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v29
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v30
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v31
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v7
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v6
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v5
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v4
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v11, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v11, v8, v11
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v2
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v11, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v11, v8, v11
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: vxor.vv v9, v9, v10
+; RV32-NEXT: vmul.vv v10, v8, v3
+; RV32-NEXT: vxor.vv v9, v9, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 2
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v10, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: vxor.vv v9, v9, v10
+; RV32-NEXT: vmul.vv v8, v8, v12
+; RV32-NEXT: vxor.vv v8, v9, v8
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 3
+; RV32-NEXT: sub a0, a1, a0
+; RV32-NEXT: add sp, sp, a0
+; RV32-NEXT: lw ra, 348(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s0, 344(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s1, 340(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s2, 336(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s3, 332(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s4, 328(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s5, 324(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s6, 320(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s7, 316(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s8, 312(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s9, 308(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s10, 304(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s11, 300(sp) # 4-byte Folded Reload
+; RV32-NEXT: addi sp, sp, 352
+; RV32-NEXT: ret
+;
+; RV64-LABEL: clmul_v1i64:
+; RV64: # %bb.0:
+; RV64-NEXT: vsetivli zero, 1, e64, m1, ta, ma
+; RV64-NEXT: vand.vi v10, v9, 2
+; RV64-NEXT: vand.vi v11, v9, 1
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v11, v10
+; RV64-NEXT: vand.vi v11, v9, 4
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vi v11, v9, 8
+; RV64-NEXT: li a0, 16
+; RV64-NEXT: li a1, 32
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a0
+; RV64-NEXT: li a0, 64
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: li a1, 128
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a0
+; RV64-NEXT: li a0, 256
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: li a1, 512
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a0
+; RV64-NEXT: li a2, 1024
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: li a0, 1
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a2
+; RV64-NEXT: slli a1, a0, 11
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 1
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 2
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 4
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 8
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 16
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 32
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 64
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 128
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 256
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 512
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 1024
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 2048
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 4096
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 8192
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 16384
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 32768
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 65536
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 131072
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 262144
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 31
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 32
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 33
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 34
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 35
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 36
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 37
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 38
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 39
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 40
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 41
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 42
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 43
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 44
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 45
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 46
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 47
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 48
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 49
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 50
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 51
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 52
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 53
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 54
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 55
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 56
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 57
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 58
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 59
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 60
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 61
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: li a1, -1
+; RV64-NEXT: slli a0, a0, 62
+; RV64-NEXT: slli a1, a1, 63
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a0
+; RV64-NEXT: vand.vx v9, v9, a1
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vmul.vv v8, v8, v9
+; RV64-NEXT: vxor.vv v8, v10, v8
+; RV64-NEXT: ret
+ %a = call <1 x i64> @llvm.clmul.v1i64(<1 x i64> %x, <1 x i64> %y)
+ ret <1 x i64> %a
+}
+
+define <2 x i64> @clmul_v2i64(<2 x i64> %x, <2 x i64> %y) nounwind {
+; RV32-LABEL: clmul_v2i64:
+; RV32: # %bb.0:
+; RV32-NEXT: addi sp, sp, -352
+; RV32-NEXT: sw ra, 348(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s0, 344(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s1, 340(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s2, 336(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s3, 332(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s4, 328(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s5, 324(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s6, 320(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s7, 316(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s8, 312(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s9, 308(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s10, 304(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s11, 300(sp) # 4-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 3
+; RV32-NEXT: sub a0, a1, a0
+; RV32-NEXT: sub sp, sp, a0
+; RV32-NEXT: lui a1, 524288
+; RV32-NEXT: li t5, 1
+; RV32-NEXT: li a4, 2
+; RV32-NEXT: li a2, 4
+; RV32-NEXT: li s11, 8
+; RV32-NEXT: li a0, 16
+; RV32-NEXT: li ra, 32
+; RV32-NEXT: li s10, 64
+; RV32-NEXT: li s9, 128
+; RV32-NEXT: li s8, 256
+; RV32-NEXT: li s7, 512
+; RV32-NEXT: li s1, 1024
+; RV32-NEXT: lui s6, 1
+; RV32-NEXT: lui s5, 2
+; RV32-NEXT: lui s4, 4
+; RV32-NEXT: lui s3, 8
+; RV32-NEXT: lui s2, 16
+; RV32-NEXT: lui s0, 32
+; RV32-NEXT: lui t6, 64
+; RV32-NEXT: lui t4, 128
+; RV32-NEXT: lui t3, 256
+; RV32-NEXT: lui t2, 512
+; RV32-NEXT: lui t1, 1024
+; RV32-NEXT: lui t0, 2048
+; RV32-NEXT: lui a7, 4096
+; RV32-NEXT: lui a6, 8192
+; RV32-NEXT: lui a5, 16384
+; RV32-NEXT: lui a3, 32768
+; RV32-NEXT: sw a1, 272(sp)
+; RV32-NEXT: sw zero, 276(sp)
+; RV32-NEXT: sw zero, 264(sp)
+; RV32-NEXT: sw t5, 268(sp)
+; RV32-NEXT: sw zero, 256(sp)
+; RV32-NEXT: sw a4, 260(sp)
+; RV32-NEXT: lui a4, 65536
+; RV32-NEXT: sw zero, 248(sp)
+; RV32-NEXT: sw a2, 252(sp)
+; RV32-NEXT: lui a2, 131072
+; RV32-NEXT: sw zero, 240(sp)
+; RV32-NEXT: sw s11, 244(sp)
+; RV32-NEXT: vsetivli zero, 2, e64, m1, ta, ma
+; RV32-NEXT: vand.vi v13, v9, 2
+; RV32-NEXT: vand.vi v14, v9, 1
+; RV32-NEXT: vand.vi v12, v9, 4
+; RV32-NEXT: vand.vi v11, v9, 8
+; RV32-NEXT: sw zero, 232(sp)
+; RV32-NEXT: sw a0, 236(sp)
+; RV32-NEXT: vand.vx v10, v9, a0
+; RV32-NEXT: addi s11, sp, 272
+; RV32-NEXT: sw zero, 224(sp)
+; RV32-NEXT: sw ra, 228(sp)
+; RV32-NEXT: vand.vx v15, v9, ra
+; RV32-NEXT: addi ra, sp, 264
+; RV32-NEXT: sw zero, 216(sp)
+; RV32-NEXT: sw s10, 220(sp)
+; RV32-NEXT: vand.vx v16, v9, s10
+; RV32-NEXT: addi s10, sp, 256
+; RV32-NEXT: sw zero, 208(sp)
+; RV32-NEXT: sw s9, 212(sp)
+; RV32-NEXT: vand.vx v17, v9, s9
+; RV32-NEXT: addi s9, sp, 248
+; RV32-NEXT: sw zero, 200(sp)
+; RV32-NEXT: sw s8, 204(sp)
+; RV32-NEXT: vand.vx v18, v9, s8
+; RV32-NEXT: addi s8, sp, 240
+; RV32-NEXT: sw zero, 192(sp)
+; RV32-NEXT: sw s7, 196(sp)
+; RV32-NEXT: vand.vx v19, v9, s7
+; RV32-NEXT: addi s7, sp, 232
+; RV32-NEXT: sw zero, 184(sp)
+; RV32-NEXT: sw s1, 188(sp)
+; RV32-NEXT: vand.vx v20, v9, s1
+; RV32-NEXT: slli t5, t5, 11
+; RV32-NEXT: vand.vx v21, v9, s6
+; RV32-NEXT: sw zero, 176(sp)
+; RV32-NEXT: sw t5, 180(sp)
+; RV32-NEXT: sw zero, 168(sp)
+; RV32-NEXT: sw s6, 172(sp)
+; RV32-NEXT: addi s6, sp, 216
+; RV32-NEXT: vand.vx v22, v9, s5
+; RV32-NEXT: sw zero, 160(sp)
+; RV32-NEXT: sw s5, 164(sp)
+; RV32-NEXT: addi s5, sp, 208
+; RV32-NEXT: vand.vx v23, v9, s4
+; RV32-NEXT: sw zero, 152(sp)
+; RV32-NEXT: sw s4, 156(sp)
+; RV32-NEXT: addi s4, sp, 200
+; RV32-NEXT: vand.vx v24, v9, s3
+; RV32-NEXT: sw zero, 144(sp)
+; RV32-NEXT: sw s3, 148(sp)
+; RV32-NEXT: addi s3, sp, 192
+; RV32-NEXT: vand.vx v25, v9, s2
+; RV32-NEXT: sw zero, 136(sp)
+; RV32-NEXT: sw s2, 140(sp)
+; RV32-NEXT: addi s2, sp, 184
+; RV32-NEXT: vand.vx v26, v9, s0
+; RV32-NEXT: sw zero, 128(sp)
+; RV32-NEXT: sw s0, 132(sp)
+; RV32-NEXT: addi s1, sp, 176
+; RV32-NEXT: vand.vx v27, v9, t6
+; RV32-NEXT: sw zero, 120(sp)
+; RV32-NEXT: sw t6, 124(sp)
+; RV32-NEXT: addi s0, sp, 168
+; RV32-NEXT: vand.vx v28, v9, t4
+; RV32-NEXT: sw zero, 112(sp)
+; RV32-NEXT: sw t4, 116(sp)
+; RV32-NEXT: addi t6, sp, 160
+; RV32-NEXT: vand.vx v29, v9, t3
+; RV32-NEXT: sw zero, 104(sp)
+; RV32-NEXT: sw t3, 108(sp)
+; RV32-NEXT: addi t4, sp, 152
+; RV32-NEXT: vand.vx v30, v9, t2
+; RV32-NEXT: sw zero, 96(sp)
+; RV32-NEXT: sw t2, 100(sp)
+; RV32-NEXT: addi t3, sp, 144
+; RV32-NEXT: vand.vx v31, v9, t1
+; RV32-NEXT: sw zero, 88(sp)
+; RV32-NEXT: sw t1, 92(sp)
+; RV32-NEXT: addi t2, sp, 136
+; RV32-NEXT: vand.vx v7, v9, t0
+; RV32-NEXT: sw zero, 80(sp)
+; RV32-NEXT: sw t0, 84(sp)
+; RV32-NEXT: addi t1, sp, 128
+; RV32-NEXT: vand.vx v6, v9, a7
+; RV32-NEXT: sw zero, 72(sp)
+; RV32-NEXT: sw a7, 76(sp)
+; RV32-NEXT: addi t0, sp, 120
+; RV32-NEXT: vand.vx v5, v9, a6
+; RV32-NEXT: sw zero, 64(sp)
+; RV32-NEXT: sw a6, 68(sp)
+; RV32-NEXT: addi a7, sp, 112
+; RV32-NEXT: vand.vx v4, v9, a5
+; RV32-NEXT: sw zero, 56(sp)
+; RV32-NEXT: sw a5, 60(sp)
+; RV32-NEXT: addi a6, sp, 104
+; RV32-NEXT: vand.vx v3, v9, a3
+; RV32-NEXT: sw zero, 48(sp)
+; RV32-NEXT: sw a3, 52(sp)
+; RV32-NEXT: addi a5, sp, 96
+; RV32-NEXT: vand.vx v2, v9, a4
+; RV32-NEXT: sw zero, 40(sp)
+; RV32-NEXT: sw a4, 44(sp)
+; RV32-NEXT: addi a4, sp, 88
+; RV32-NEXT: vand.vx v1, v9, a2
+; RV32-NEXT: sw zero, 32(sp)
+; RV32-NEXT: sw a2, 36(sp)
+; RV32-NEXT: addi a3, sp, 80
+; RV32-NEXT: sw zero, 24(sp)
+; RV32-NEXT: lui a0, 262144
+; RV32-NEXT: sw a0, 28(sp)
+; RV32-NEXT: sw zero, 16(sp)
+; RV32-NEXT: sw a1, 20(sp)
+; RV32-NEXT: addi a2, sp, 72
+; RV32-NEXT: vand.vx v0, v9, t5
+; RV32-NEXT: addi a1, sp, 64
+; RV32-NEXT: vmul.vv v13, v8, v13
+; RV32-NEXT: vmul.vv v14, v8, v14
+; RV32-NEXT: vxor.vi v14, v14, 0
+; RV32-NEXT: vxor.vv v14, v14, v13
+; RV32-NEXT: vlse64.v v13, (s11), zero
+; RV32-NEXT: addi s11, sp, 56
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vxor.vv v14, v14, v12
+; RV32-NEXT: vlse64.v v12, (ra), zero
+; RV32-NEXT: csrr t5, vlenb
+; RV32-NEXT: slli t5, t5, 1
+; RV32-NEXT: mv ra, t5
+; RV32-NEXT: slli t5, t5, 1
+; RV32-NEXT: add t5, t5, ra
+; RV32-NEXT: add t5, sp, t5
+; RV32-NEXT: addi t5, t5, 288
+; RV32-NEXT: vs1r.v v12, (t5) # vscale x 8-byte Folded Spill
+; RV32-NEXT: addi ra, sp, 48
+; RV32-NEXT: vmul.vv v11, v8, v11
+; RV32-NEXT: vxor.vv v14, v14, v11
+; RV32-NEXT: vlse64.v v11, (s10), zero
+; RV32-NEXT: csrr t5, vlenb
+; RV32-NEXT: slli s10, t5, 2
+; RV32-NEXT: add t5, s10, t5
+; RV32-NEXT: add t5, sp, t5
+; RV32-NEXT: addi t5, t5, 288
+; RV32-NEXT: vs1r.v v11, (t5) # vscale x 8-byte Folded Spill
+; RV32-NEXT: addi s10, sp, 40
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: vxor.vv v14, v14, v10
+; RV32-NEXT: vlse64.v v10, (s9), zero
+; RV32-NEXT: csrr t5, vlenb
+; RV32-NEXT: slli t5, t5, 2
+; RV32-NEXT: add t5, sp, t5
+; RV32-NEXT: addi t5, t5, 288
+; RV32-NEXT: vs1r.v v10, (t5) # vscale x 8-byte Folded Spill
+; RV32-NEXT: addi t5, sp, 32
+; RV32-NEXT: vmul.vv v15, v8, v15
+; RV32-NEXT: vxor.vv v15, v14, v15
+; RV32-NEXT: vlse64.v v10, (s8), zero
+; RV32-NEXT: csrr s8, vlenb
+; RV32-NEXT: slli s9, s8, 1
+; RV32-NEXT: add s8, s9, s8
+; RV32-NEXT: add s8, sp, s8
+; RV32-NEXT: addi s8, s8, 288
+; RV32-NEXT: vs1r.v v10, (s8) # vscale x 8-byte Folded Spill
+; RV32-NEXT: addi s8, sp, 24
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v16, v15, v16
+; RV32-NEXT: vlse64.v v10, (s7), zero
+; RV32-NEXT: csrr s7, vlenb
+; RV32-NEXT: slli s7, s7, 1
+; RV32-NEXT: add s7, sp, s7
+; RV32-NEXT: addi s7, s7, 288
+; RV32-NEXT: vs1r.v v10, (s7) # vscale x 8-byte Folded Spill
+; RV32-NEXT: addi s7, sp, 16
+; RV32-NEXT: vmul.vv v17, v8, v17
+; RV32-NEXT: vmul.vv v18, v8, v18
+; RV32-NEXT: vmul.vv v19, v8, v19
+; RV32-NEXT: vmul.vv v20, v8, v20
+; RV32-NEXT: vmul.vv v21, v8, v21
+; RV32-NEXT: vmul.vv v22, v8, v22
+; RV32-NEXT: vmul.vv v23, v8, v23
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vmul.vv v25, v8, v25
+; RV32-NEXT: vmul.vv v26, v8, v26
+; RV32-NEXT: vmul.vv v27, v8, v27
+; RV32-NEXT: vmul.vv v28, v8, v28
+; RV32-NEXT: vmul.vv v29, v8, v29
+; RV32-NEXT: vmul.vv v30, v8, v30
+; RV32-NEXT: vmul.vv v31, v8, v31
+; RV32-NEXT: vmul.vv v7, v8, v7
+; RV32-NEXT: vmul.vv v6, v8, v6
+; RV32-NEXT: vmul.vv v5, v8, v5
+; RV32-NEXT: vmul.vv v4, v8, v4
+; RV32-NEXT: vmul.vv v3, v8, v3
+; RV32-NEXT: vmul.vv v2, v8, v2
+; RV32-NEXT: vmul.vv v1, v8, v1
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: vxor.vv v16, v16, v17
+; RV32-NEXT: addi s9, sp, 224
+; RV32-NEXT: vlse64.v v11, (s9), zero
+; RV32-NEXT: vxor.vv v16, v16, v18
+; RV32-NEXT: vlse64.v v10, (s6), zero
+; RV32-NEXT: csrr s6, vlenb
+; RV32-NEXT: add s6, sp, s6
+; RV32-NEXT: addi s6, s6, 288
+; RV32-NEXT: vs1r.v v10, (s6) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vxor.vv v16, v16, v19
+; RV32-NEXT: vlse64.v v10, (s5), zero
+; RV32-NEXT: addi s5, sp, 288
+; RV32-NEXT: vs1r.v v10, (s5) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vxor.vv v16, v16, v20
+; RV32-NEXT: vlse64.v v12, (s4), zero
+; RV32-NEXT: vxor.vv v16, v16, v0
+; RV32-NEXT: vlse64.v v0, (s3), zero
+; RV32-NEXT: vxor.vv v16, v16, v21
+; RV32-NEXT: vlse64.v v21, (s2), zero
+; RV32-NEXT: vxor.vv v16, v16, v22
+; RV32-NEXT: vlse64.v v22, (s1), zero
+; RV32-NEXT: vxor.vv v16, v16, v23
+; RV32-NEXT: vlse64.v v23, (s0), zero
+; RV32-NEXT: vxor.vv v16, v16, v24
+; RV32-NEXT: vlse64.v v24, (t6), zero
+; RV32-NEXT: vxor.vv v16, v16, v25
+; RV32-NEXT: vlse64.v v25, (t4), zero
+; RV32-NEXT: vxor.vv v16, v16, v26
+; RV32-NEXT: vlse64.v v26, (t3), zero
+; RV32-NEXT: vxor.vv v16, v16, v27
+; RV32-NEXT: vlse64.v v27, (t2), zero
+; RV32-NEXT: vxor.vv v16, v16, v28
+; RV32-NEXT: vlse64.v v28, (t1), zero
+; RV32-NEXT: vxor.vv v16, v16, v29
+; RV32-NEXT: vlse64.v v29, (t0), zero
+; RV32-NEXT: vxor.vv v16, v16, v30
+; RV32-NEXT: vlse64.v v30, (a7), zero
+; RV32-NEXT: vxor.vv v16, v16, v31
+; RV32-NEXT: vlse64.v v31, (a6), zero
+; RV32-NEXT: vxor.vv v16, v16, v7
+; RV32-NEXT: vlse64.v v7, (a5), zero
+; RV32-NEXT: vxor.vv v16, v16, v6
+; RV32-NEXT: vlse64.v v6, (a4), zero
+; RV32-NEXT: vxor.vv v16, v16, v5
+; RV32-NEXT: vlse64.v v5, (a3), zero
+; RV32-NEXT: vxor.vv v16, v16, v4
+; RV32-NEXT: vlse64.v v4, (a2), zero
+; RV32-NEXT: vxor.vv v16, v16, v3
+; RV32-NEXT: vlse64.v v3, (a1), zero
+; RV32-NEXT: vxor.vv v16, v16, v2
+; RV32-NEXT: vlse64.v v2, (s11), zero
+; RV32-NEXT: vxor.vv v1, v16, v1
+; RV32-NEXT: vlse64.v v10, (ra), zero
+; RV32-NEXT: vand.vv v13, v9, v13
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a1, a1, 1
+; RV32-NEXT: mv a2, a1
+; RV32-NEXT: slli a1, a1, 1
+; RV32-NEXT: add a1, a1, a2
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vl1r.v v14, (a1) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vand.vv v14, v9, v14
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a2, a1, 2
+; RV32-NEXT: add a1, a2, a1
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vl1r.v v15, (a1) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vand.vv v15, v9, v15
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a1, a1, 2
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vl1r.v v16, (a1) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vand.vv v16, v9, v16
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a2, a1, 1
+; RV32-NEXT: add a1, a2, a1
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vl1r.v v17, (a1) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vand.vv v17, v9, v17
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a1, a1, 1
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vl1r.v v18, (a1) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vand.vv v18, v9, v18
+; RV32-NEXT: vand.vv v19, v9, v11
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vl1r.v v11, (a1) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vand.vv v20, v9, v11
+; RV32-NEXT: addi a1, sp, 288
+; RV32-NEXT: vl1r.v v11, (a1) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vand.vv v11, v9, v11
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a1, a1, 1
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vs1r.v v11, (a1) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v11, v9, v12
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a2, a1, 1
+; RV32-NEXT: add a1, a2, a1
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vs1r.v v11, (a1) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v0, v9, v0
+; RV32-NEXT: vand.vv v21, v9, v21
+; RV32-NEXT: vand.vv v22, v9, v22
+; RV32-NEXT: vand.vv v23, v9, v23
+; RV32-NEXT: vand.vv v24, v9, v24
+; RV32-NEXT: vand.vv v25, v9, v25
+; RV32-NEXT: vand.vv v26, v9, v26
+; RV32-NEXT: vand.vv v27, v9, v27
+; RV32-NEXT: vand.vv v28, v9, v28
+; RV32-NEXT: vand.vv v29, v9, v29
+; RV32-NEXT: vand.vv v30, v9, v30
+; RV32-NEXT: vand.vv v31, v9, v31
+; RV32-NEXT: vand.vv v7, v9, v7
+; RV32-NEXT: vand.vv v6, v9, v6
+; RV32-NEXT: vand.vv v5, v9, v5
+; RV32-NEXT: vand.vv v4, v9, v4
+; RV32-NEXT: vand.vv v11, v9, v3
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a1, a1, 2
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vs1r.v v11, (a1) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v2, v9, v2
+; RV32-NEXT: vand.vv v10, v9, v10
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a1, a1, 1
+; RV32-NEXT: mv a2, a1
+; RV32-NEXT: slli a1, a1, 1
+; RV32-NEXT: add a1, a1, a2
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vs1r.v v10, (a1) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vlse64.v v10, (s10), zero
+; RV32-NEXT: vlse64.v v3, (t5), zero
+; RV32-NEXT: vlse64.v v11, (s8), zero
+; RV32-NEXT: vlse64.v v12, (s7), zero
+; RV32-NEXT: vand.vv v10, v9, v10
+; RV32-NEXT: vand.vv v3, v9, v3
+; RV32-NEXT: vand.vv v11, v9, v11
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a2, a1, 2
+; RV32-NEXT: add a1, a2, a1
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vs1r.v v11, (a1) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v9, v12
+; RV32-NEXT: vand.vx v9, v9, a0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: vxor.vv v9, v1, v9
+; RV32-NEXT: vmul.vv v11, v8, v13
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v14
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v15
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v16
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v17
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v18
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v19
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v20
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v11, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v11, v8, v11
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 1
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v11, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v11, v8, v11
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v0
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v21
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v22
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v23
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v24
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v25
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v26
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v27
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v28
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v29
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v30
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v31
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v7
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v6
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v5
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v4
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v11, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v11, v8, v11
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v11, v8, v2
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v11, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v11, v8, v11
+; RV32-NEXT: vxor.vv v9, v9, v11
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: vxor.vv v9, v9, v10
+; RV32-NEXT: vmul.vv v10, v8, v3
+; RV32-NEXT: vxor.vv v9, v9, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 2
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v10, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: vxor.vv v9, v9, v10
+; RV32-NEXT: vmul.vv v8, v8, v12
+; RV32-NEXT: vxor.vv v8, v9, v8
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 3
+; RV32-NEXT: sub a0, a1, a0
+; RV32-NEXT: add sp, sp, a0
+; RV32-NEXT: lw ra, 348(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s0, 344(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s1, 340(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s2, 336(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s3, 332(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s4, 328(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s5, 324(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s6, 320(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s7, 316(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s8, 312(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s9, 308(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s10, 304(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s11, 300(sp) # 4-byte Folded Reload
+; RV32-NEXT: addi sp, sp, 352
+; RV32-NEXT: ret
+;
+; RV64-LABEL: clmul_v2i64:
+; RV64: # %bb.0:
+; RV64-NEXT: vsetivli zero, 2, e64, m1, ta, ma
+; RV64-NEXT: vand.vi v10, v9, 2
+; RV64-NEXT: vand.vi v11, v9, 1
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v11, v10
+; RV64-NEXT: vand.vi v11, v9, 4
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vi v11, v9, 8
+; RV64-NEXT: li a0, 16
+; RV64-NEXT: li a1, 32
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a0
+; RV64-NEXT: li a0, 64
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: li a1, 128
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a0
+; RV64-NEXT: li a0, 256
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: li a1, 512
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a0
+; RV64-NEXT: li a2, 1024
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: li a0, 1
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a2
+; RV64-NEXT: slli a1, a0, 11
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 1
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 2
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 4
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 8
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 16
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 32
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 64
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 128
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 256
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 512
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 1024
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 2048
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 4096
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 8192
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 16384
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 32768
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 65536
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 131072
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: lui a1, 262144
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 31
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 32
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 33
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 34
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 35
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 36
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 37
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 38
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 39
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 40
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 41
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 42
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 43
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 44
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 45
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 46
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 47
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 48
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 49
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 50
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 51
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 52
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 53
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 54
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 55
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 56
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 57
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 58
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 59
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 60
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: slli a1, a0, 61
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a1
+; RV64-NEXT: li a1, -1
+; RV64-NEXT: slli a0, a0, 62
+; RV64-NEXT: slli a1, a1, 63
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vand.vx v11, v9, a0
+; RV64-NEXT: vand.vx v9, v9, a1
+; RV64-NEXT: vmul.vv v11, v8, v11
+; RV64-NEXT: vxor.vv v10, v10, v11
+; RV64-NEXT: vmul.vv v8, v8, v9
+; RV64-NEXT: vxor.vv v8, v10, v8
+; RV64-NEXT: ret
+ %a = call <2 x i64> @llvm.clmul.v2i64(<2 x i64> %x, <2 x i64> %y)
+ ret <2 x i64> %a
+}
+
+define <4 x i64> @clmul_v4i64(<4 x i64> %x, <4 x i64> %y) nounwind {
+; RV32-LABEL: clmul_v4i64:
+; RV32: # %bb.0:
+; RV32-NEXT: addi sp, sp, -352
+; RV32-NEXT: sw ra, 348(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s0, 344(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s1, 340(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s2, 336(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s3, 332(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s4, 328(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s5, 324(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s6, 320(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s7, 316(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s8, 312(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s9, 308(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s10, 304(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s11, 300(sp) # 4-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: sub sp, sp, a0
+; RV32-NEXT: lui a1, 524288
+; RV32-NEXT: li s2, 1
+; RV32-NEXT: li a3, 2
+; RV32-NEXT: li a2, 4
+; RV32-NEXT: li s7, 8
+; RV32-NEXT: li a0, 16
+; RV32-NEXT: li s6, 32
+; RV32-NEXT: li s5, 64
+; RV32-NEXT: li s4, 128
+; RV32-NEXT: li s1, 256
+; RV32-NEXT: li s0, 512
+; RV32-NEXT: li t5, 1024
+; RV32-NEXT: lui ra, 1
+; RV32-NEXT: lui s8, 2
+; RV32-NEXT: lui s10, 4
+; RV32-NEXT: lui s11, 8
+; RV32-NEXT: lui s9, 16
+; RV32-NEXT: lui s3, 32
+; RV32-NEXT: lui t6, 64
+; RV32-NEXT: lui t4, 128
+; RV32-NEXT: lui t3, 256
+; RV32-NEXT: lui t2, 512
+; RV32-NEXT: lui t1, 1024
+; RV32-NEXT: lui t0, 2048
+; RV32-NEXT: lui a7, 4096
+; RV32-NEXT: lui a6, 8192
+; RV32-NEXT: lui a5, 16384
+; RV32-NEXT: lui a4, 32768
+; RV32-NEXT: sw a1, 272(sp)
+; RV32-NEXT: sw zero, 276(sp)
+; RV32-NEXT: sw zero, 264(sp)
+; RV32-NEXT: sw s2, 268(sp)
+; RV32-NEXT: sw zero, 256(sp)
+; RV32-NEXT: sw a3, 260(sp)
+; RV32-NEXT: lui a3, 65536
+; RV32-NEXT: sw zero, 248(sp)
+; RV32-NEXT: sw a2, 252(sp)
+; RV32-NEXT: lui a2, 131072
+; RV32-NEXT: sw zero, 240(sp)
+; RV32-NEXT: sw s7, 244(sp)
+; RV32-NEXT: vsetivli zero, 4, e64, m2, ta, ma
+; RV32-NEXT: vand.vi v28, v10, 2
+; RV32-NEXT: vand.vi v20, v10, 1
+; RV32-NEXT: vand.vi v30, v10, 4
+; RV32-NEXT: vand.vi v14, v10, 8
+; RV32-NEXT: sw zero, 232(sp)
+; RV32-NEXT: sw a0, 236(sp)
+; RV32-NEXT: vand.vx v12, v10, a0
+; RV32-NEXT: addi s7, sp, 272
+; RV32-NEXT: sw zero, 224(sp)
+; RV32-NEXT: sw s6, 228(sp)
+; RV32-NEXT: vand.vx v16, v10, s6
+; RV32-NEXT: addi s6, sp, 264
+; RV32-NEXT: sw zero, 216(sp)
+; RV32-NEXT: sw s5, 220(sp)
+; RV32-NEXT: vand.vx v18, v10, s5
+; RV32-NEXT: addi s5, sp, 256
+; RV32-NEXT: sw zero, 208(sp)
+; RV32-NEXT: sw s4, 212(sp)
+; RV32-NEXT: vand.vx v0, v10, s4
+; RV32-NEXT: addi s4, sp, 248
+; RV32-NEXT: sw zero, 200(sp)
+; RV32-NEXT: sw s1, 204(sp)
+; RV32-NEXT: vand.vx v6, v10, s1
+; RV32-NEXT: addi s1, sp, 240
+; RV32-NEXT: sw zero, 192(sp)
+; RV32-NEXT: sw s0, 196(sp)
+; RV32-NEXT: vand.vx v4, v10, s0
+; RV32-NEXT: addi s0, sp, 232
+; RV32-NEXT: sw zero, 184(sp)
+; RV32-NEXT: sw t5, 188(sp)
+; RV32-NEXT: vand.vx v2, v10, t5
+; RV32-NEXT: slli s2, s2, 11
+; RV32-NEXT: vand.vx v24, v10, ra
+; RV32-NEXT: sw zero, 176(sp)
+; RV32-NEXT: sw s2, 180(sp)
+; RV32-NEXT: sw zero, 168(sp)
+; RV32-NEXT: sw ra, 172(sp)
+; RV32-NEXT: addi t5, sp, 216
+; RV32-NEXT: vand.vx v26, v10, s8
+; RV32-NEXT: sw zero, 160(sp)
+; RV32-NEXT: sw s8, 164(sp)
+; RV32-NEXT: addi s8, sp, 208
+; RV32-NEXT: vand.vx v22, v10, s10
+; RV32-NEXT: sw zero, 152(sp)
+; RV32-NEXT: sw s10, 156(sp)
+; RV32-NEXT: addi s10, sp, 200
+; RV32-NEXT: vmul.vv v28, v8, v28
+; RV32-NEXT: vmul.vv v20, v8, v20
+; RV32-NEXT: vxor.vi v20, v20, 0
+; RV32-NEXT: vxor.vv v20, v20, v28
+; RV32-NEXT: vand.vx v28, v10, s11
+; RV32-NEXT: sw zero, 144(sp)
+; RV32-NEXT: sw s11, 148(sp)
+; RV32-NEXT: addi s11, sp, 192
+; RV32-NEXT: vmul.vv v30, v8, v30
+; RV32-NEXT: vxor.vv v20, v20, v30
+; RV32-NEXT: vand.vx v30, v10, s9
+; RV32-NEXT: sw zero, 136(sp)
+; RV32-NEXT: sw s9, 140(sp)
+; RV32-NEXT: addi s9, sp, 184
+; RV32-NEXT: vmul.vv v14, v8, v14
+; RV32-NEXT: vxor.vv v14, v20, v14
+; RV32-NEXT: vand.vx v20, v10, s3
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv ra, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, ra
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v20, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: sw zero, 128(sp)
+; RV32-NEXT: sw s3, 132(sp)
+; RV32-NEXT: addi s3, sp, 176
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vxor.vv v12, v14, v12
+; RV32-NEXT: vand.vx v14, v10, t6
+; RV32-NEXT: sw zero, 120(sp)
+; RV32-NEXT: sw t6, 124(sp)
+; RV32-NEXT: addi t6, sp, 168
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: vand.vx v16, v10, t4
+; RV32-NEXT: sw zero, 112(sp)
+; RV32-NEXT: sw t4, 116(sp)
+; RV32-NEXT: addi t4, sp, 160
+; RV32-NEXT: vmul.vv v18, v8, v18
+; RV32-NEXT: vxor.vv v18, v12, v18
+; RV32-NEXT: vand.vx v12, v10, t3
+; RV32-NEXT: sw zero, 104(sp)
+; RV32-NEXT: sw t3, 108(sp)
+; RV32-NEXT: addi t3, sp, 152
+; RV32-NEXT: vmul.vv v20, v8, v0
+; RV32-NEXT: vxor.vv v18, v18, v20
+; RV32-NEXT: vand.vx v20, v10, t2
+; RV32-NEXT: sw zero, 96(sp)
+; RV32-NEXT: sw t2, 100(sp)
+; RV32-NEXT: addi t2, sp, 144
+; RV32-NEXT: vmul.vv v6, v8, v6
+; RV32-NEXT: vxor.vv v18, v18, v6
+; RV32-NEXT: vand.vx v6, v10, t1
+; RV32-NEXT: sw zero, 88(sp)
+; RV32-NEXT: sw t1, 92(sp)
+; RV32-NEXT: addi t1, sp, 136
+; RV32-NEXT: vmul.vv v4, v8, v4
+; RV32-NEXT: vxor.vv v18, v18, v4
+; RV32-NEXT: vand.vx v4, v10, t0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv ra, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add ra, ra, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, ra
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v4, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: sw zero, 80(sp)
+; RV32-NEXT: sw t0, 84(sp)
+; RV32-NEXT: addi t0, sp, 128
+; RV32-NEXT: vmul.vv v2, v8, v2
+; RV32-NEXT: vxor.vv v18, v18, v2
+; RV32-NEXT: vand.vx v2, v10, s2
+; RV32-NEXT: addi ra, sp, 120
+; RV32-NEXT: vmul.vv v2, v8, v2
+; RV32-NEXT: vxor.vv v18, v18, v2
+; RV32-NEXT: vand.vx v2, v10, a7
+; RV32-NEXT: sw zero, 72(sp)
+; RV32-NEXT: sw a7, 76(sp)
+; RV32-NEXT: addi a7, sp, 112
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vxor.vv v18, v18, v24
+; RV32-NEXT: vand.vx v4, v10, a6
+; RV32-NEXT: sw zero, 64(sp)
+; RV32-NEXT: sw a6, 68(sp)
+; RV32-NEXT: addi a6, sp, 104
+; RV32-NEXT: vmul.vv v26, v8, v26
+; RV32-NEXT: vxor.vv v18, v18, v26
+; RV32-NEXT: vand.vx v26, v10, a5
+; RV32-NEXT: sw zero, 56(sp)
+; RV32-NEXT: sw a5, 60(sp)
+; RV32-NEXT: addi a5, sp, 96
+; RV32-NEXT: vmul.vv v22, v8, v22
+; RV32-NEXT: vxor.vv v18, v18, v22
+; RV32-NEXT: vand.vx v24, v10, a4
+; RV32-NEXT: sw zero, 48(sp)
+; RV32-NEXT: sw a4, 52(sp)
+; RV32-NEXT: addi a4, sp, 88
+; RV32-NEXT: vmul.vv v28, v8, v28
+; RV32-NEXT: vxor.vv v18, v18, v28
+; RV32-NEXT: vand.vx v28, v10, a3
+; RV32-NEXT: sw zero, 40(sp)
+; RV32-NEXT: sw a3, 44(sp)
+; RV32-NEXT: addi a3, sp, 80
+; RV32-NEXT: vmul.vv v30, v8, v30
+; RV32-NEXT: vxor.vv v18, v18, v30
+; RV32-NEXT: vand.vx v30, v10, a2
+; RV32-NEXT: sw zero, 32(sp)
+; RV32-NEXT: sw a2, 36(sp)
+; RV32-NEXT: addi a2, sp, 72
+; RV32-NEXT: sw zero, 24(sp)
+; RV32-NEXT: lui a0, 262144
+; RV32-NEXT: sw a0, 28(sp)
+; RV32-NEXT: sw zero, 16(sp)
+; RV32-NEXT: sw a1, 20(sp)
+; RV32-NEXT: addi a1, sp, 64
+; RV32-NEXT: sw a6, 4(sp) # 4-byte Folded Spill
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 3
+; RV32-NEXT: mv s2, a6
+; RV32-NEXT: slli a6, a6, 2
+; RV32-NEXT: add a6, a6, s2
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 288
+; RV32-NEXT: vl2r.v v22, (a6) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v0, v8, v22
+; RV32-NEXT: vxor.vv v0, v18, v0
+; RV32-NEXT: vlse64.v v18, (s7), zero
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 3
+; RV32-NEXT: mv s2, a6
+; RV32-NEXT: slli a6, a6, 2
+; RV32-NEXT: add a6, a6, s2
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 288
+; RV32-NEXT: vs2r.v v18, (a6) # vscale x 16-byte Folded Spill
+; RV32-NEXT: addi s7, sp, 56
+; RV32-NEXT: vmul.vv v14, v8, v14
+; RV32-NEXT: vxor.vv v14, v0, v14
+; RV32-NEXT: vlse64.v v18, (s6), zero
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 2
+; RV32-NEXT: mv s2, a6
+; RV32-NEXT: slli a6, a6, 3
+; RV32-NEXT: add a6, a6, s2
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 288
+; RV32-NEXT: vs2r.v v18, (a6) # vscale x 16-byte Folded Spill
+; RV32-NEXT: addi s2, sp, 48
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v14, v14, v16
+; RV32-NEXT: vlse64.v v16, (s5), zero
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: mv s5, a6
+; RV32-NEXT: slli a6, a6, 4
+; RV32-NEXT: add a6, a6, s5
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 288
+; RV32-NEXT: vs2r.v v16, (a6) # vscale x 16-byte Folded Spill
+; RV32-NEXT: addi s5, sp, 40
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vxor.vv v12, v14, v12
+; RV32-NEXT: vlse64.v v14, (s4), zero
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 5
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 288
+; RV32-NEXT: vs2r.v v14, (a6) # vscale x 16-byte Folded Spill
+; RV32-NEXT: addi s4, sp, 32
+; RV32-NEXT: vmul.vv v20, v8, v20
+; RV32-NEXT: vxor.vv v20, v12, v20
+; RV32-NEXT: vlse64.v v12, (s1), zero
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: mv s1, a6
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: add s1, s1, a6
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: add s1, s1, a6
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: add a6, a6, s1
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 288
+; RV32-NEXT: vs2r.v v12, (a6) # vscale x 16-byte Folded Spill
+; RV32-NEXT: addi s1, sp, 24
+; RV32-NEXT: vmul.vv v6, v8, v6
+; RV32-NEXT: vxor.vv v20, v20, v6
+; RV32-NEXT: vlse64.v v12, (s0), zero
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 2
+; RV32-NEXT: mv s0, a6
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: add s0, s0, a6
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: add a6, a6, s0
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 288
+; RV32-NEXT: vs2r.v v12, (a6) # vscale x 16-byte Folded Spill
+; RV32-NEXT: addi s0, sp, 16
+; RV32-NEXT: csrr s6, vlenb
+; RV32-NEXT: slli s6, s6, 1
+; RV32-NEXT: mv a6, s6
+; RV32-NEXT: slli s6, s6, 1
+; RV32-NEXT: add a6, a6, s6
+; RV32-NEXT: slli s6, s6, 3
+; RV32-NEXT: add s6, s6, a6
+; RV32-NEXT: lw a6, 4(sp) # 4-byte Folded Reload
+; RV32-NEXT: add s6, sp, s6
+; RV32-NEXT: addi s6, s6, 288
+; RV32-NEXT: vl2r.v v12, (s6) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v6, v8, v12
+; RV32-NEXT: vmul.vv v2, v8, v2
+; RV32-NEXT: vmul.vv v4, v8, v4
+; RV32-NEXT: vmul.vv v26, v8, v26
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vmul.vv v28, v8, v28
+; RV32-NEXT: vmul.vv v30, v8, v30
+; RV32-NEXT: vxor.vv v20, v20, v6
+; RV32-NEXT: addi s6, sp, 224
+; RV32-NEXT: vlse64.v v0, (s6), zero
+; RV32-NEXT: vxor.vv v20, v20, v2
+; RV32-NEXT: vlse64.v v6, (t5), zero
+; RV32-NEXT: vxor.vv v20, v20, v4
+; RV32-NEXT: vlse64.v v22, (s8), zero
+; RV32-NEXT: vxor.vv v20, v20, v26
+; RV32-NEXT: vlse64.v v18, (s10), zero
+; RV32-NEXT: vxor.vv v20, v20, v24
+; RV32-NEXT: vlse64.v v16, (s11), zero
+; RV32-NEXT: vxor.vv v20, v20, v28
+; RV32-NEXT: vlse64.v v14, (s9), zero
+; RV32-NEXT: vxor.vv v2, v20, v30
+; RV32-NEXT: vlse64.v v12, (s3), zero
+; RV32-NEXT: csrr t5, vlenb
+; RV32-NEXT: slli t5, t5, 3
+; RV32-NEXT: mv s3, t5
+; RV32-NEXT: slli t5, t5, 2
+; RV32-NEXT: add t5, t5, s3
+; RV32-NEXT: add t5, sp, t5
+; RV32-NEXT: addi t5, t5, 288
+; RV32-NEXT: vl2r.v v20, (t5) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vand.vv v26, v10, v20
+; RV32-NEXT: csrr t5, vlenb
+; RV32-NEXT: slli t5, t5, 2
+; RV32-NEXT: mv s3, t5
+; RV32-NEXT: slli t5, t5, 3
+; RV32-NEXT: add t5, t5, s3
+; RV32-NEXT: add t5, sp, t5
+; RV32-NEXT: addi t5, t5, 288
+; RV32-NEXT: vl2r.v v20, (t5) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vand.vv v4, v10, v20
+; RV32-NEXT: csrr t5, vlenb
+; RV32-NEXT: slli t5, t5, 1
+; RV32-NEXT: mv s3, t5
+; RV32-NEXT: slli t5, t5, 4
+; RV32-NEXT: add t5, t5, s3
+; RV32-NEXT: add t5, sp, t5
+; RV32-NEXT: addi t5, t5, 288
+; RV32-NEXT: vl2r.v v20, (t5) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vand.vv v30, v10, v20
+; RV32-NEXT: csrr t5, vlenb
+; RV32-NEXT: slli t5, t5, 5
+; RV32-NEXT: add t5, sp, t5
+; RV32-NEXT: addi t5, t5, 288
+; RV32-NEXT: vl2r.v v20, (t5) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vand.vv v20, v10, v20
+; RV32-NEXT: csrr t5, vlenb
+; RV32-NEXT: slli t5, t5, 1
+; RV32-NEXT: mv s3, t5
+; RV32-NEXT: slli t5, t5, 1
+; RV32-NEXT: add s3, s3, t5
+; RV32-NEXT: slli t5, t5, 1
+; RV32-NEXT: add s3, s3, t5
+; RV32-NEXT: slli t5, t5, 1
+; RV32-NEXT: add t5, t5, s3
+; RV32-NEXT: add t5, sp, t5
+; RV32-NEXT: addi t5, t5, 288
+; RV32-NEXT: vl2r.v v24, (t5) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vand.vv v28, v10, v24
+; RV32-NEXT: csrr t5, vlenb
+; RV32-NEXT: slli t5, t5, 2
+; RV32-NEXT: mv s3, t5
+; RV32-NEXT: slli t5, t5, 1
+; RV32-NEXT: add s3, s3, t5
+; RV32-NEXT: slli t5, t5, 1
+; RV32-NEXT: add t5, t5, s3
+; RV32-NEXT: add t5, sp, t5
+; RV32-NEXT: addi t5, t5, 288
+; RV32-NEXT: vl2r.v v24, (t5) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vand.vv v24, v10, v24
+; RV32-NEXT: vand.vv v0, v10, v0
+; RV32-NEXT: vand.vv v6, v10, v6
+; RV32-NEXT: vand.vv v22, v10, v22
+; RV32-NEXT: vand.vv v18, v10, v18
+; RV32-NEXT: csrr t5, vlenb
+; RV32-NEXT: slli t5, t5, 3
+; RV32-NEXT: add t5, sp, t5
+; RV32-NEXT: addi t5, t5, 288
+; RV32-NEXT: vs2r.v v18, (t5) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v10, v16
+; RV32-NEXT: csrr t5, vlenb
+; RV32-NEXT: slli t5, t5, 2
+; RV32-NEXT: mv s3, t5
+; RV32-NEXT: slli t5, t5, 2
+; RV32-NEXT: add t5, t5, s3
+; RV32-NEXT: add t5, sp, t5
+; RV32-NEXT: addi t5, t5, 288
+; RV32-NEXT: vs2r.v v16, (t5) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v14, v10, v14
+; RV32-NEXT: csrr t5, vlenb
+; RV32-NEXT: slli t5, t5, 1
+; RV32-NEXT: mv s3, t5
+; RV32-NEXT: slli t5, t5, 1
+; RV32-NEXT: add s3, s3, t5
+; RV32-NEXT: slli t5, t5, 1
+; RV32-NEXT: add s3, s3, t5
+; RV32-NEXT: slli t5, t5, 1
+; RV32-NEXT: add t5, t5, s3
+; RV32-NEXT: add t5, sp, t5
+; RV32-NEXT: addi t5, t5, 288
+; RV32-NEXT: vs2r.v v14, (t5) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v10, v12
+; RV32-NEXT: csrr t5, vlenb
+; RV32-NEXT: slli t5, t5, 3
+; RV32-NEXT: mv s3, t5
+; RV32-NEXT: slli t5, t5, 2
+; RV32-NEXT: add t5, t5, s3
+; RV32-NEXT: add t5, sp, t5
+; RV32-NEXT: addi t5, t5, 288
+; RV32-NEXT: vs2r.v v12, (t5) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vlse64.v v12, (t6), zero
+; RV32-NEXT: vlse64.v v14, (t4), zero
+; RV32-NEXT: vlse64.v v16, (t3), zero
+; RV32-NEXT: vlse64.v v18, (t2), zero
+; RV32-NEXT: vand.vv v12, v10, v12
+; RV32-NEXT: csrr t2, vlenb
+; RV32-NEXT: slli t2, t2, 1
+; RV32-NEXT: mv t3, t2
+; RV32-NEXT: slli t2, t2, 1
+; RV32-NEXT: add t2, t2, t3
+; RV32-NEXT: add t2, sp, t2
+; RV32-NEXT: addi t2, t2, 288
+; RV32-NEXT: vs2r.v v12, (t2) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v10, v14
+; RV32-NEXT: csrr t2, vlenb
+; RV32-NEXT: slli t2, t2, 1
+; RV32-NEXT: mv t3, t2
+; RV32-NEXT: slli t2, t2, 3
+; RV32-NEXT: add t2, t2, t3
+; RV32-NEXT: add t2, sp, t2
+; RV32-NEXT: addi t2, t2, 288
+; RV32-NEXT: vs2r.v v12, (t2) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v10, v16
+; RV32-NEXT: csrr t2, vlenb
+; RV32-NEXT: slli t2, t2, 2
+; RV32-NEXT: mv t3, t2
+; RV32-NEXT: slli t2, t2, 1
+; RV32-NEXT: add t3, t3, t2
+; RV32-NEXT: slli t2, t2, 1
+; RV32-NEXT: add t2, t2, t3
+; RV32-NEXT: add t2, sp, t2
+; RV32-NEXT: addi t2, t2, 288
+; RV32-NEXT: vs2r.v v12, (t2) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v10, v18
+; RV32-NEXT: csrr t2, vlenb
+; RV32-NEXT: slli t2, t2, 1
+; RV32-NEXT: mv t3, t2
+; RV32-NEXT: slli t2, t2, 1
+; RV32-NEXT: add t3, t3, t2
+; RV32-NEXT: slli t2, t2, 3
+; RV32-NEXT: add t2, t2, t3
+; RV32-NEXT: add t2, sp, t2
+; RV32-NEXT: addi t2, t2, 288
+; RV32-NEXT: vs2r.v v12, (t2) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vlse64.v v12, (t1), zero
+; RV32-NEXT: vlse64.v v14, (t0), zero
+; RV32-NEXT: vlse64.v v16, (ra), zero
+; RV32-NEXT: vlse64.v v18, (a7), zero
+; RV32-NEXT: vand.vv v12, v10, v12
+; RV32-NEXT: csrr a7, vlenb
+; RV32-NEXT: slli a7, a7, 2
+; RV32-NEXT: add a7, sp, a7
+; RV32-NEXT: addi a7, a7, 288
+; RV32-NEXT: vs2r.v v12, (a7) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v10, v14
+; RV32-NEXT: csrr a7, vlenb
+; RV32-NEXT: slli a7, a7, 4
+; RV32-NEXT: add a7, sp, a7
+; RV32-NEXT: addi a7, a7, 288
+; RV32-NEXT: vs2r.v v12, (a7) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v10, v16
+; RV32-NEXT: csrr a7, vlenb
+; RV32-NEXT: slli a7, a7, 1
+; RV32-NEXT: mv t0, a7
+; RV32-NEXT: slli a7, a7, 2
+; RV32-NEXT: add t0, t0, a7
+; RV32-NEXT: slli a7, a7, 1
+; RV32-NEXT: add a7, a7, t0
+; RV32-NEXT: add a7, sp, a7
+; RV32-NEXT: addi a7, a7, 288
+; RV32-NEXT: vs2r.v v12, (a7) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v10, v18
+; RV32-NEXT: csrr a7, vlenb
+; RV32-NEXT: slli a7, a7, 2
+; RV32-NEXT: mv t0, a7
+; RV32-NEXT: slli a7, a7, 3
+; RV32-NEXT: add a7, a7, t0
+; RV32-NEXT: add a7, sp, a7
+; RV32-NEXT: addi a7, a7, 288
+; RV32-NEXT: vs2r.v v12, (a7) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vlse64.v v12, (a6), zero
+; RV32-NEXT: vlse64.v v14, (a5), zero
+; RV32-NEXT: vlse64.v v16, (a4), zero
+; RV32-NEXT: vlse64.v v18, (a3), zero
+; RV32-NEXT: vand.vv v12, v10, v12
+; RV32-NEXT: csrr a3, vlenb
+; RV32-NEXT: slli a3, a3, 1
+; RV32-NEXT: add a3, sp, a3
+; RV32-NEXT: addi a3, a3, 288
+; RV32-NEXT: vs2r.v v12, (a3) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v10, v14
+; RV32-NEXT: csrr a3, vlenb
+; RV32-NEXT: slli a3, a3, 1
+; RV32-NEXT: mv a4, a3
+; RV32-NEXT: slli a3, a3, 1
+; RV32-NEXT: add a4, a4, a3
+; RV32-NEXT: slli a3, a3, 1
+; RV32-NEXT: add a3, a3, a4
+; RV32-NEXT: add a3, sp, a3
+; RV32-NEXT: addi a3, a3, 288
+; RV32-NEXT: vs2r.v v12, (a3) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v10, v16
+; RV32-NEXT: csrr a3, vlenb
+; RV32-NEXT: slli a3, a3, 3
+; RV32-NEXT: mv a4, a3
+; RV32-NEXT: slli a3, a3, 1
+; RV32-NEXT: add a3, a3, a4
+; RV32-NEXT: add a3, sp, a3
+; RV32-NEXT: addi a3, a3, 288
+; RV32-NEXT: vs2r.v v12, (a3) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v10, v18
+; RV32-NEXT: csrr a3, vlenb
+; RV32-NEXT: slli a3, a3, 1
+; RV32-NEXT: mv a4, a3
+; RV32-NEXT: slli a3, a3, 4
+; RV32-NEXT: add a3, a3, a4
+; RV32-NEXT: add a3, sp, a3
+; RV32-NEXT: addi a3, a3, 288
+; RV32-NEXT: vs2r.v v12, (a3) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vlse64.v v12, (a2), zero
+; RV32-NEXT: vlse64.v v14, (a1), zero
+; RV32-NEXT: vlse64.v v16, (s7), zero
+; RV32-NEXT: vlse64.v v18, (s2), zero
+; RV32-NEXT: vand.vv v12, v10, v12
+; RV32-NEXT: addi a1, sp, 288
+; RV32-NEXT: vs2r.v v12, (a1) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v10, v14
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a1, a1, 2
+; RV32-NEXT: mv a2, a1
+; RV32-NEXT: slli a1, a1, 1
+; RV32-NEXT: add a1, a1, a2
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vs2r.v v12, (a1) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v10, v16
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a1, a1, 1
+; RV32-NEXT: mv a2, a1
+; RV32-NEXT: slli a1, a1, 1
+; RV32-NEXT: add a2, a2, a1
+; RV32-NEXT: slli a1, a1, 2
+; RV32-NEXT: add a1, a1, a2
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vs2r.v v12, (a1) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v10, v18
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a1, a1, 5
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vs2r.v v12, (a1) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vlse64.v v14, (s5), zero
+; RV32-NEXT: vlse64.v v16, (s4), zero
+; RV32-NEXT: vlse64.v v18, (s1), zero
+; RV32-NEXT: vlse64.v v12, (s0), zero
+; RV32-NEXT: vand.vv v14, v10, v14
+; RV32-NEXT: vand.vv v16, v10, v16
+; RV32-NEXT: csrr a1, vlenb
+; RV32-NEXT: slli a1, a1, 1
+; RV32-NEXT: mv a2, a1
+; RV32-NEXT: slli a1, a1, 2
+; RV32-NEXT: add a1, a1, a2
+; RV32-NEXT: add a1, sp, a1
+; RV32-NEXT: addi a1, a1, 288
+; RV32-NEXT: vs2r.v v16, (a1) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v18, v10, v18
+; RV32-NEXT: vand.vv v16, v10, v12
+; RV32-NEXT: vand.vx v10, v10, a0
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: vxor.vv v10, v2, v10
+; RV32-NEXT: vmul.vv v12, v8, v26
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: vmul.vv v12, v8, v4
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: vmul.vv v12, v8, v30
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: vmul.vv v12, v8, v20
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: vmul.vv v12, v8, v28
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: vmul.vv v12, v8, v24
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: vmul.vv v12, v8, v0
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: vmul.vv v12, v8, v6
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: vmul.vv v12, v8, v22
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: addi a0, sp, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: vmul.vv v12, v8, v14
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: vmul.vv v12, v8, v18
+; RV32-NEXT: vxor.vv v10, v10, v12
+; RV32-NEXT: vmul.vv v8, v8, v16
+; RV32-NEXT: vxor.vv v8, v10, v8
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add sp, sp, a0
+; RV32-NEXT: lw ra, 348(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s0, 344(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s1, 340(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s2, 336(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s3, 332(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s4, 328(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s5, 324(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s6, 320(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s7, 316(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s8, 312(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s9, 308(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s10, 304(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s11, 300(sp) # 4-byte Folded Reload
+; RV32-NEXT: addi sp, sp, 352
+; RV32-NEXT: ret
+;
+; RV64-LABEL: clmul_v4i64:
+; RV64: # %bb.0:
+; RV64-NEXT: vsetivli zero, 4, e64, m2, ta, ma
+; RV64-NEXT: vand.vi v12, v10, 2
+; RV64-NEXT: vand.vi v14, v10, 1
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v14, v12
+; RV64-NEXT: vand.vi v14, v10, 4
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vi v14, v10, 8
+; RV64-NEXT: li a0, 16
+; RV64-NEXT: li a1, 32
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a0
+; RV64-NEXT: li a0, 64
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: li a1, 128
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a0
+; RV64-NEXT: li a0, 256
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: li a1, 512
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a0
+; RV64-NEXT: li a2, 1024
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: li a0, 1
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a2
+; RV64-NEXT: slli a1, a0, 11
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: lui a1, 1
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: lui a1, 2
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: lui a1, 4
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: lui a1, 8
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: lui a1, 16
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: lui a1, 32
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: lui a1, 64
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: lui a1, 128
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: lui a1, 256
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: lui a1, 512
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: lui a1, 1024
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: lui a1, 2048
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: lui a1, 4096
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: lui a1, 8192
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: lui a1, 16384
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: lui a1, 32768
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: lui a1, 65536
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: lui a1, 131072
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: lui a1, 262144
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 31
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 32
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 33
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 34
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 35
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 36
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 37
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 38
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 39
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 40
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 41
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 42
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 43
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 44
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 45
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 46
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 47
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 48
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 49
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 50
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 51
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 52
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 53
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 54
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 55
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 56
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 57
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 58
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 59
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 60
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: slli a1, a0, 61
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a1
+; RV64-NEXT: li a1, -1
+; RV64-NEXT: slli a0, a0, 62
+; RV64-NEXT: slli a1, a1, 63
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vand.vx v14, v10, a0
+; RV64-NEXT: vand.vx v10, v10, a1
+; RV64-NEXT: vmul.vv v14, v8, v14
+; RV64-NEXT: vxor.vv v12, v12, v14
+; RV64-NEXT: vmul.vv v8, v8, v10
+; RV64-NEXT: vxor.vv v8, v12, v8
+; RV64-NEXT: ret
+ %a = call <4 x i64> @llvm.clmul.v4i64(<4 x i64> %x, <4 x i64> %y)
+ ret <4 x i64> %a
+}
+
+define <8 x i64> @clmul_v8i64(<8 x i64> %x, <8 x i64> %y) nounwind {
+; RV32-LABEL: clmul_v8i64:
+; RV32: # %bb.0:
+; RV32-NEXT: addi sp, sp, -352
+; RV32-NEXT: sw ra, 348(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s0, 344(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s1, 340(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s2, 336(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s3, 332(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s4, 328(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s5, 324(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s6, 320(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s7, 316(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s8, 312(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s9, 308(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s10, 304(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s11, 300(sp) # 4-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: sub sp, sp, a0
+; RV32-NEXT: lui a1, 524288
+; RV32-NEXT: li s4, 1
+; RV32-NEXT: li a3, 2
+; RV32-NEXT: li a2, 4
+; RV32-NEXT: li a0, 8
+; RV32-NEXT: li s3, 16
+; RV32-NEXT: li s2, 32
+; RV32-NEXT: li s5, 64
+; RV32-NEXT: li s6, 128
+; RV32-NEXT: li s8, 256
+; RV32-NEXT: li s1, 512
+; RV32-NEXT: li s7, 1024
+; RV32-NEXT: lui ra, 1
+; RV32-NEXT: lui s11, 2
+; RV32-NEXT: lui s10, 4
+; RV32-NEXT: lui s9, 8
+; RV32-NEXT: lui s0, 16
+; RV32-NEXT: lui t6, 32
+; RV32-NEXT: lui t5, 64
+; RV32-NEXT: lui t4, 128
+; RV32-NEXT: lui t3, 256
+; RV32-NEXT: lui t2, 512
+; RV32-NEXT: lui t1, 1024
+; RV32-NEXT: lui t0, 2048
+; RV32-NEXT: lui a7, 4096
+; RV32-NEXT: lui a6, 8192
+; RV32-NEXT: lui a5, 16384
+; RV32-NEXT: lui a4, 32768
+; RV32-NEXT: sw a1, 272(sp)
+; RV32-NEXT: sw zero, 276(sp)
+; RV32-NEXT: sw zero, 264(sp)
+; RV32-NEXT: sw s4, 268(sp)
+; RV32-NEXT: sw zero, 256(sp)
+; RV32-NEXT: sw a3, 260(sp)
+; RV32-NEXT: lui a3, 65536
+; RV32-NEXT: sw zero, 248(sp)
+; RV32-NEXT: sw a2, 252(sp)
+; RV32-NEXT: lui a2, 131072
+; RV32-NEXT: sw zero, 240(sp)
+; RV32-NEXT: sw a0, 244(sp)
+; RV32-NEXT: vsetivli zero, 8, e64, m4, ta, ma
+; RV32-NEXT: vand.vi v28, v12, 2
+; RV32-NEXT: vand.vi v4, v12, 1
+; RV32-NEXT: vand.vi v24, v12, 4
+; RV32-NEXT: vand.vi v20, v12, 8
+; RV32-NEXT: sw zero, 232(sp)
+; RV32-NEXT: sw s3, 236(sp)
+; RV32-NEXT: vand.vx v16, v12, s3
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v16, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: addi s3, sp, 272
+; RV32-NEXT: sw zero, 224(sp)
+; RV32-NEXT: sw s2, 228(sp)
+; RV32-NEXT: vand.vx v0, v12, s2
+; RV32-NEXT: addi s2, sp, 264
+; RV32-NEXT: sw zero, 216(sp)
+; RV32-NEXT: sw s5, 220(sp)
+; RV32-NEXT: vmul.vv v16, v8, v28
+; RV32-NEXT: vmul.vv v28, v8, v4
+; RV32-NEXT: vxor.vi v28, v28, 0
+; RV32-NEXT: vxor.vv v28, v28, v16
+; RV32-NEXT: vand.vx v16, v12, s5
+; RV32-NEXT: addi s5, sp, 256
+; RV32-NEXT: sw zero, 208(sp)
+; RV32-NEXT: sw s6, 212(sp)
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vxor.vv v28, v28, v24
+; RV32-NEXT: vand.vx v24, v12, s6
+; RV32-NEXT: addi s6, sp, 248
+; RV32-NEXT: sw zero, 200(sp)
+; RV32-NEXT: sw s8, 204(sp)
+; RV32-NEXT: vmul.vv v20, v8, v20
+; RV32-NEXT: vxor.vv v20, v28, v20
+; RV32-NEXT: vand.vx v28, v12, s8
+; RV32-NEXT: addi s8, sp, 240
+; RV32-NEXT: sw zero, 192(sp)
+; RV32-NEXT: sw s1, 196(sp)
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v4, v8, v4
+; RV32-NEXT: vxor.vv v20, v20, v4
+; RV32-NEXT: vand.vx v4, v12, s1
+; RV32-NEXT: sw zero, 184(sp)
+; RV32-NEXT: sw s7, 188(sp)
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: vxor.vv v20, v20, v0
+; RV32-NEXT: vand.vx v0, v12, s7
+; RV32-NEXT: slli a0, s4, 11
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v20, v20, v16
+; RV32-NEXT: vand.vx v16, v12, ra
+; RV32-NEXT: sw zero, 176(sp)
+; RV32-NEXT: sw a0, 180(sp)
+; RV32-NEXT: sw zero, 168(sp)
+; RV32-NEXT: sw ra, 172(sp)
+; RV32-NEXT: addi s4, sp, 216
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vxor.vv v24, v20, v24
+; RV32-NEXT: vand.vx v20, v12, s11
+; RV32-NEXT: sw zero, 160(sp)
+; RV32-NEXT: sw s11, 164(sp)
+; RV32-NEXT: addi s11, sp, 208
+; RV32-NEXT: vmul.vv v28, v8, v28
+; RV32-NEXT: vxor.vv v28, v24, v28
+; RV32-NEXT: vand.vx v24, v12, s10
+; RV32-NEXT: sw zero, 152(sp)
+; RV32-NEXT: sw s10, 156(sp)
+; RV32-NEXT: addi s10, sp, 200
+; RV32-NEXT: vmul.vv v4, v8, v4
+; RV32-NEXT: vxor.vv v4, v28, v4
+; RV32-NEXT: vand.vx v28, v12, s9
+; RV32-NEXT: sw zero, 144(sp)
+; RV32-NEXT: sw s9, 148(sp)
+; RV32-NEXT: addi s9, sp, 192
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: vxor.vv v4, v4, v0
+; RV32-NEXT: vand.vx v0, v12, a0
+; RV32-NEXT: addi ra, sp, 184
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: vxor.vv v0, v4, v0
+; RV32-NEXT: vand.vx v4, v12, s0
+; RV32-NEXT: sw zero, 136(sp)
+; RV32-NEXT: sw s0, 140(sp)
+; RV32-NEXT: addi s1, sp, 176
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v0, v0, v16
+; RV32-NEXT: vand.vx v16, v12, t6
+; RV32-NEXT: sw zero, 128(sp)
+; RV32-NEXT: sw t6, 132(sp)
+; RV32-NEXT: addi s0, sp, 168
+; RV32-NEXT: vmul.vv v20, v8, v20
+; RV32-NEXT: vxor.vv v0, v0, v20
+; RV32-NEXT: vand.vx v20, v12, t5
+; RV32-NEXT: sw zero, 120(sp)
+; RV32-NEXT: sw t5, 124(sp)
+; RV32-NEXT: addi t6, sp, 160
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vxor.vv v0, v0, v24
+; RV32-NEXT: vand.vx v24, v12, t4
+; RV32-NEXT: sw zero, 112(sp)
+; RV32-NEXT: sw t4, 116(sp)
+; RV32-NEXT: addi t5, sp, 152
+; RV32-NEXT: vmul.vv v28, v8, v28
+; RV32-NEXT: vxor.vv v0, v0, v28
+; RV32-NEXT: vand.vx v28, v12, t3
+; RV32-NEXT: sw zero, 104(sp)
+; RV32-NEXT: sw t3, 108(sp)
+; RV32-NEXT: addi t4, sp, 144
+; RV32-NEXT: vmul.vv v4, v8, v4
+; RV32-NEXT: vxor.vv v0, v0, v4
+; RV32-NEXT: vand.vx v4, v12, t2
+; RV32-NEXT: sw zero, 96(sp)
+; RV32-NEXT: sw t2, 100(sp)
+; RV32-NEXT: addi t3, sp, 136
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v16, v0, v16
+; RV32-NEXT: vand.vx v0, v12, t1
+; RV32-NEXT: sw zero, 88(sp)
+; RV32-NEXT: sw t1, 92(sp)
+; RV32-NEXT: addi t2, sp, 128
+; RV32-NEXT: vmul.vv v20, v8, v20
+; RV32-NEXT: vxor.vv v20, v16, v20
+; RV32-NEXT: vand.vx v16, v12, t0
+; RV32-NEXT: sw zero, 80(sp)
+; RV32-NEXT: sw t0, 84(sp)
+; RV32-NEXT: addi t1, sp, 120
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vxor.vv v24, v20, v24
+; RV32-NEXT: vand.vx v20, v12, a7
+; RV32-NEXT: sw zero, 72(sp)
+; RV32-NEXT: sw a7, 76(sp)
+; RV32-NEXT: addi t0, sp, 112
+; RV32-NEXT: vmul.vv v28, v8, v28
+; RV32-NEXT: vxor.vv v24, v24, v28
+; RV32-NEXT: vand.vx v28, v12, a6
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v28, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: sw zero, 64(sp)
+; RV32-NEXT: sw a6, 68(sp)
+; RV32-NEXT: addi a7, sp, 104
+; RV32-NEXT: vmul.vv v28, v8, v4
+; RV32-NEXT: vxor.vv v24, v24, v28
+; RV32-NEXT: vand.vx v28, v12, a5
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v28, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: sw zero, 56(sp)
+; RV32-NEXT: sw a5, 60(sp)
+; RV32-NEXT: addi a6, sp, 96
+; RV32-NEXT: vmul.vv v28, v8, v0
+; RV32-NEXT: vxor.vv v28, v24, v28
+; RV32-NEXT: vand.vx v24, v12, a4
+; RV32-NEXT: sw zero, 48(sp)
+; RV32-NEXT: sw a4, 52(sp)
+; RV32-NEXT: addi a5, sp, 88
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v16, v28, v16
+; RV32-NEXT: vand.vx v28, v12, a3
+; RV32-NEXT: sw zero, 40(sp)
+; RV32-NEXT: sw a3, 44(sp)
+; RV32-NEXT: addi a4, sp, 80
+; RV32-NEXT: vmul.vv v20, v8, v20
+; RV32-NEXT: vxor.vv v16, v16, v20
+; RV32-NEXT: vand.vx v4, v12, a2
+; RV32-NEXT: sw zero, 32(sp)
+; RV32-NEXT: sw a2, 36(sp)
+; RV32-NEXT: addi a3, sp, 72
+; RV32-NEXT: sw zero, 24(sp)
+; RV32-NEXT: lui a1, 262144
+; RV32-NEXT: sw a1, 28(sp)
+; RV32-NEXT: sw zero, 16(sp)
+; RV32-NEXT: lui a0, 524288
+; RV32-NEXT: sw a0, 20(sp)
+; RV32-NEXT: addi a2, sp, 64
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv s7, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add s7, s7, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add s7, s7, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, s7
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v20, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v20, v8, v20
+; RV32-NEXT: vxor.vv v20, v16, v20
+; RV32-NEXT: vlse64.v v16, (s3), zero
+; RV32-NEXT: addi s3, sp, 56
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv s7, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add s7, s7, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, s7
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v0, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: vxor.vv v0, v20, v0
+; RV32-NEXT: vlse64.v v20, (s2), zero
+; RV32-NEXT: addi s2, sp, 48
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: vxor.vv v0, v0, v24
+; RV32-NEXT: vlse64.v v24, (s5), zero
+; RV32-NEXT: addi s5, sp, 40
+; RV32-NEXT: vmul.vv v28, v8, v28
+; RV32-NEXT: vxor.vv v0, v0, v28
+; RV32-NEXT: vlse64.v v28, (s6), zero
+; RV32-NEXT: addi s6, sp, 32
+; RV32-NEXT: vmul.vv v4, v8, v4
+; RV32-NEXT: vxor.vv v4, v0, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv s7, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add s7, s7, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add s7, s7, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, s7
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v4, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vlse64.v v4, (s8), zero
+; RV32-NEXT: addi s8, sp, 24
+; RV32-NEXT: vand.vv v16, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv s7, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, s7
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v16, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v12, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv s7, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add s7, s7, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, s7
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v16, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v12, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv s7, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add s7, s7, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, s7
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v16, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v12, v28
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv s7, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add s7, s7, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add s7, s7, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, s7
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v16, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v12, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv s7, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add s7, s7, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, s7
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v16, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 16
+; RV32-NEXT: addi s7, sp, 232
+; RV32-NEXT: vlse64.v v16, (s7), zero
+; RV32-NEXT: addi s7, sp, 224
+; RV32-NEXT: vlse64.v v20, (s7), zero
+; RV32-NEXT: vlse64.v v24, (s4), zero
+; RV32-NEXT: vlse64.v v28, (s11), zero
+; RV32-NEXT: vand.vv v16, v12, v16
+; RV32-NEXT: csrr s4, vlenb
+; RV32-NEXT: slli s4, s4, 4
+; RV32-NEXT: add s4, sp, s4
+; RV32-NEXT: addi s4, s4, 288
+; RV32-NEXT: vs4r.v v16, (s4) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v12, v20
+; RV32-NEXT: csrr s4, vlenb
+; RV32-NEXT: slli s4, s4, 2
+; RV32-NEXT: mv s7, s4
+; RV32-NEXT: slli s4, s4, 1
+; RV32-NEXT: add s7, s7, s4
+; RV32-NEXT: slli s4, s4, 2
+; RV32-NEXT: add s4, s4, s7
+; RV32-NEXT: add s4, sp, s4
+; RV32-NEXT: addi s4, s4, 288
+; RV32-NEXT: vs4r.v v16, (s4) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v12, v24
+; RV32-NEXT: csrr s4, vlenb
+; RV32-NEXT: slli s4, s4, 2
+; RV32-NEXT: mv s7, s4
+; RV32-NEXT: slli s4, s4, 4
+; RV32-NEXT: add s4, s4, s7
+; RV32-NEXT: add s4, sp, s4
+; RV32-NEXT: addi s4, s4, 288
+; RV32-NEXT: vs4r.v v16, (s4) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v12, v28
+; RV32-NEXT: csrr s4, vlenb
+; RV32-NEXT: slli s4, s4, 2
+; RV32-NEXT: mv s7, s4
+; RV32-NEXT: slli s4, s4, 1
+; RV32-NEXT: add s7, s7, s4
+; RV32-NEXT: slli s4, s4, 1
+; RV32-NEXT: add s7, s7, s4
+; RV32-NEXT: slli s4, s4, 2
+; RV32-NEXT: add s4, s4, s7
+; RV32-NEXT: add s4, sp, s4
+; RV32-NEXT: addi s4, s4, 288
+; RV32-NEXT: vs4r.v v16, (s4) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vlse64.v v20, (s10), zero
+; RV32-NEXT: vlse64.v v24, (s9), zero
+; RV32-NEXT: vlse64.v v28, (ra), zero
+; RV32-NEXT: vlse64.v v4, (s1), zero
+; RV32-NEXT: vand.vv v16, v12, v20
+; RV32-NEXT: csrr s1, vlenb
+; RV32-NEXT: slli s1, s1, 2
+; RV32-NEXT: mv s4, s1
+; RV32-NEXT: slli s1, s1, 1
+; RV32-NEXT: add s1, s1, s4
+; RV32-NEXT: add s1, sp, s1
+; RV32-NEXT: addi s1, s1, 288
+; RV32-NEXT: vs4r.v v16, (s1) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v12, v24
+; RV32-NEXT: csrr s1, vlenb
+; RV32-NEXT: slli s1, s1, 3
+; RV32-NEXT: mv s4, s1
+; RV32-NEXT: slli s1, s1, 2
+; RV32-NEXT: add s1, s1, s4
+; RV32-NEXT: add s1, sp, s1
+; RV32-NEXT: addi s1, s1, 288
+; RV32-NEXT: vs4r.v v16, (s1) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v12, v28
+; RV32-NEXT: csrr s1, vlenb
+; RV32-NEXT: slli s1, s1, 6
+; RV32-NEXT: add s1, sp, s1
+; RV32-NEXT: addi s1, s1, 288
+; RV32-NEXT: vs4r.v v16, (s1) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v12, v4
+; RV32-NEXT: csrr s1, vlenb
+; RV32-NEXT: slli s1, s1, 3
+; RV32-NEXT: mv s4, s1
+; RV32-NEXT: slli s1, s1, 1
+; RV32-NEXT: add s4, s4, s1
+; RV32-NEXT: slli s1, s1, 2
+; RV32-NEXT: add s1, s1, s4
+; RV32-NEXT: add s1, sp, s1
+; RV32-NEXT: addi s1, s1, 288
+; RV32-NEXT: vs4r.v v16, (s1) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vlse64.v v24, (s0), zero
+; RV32-NEXT: vlse64.v v28, (t6), zero
+; RV32-NEXT: vlse64.v v4, (t5), zero
+; RV32-NEXT: vlse64.v v0, (t4), zero
+; RV32-NEXT: vand.vv v16, v12, v24
+; RV32-NEXT: csrr t4, vlenb
+; RV32-NEXT: slli t4, t4, 3
+; RV32-NEXT: add t4, sp, t4
+; RV32-NEXT: addi t4, t4, 288
+; RV32-NEXT: vs4r.v v16, (t4) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v12, v28
+; RV32-NEXT: csrr t4, vlenb
+; RV32-NEXT: slli t4, t4, 2
+; RV32-NEXT: mv t5, t4
+; RV32-NEXT: slli t4, t4, 3
+; RV32-NEXT: add t4, t4, t5
+; RV32-NEXT: add t4, sp, t4
+; RV32-NEXT: addi t4, t4, 288
+; RV32-NEXT: vs4r.v v16, (t4) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v12, v4
+; RV32-NEXT: csrr t4, vlenb
+; RV32-NEXT: slli t4, t4, 2
+; RV32-NEXT: mv t5, t4
+; RV32-NEXT: slli t4, t4, 1
+; RV32-NEXT: add t5, t5, t4
+; RV32-NEXT: slli t4, t4, 1
+; RV32-NEXT: add t5, t5, t4
+; RV32-NEXT: slli t4, t4, 1
+; RV32-NEXT: add t4, t4, t5
+; RV32-NEXT: add t4, sp, t4
+; RV32-NEXT: addi t4, t4, 288
+; RV32-NEXT: vs4r.v v16, (t4) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v12, v0
+; RV32-NEXT: csrr t4, vlenb
+; RV32-NEXT: slli t4, t4, 2
+; RV32-NEXT: mv t5, t4
+; RV32-NEXT: slli t4, t4, 2
+; RV32-NEXT: add t5, t5, t4
+; RV32-NEXT: slli t4, t4, 2
+; RV32-NEXT: add t4, t4, t5
+; RV32-NEXT: add t4, sp, t4
+; RV32-NEXT: addi t4, t4, 288
+; RV32-NEXT: vs4r.v v16, (t4) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vlse64.v v28, (t3), zero
+; RV32-NEXT: vlse64.v v4, (t2), zero
+; RV32-NEXT: vlse64.v v0, (t1), zero
+; RV32-NEXT: vlse64.v v16, (t0), zero
+; RV32-NEXT: vand.vv v20, v12, v28
+; RV32-NEXT: csrr t0, vlenb
+; RV32-NEXT: slli t0, t0, 2
+; RV32-NEXT: add t0, sp, t0
+; RV32-NEXT: addi t0, t0, 288
+; RV32-NEXT: vs4r.v v20, (t0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v20, v12, v4
+; RV32-NEXT: csrr t0, vlenb
+; RV32-NEXT: slli t0, t0, 5
+; RV32-NEXT: add t0, sp, t0
+; RV32-NEXT: addi t0, t0, 288
+; RV32-NEXT: vs4r.v v20, (t0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v20, v12, v0
+; RV32-NEXT: csrr t0, vlenb
+; RV32-NEXT: slli t0, t0, 3
+; RV32-NEXT: mv t1, t0
+; RV32-NEXT: slli t0, t0, 1
+; RV32-NEXT: add t1, t1, t0
+; RV32-NEXT: slli t0, t0, 1
+; RV32-NEXT: add t0, t0, t1
+; RV32-NEXT: add t0, sp, t0
+; RV32-NEXT: addi t0, t0, 288
+; RV32-NEXT: vs4r.v v20, (t0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v12, v16
+; RV32-NEXT: csrr t0, vlenb
+; RV32-NEXT: slli t0, t0, 4
+; RV32-NEXT: mv t1, t0
+; RV32-NEXT: slli t0, t0, 2
+; RV32-NEXT: add t0, t0, t1
+; RV32-NEXT: add t0, sp, t0
+; RV32-NEXT: addi t0, t0, 288
+; RV32-NEXT: vs4r.v v16, (t0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vlse64.v v16, (a7), zero
+; RV32-NEXT: vlse64.v v0, (a6), zero
+; RV32-NEXT: vlse64.v v20, (a5), zero
+; RV32-NEXT: vlse64.v v24, (a4), zero
+; RV32-NEXT: vand.vv v4, v12, v16
+; RV32-NEXT: vand.vv v16, v12, v0
+; RV32-NEXT: csrr a4, vlenb
+; RV32-NEXT: slli a4, a4, 2
+; RV32-NEXT: mv a5, a4
+; RV32-NEXT: slli a4, a4, 1
+; RV32-NEXT: add a5, a5, a4
+; RV32-NEXT: slli a4, a4, 1
+; RV32-NEXT: add a4, a4, a5
+; RV32-NEXT: add a4, sp, a4
+; RV32-NEXT: addi a4, a4, 288
+; RV32-NEXT: vs4r.v v16, (a4) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v12, v20
+; RV32-NEXT: csrr a4, vlenb
+; RV32-NEXT: slli a4, a4, 2
+; RV32-NEXT: mv a5, a4
+; RV32-NEXT: slli a4, a4, 2
+; RV32-NEXT: add a5, a5, a4
+; RV32-NEXT: slli a4, a4, 1
+; RV32-NEXT: add a4, a4, a5
+; RV32-NEXT: add a4, sp, a4
+; RV32-NEXT: addi a4, a4, 288
+; RV32-NEXT: vs4r.v v16, (a4) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v12, v24
+; RV32-NEXT: csrr a4, vlenb
+; RV32-NEXT: slli a4, a4, 2
+; RV32-NEXT: mv a5, a4
+; RV32-NEXT: slli a4, a4, 1
+; RV32-NEXT: add a5, a5, a4
+; RV32-NEXT: slli a4, a4, 3
+; RV32-NEXT: add a4, a4, a5
+; RV32-NEXT: add a4, sp, a4
+; RV32-NEXT: addi a4, a4, 288
+; RV32-NEXT: vs4r.v v16, (a4) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vlse64.v v16, (a3), zero
+; RV32-NEXT: vlse64.v v20, (a2), zero
+; RV32-NEXT: vlse64.v v24, (s3), zero
+; RV32-NEXT: vlse64.v v28, (s2), zero
+; RV32-NEXT: vand.vv v0, v12, v16
+; RV32-NEXT: vand.vv v16, v12, v20
+; RV32-NEXT: csrr a2, vlenb
+; RV32-NEXT: slli a2, a2, 3
+; RV32-NEXT: mv a3, a2
+; RV32-NEXT: slli a2, a2, 1
+; RV32-NEXT: add a2, a2, a3
+; RV32-NEXT: add a2, sp, a2
+; RV32-NEXT: addi a2, a2, 288
+; RV32-NEXT: vs4r.v v16, (a2) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v12, v24
+; RV32-NEXT: csrr a2, vlenb
+; RV32-NEXT: slli a2, a2, 4
+; RV32-NEXT: mv a3, a2
+; RV32-NEXT: slli a2, a2, 1
+; RV32-NEXT: add a2, a2, a3
+; RV32-NEXT: add a2, sp, a2
+; RV32-NEXT: addi a2, a2, 288
+; RV32-NEXT: vs4r.v v16, (a2) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v12, v28
+; RV32-NEXT: csrr a2, vlenb
+; RV32-NEXT: slli a2, a2, 3
+; RV32-NEXT: mv a3, a2
+; RV32-NEXT: slli a2, a2, 3
+; RV32-NEXT: add a2, a2, a3
+; RV32-NEXT: add a2, sp, a2
+; RV32-NEXT: addi a2, a2, 288
+; RV32-NEXT: vs4r.v v16, (a2) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vlse64.v v16, (s5), zero
+; RV32-NEXT: vlse64.v v20, (s6), zero
+; RV32-NEXT: vlse64.v v24, (s8), zero
+; RV32-NEXT: vlse64.v v28, (a0), zero
+; RV32-NEXT: vand.vv v16, v12, v16
+; RV32-NEXT: addi a0, sp, 288
+; RV32-NEXT: vs4r.v v16, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v16, v12, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a2, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a2
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v16, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v24, v12, v24
+; RV32-NEXT: vand.vv v20, v12, v28
+; RV32-NEXT: vand.vx v12, v12, a1
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v12, v16, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: vmul.vv v16, v8, v4
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: vmul.vv v16, v8, v0
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: addi a0, sp, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v16, v8, v16
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: vmul.vv v16, v8, v24
+; RV32-NEXT: vxor.vv v12, v12, v16
+; RV32-NEXT: vmul.vv v8, v8, v20
+; RV32-NEXT: vxor.vv v8, v12, v8
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add sp, sp, a0
+; RV32-NEXT: lw ra, 348(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s0, 344(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s1, 340(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s2, 336(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s3, 332(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s4, 328(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s5, 324(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s6, 320(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s7, 316(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s8, 312(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s9, 308(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s10, 304(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s11, 300(sp) # 4-byte Folded Reload
+; RV32-NEXT: addi sp, sp, 352
+; RV32-NEXT: ret
+;
+; RV64-LABEL: clmul_v8i64:
+; RV64: # %bb.0:
+; RV64-NEXT: vsetivli zero, 8, e64, m4, ta, ma
+; RV64-NEXT: vand.vi v16, v12, 2
+; RV64-NEXT: vand.vi v20, v12, 1
+; RV64-NEXT: vmul.vv v16, v8, v16
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v20, v16
+; RV64-NEXT: vand.vi v20, v12, 4
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vi v20, v12, 8
+; RV64-NEXT: li a0, 16
+; RV64-NEXT: li a1, 32
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a0
+; RV64-NEXT: li a0, 64
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: li a1, 128
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a0
+; RV64-NEXT: li a0, 256
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: li a1, 512
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a0
+; RV64-NEXT: li a2, 1024
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: li a0, 1
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a2
+; RV64-NEXT: slli a1, a0, 11
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: lui a1, 1
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: lui a1, 2
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: lui a1, 4
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: lui a1, 8
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: lui a1, 16
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: lui a1, 32
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: lui a1, 64
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: lui a1, 128
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: lui a1, 256
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: lui a1, 512
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: lui a1, 1024
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: lui a1, 2048
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: lui a1, 4096
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: lui a1, 8192
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: lui a1, 16384
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: lui a1, 32768
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: lui a1, 65536
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: lui a1, 131072
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: lui a1, 262144
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 31
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 32
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 33
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 34
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 35
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 36
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 37
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 38
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 39
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 40
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 41
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 42
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 43
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 44
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 45
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 46
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 47
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 48
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 49
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 50
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 51
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 52
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 53
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 54
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 55
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 56
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 57
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 58
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 59
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 60
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: slli a1, a0, 61
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a1
+; RV64-NEXT: li a1, -1
+; RV64-NEXT: slli a0, a0, 62
+; RV64-NEXT: slli a1, a1, 63
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vand.vx v20, v12, a0
+; RV64-NEXT: vand.vx v12, v12, a1
+; RV64-NEXT: vmul.vv v20, v8, v20
+; RV64-NEXT: vxor.vv v16, v16, v20
+; RV64-NEXT: vmul.vv v8, v8, v12
+; RV64-NEXT: vxor.vv v8, v16, v8
+; RV64-NEXT: ret
+ %a = call <8 x i64> @llvm.clmul.v8i64(<8 x i64> %x, <8 x i64> %y)
+ ret <8 x i64> %a
+}
+
+define <1 x i32> @clmulr_v1i32(<1 x i32> %x, <1 x i32> %y) nounwind {
+; CHECK-LABEL: clmulr_v1i32:
+; CHECK: # %bb.0:
+; CHECK-NEXT: addi sp, sp, -16
+; CHECK-NEXT: csrr a0, vlenb
+; CHECK-NEXT: sub sp, sp, a0
+; CHECK-NEXT: vsetivli zero, 1, e32, mf2, ta, ma
+; CHECK-NEXT: vsrl.vi v9, v8, 8
+; CHECK-NEXT: lui a4, 16
+; CHECK-NEXT: vsrl.vi v10, v8, 24
+; CHECK-NEXT: vsll.vi v11, v8, 24
+; CHECK-NEXT: lui a0, 61681
+; CHECK-NEXT: lui a1, 209715
+; CHECK-NEXT: lui a5, 349525
+; CHECK-NEXT: li a6, 16
+; CHECK-NEXT: addi a3, a4, -256
+; CHECK-NEXT: addi a2, a0, -241
+; CHECK-NEXT: addi a1, a1, 819
+; CHECK-NEXT: addi a0, a5, 1365
+; CHECK-NEXT: vand.vx v9, v9, a3
+; CHECK-NEXT: vand.vx v8, v8, a3
+; CHECK-NEXT: vor.vv v9, v9, v10
+; CHECK-NEXT: vsll.vi v8, v8, 8
+; CHECK-NEXT: vor.vv v8, v11, v8
+; CHECK-NEXT: vor.vv v8, v8, v9
+; CHECK-NEXT: vsrl.vi v9, v8, 4
+; CHECK-NEXT: vand.vx v8, v8, a2
+; CHECK-NEXT: vand.vx v9, v9, a2
+; CHECK-NEXT: vsll.vi v8, v8, 4
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v9, v8, 2
+; CHECK-NEXT: vand.vx v8, v8, a1
+; CHECK-NEXT: vand.vx v9, v9, a1
+; CHECK-NEXT: vsll.vi v8, v8, 2
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v9, v8, 1
+; CHECK-NEXT: vand.vx v8, v8, a0
+; CHECK-NEXT: vand.vx v9, v9, a0
+; CHECK-NEXT: vadd.vv v8, v8, v8
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vand.vx v9, v8, a6
+; CHECK-NEXT: li a5, 32
+; CHECK-NEXT: vand.vx v10, v8, a5
+; CHECK-NEXT: li a5, 64
+; CHECK-NEXT: vand.vx v11, v8, a5
+; CHECK-NEXT: li a5, 128
+; CHECK-NEXT: vand.vx v12, v8, a5
+; CHECK-NEXT: li a5, 256
+; CHECK-NEXT: vand.vx v13, v8, a5
+; CHECK-NEXT: li a5, 512
+; CHECK-NEXT: vand.vx v14, v8, a5
+; CHECK-NEXT: li a5, 1024
+; CHECK-NEXT: vand.vx v15, v8, a5
+; CHECK-NEXT: li a5, 1
+; CHECK-NEXT: slli a5, a5, 11
+; CHECK-NEXT: vand.vx v16, v8, a5
+; CHECK-NEXT: lui a5, 1
+; CHECK-NEXT: vand.vx v17, v8, a5
+; CHECK-NEXT: lui a5, 2
+; CHECK-NEXT: vand.vx v18, v8, a5
+; CHECK-NEXT: lui a5, 4
+; CHECK-NEXT: vand.vx v19, v8, a5
+; CHECK-NEXT: lui a5, 8
+; CHECK-NEXT: vand.vx v20, v8, a5
+; CHECK-NEXT: lui a5, 32
+; CHECK-NEXT: vand.vx v21, v8, a4
+; CHECK-NEXT: lui a4, 64
+; CHECK-NEXT: vand.vx v22, v8, a5
+; CHECK-NEXT: lui a5, 128
+; CHECK-NEXT: vand.vx v23, v8, a4
+; CHECK-NEXT: lui a4, 256
+; CHECK-NEXT: vand.vx v24, v8, a5
+; CHECK-NEXT: lui a5, 512
+; CHECK-NEXT: vand.vx v25, v8, a4
+; CHECK-NEXT: lui a4, 1024
+; CHECK-NEXT: vand.vx v26, v8, a5
+; CHECK-NEXT: lui a5, 2048
+; CHECK-NEXT: vand.vx v27, v8, a4
+; CHECK-NEXT: lui a4, 4096
+; CHECK-NEXT: vand.vx v28, v8, a5
+; CHECK-NEXT: lui a5, 8192
+; CHECK-NEXT: vand.vx v29, v8, a4
+; CHECK-NEXT: lui a4, 16384
+; CHECK-NEXT: vand.vx v30, v8, a5
+; CHECK-NEXT: lui a5, 32768
+; CHECK-NEXT: vand.vx v31, v8, a4
+; CHECK-NEXT: lui a4, 65536
+; CHECK-NEXT: vand.vx v7, v8, a5
+; CHECK-NEXT: lui a5, 131072
+; CHECK-NEXT: vand.vx v6, v8, a4
+; CHECK-NEXT: lui a4, 262144
+; CHECK-NEXT: vand.vx v5, v8, a5
+; CHECK-NEXT: lui a5, 524288
+; CHECK-NEXT: vand.vi v4, v8, 2
+; CHECK-NEXT: vand.vi v3, v8, 1
+; CHECK-NEXT: vand.vi v2, v8, 4
+; CHECK-NEXT: vand.vi v1, v8, 8
+; CHECK-NEXT: vand.vx v0, v8, a4
+; CHECK-NEXT: vmul.vv v4, v8, v4
+; CHECK-NEXT: addi a4, sp, 16
+; CHECK-NEXT: vs1r.v v4, (a4) # vscale x 8-byte Folded Spill
+; CHECK-NEXT: vmul.vv v3, v8, v3
+; CHECK-NEXT: vmul.vv v2, v8, v2
+; CHECK-NEXT: vmul.vv v1, v8, v1
+; CHECK-NEXT: vmul.vv v9, v8, v9
+; CHECK-NEXT: vmul.vv v10, v8, v10
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vmul.vv v12, v8, v12
+; CHECK-NEXT: vmul.vv v13, v8, v13
+; CHECK-NEXT: vmul.vv v14, v8, v14
+; CHECK-NEXT: vmul.vv v15, v8, v15
+; CHECK-NEXT: vmul.vv v16, v8, v16
+; CHECK-NEXT: vmul.vv v17, v8, v17
+; CHECK-NEXT: vmul.vv v18, v8, v18
+; CHECK-NEXT: vmul.vv v19, v8, v19
+; CHECK-NEXT: vmul.vv v20, v8, v20
+; CHECK-NEXT: vmul.vv v21, v8, v21
+; CHECK-NEXT: vmul.vv v22, v8, v22
+; CHECK-NEXT: vmul.vv v23, v8, v23
+; CHECK-NEXT: vmul.vv v24, v8, v24
+; CHECK-NEXT: vmul.vv v25, v8, v25
+; CHECK-NEXT: vmul.vv v26, v8, v26
+; CHECK-NEXT: vmul.vv v27, v8, v27
+; CHECK-NEXT: vmul.vv v28, v8, v28
+; CHECK-NEXT: vmul.vv v29, v8, v29
+; CHECK-NEXT: vmul.vv v30, v8, v30
+; CHECK-NEXT: vmul.vv v31, v8, v31
+; CHECK-NEXT: vmul.vv v7, v8, v7
+; CHECK-NEXT: vmul.vv v6, v8, v6
+; CHECK-NEXT: vmul.vv v5, v8, v5
+; CHECK-NEXT: vmul.vv v0, v8, v0
+; CHECK-NEXT: vand.vx v4, v8, a5
+; CHECK-NEXT: vmul.vv v8, v8, v4
+; CHECK-NEXT: vl1r.v v4, (a4) # vscale x 8-byte Folded Reload
+; CHECK-NEXT: vxor.vv v4, v3, v4
+; CHECK-NEXT: vxor.vv v4, v4, v2
+; CHECK-NEXT: vxor.vv v4, v4, v1
+; CHECK-NEXT: vxor.vv v9, v4, v9
+; CHECK-NEXT: vxor.vv v9, v9, v10
+; CHECK-NEXT: vxor.vv v9, v9, v11
+; CHECK-NEXT: vxor.vv v9, v9, v12
+; CHECK-NEXT: vxor.vv v9, v9, v13
+; CHECK-NEXT: vxor.vv v9, v9, v14
+; CHECK-NEXT: vxor.vv v9, v9, v15
+; CHECK-NEXT: vxor.vv v9, v9, v16
+; CHECK-NEXT: vxor.vv v9, v9, v17
+; CHECK-NEXT: vxor.vv v9, v9, v18
+; CHECK-NEXT: vxor.vv v9, v9, v19
+; CHECK-NEXT: vxor.vv v9, v9, v20
+; CHECK-NEXT: vxor.vv v9, v9, v21
+; CHECK-NEXT: vxor.vv v9, v9, v22
+; CHECK-NEXT: vxor.vv v9, v9, v23
+; CHECK-NEXT: vxor.vv v9, v9, v24
+; CHECK-NEXT: vxor.vv v9, v9, v25
+; CHECK-NEXT: vxor.vv v9, v9, v26
+; CHECK-NEXT: vxor.vv v9, v9, v27
+; CHECK-NEXT: vxor.vv v9, v9, v28
+; CHECK-NEXT: vxor.vv v9, v9, v29
+; CHECK-NEXT: vxor.vv v9, v9, v30
+; CHECK-NEXT: vxor.vv v9, v9, v31
+; CHECK-NEXT: vxor.vv v9, v9, v7
+; CHECK-NEXT: vxor.vv v9, v9, v6
+; CHECK-NEXT: vxor.vv v9, v9, v5
+; CHECK-NEXT: vxor.vv v9, v9, v0
+; CHECK-NEXT: vxor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v9, v8, 8
+; CHECK-NEXT: vsrl.vi v10, v8, 24
+; CHECK-NEXT: vand.vx v9, v9, a3
+; CHECK-NEXT: vor.vv v9, v9, v10
+; CHECK-NEXT: vsll.vi v10, v8, 24
+; CHECK-NEXT: vand.vx v8, v8, a3
+; CHECK-NEXT: vsll.vi v8, v8, 8
+; CHECK-NEXT: vor.vv v8, v10, v8
+; CHECK-NEXT: vor.vv v8, v8, v9
+; CHECK-NEXT: vsrl.vi v9, v8, 4
+; CHECK-NEXT: vand.vx v8, v8, a2
+; CHECK-NEXT: vand.vx v9, v9, a2
+; CHECK-NEXT: vsll.vi v8, v8, 4
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v9, v8, 2
+; CHECK-NEXT: vand.vx v8, v8, a1
+; CHECK-NEXT: vand.vx v9, v9, a1
+; CHECK-NEXT: vsll.vi v8, v8, 2
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v9, v8, 1
+; CHECK-NEXT: vand.vx v8, v8, a0
+; CHECK-NEXT: vand.vx v9, v9, a0
+; CHECK-NEXT: vadd.vv v8, v8, v8
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: csrr a0, vlenb
+; CHECK-NEXT: add sp, sp, a0
+; CHECK-NEXT: addi sp, sp, 16
+; CHECK-NEXT: ret
+ %a = call <1 x i32> @llvm.clmulr.v1i32(<1 x i32> %x, <1 x i32> %y)
+ ret <1 x i32> %a
+}
+
+define <2 x i32> @clmulr_v2i32(<2 x i32> %x, <2 x i32> %y) nounwind {
+; CHECK-LABEL: clmulr_v2i32:
+; CHECK: # %bb.0:
+; CHECK-NEXT: addi sp, sp, -16
+; CHECK-NEXT: csrr a0, vlenb
+; CHECK-NEXT: sub sp, sp, a0
+; CHECK-NEXT: vsetivli zero, 2, e32, mf2, ta, ma
+; CHECK-NEXT: vsrl.vi v9, v8, 8
+; CHECK-NEXT: lui a4, 16
+; CHECK-NEXT: vsrl.vi v10, v8, 24
+; CHECK-NEXT: vsll.vi v11, v8, 24
+; CHECK-NEXT: lui a0, 61681
+; CHECK-NEXT: lui a1, 209715
+; CHECK-NEXT: lui a5, 349525
+; CHECK-NEXT: li a6, 16
+; CHECK-NEXT: addi a3, a4, -256
+; CHECK-NEXT: addi a2, a0, -241
+; CHECK-NEXT: addi a1, a1, 819
+; CHECK-NEXT: addi a0, a5, 1365
+; CHECK-NEXT: vand.vx v9, v9, a3
+; CHECK-NEXT: vand.vx v8, v8, a3
+; CHECK-NEXT: vor.vv v9, v9, v10
+; CHECK-NEXT: vsll.vi v8, v8, 8
+; CHECK-NEXT: vor.vv v8, v11, v8
+; CHECK-NEXT: vor.vv v8, v8, v9
+; CHECK-NEXT: vsrl.vi v9, v8, 4
+; CHECK-NEXT: vand.vx v8, v8, a2
+; CHECK-NEXT: vand.vx v9, v9, a2
+; CHECK-NEXT: vsll.vi v8, v8, 4
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v9, v8, 2
+; CHECK-NEXT: vand.vx v8, v8, a1
+; CHECK-NEXT: vand.vx v9, v9, a1
+; CHECK-NEXT: vsll.vi v8, v8, 2
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v9, v8, 1
+; CHECK-NEXT: vand.vx v8, v8, a0
+; CHECK-NEXT: vand.vx v9, v9, a0
+; CHECK-NEXT: vadd.vv v8, v8, v8
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vand.vx v9, v8, a6
+; CHECK-NEXT: li a5, 32
+; CHECK-NEXT: vand.vx v10, v8, a5
+; CHECK-NEXT: li a5, 64
+; CHECK-NEXT: vand.vx v11, v8, a5
+; CHECK-NEXT: li a5, 128
+; CHECK-NEXT: vand.vx v12, v8, a5
+; CHECK-NEXT: li a5, 256
+; CHECK-NEXT: vand.vx v13, v8, a5
+; CHECK-NEXT: li a5, 512
+; CHECK-NEXT: vand.vx v14, v8, a5
+; CHECK-NEXT: li a5, 1024
+; CHECK-NEXT: vand.vx v15, v8, a5
+; CHECK-NEXT: li a5, 1
+; CHECK-NEXT: slli a5, a5, 11
+; CHECK-NEXT: vand.vx v16, v8, a5
+; CHECK-NEXT: lui a5, 1
+; CHECK-NEXT: vand.vx v17, v8, a5
+; CHECK-NEXT: lui a5, 2
+; CHECK-NEXT: vand.vx v18, v8, a5
+; CHECK-NEXT: lui a5, 4
+; CHECK-NEXT: vand.vx v19, v8, a5
+; CHECK-NEXT: lui a5, 8
+; CHECK-NEXT: vand.vx v20, v8, a5
+; CHECK-NEXT: lui a5, 32
+; CHECK-NEXT: vand.vx v21, v8, a4
+; CHECK-NEXT: lui a4, 64
+; CHECK-NEXT: vand.vx v22, v8, a5
+; CHECK-NEXT: lui a5, 128
+; CHECK-NEXT: vand.vx v23, v8, a4
+; CHECK-NEXT: lui a4, 256
+; CHECK-NEXT: vand.vx v24, v8, a5
+; CHECK-NEXT: lui a5, 512
+; CHECK-NEXT: vand.vx v25, v8, a4
+; CHECK-NEXT: lui a4, 1024
+; CHECK-NEXT: vand.vx v26, v8, a5
+; CHECK-NEXT: lui a5, 2048
+; CHECK-NEXT: vand.vx v27, v8, a4
+; CHECK-NEXT: lui a4, 4096
+; CHECK-NEXT: vand.vx v28, v8, a5
+; CHECK-NEXT: lui a5, 8192
+; CHECK-NEXT: vand.vx v29, v8, a4
+; CHECK-NEXT: lui a4, 16384
+; CHECK-NEXT: vand.vx v30, v8, a5
+; CHECK-NEXT: lui a5, 32768
+; CHECK-NEXT: vand.vx v31, v8, a4
+; CHECK-NEXT: lui a4, 65536
+; CHECK-NEXT: vand.vx v7, v8, a5
+; CHECK-NEXT: lui a5, 131072
+; CHECK-NEXT: vand.vx v6, v8, a4
+; CHECK-NEXT: lui a4, 262144
+; CHECK-NEXT: vand.vx v5, v8, a5
+; CHECK-NEXT: lui a5, 524288
+; CHECK-NEXT: vand.vi v4, v8, 2
+; CHECK-NEXT: vand.vi v3, v8, 1
+; CHECK-NEXT: vand.vi v2, v8, 4
+; CHECK-NEXT: vand.vi v1, v8, 8
+; CHECK-NEXT: vand.vx v0, v8, a4
+; CHECK-NEXT: vmul.vv v4, v8, v4
+; CHECK-NEXT: addi a4, sp, 16
+; CHECK-NEXT: vs1r.v v4, (a4) # vscale x 8-byte Folded Spill
+; CHECK-NEXT: vmul.vv v3, v8, v3
+; CHECK-NEXT: vmul.vv v2, v8, v2
+; CHECK-NEXT: vmul.vv v1, v8, v1
+; CHECK-NEXT: vmul.vv v9, v8, v9
+; CHECK-NEXT: vmul.vv v10, v8, v10
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vmul.vv v12, v8, v12
+; CHECK-NEXT: vmul.vv v13, v8, v13
+; CHECK-NEXT: vmul.vv v14, v8, v14
+; CHECK-NEXT: vmul.vv v15, v8, v15
+; CHECK-NEXT: vmul.vv v16, v8, v16
+; CHECK-NEXT: vmul.vv v17, v8, v17
+; CHECK-NEXT: vmul.vv v18, v8, v18
+; CHECK-NEXT: vmul.vv v19, v8, v19
+; CHECK-NEXT: vmul.vv v20, v8, v20
+; CHECK-NEXT: vmul.vv v21, v8, v21
+; CHECK-NEXT: vmul.vv v22, v8, v22
+; CHECK-NEXT: vmul.vv v23, v8, v23
+; CHECK-NEXT: vmul.vv v24, v8, v24
+; CHECK-NEXT: vmul.vv v25, v8, v25
+; CHECK-NEXT: vmul.vv v26, v8, v26
+; CHECK-NEXT: vmul.vv v27, v8, v27
+; CHECK-NEXT: vmul.vv v28, v8, v28
+; CHECK-NEXT: vmul.vv v29, v8, v29
+; CHECK-NEXT: vmul.vv v30, v8, v30
+; CHECK-NEXT: vmul.vv v31, v8, v31
+; CHECK-NEXT: vmul.vv v7, v8, v7
+; CHECK-NEXT: vmul.vv v6, v8, v6
+; CHECK-NEXT: vmul.vv v5, v8, v5
+; CHECK-NEXT: vmul.vv v0, v8, v0
+; CHECK-NEXT: vand.vx v4, v8, a5
+; CHECK-NEXT: vmul.vv v8, v8, v4
+; CHECK-NEXT: vl1r.v v4, (a4) # vscale x 8-byte Folded Reload
+; CHECK-NEXT: vxor.vv v4, v3, v4
+; CHECK-NEXT: vxor.vv v4, v4, v2
+; CHECK-NEXT: vxor.vv v4, v4, v1
+; CHECK-NEXT: vxor.vv v9, v4, v9
+; CHECK-NEXT: vxor.vv v9, v9, v10
+; CHECK-NEXT: vxor.vv v9, v9, v11
+; CHECK-NEXT: vxor.vv v9, v9, v12
+; CHECK-NEXT: vxor.vv v9, v9, v13
+; CHECK-NEXT: vxor.vv v9, v9, v14
+; CHECK-NEXT: vxor.vv v9, v9, v15
+; CHECK-NEXT: vxor.vv v9, v9, v16
+; CHECK-NEXT: vxor.vv v9, v9, v17
+; CHECK-NEXT: vxor.vv v9, v9, v18
+; CHECK-NEXT: vxor.vv v9, v9, v19
+; CHECK-NEXT: vxor.vv v9, v9, v20
+; CHECK-NEXT: vxor.vv v9, v9, v21
+; CHECK-NEXT: vxor.vv v9, v9, v22
+; CHECK-NEXT: vxor.vv v9, v9, v23
+; CHECK-NEXT: vxor.vv v9, v9, v24
+; CHECK-NEXT: vxor.vv v9, v9, v25
+; CHECK-NEXT: vxor.vv v9, v9, v26
+; CHECK-NEXT: vxor.vv v9, v9, v27
+; CHECK-NEXT: vxor.vv v9, v9, v28
+; CHECK-NEXT: vxor.vv v9, v9, v29
+; CHECK-NEXT: vxor.vv v9, v9, v30
+; CHECK-NEXT: vxor.vv v9, v9, v31
+; CHECK-NEXT: vxor.vv v9, v9, v7
+; CHECK-NEXT: vxor.vv v9, v9, v6
+; CHECK-NEXT: vxor.vv v9, v9, v5
+; CHECK-NEXT: vxor.vv v9, v9, v0
+; CHECK-NEXT: vxor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v9, v8, 8
+; CHECK-NEXT: vsrl.vi v10, v8, 24
+; CHECK-NEXT: vand.vx v9, v9, a3
+; CHECK-NEXT: vor.vv v9, v9, v10
+; CHECK-NEXT: vsll.vi v10, v8, 24
+; CHECK-NEXT: vand.vx v8, v8, a3
+; CHECK-NEXT: vsll.vi v8, v8, 8
+; CHECK-NEXT: vor.vv v8, v10, v8
+; CHECK-NEXT: vor.vv v8, v8, v9
+; CHECK-NEXT: vsrl.vi v9, v8, 4
+; CHECK-NEXT: vand.vx v8, v8, a2
+; CHECK-NEXT: vand.vx v9, v9, a2
+; CHECK-NEXT: vsll.vi v8, v8, 4
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v9, v8, 2
+; CHECK-NEXT: vand.vx v8, v8, a1
+; CHECK-NEXT: vand.vx v9, v9, a1
+; CHECK-NEXT: vsll.vi v8, v8, 2
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v9, v8, 1
+; CHECK-NEXT: vand.vx v8, v8, a0
+; CHECK-NEXT: vand.vx v9, v9, a0
+; CHECK-NEXT: vadd.vv v8, v8, v8
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: csrr a0, vlenb
+; CHECK-NEXT: add sp, sp, a0
+; CHECK-NEXT: addi sp, sp, 16
+; CHECK-NEXT: ret
+ %a = call <2 x i32> @llvm.clmulr.v2i32(<2 x i32> %x, <2 x i32> %y)
+ ret <2 x i32> %a
+}
+
+define <4 x i32> @clmulr_v4i32(<4 x i32> %x, <4 x i32> %y) nounwind {
+; CHECK-LABEL: clmulr_v4i32:
+; CHECK: # %bb.0:
+; CHECK-NEXT: addi sp, sp, -16
+; CHECK-NEXT: csrr a0, vlenb
+; CHECK-NEXT: sub sp, sp, a0
+; CHECK-NEXT: vsetivli zero, 4, e32, m1, ta, ma
+; CHECK-NEXT: vsrl.vi v9, v8, 8
+; CHECK-NEXT: lui a4, 16
+; CHECK-NEXT: vsrl.vi v10, v8, 24
+; CHECK-NEXT: vsll.vi v11, v8, 24
+; CHECK-NEXT: lui a0, 61681
+; CHECK-NEXT: lui a1, 209715
+; CHECK-NEXT: lui a5, 349525
+; CHECK-NEXT: li a6, 16
+; CHECK-NEXT: addi a3, a4, -256
+; CHECK-NEXT: addi a2, a0, -241
+; CHECK-NEXT: addi a1, a1, 819
+; CHECK-NEXT: addi a0, a5, 1365
+; CHECK-NEXT: vand.vx v9, v9, a3
+; CHECK-NEXT: vand.vx v8, v8, a3
+; CHECK-NEXT: vor.vv v9, v9, v10
+; CHECK-NEXT: vsll.vi v8, v8, 8
+; CHECK-NEXT: vor.vv v8, v11, v8
+; CHECK-NEXT: vor.vv v8, v8, v9
+; CHECK-NEXT: vsrl.vi v9, v8, 4
+; CHECK-NEXT: vand.vx v8, v8, a2
+; CHECK-NEXT: vand.vx v9, v9, a2
+; CHECK-NEXT: vsll.vi v8, v8, 4
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v9, v8, 2
+; CHECK-NEXT: vand.vx v8, v8, a1
+; CHECK-NEXT: vand.vx v9, v9, a1
+; CHECK-NEXT: vsll.vi v8, v8, 2
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v9, v8, 1
+; CHECK-NEXT: vand.vx v8, v8, a0
+; CHECK-NEXT: vand.vx v9, v9, a0
+; CHECK-NEXT: vadd.vv v8, v8, v8
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vand.vx v9, v8, a6
+; CHECK-NEXT: li a5, 32
+; CHECK-NEXT: vand.vx v10, v8, a5
+; CHECK-NEXT: li a5, 64
+; CHECK-NEXT: vand.vx v11, v8, a5
+; CHECK-NEXT: li a5, 128
+; CHECK-NEXT: vand.vx v12, v8, a5
+; CHECK-NEXT: li a5, 256
+; CHECK-NEXT: vand.vx v13, v8, a5
+; CHECK-NEXT: li a5, 512
+; CHECK-NEXT: vand.vx v14, v8, a5
+; CHECK-NEXT: li a5, 1024
+; CHECK-NEXT: vand.vx v15, v8, a5
+; CHECK-NEXT: li a5, 1
+; CHECK-NEXT: slli a5, a5, 11
+; CHECK-NEXT: vand.vx v16, v8, a5
+; CHECK-NEXT: lui a5, 1
+; CHECK-NEXT: vand.vx v17, v8, a5
+; CHECK-NEXT: lui a5, 2
+; CHECK-NEXT: vand.vx v18, v8, a5
+; CHECK-NEXT: lui a5, 4
+; CHECK-NEXT: vand.vx v19, v8, a5
+; CHECK-NEXT: lui a5, 8
+; CHECK-NEXT: vand.vx v20, v8, a5
+; CHECK-NEXT: lui a5, 32
+; CHECK-NEXT: vand.vx v21, v8, a4
+; CHECK-NEXT: lui a4, 64
+; CHECK-NEXT: vand.vx v22, v8, a5
+; CHECK-NEXT: lui a5, 128
+; CHECK-NEXT: vand.vx v23, v8, a4
+; CHECK-NEXT: lui a4, 256
+; CHECK-NEXT: vand.vx v24, v8, a5
+; CHECK-NEXT: lui a5, 512
+; CHECK-NEXT: vand.vx v25, v8, a4
+; CHECK-NEXT: lui a4, 1024
+; CHECK-NEXT: vand.vx v26, v8, a5
+; CHECK-NEXT: lui a5, 2048
+; CHECK-NEXT: vand.vx v27, v8, a4
+; CHECK-NEXT: lui a4, 4096
+; CHECK-NEXT: vand.vx v28, v8, a5
+; CHECK-NEXT: lui a5, 8192
+; CHECK-NEXT: vand.vx v29, v8, a4
+; CHECK-NEXT: lui a4, 16384
+; CHECK-NEXT: vand.vx v30, v8, a5
+; CHECK-NEXT: lui a5, 32768
+; CHECK-NEXT: vand.vx v31, v8, a4
+; CHECK-NEXT: lui a4, 65536
+; CHECK-NEXT: vand.vx v7, v8, a5
+; CHECK-NEXT: lui a5, 131072
+; CHECK-NEXT: vand.vx v6, v8, a4
+; CHECK-NEXT: lui a4, 262144
+; CHECK-NEXT: vand.vx v5, v8, a5
+; CHECK-NEXT: lui a5, 524288
+; CHECK-NEXT: vand.vi v4, v8, 2
+; CHECK-NEXT: vand.vi v3, v8, 1
+; CHECK-NEXT: vand.vi v2, v8, 4
+; CHECK-NEXT: vand.vi v1, v8, 8
+; CHECK-NEXT: vand.vx v0, v8, a4
+; CHECK-NEXT: vmul.vv v4, v8, v4
+; CHECK-NEXT: addi a4, sp, 16
+; CHECK-NEXT: vs1r.v v4, (a4) # vscale x 8-byte Folded Spill
+; CHECK-NEXT: vmul.vv v3, v8, v3
+; CHECK-NEXT: vmul.vv v2, v8, v2
+; CHECK-NEXT: vmul.vv v1, v8, v1
+; CHECK-NEXT: vmul.vv v9, v8, v9
+; CHECK-NEXT: vmul.vv v10, v8, v10
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vmul.vv v12, v8, v12
+; CHECK-NEXT: vmul.vv v13, v8, v13
+; CHECK-NEXT: vmul.vv v14, v8, v14
+; CHECK-NEXT: vmul.vv v15, v8, v15
+; CHECK-NEXT: vmul.vv v16, v8, v16
+; CHECK-NEXT: vmul.vv v17, v8, v17
+; CHECK-NEXT: vmul.vv v18, v8, v18
+; CHECK-NEXT: vmul.vv v19, v8, v19
+; CHECK-NEXT: vmul.vv v20, v8, v20
+; CHECK-NEXT: vmul.vv v21, v8, v21
+; CHECK-NEXT: vmul.vv v22, v8, v22
+; CHECK-NEXT: vmul.vv v23, v8, v23
+; CHECK-NEXT: vmul.vv v24, v8, v24
+; CHECK-NEXT: vmul.vv v25, v8, v25
+; CHECK-NEXT: vmul.vv v26, v8, v26
+; CHECK-NEXT: vmul.vv v27, v8, v27
+; CHECK-NEXT: vmul.vv v28, v8, v28
+; CHECK-NEXT: vmul.vv v29, v8, v29
+; CHECK-NEXT: vmul.vv v30, v8, v30
+; CHECK-NEXT: vmul.vv v31, v8, v31
+; CHECK-NEXT: vmul.vv v7, v8, v7
+; CHECK-NEXT: vmul.vv v6, v8, v6
+; CHECK-NEXT: vmul.vv v5, v8, v5
+; CHECK-NEXT: vmul.vv v0, v8, v0
+; CHECK-NEXT: vand.vx v4, v8, a5
+; CHECK-NEXT: vmul.vv v8, v8, v4
+; CHECK-NEXT: vl1r.v v4, (a4) # vscale x 8-byte Folded Reload
+; CHECK-NEXT: vxor.vv v4, v3, v4
+; CHECK-NEXT: vxor.vv v4, v4, v2
+; CHECK-NEXT: vxor.vv v4, v4, v1
+; CHECK-NEXT: vxor.vv v9, v4, v9
+; CHECK-NEXT: vxor.vv v9, v9, v10
+; CHECK-NEXT: vxor.vv v9, v9, v11
+; CHECK-NEXT: vxor.vv v9, v9, v12
+; CHECK-NEXT: vxor.vv v9, v9, v13
+; CHECK-NEXT: vxor.vv v9, v9, v14
+; CHECK-NEXT: vxor.vv v9, v9, v15
+; CHECK-NEXT: vxor.vv v9, v9, v16
+; CHECK-NEXT: vxor.vv v9, v9, v17
+; CHECK-NEXT: vxor.vv v9, v9, v18
+; CHECK-NEXT: vxor.vv v9, v9, v19
+; CHECK-NEXT: vxor.vv v9, v9, v20
+; CHECK-NEXT: vxor.vv v9, v9, v21
+; CHECK-NEXT: vxor.vv v9, v9, v22
+; CHECK-NEXT: vxor.vv v9, v9, v23
+; CHECK-NEXT: vxor.vv v9, v9, v24
+; CHECK-NEXT: vxor.vv v9, v9, v25
+; CHECK-NEXT: vxor.vv v9, v9, v26
+; CHECK-NEXT: vxor.vv v9, v9, v27
+; CHECK-NEXT: vxor.vv v9, v9, v28
+; CHECK-NEXT: vxor.vv v9, v9, v29
+; CHECK-NEXT: vxor.vv v9, v9, v30
+; CHECK-NEXT: vxor.vv v9, v9, v31
+; CHECK-NEXT: vxor.vv v9, v9, v7
+; CHECK-NEXT: vxor.vv v9, v9, v6
+; CHECK-NEXT: vxor.vv v9, v9, v5
+; CHECK-NEXT: vxor.vv v9, v9, v0
+; CHECK-NEXT: vxor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v9, v8, 8
+; CHECK-NEXT: vsrl.vi v10, v8, 24
+; CHECK-NEXT: vand.vx v9, v9, a3
+; CHECK-NEXT: vor.vv v9, v9, v10
+; CHECK-NEXT: vsll.vi v10, v8, 24
+; CHECK-NEXT: vand.vx v8, v8, a3
+; CHECK-NEXT: vsll.vi v8, v8, 8
+; CHECK-NEXT: vor.vv v8, v10, v8
+; CHECK-NEXT: vor.vv v8, v8, v9
+; CHECK-NEXT: vsrl.vi v9, v8, 4
+; CHECK-NEXT: vand.vx v8, v8, a2
+; CHECK-NEXT: vand.vx v9, v9, a2
+; CHECK-NEXT: vsll.vi v8, v8, 4
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v9, v8, 2
+; CHECK-NEXT: vand.vx v8, v8, a1
+; CHECK-NEXT: vand.vx v9, v9, a1
+; CHECK-NEXT: vsll.vi v8, v8, 2
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v9, v8, 1
+; CHECK-NEXT: vand.vx v8, v8, a0
+; CHECK-NEXT: vand.vx v9, v9, a0
+; CHECK-NEXT: vadd.vv v8, v8, v8
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: csrr a0, vlenb
+; CHECK-NEXT: add sp, sp, a0
+; CHECK-NEXT: addi sp, sp, 16
+; CHECK-NEXT: ret
+ %a = call <4 x i32> @llvm.clmulr.v4i32(<4 x i32> %x, <4 x i32> %y)
+ ret <4 x i32> %a
+}
+
+define <8 x i32> @clmulr_v8i32(<8 x i32> %x, <8 x i32> %y) nounwind {
+; RV32-LABEL: clmulr_v8i32:
+; RV32: # %bb.0:
+; RV32-NEXT: addi sp, sp, -64
+; RV32-NEXT: sw s0, 60(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s1, 56(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s2, 52(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s3, 48(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s4, 44(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s5, 40(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s6, 36(sp) # 4-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: sub sp, sp, a0
+; RV32-NEXT: vsetivli zero, 8, e32, m2, ta, ma
+; RV32-NEXT: vsrl.vi v10, v8, 8
+; RV32-NEXT: lui a0, 16
+; RV32-NEXT: vsrl.vi v12, v8, 24
+; RV32-NEXT: vsll.vi v14, v8, 24
+; RV32-NEXT: lui a1, 61681
+; RV32-NEXT: lui a2, 209715
+; RV32-NEXT: lui s6, 349525
+; RV32-NEXT: li t2, 16
+; RV32-NEXT: li t6, 32
+; RV32-NEXT: li s3, 64
+; RV32-NEXT: li s5, 128
+; RV32-NEXT: li s4, 256
+; RV32-NEXT: li s2, 512
+; RV32-NEXT: li s1, 1024
+; RV32-NEXT: li s0, 1
+; RV32-NEXT: lui t5, 1
+; RV32-NEXT: lui t4, 2
+; RV32-NEXT: lui t3, 4
+; RV32-NEXT: lui a5, 8
+; RV32-NEXT: lui a6, 32
+; RV32-NEXT: lui a7, 64
+; RV32-NEXT: lui t0, 128
+; RV32-NEXT: lui t1, 256
+; RV32-NEXT: addi a4, a0, -256
+; RV32-NEXT: addi a3, a1, -241
+; RV32-NEXT: addi a2, a2, 819
+; RV32-NEXT: addi a1, s6, 1365
+; RV32-NEXT: vand.vx v10, v10, a4
+; RV32-NEXT: vand.vx v8, v8, a4
+; RV32-NEXT: vor.vv v10, v10, v12
+; RV32-NEXT: vsll.vi v8, v8, 8
+; RV32-NEXT: vor.vv v8, v14, v8
+; RV32-NEXT: vor.vv v8, v8, v10
+; RV32-NEXT: vsrl.vi v10, v8, 4
+; RV32-NEXT: vand.vx v8, v8, a3
+; RV32-NEXT: vand.vx v10, v10, a3
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v10, v8
+; RV32-NEXT: vsrl.vi v10, v8, 2
+; RV32-NEXT: vand.vx v8, v8, a2
+; RV32-NEXT: vand.vx v10, v10, a2
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v8, v10, v8
+; RV32-NEXT: vsrl.vi v10, v8, 1
+; RV32-NEXT: vand.vx v8, v8, a1
+; RV32-NEXT: vand.vx v10, v10, a1
+; RV32-NEXT: vadd.vv v8, v8, v8
+; RV32-NEXT: vor.vv v8, v10, v8
+; RV32-NEXT: vand.vx v10, v8, t2
+; RV32-NEXT: lui t2, 512
+; RV32-NEXT: vand.vx v12, v8, t6
+; RV32-NEXT: lui t6, 1024
+; RV32-NEXT: vand.vx v14, v8, s3
+; RV32-NEXT: lui s3, 2048
+; RV32-NEXT: vand.vx v16, v8, s5
+; RV32-NEXT: lui s5, 4096
+; RV32-NEXT: vand.vx v26, v8, s4
+; RV32-NEXT: lui s4, 8192
+; RV32-NEXT: vand.vx v28, v8, s2
+; RV32-NEXT: lui s2, 16384
+; RV32-NEXT: vand.vx v18, v8, s1
+; RV32-NEXT: lui s1, 32768
+; RV32-NEXT: slli s0, s0, 11
+; RV32-NEXT: vand.vx v20, v8, s0
+; RV32-NEXT: lui s0, 65536
+; RV32-NEXT: vand.vx v22, v8, t5
+; RV32-NEXT: lui t5, 131072
+; RV32-NEXT: vand.vx v24, v8, t4
+; RV32-NEXT: lui t4, 262144
+; RV32-NEXT: vand.vx v30, v8, t3
+; RV32-NEXT: lui t3, 524288
+; RV32-NEXT: vand.vi v6, v8, 2
+; RV32-NEXT: vand.vi v4, v8, 1
+; RV32-NEXT: vand.vi v2, v8, 4
+; RV32-NEXT: vand.vi v0, v8, 8
+; RV32-NEXT: vmul.vv v6, v8, v6
+; RV32-NEXT: sw a0, 4(sp) # 4-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv s6, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, s6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v6, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v6, v8, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v6, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v6, v8, v2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv s6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add s6, s6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add s6, s6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, s6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v6, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v6, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv s6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add s6, s6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, s6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v6, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv s6, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add s6, s6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, s6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v10, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv s6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, s6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v10, v8, v14
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv s6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add s6, s6, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, s6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v10, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv s6, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, s6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v10, v8, v26
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv s6, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, s6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v10, v8, v28
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v10, v8, v18
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv s6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add s6, s6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, s6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v10, v8, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv s6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, s6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v10, v8, v22
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv s6, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, s6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v10, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v10, v8, v30
+; RV32-NEXT: csrr s6, vlenb
+; RV32-NEXT: slli s6, s6, 1
+; RV32-NEXT: mv a0, s6
+; RV32-NEXT: slli s6, s6, 1
+; RV32-NEXT: add s6, s6, a0
+; RV32-NEXT: lw a0, 4(sp) # 4-byte Folded Reload
+; RV32-NEXT: add s6, sp, s6
+; RV32-NEXT: addi s6, s6, 32
+; RV32-NEXT: vs2r.v v10, (s6) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, a5
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a5, vlenb
+; RV32-NEXT: slli a5, a5, 2
+; RV32-NEXT: add a5, sp, a5
+; RV32-NEXT: addi a5, a5, 32
+; RV32-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, a0
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, a6
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: addi a0, sp, 32
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, a7
+; RV32-NEXT: vmul.vv v6, v8, v10
+; RV32-NEXT: vand.vx v10, v8, t0
+; RV32-NEXT: vmul.vv v30, v8, v10
+; RV32-NEXT: vand.vx v10, v8, t1
+; RV32-NEXT: vmul.vv v28, v8, v10
+; RV32-NEXT: vand.vx v10, v8, t2
+; RV32-NEXT: vmul.vv v26, v8, v10
+; RV32-NEXT: vand.vx v10, v8, t6
+; RV32-NEXT: vmul.vv v24, v8, v10
+; RV32-NEXT: vand.vx v10, v8, s3
+; RV32-NEXT: vmul.vv v22, v8, v10
+; RV32-NEXT: vand.vx v10, v8, s5
+; RV32-NEXT: vmul.vv v20, v8, v10
+; RV32-NEXT: vand.vx v10, v8, s4
+; RV32-NEXT: vmul.vv v18, v8, v10
+; RV32-NEXT: vand.vx v10, v8, s2
+; RV32-NEXT: vmul.vv v16, v8, v10
+; RV32-NEXT: vand.vx v10, v8, s1
+; RV32-NEXT: vmul.vv v14, v8, v10
+; RV32-NEXT: vand.vx v10, v8, s0
+; RV32-NEXT: vmul.vv v12, v8, v10
+; RV32-NEXT: vand.vx v10, v8, t5
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: vand.vx v0, v8, t4
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: vand.vx v2, v8, t3
+; RV32-NEXT: vmul.vv v8, v8, v2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v4, v2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v2, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v2, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v2, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v2, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v2, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v2, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v2, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v2, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v2, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v2, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v2, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v2, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v2, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v2, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v2, v4
+; RV32-NEXT: addi a0, sp, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v4, v2, v4
+; RV32-NEXT: vxor.vv v6, v4, v6
+; RV32-NEXT: vxor.vv v30, v6, v30
+; RV32-NEXT: vxor.vv v28, v30, v28
+; RV32-NEXT: vxor.vv v26, v28, v26
+; RV32-NEXT: vxor.vv v24, v26, v24
+; RV32-NEXT: vxor.vv v22, v24, v22
+; RV32-NEXT: vxor.vv v20, v22, v20
+; RV32-NEXT: vxor.vv v18, v20, v18
+; RV32-NEXT: vxor.vv v16, v18, v16
+; RV32-NEXT: vxor.vv v14, v16, v14
+; RV32-NEXT: vxor.vv v12, v14, v12
+; RV32-NEXT: vxor.vv v10, v12, v10
+; RV32-NEXT: vxor.vv v10, v10, v0
+; RV32-NEXT: vxor.vv v8, v10, v8
+; RV32-NEXT: vsrl.vi v10, v8, 8
+; RV32-NEXT: vsrl.vi v12, v8, 24
+; RV32-NEXT: vand.vx v10, v10, a4
+; RV32-NEXT: vor.vv v10, v10, v12
+; RV32-NEXT: vsll.vi v12, v8, 24
+; RV32-NEXT: vand.vx v8, v8, a4
+; RV32-NEXT: vsll.vi v8, v8, 8
+; RV32-NEXT: vor.vv v8, v12, v8
+; RV32-NEXT: vor.vv v8, v8, v10
+; RV32-NEXT: vsrl.vi v10, v8, 4
+; RV32-NEXT: vand.vx v8, v8, a3
+; RV32-NEXT: vand.vx v10, v10, a3
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v10, v8
+; RV32-NEXT: vsrl.vi v10, v8, 2
+; RV32-NEXT: vand.vx v8, v8, a2
+; RV32-NEXT: vand.vx v10, v10, a2
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v8, v10, v8
+; RV32-NEXT: vsrl.vi v10, v8, 1
+; RV32-NEXT: vand.vx v8, v8, a1
+; RV32-NEXT: vand.vx v10, v10, a1
+; RV32-NEXT: vadd.vv v8, v8, v8
+; RV32-NEXT: vor.vv v8, v10, v8
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add sp, sp, a0
+; RV32-NEXT: lw s0, 60(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s1, 56(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s2, 52(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s3, 48(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s4, 44(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s5, 40(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s6, 36(sp) # 4-byte Folded Reload
+; RV32-NEXT: addi sp, sp, 64
+; RV32-NEXT: ret
+;
+; RV64-LABEL: clmulr_v8i32:
+; RV64: # %bb.0:
+; RV64-NEXT: addi sp, sp, -96
+; RV64-NEXT: sd s0, 88(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s1, 80(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s2, 72(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s3, 64(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s4, 56(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s5, 48(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s6, 40(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: sub sp, sp, a0
+; RV64-NEXT: vsetivli zero, 8, e32, m2, ta, ma
+; RV64-NEXT: vsrl.vi v10, v8, 8
+; RV64-NEXT: lui a0, 16
+; RV64-NEXT: vsrl.vi v12, v8, 24
+; RV64-NEXT: vsll.vi v14, v8, 24
+; RV64-NEXT: lui a1, 61681
+; RV64-NEXT: lui a2, 209715
+; RV64-NEXT: lui s6, 349525
+; RV64-NEXT: li t2, 16
+; RV64-NEXT: li t6, 32
+; RV64-NEXT: li s3, 64
+; RV64-NEXT: li s5, 128
+; RV64-NEXT: li s4, 256
+; RV64-NEXT: li s2, 512
+; RV64-NEXT: li s1, 1024
+; RV64-NEXT: li s0, 1
+; RV64-NEXT: lui t5, 1
+; RV64-NEXT: lui t4, 2
+; RV64-NEXT: lui t3, 4
+; RV64-NEXT: lui a5, 8
+; RV64-NEXT: lui a6, 32
+; RV64-NEXT: lui a7, 64
+; RV64-NEXT: lui t0, 128
+; RV64-NEXT: lui t1, 256
+; RV64-NEXT: addi a4, a0, -256
+; RV64-NEXT: addi a3, a1, -241
+; RV64-NEXT: addi a2, a2, 819
+; RV64-NEXT: addi a1, s6, 1365
+; RV64-NEXT: vand.vx v10, v10, a4
+; RV64-NEXT: vand.vx v8, v8, a4
+; RV64-NEXT: vor.vv v10, v10, v12
+; RV64-NEXT: vsll.vi v8, v8, 8
+; RV64-NEXT: vor.vv v8, v14, v8
+; RV64-NEXT: vor.vv v8, v8, v10
+; RV64-NEXT: vsrl.vi v10, v8, 4
+; RV64-NEXT: vand.vx v8, v8, a3
+; RV64-NEXT: vand.vx v10, v10, a3
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v10, v8
+; RV64-NEXT: vsrl.vi v10, v8, 2
+; RV64-NEXT: vand.vx v8, v8, a2
+; RV64-NEXT: vand.vx v10, v10, a2
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v10, v8
+; RV64-NEXT: vsrl.vi v10, v8, 1
+; RV64-NEXT: vand.vx v8, v8, a1
+; RV64-NEXT: vand.vx v10, v10, a1
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v10, v8
+; RV64-NEXT: vand.vx v10, v8, t2
+; RV64-NEXT: lui t2, 512
+; RV64-NEXT: vand.vx v12, v8, t6
+; RV64-NEXT: lui t6, 1024
+; RV64-NEXT: vand.vx v14, v8, s3
+; RV64-NEXT: lui s3, 2048
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: lui s5, 4096
+; RV64-NEXT: vand.vx v26, v8, s4
+; RV64-NEXT: lui s4, 8192
+; RV64-NEXT: vand.vx v28, v8, s2
+; RV64-NEXT: lui s2, 16384
+; RV64-NEXT: vand.vx v18, v8, s1
+; RV64-NEXT: lui s1, 32768
+; RV64-NEXT: slli s0, s0, 11
+; RV64-NEXT: vand.vx v20, v8, s0
+; RV64-NEXT: lui s0, 65536
+; RV64-NEXT: vand.vx v22, v8, t5
+; RV64-NEXT: lui t5, 131072
+; RV64-NEXT: vand.vx v24, v8, t4
+; RV64-NEXT: lui t4, 262144
+; RV64-NEXT: vand.vx v30, v8, t3
+; RV64-NEXT: lui t3, 524288
+; RV64-NEXT: vand.vi v6, v8, 2
+; RV64-NEXT: vand.vi v4, v8, 1
+; RV64-NEXT: vand.vi v2, v8, 4
+; RV64-NEXT: vand.vi v0, v8, 8
+; RV64-NEXT: vmul.vv v6, v8, v6
+; RV64-NEXT: sd a0, 8(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv s6, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, a0, s6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v6, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v6, v8, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v6, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v6, v8, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv s6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add s6, s6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add s6, s6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, s6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v6, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v6, v8, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv s6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add s6, s6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, s6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v6, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv s6, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add s6, s6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, s6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v12
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv s6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, s6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v14
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv s6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add s6, s6, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, s6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv s6, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, s6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v26
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv s6, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, s6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v28
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v18
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv s6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add s6, s6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, s6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v20
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv s6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, s6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v22
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv s6, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, s6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v30
+; RV64-NEXT: csrr s6, vlenb
+; RV64-NEXT: slli s6, s6, 1
+; RV64-NEXT: mv a0, s6
+; RV64-NEXT: slli s6, s6, 1
+; RV64-NEXT: add s6, s6, a0
+; RV64-NEXT: ld a0, 8(sp) # 8-byte Folded Reload
+; RV64-NEXT: add s6, sp, s6
+; RV64-NEXT: addi s6, s6, 32
+; RV64-NEXT: vs2r.v v10, (s6) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, a5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 32
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, a0
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, a6
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: addi a0, sp, 32
+; RV64-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, a7
+; RV64-NEXT: vmul.vv v6, v8, v10
+; RV64-NEXT: vand.vx v10, v8, t0
+; RV64-NEXT: vmul.vv v30, v8, v10
+; RV64-NEXT: vand.vx v10, v8, t1
+; RV64-NEXT: vmul.vv v28, v8, v10
+; RV64-NEXT: vand.vx v10, v8, t2
+; RV64-NEXT: vmul.vv v26, v8, v10
+; RV64-NEXT: vand.vx v10, v8, t6
+; RV64-NEXT: vmul.vv v24, v8, v10
+; RV64-NEXT: vand.vx v10, v8, s3
+; RV64-NEXT: vmul.vv v22, v8, v10
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v20, v8, v10
+; RV64-NEXT: vand.vx v10, v8, s4
+; RV64-NEXT: vmul.vv v18, v8, v10
+; RV64-NEXT: vand.vx v10, v8, s2
+; RV64-NEXT: vmul.vv v16, v8, v10
+; RV64-NEXT: vand.vx v10, v8, s1
+; RV64-NEXT: vmul.vv v14, v8, v10
+; RV64-NEXT: vand.vx v10, v8, s0
+; RV64-NEXT: vmul.vv v12, v8, v10
+; RV64-NEXT: vand.vx v10, v8, t5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: vand.vx v0, v8, t4
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vand.vx v2, v8, t3
+; RV64-NEXT: vmul.vv v8, v8, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v4, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v4
+; RV64-NEXT: addi a0, sp, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v4, v2, v4
+; RV64-NEXT: vxor.vv v6, v4, v6
+; RV64-NEXT: vxor.vv v30, v6, v30
+; RV64-NEXT: vxor.vv v28, v30, v28
+; RV64-NEXT: vxor.vv v26, v28, v26
+; RV64-NEXT: vxor.vv v24, v26, v24
+; RV64-NEXT: vxor.vv v22, v24, v22
+; RV64-NEXT: vxor.vv v20, v22, v20
+; RV64-NEXT: vxor.vv v18, v20, v18
+; RV64-NEXT: vxor.vv v16, v18, v16
+; RV64-NEXT: vxor.vv v14, v16, v14
+; RV64-NEXT: vxor.vv v12, v14, v12
+; RV64-NEXT: vxor.vv v10, v12, v10
+; RV64-NEXT: vxor.vv v10, v10, v0
+; RV64-NEXT: vxor.vv v8, v10, v8
+; RV64-NEXT: vsrl.vi v10, v8, 8
+; RV64-NEXT: vsrl.vi v12, v8, 24
+; RV64-NEXT: vand.vx v10, v10, a4
+; RV64-NEXT: vor.vv v10, v10, v12
+; RV64-NEXT: vsll.vi v12, v8, 24
+; RV64-NEXT: vand.vx v8, v8, a4
+; RV64-NEXT: vsll.vi v8, v8, 8
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vor.vv v8, v8, v10
+; RV64-NEXT: vsrl.vi v10, v8, 4
+; RV64-NEXT: vand.vx v8, v8, a3
+; RV64-NEXT: vand.vx v10, v10, a3
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v10, v8
+; RV64-NEXT: vsrl.vi v10, v8, 2
+; RV64-NEXT: vand.vx v8, v8, a2
+; RV64-NEXT: vand.vx v10, v10, a2
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v10, v8
+; RV64-NEXT: vsrl.vi v10, v8, 1
+; RV64-NEXT: vand.vx v8, v8, a1
+; RV64-NEXT: vand.vx v10, v10, a1
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v10, v8
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add sp, sp, a0
+; RV64-NEXT: ld s0, 88(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s1, 80(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s2, 72(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s3, 64(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s4, 56(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s5, 48(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s6, 40(sp) # 8-byte Folded Reload
+; RV64-NEXT: addi sp, sp, 96
+; RV64-NEXT: ret
+ %a = call <8 x i32> @llvm.clmulr.v8i32(<8 x i32> %x, <8 x i32> %x)
+ ret <8 x i32> %a
+}
+
+define <16 x i32> @clmulr_v16i32(<16 x i32> %x, <16 x i32> %y) nounwind {
+; RV32-LABEL: clmulr_v16i32:
+; RV32: # %bb.0:
+; RV32-NEXT: addi sp, sp, -80
+; RV32-NEXT: sw ra, 76(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s0, 72(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s1, 68(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s2, 64(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s3, 60(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s4, 56(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s5, 52(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s6, 48(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s7, 44(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s8, 40(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s9, 36(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s10, 32(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s11, 28(sp) # 4-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: sub sp, sp, a0
+; RV32-NEXT: vsetivli zero, 16, e32, m4, ta, ma
+; RV32-NEXT: vsrl.vi v12, v8, 8
+; RV32-NEXT: lui a5, 16
+; RV32-NEXT: vsrl.vi v16, v8, 24
+; RV32-NEXT: vsll.vi v20, v8, 24
+; RV32-NEXT: lui a1, 61681
+; RV32-NEXT: lui a2, 209715
+; RV32-NEXT: lui ra, 349525
+; RV32-NEXT: li s11, 16
+; RV32-NEXT: li s10, 32
+; RV32-NEXT: li s9, 64
+; RV32-NEXT: li a7, 512
+; RV32-NEXT: li t0, 1024
+; RV32-NEXT: li a0, 1
+; RV32-NEXT: lui t1, 1
+; RV32-NEXT: lui t2, 2
+; RV32-NEXT: lui t3, 4
+; RV32-NEXT: lui t4, 8
+; RV32-NEXT: lui t5, 32
+; RV32-NEXT: lui t6, 64
+; RV32-NEXT: lui s0, 128
+; RV32-NEXT: lui s1, 256
+; RV32-NEXT: lui s2, 512
+; RV32-NEXT: lui s3, 1024
+; RV32-NEXT: lui s4, 2048
+; RV32-NEXT: lui s5, 4096
+; RV32-NEXT: lui s6, 8192
+; RV32-NEXT: lui s7, 16384
+; RV32-NEXT: lui s8, 32768
+; RV32-NEXT: addi a4, a5, -256
+; RV32-NEXT: addi a3, a1, -241
+; RV32-NEXT: addi a2, a2, 819
+; RV32-NEXT: addi a1, ra, 1365
+; RV32-NEXT: vand.vx v12, v12, a4
+; RV32-NEXT: vand.vx v8, v8, a4
+; RV32-NEXT: vor.vv v12, v12, v16
+; RV32-NEXT: vsll.vi v8, v8, 8
+; RV32-NEXT: vor.vv v8, v20, v8
+; RV32-NEXT: vor.vv v8, v8, v12
+; RV32-NEXT: vsrl.vi v12, v8, 4
+; RV32-NEXT: vand.vx v8, v8, a3
+; RV32-NEXT: vand.vx v12, v12, a3
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v12, v8
+; RV32-NEXT: vsrl.vi v12, v8, 2
+; RV32-NEXT: vand.vx v8, v8, a2
+; RV32-NEXT: vand.vx v12, v12, a2
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v8, v12, v8
+; RV32-NEXT: vsrl.vi v12, v8, 1
+; RV32-NEXT: vand.vx v8, v8, a1
+; RV32-NEXT: vand.vx v12, v12, a1
+; RV32-NEXT: vadd.vv v8, v8, v8
+; RV32-NEXT: vor.vv v8, v12, v8
+; RV32-NEXT: vand.vx v12, v8, s11
+; RV32-NEXT: lui s11, 65536
+; RV32-NEXT: vand.vx v16, v8, s10
+; RV32-NEXT: lui s10, 131072
+; RV32-NEXT: vand.vx v20, v8, s9
+; RV32-NEXT: lui s9, 262144
+; RV32-NEXT: slli ra, a0, 11
+; RV32-NEXT: vand.vi v24, v8, 2
+; RV32-NEXT: vand.vi v28, v8, 1
+; RV32-NEXT: vand.vi v4, v8, 4
+; RV32-NEXT: vand.vi v0, v8, 8
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: sw a4, 4(sp) # 4-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a4, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a4, a4, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs4r.v v24, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vmul.vv v24, v8, v28
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a4, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs4r.v v24, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vmul.vv v24, v8, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a4, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a4, a4, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a4, a4, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs4r.v v24, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vmul.vv v24, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a4, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a4, a4, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs4r.v v24, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a4, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a4, a4, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vmul.vv v12, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a4, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vmul.vv v12, v8, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a4, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a4, a4, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: lui a0, 524288
+; RV32-NEXT: li a6, 128
+; RV32-NEXT: vand.vx v12, v8, a6
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a4, vlenb
+; RV32-NEXT: slli a4, a4, 3
+; RV32-NEXT: mv a6, a4
+; RV32-NEXT: slli a4, a4, 3
+; RV32-NEXT: add a4, a4, a6
+; RV32-NEXT: add a4, sp, a4
+; RV32-NEXT: addi a4, a4, 16
+; RV32-NEXT: vs4r.v v12, (a4) # vscale x 32-byte Folded Spill
+; RV32-NEXT: li a6, 256
+; RV32-NEXT: vand.vx v12, v8, a6
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 2
+; RV32-NEXT: mv a4, a6
+; RV32-NEXT: slli a6, a6, 4
+; RV32-NEXT: add a6, a6, a4
+; RV32-NEXT: lw a4, 4(sp) # 4-byte Folded Reload
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 16
+; RV32-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, a7
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 6
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 16
+; RV32-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, t0
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 2
+; RV32-NEXT: mv a7, a6
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: add a7, a7, a6
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: add a7, a7, a6
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: add a6, a6, a7
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 16
+; RV32-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, ra
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 3
+; RV32-NEXT: mv a7, a6
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: add a7, a7, a6
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: add a6, a6, a7
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 16
+; RV32-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, t1
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 2
+; RV32-NEXT: mv a7, a6
+; RV32-NEXT: slli a6, a6, 2
+; RV32-NEXT: add a7, a7, a6
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: add a6, a6, a7
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 16
+; RV32-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, t2
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 4
+; RV32-NEXT: mv a7, a6
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: add a6, a6, a7
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 16
+; RV32-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, t3
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 2
+; RV32-NEXT: mv a7, a6
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: add a7, a7, a6
+; RV32-NEXT: slli a6, a6, 2
+; RV32-NEXT: add a6, a6, a7
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 16
+; RV32-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, t4
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 3
+; RV32-NEXT: mv a7, a6
+; RV32-NEXT: slli a6, a6, 2
+; RV32-NEXT: add a6, a6, a7
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 16
+; RV32-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, a5
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a5, vlenb
+; RV32-NEXT: slli a5, a5, 2
+; RV32-NEXT: mv a6, a5
+; RV32-NEXT: slli a5, a5, 3
+; RV32-NEXT: add a5, a5, a6
+; RV32-NEXT: add a5, sp, a5
+; RV32-NEXT: addi a5, a5, 16
+; RV32-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, t5
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a5, vlenb
+; RV32-NEXT: slli a5, a5, 5
+; RV32-NEXT: add a5, sp, a5
+; RV32-NEXT: addi a5, a5, 16
+; RV32-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, t6
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a5, vlenb
+; RV32-NEXT: slli a5, a5, 2
+; RV32-NEXT: mv a6, a5
+; RV32-NEXT: slli a5, a5, 1
+; RV32-NEXT: add a6, a6, a5
+; RV32-NEXT: slli a5, a5, 1
+; RV32-NEXT: add a5, a5, a6
+; RV32-NEXT: add a5, sp, a5
+; RV32-NEXT: addi a5, a5, 16
+; RV32-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s0
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a5, vlenb
+; RV32-NEXT: slli a5, a5, 3
+; RV32-NEXT: mv a6, a5
+; RV32-NEXT: slli a5, a5, 1
+; RV32-NEXT: add a5, a5, a6
+; RV32-NEXT: add a5, sp, a5
+; RV32-NEXT: addi a5, a5, 16
+; RV32-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s1
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a5, vlenb
+; RV32-NEXT: slli a5, a5, 2
+; RV32-NEXT: mv a6, a5
+; RV32-NEXT: slli a5, a5, 2
+; RV32-NEXT: add a5, a5, a6
+; RV32-NEXT: add a5, sp, a5
+; RV32-NEXT: addi a5, a5, 16
+; RV32-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s2
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a5, vlenb
+; RV32-NEXT: slli a5, a5, 4
+; RV32-NEXT: add a5, sp, a5
+; RV32-NEXT: addi a5, a5, 16
+; RV32-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s3
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a5, vlenb
+; RV32-NEXT: slli a5, a5, 2
+; RV32-NEXT: mv a6, a5
+; RV32-NEXT: slli a5, a5, 1
+; RV32-NEXT: add a5, a5, a6
+; RV32-NEXT: add a5, sp, a5
+; RV32-NEXT: addi a5, a5, 16
+; RV32-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s4
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a5, vlenb
+; RV32-NEXT: slli a5, a5, 3
+; RV32-NEXT: add a5, sp, a5
+; RV32-NEXT: addi a5, a5, 16
+; RV32-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s5
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a5, vlenb
+; RV32-NEXT: slli a5, a5, 2
+; RV32-NEXT: add a5, sp, a5
+; RV32-NEXT: addi a5, a5, 16
+; RV32-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s6
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: addi a5, sp, 16
+; RV32-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s7
+; RV32-NEXT: vmul.vv v28, v8, v12
+; RV32-NEXT: vand.vx v12, v8, s8
+; RV32-NEXT: vmul.vv v24, v8, v12
+; RV32-NEXT: vand.vx v12, v8, s11
+; RV32-NEXT: vmul.vv v20, v8, v12
+; RV32-NEXT: vand.vx v12, v8, s10
+; RV32-NEXT: vmul.vv v16, v8, v12
+; RV32-NEXT: vand.vx v12, v8, s9
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vand.vx v0, v8, a0
+; RV32-NEXT: vmul.vv v8, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v0, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v4, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v4
+; RV32-NEXT: addi a0, sp, 16
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v4, v0, v4
+; RV32-NEXT: vxor.vv v28, v4, v28
+; RV32-NEXT: vxor.vv v24, v28, v24
+; RV32-NEXT: vxor.vv v20, v24, v20
+; RV32-NEXT: vxor.vv v16, v20, v16
+; RV32-NEXT: vxor.vv v12, v16, v12
+; RV32-NEXT: vxor.vv v8, v12, v8
+; RV32-NEXT: vsrl.vi v12, v8, 8
+; RV32-NEXT: vsrl.vi v16, v8, 24
+; RV32-NEXT: vand.vx v12, v12, a4
+; RV32-NEXT: vor.vv v12, v12, v16
+; RV32-NEXT: vsll.vi v16, v8, 24
+; RV32-NEXT: vand.vx v8, v8, a4
+; RV32-NEXT: vsll.vi v8, v8, 8
+; RV32-NEXT: vor.vv v8, v16, v8
+; RV32-NEXT: vor.vv v8, v8, v12
+; RV32-NEXT: vsrl.vi v12, v8, 4
+; RV32-NEXT: vand.vx v8, v8, a3
+; RV32-NEXT: vand.vx v12, v12, a3
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v12, v8
+; RV32-NEXT: vsrl.vi v12, v8, 2
+; RV32-NEXT: vand.vx v8, v8, a2
+; RV32-NEXT: vand.vx v12, v12, a2
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v8, v12, v8
+; RV32-NEXT: vsrl.vi v12, v8, 1
+; RV32-NEXT: vand.vx v8, v8, a1
+; RV32-NEXT: vand.vx v12, v12, a1
+; RV32-NEXT: vadd.vv v8, v8, v8
+; RV32-NEXT: vor.vv v8, v12, v8
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add sp, sp, a0
+; RV32-NEXT: lw ra, 76(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s0, 72(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s1, 68(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s2, 64(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s3, 60(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s4, 56(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s5, 52(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s6, 48(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s7, 44(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s8, 40(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s9, 36(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s10, 32(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s11, 28(sp) # 4-byte Folded Reload
+; RV32-NEXT: addi sp, sp, 80
+; RV32-NEXT: ret
+;
+; RV64-LABEL: clmulr_v16i32:
+; RV64: # %bb.0:
+; RV64-NEXT: addi sp, sp, -144
+; RV64-NEXT: sd ra, 136(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s0, 128(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s1, 120(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s2, 112(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s3, 104(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s4, 96(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s5, 88(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s6, 80(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s7, 72(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s8, 64(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s9, 56(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s10, 48(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s11, 40(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: sub sp, sp, a0
+; RV64-NEXT: vsetivli zero, 16, e32, m4, ta, ma
+; RV64-NEXT: vsrl.vi v12, v8, 8
+; RV64-NEXT: lui a5, 16
+; RV64-NEXT: vsrl.vi v16, v8, 24
+; RV64-NEXT: vsll.vi v20, v8, 24
+; RV64-NEXT: lui a1, 61681
+; RV64-NEXT: lui a2, 209715
+; RV64-NEXT: lui ra, 349525
+; RV64-NEXT: li s11, 16
+; RV64-NEXT: li s10, 32
+; RV64-NEXT: li s9, 64
+; RV64-NEXT: li a7, 512
+; RV64-NEXT: li t0, 1024
+; RV64-NEXT: li a0, 1
+; RV64-NEXT: lui t1, 1
+; RV64-NEXT: lui t2, 2
+; RV64-NEXT: lui t3, 4
+; RV64-NEXT: lui t4, 8
+; RV64-NEXT: lui t5, 32
+; RV64-NEXT: lui t6, 64
+; RV64-NEXT: lui s0, 128
+; RV64-NEXT: lui s1, 256
+; RV64-NEXT: lui s2, 512
+; RV64-NEXT: lui s3, 1024
+; RV64-NEXT: lui s4, 2048
+; RV64-NEXT: lui s5, 4096
+; RV64-NEXT: lui s6, 8192
+; RV64-NEXT: lui s7, 16384
+; RV64-NEXT: lui s8, 32768
+; RV64-NEXT: addi a4, a5, -256
+; RV64-NEXT: addi a3, a1, -241
+; RV64-NEXT: addi a2, a2, 819
+; RV64-NEXT: addi a1, ra, 1365
+; RV64-NEXT: vand.vx v12, v12, a4
+; RV64-NEXT: vand.vx v8, v8, a4
+; RV64-NEXT: vor.vv v12, v12, v16
+; RV64-NEXT: vsll.vi v8, v8, 8
+; RV64-NEXT: vor.vv v8, v20, v8
+; RV64-NEXT: vor.vv v8, v8, v12
+; RV64-NEXT: vsrl.vi v12, v8, 4
+; RV64-NEXT: vand.vx v8, v8, a3
+; RV64-NEXT: vand.vx v12, v12, a3
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vsrl.vi v12, v8, 2
+; RV64-NEXT: vand.vx v8, v8, a2
+; RV64-NEXT: vand.vx v12, v12, a2
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vsrl.vi v12, v8, 1
+; RV64-NEXT: vand.vx v8, v8, a1
+; RV64-NEXT: vand.vx v12, v12, a1
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vand.vx v12, v8, s11
+; RV64-NEXT: lui s11, 65536
+; RV64-NEXT: vand.vx v16, v8, s10
+; RV64-NEXT: lui s10, 131072
+; RV64-NEXT: vand.vx v20, v8, s9
+; RV64-NEXT: lui s9, 262144
+; RV64-NEXT: slli ra, a0, 11
+; RV64-NEXT: vand.vi v24, v8, 2
+; RV64-NEXT: vand.vi v28, v8, 1
+; RV64-NEXT: vand.vi v4, v8, 4
+; RV64-NEXT: vand.vi v0, v8, 8
+; RV64-NEXT: vmul.vv v24, v8, v24
+; RV64-NEXT: sd a4, 8(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a4, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a4, a4, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs4r.v v24, (a0) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vmul.vv v24, v8, v28
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: mv a4, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs4r.v v24, (a0) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vmul.vv v24, v8, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a4, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a4, a4, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a4, a4, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs4r.v v24, (a0) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vmul.vv v24, v8, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a4, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a4, a4, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs4r.v v24, (a0) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a4, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a4, a4, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vmul.vv v12, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a4, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vmul.vv v12, v8, v20
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a4, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a4, a4, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui a0, 524288
+; RV64-NEXT: li a6, 128
+; RV64-NEXT: vand.vx v12, v8, a6
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a4, vlenb
+; RV64-NEXT: slli a4, a4, 3
+; RV64-NEXT: mv a6, a4
+; RV64-NEXT: slli a4, a4, 3
+; RV64-NEXT: add a4, a4, a6
+; RV64-NEXT: add a4, sp, a4
+; RV64-NEXT: addi a4, a4, 32
+; RV64-NEXT: vs4r.v v12, (a4) # vscale x 32-byte Folded Spill
+; RV64-NEXT: li a6, 256
+; RV64-NEXT: vand.vx v12, v8, a6
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a6, vlenb
+; RV64-NEXT: slli a6, a6, 2
+; RV64-NEXT: mv a4, a6
+; RV64-NEXT: slli a6, a6, 4
+; RV64-NEXT: add a6, a6, a4
+; RV64-NEXT: ld a4, 8(sp) # 8-byte Folded Reload
+; RV64-NEXT: add a6, sp, a6
+; RV64-NEXT: addi a6, a6, 32
+; RV64-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, a7
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a6, vlenb
+; RV64-NEXT: slli a6, a6, 6
+; RV64-NEXT: add a6, sp, a6
+; RV64-NEXT: addi a6, a6, 32
+; RV64-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t0
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a6, vlenb
+; RV64-NEXT: slli a6, a6, 2
+; RV64-NEXT: mv a7, a6
+; RV64-NEXT: slli a6, a6, 1
+; RV64-NEXT: add a7, a7, a6
+; RV64-NEXT: slli a6, a6, 1
+; RV64-NEXT: add a7, a7, a6
+; RV64-NEXT: slli a6, a6, 1
+; RV64-NEXT: add a6, a6, a7
+; RV64-NEXT: add a6, sp, a6
+; RV64-NEXT: addi a6, a6, 32
+; RV64-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, ra
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a6, vlenb
+; RV64-NEXT: slli a6, a6, 3
+; RV64-NEXT: mv a7, a6
+; RV64-NEXT: slli a6, a6, 1
+; RV64-NEXT: add a7, a7, a6
+; RV64-NEXT: slli a6, a6, 1
+; RV64-NEXT: add a6, a6, a7
+; RV64-NEXT: add a6, sp, a6
+; RV64-NEXT: addi a6, a6, 32
+; RV64-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t1
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a6, vlenb
+; RV64-NEXT: slli a6, a6, 2
+; RV64-NEXT: mv a7, a6
+; RV64-NEXT: slli a6, a6, 2
+; RV64-NEXT: add a7, a7, a6
+; RV64-NEXT: slli a6, a6, 1
+; RV64-NEXT: add a6, a6, a7
+; RV64-NEXT: add a6, sp, a6
+; RV64-NEXT: addi a6, a6, 32
+; RV64-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t2
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a6, vlenb
+; RV64-NEXT: slli a6, a6, 4
+; RV64-NEXT: mv a7, a6
+; RV64-NEXT: slli a6, a6, 1
+; RV64-NEXT: add a6, a6, a7
+; RV64-NEXT: add a6, sp, a6
+; RV64-NEXT: addi a6, a6, 32
+; RV64-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t3
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a6, vlenb
+; RV64-NEXT: slli a6, a6, 2
+; RV64-NEXT: mv a7, a6
+; RV64-NEXT: slli a6, a6, 1
+; RV64-NEXT: add a7, a7, a6
+; RV64-NEXT: slli a6, a6, 2
+; RV64-NEXT: add a6, a6, a7
+; RV64-NEXT: add a6, sp, a6
+; RV64-NEXT: addi a6, a6, 32
+; RV64-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t4
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a6, vlenb
+; RV64-NEXT: slli a6, a6, 3
+; RV64-NEXT: mv a7, a6
+; RV64-NEXT: slli a6, a6, 2
+; RV64-NEXT: add a6, a6, a7
+; RV64-NEXT: add a6, sp, a6
+; RV64-NEXT: addi a6, a6, 32
+; RV64-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, a5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv a6, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, a5, a6
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 32
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 32
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t6
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv a6, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a6, a6, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, a6
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 32
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s0
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv a6, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, a6
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 32
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s1
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv a6, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, a6
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 32
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s2
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 32
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s3
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv a6, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, a6
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 32
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s4
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 32
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 32
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s6
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: addi a5, sp, 32
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s7
+; RV64-NEXT: vmul.vv v28, v8, v12
+; RV64-NEXT: vand.vx v12, v8, s8
+; RV64-NEXT: vmul.vv v24, v8, v12
+; RV64-NEXT: vand.vx v12, v8, s11
+; RV64-NEXT: vmul.vv v20, v8, v12
+; RV64-NEXT: vand.vx v12, v8, s10
+; RV64-NEXT: vmul.vv v16, v8, v12
+; RV64-NEXT: vand.vx v12, v8, s9
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: vand.vx v0, v8, a0
+; RV64-NEXT: vmul.vv v8, v8, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v0, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v4, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: addi a0, sp, 32
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v4, v0, v4
+; RV64-NEXT: vxor.vv v28, v4, v28
+; RV64-NEXT: vxor.vv v24, v28, v24
+; RV64-NEXT: vxor.vv v20, v24, v20
+; RV64-NEXT: vxor.vv v16, v20, v16
+; RV64-NEXT: vxor.vv v12, v16, v12
+; RV64-NEXT: vxor.vv v8, v12, v8
+; RV64-NEXT: vsrl.vi v12, v8, 8
+; RV64-NEXT: vsrl.vi v16, v8, 24
+; RV64-NEXT: vand.vx v12, v12, a4
+; RV64-NEXT: vor.vv v12, v12, v16
+; RV64-NEXT: vsll.vi v16, v8, 24
+; RV64-NEXT: vand.vx v8, v8, a4
+; RV64-NEXT: vsll.vi v8, v8, 8
+; RV64-NEXT: vor.vv v8, v16, v8
+; RV64-NEXT: vor.vv v8, v8, v12
+; RV64-NEXT: vsrl.vi v12, v8, 4
+; RV64-NEXT: vand.vx v8, v8, a3
+; RV64-NEXT: vand.vx v12, v12, a3
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vsrl.vi v12, v8, 2
+; RV64-NEXT: vand.vx v8, v8, a2
+; RV64-NEXT: vand.vx v12, v12, a2
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vsrl.vi v12, v8, 1
+; RV64-NEXT: vand.vx v8, v8, a1
+; RV64-NEXT: vand.vx v12, v12, a1
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add sp, sp, a0
+; RV64-NEXT: ld ra, 136(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s0, 128(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s1, 120(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s2, 112(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s3, 104(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s4, 96(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s5, 88(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s6, 80(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s7, 72(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s8, 64(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s9, 56(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s10, 48(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s11, 40(sp) # 8-byte Folded Reload
+; RV64-NEXT: addi sp, sp, 144
+; RV64-NEXT: ret
+ %a = call <16 x i32> @llvm.clmulr.v16i32(<16 x i32> %x, <16 x i32> %y)
+ ret <16 x i32> %a
+}
+
+define <1 x i64> @clmulr_v1i64(<1 x i64> %x, <1 x i64> %y) nounwind {
+; RV32-LABEL: clmulr_v1i64:
+; RV32: # %bb.0:
+; RV32-NEXT: addi sp, sp, -352
+; RV32-NEXT: sw ra, 348(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s0, 344(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s1, 340(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s2, 336(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s3, 332(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s4, 328(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s5, 324(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s6, 320(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s7, 316(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s8, 312(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s9, 308(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s10, 304(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s11, 300(sp) # 4-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: sub sp, sp, a0
+; RV32-NEXT: lui s7, 1044480
+; RV32-NEXT: lui a7, 524288
+; RV32-NEXT: li s11, 1
+; RV32-NEXT: li s8, 2
+; RV32-NEXT: li s9, 4
+; RV32-NEXT: li s10, 8
+; RV32-NEXT: li a3, 16
+; RV32-NEXT: li a4, 32
+; RV32-NEXT: li a5, 64
+; RV32-NEXT: li a6, 128
+; RV32-NEXT: li ra, 256
+; RV32-NEXT: li a0, 512
+; RV32-NEXT: li a1, 1024
+; RV32-NEXT: lui a2, 1
+; RV32-NEXT: lui t0, 2
+; RV32-NEXT: lui t1, 4
+; RV32-NEXT: lui t2, 8
+; RV32-NEXT: lui t3, 16
+; RV32-NEXT: lui t4, 32
+; RV32-NEXT: lui t5, 64
+; RV32-NEXT: lui t6, 128
+; RV32-NEXT: lui s0, 256
+; RV32-NEXT: lui s1, 512
+; RV32-NEXT: lui s2, 1024
+; RV32-NEXT: lui s3, 2048
+; RV32-NEXT: lui s4, 4096
+; RV32-NEXT: lui s5, 8192
+; RV32-NEXT: lui s6, 16384
+; RV32-NEXT: sw s7, 272(sp)
+; RV32-NEXT: lui s7, 32768
+; RV32-NEXT: sw zero, 276(sp)
+; RV32-NEXT: sw a7, 264(sp)
+; RV32-NEXT: sw zero, 268(sp)
+; RV32-NEXT: sw zero, 256(sp)
+; RV32-NEXT: sw s11, 260(sp)
+; RV32-NEXT: sw zero, 248(sp)
+; RV32-NEXT: sw s8, 252(sp)
+; RV32-NEXT: lui s8, 65536
+; RV32-NEXT: sw zero, 240(sp)
+; RV32-NEXT: sw s9, 244(sp)
+; RV32-NEXT: lui s9, 131072
+; RV32-NEXT: sw zero, 232(sp)
+; RV32-NEXT: sw s10, 236(sp)
+; RV32-NEXT: lui s10, 262144
+; RV32-NEXT: sw zero, 224(sp)
+; RV32-NEXT: sw a3, 228(sp)
+; RV32-NEXT: sw zero, 216(sp)
+; RV32-NEXT: sw a4, 220(sp)
+; RV32-NEXT: sw zero, 208(sp)
+; RV32-NEXT: sw a5, 212(sp)
+; RV32-NEXT: sw zero, 200(sp)
+; RV32-NEXT: sw a6, 204(sp)
+; RV32-NEXT: sw zero, 192(sp)
+; RV32-NEXT: sw ra, 196(sp)
+; RV32-NEXT: sw zero, 184(sp)
+; RV32-NEXT: sw a0, 188(sp)
+; RV32-NEXT: sw zero, 176(sp)
+; RV32-NEXT: sw a1, 180(sp)
+; RV32-NEXT: slli s11, s11, 11
+; RV32-NEXT: sw zero, 168(sp)
+; RV32-NEXT: sw s11, 172(sp)
+; RV32-NEXT: sw zero, 160(sp)
+; RV32-NEXT: sw a2, 164(sp)
+; RV32-NEXT: sw zero, 152(sp)
+; RV32-NEXT: sw t0, 156(sp)
+; RV32-NEXT: sw zero, 144(sp)
+; RV32-NEXT: sw t1, 148(sp)
+; RV32-NEXT: sw zero, 136(sp)
+; RV32-NEXT: sw t2, 140(sp)
+; RV32-NEXT: sw zero, 128(sp)
+; RV32-NEXT: sw t3, 132(sp)
+; RV32-NEXT: sw zero, 120(sp)
+; RV32-NEXT: sw t4, 124(sp)
+; RV32-NEXT: sw zero, 112(sp)
+; RV32-NEXT: sw t5, 116(sp)
+; RV32-NEXT: sw zero, 104(sp)
+; RV32-NEXT: sw t6, 108(sp)
+; RV32-NEXT: sw zero, 96(sp)
+; RV32-NEXT: sw s0, 100(sp)
+; RV32-NEXT: sw zero, 88(sp)
+; RV32-NEXT: sw s1, 92(sp)
+; RV32-NEXT: sw zero, 80(sp)
+; RV32-NEXT: sw s2, 84(sp)
+; RV32-NEXT: sw zero, 72(sp)
+; RV32-NEXT: sw s3, 76(sp)
+; RV32-NEXT: sw zero, 64(sp)
+; RV32-NEXT: sw s4, 68(sp)
+; RV32-NEXT: sw zero, 56(sp)
+; RV32-NEXT: sw s5, 60(sp)
+; RV32-NEXT: sw zero, 48(sp)
+; RV32-NEXT: sw s6, 52(sp)
+; RV32-NEXT: sw zero, 40(sp)
+; RV32-NEXT: sw s7, 44(sp)
+; RV32-NEXT: sw zero, 32(sp)
+; RV32-NEXT: sw s8, 36(sp)
+; RV32-NEXT: sw zero, 24(sp)
+; RV32-NEXT: sw s9, 28(sp)
+; RV32-NEXT: sw zero, 16(sp)
+; RV32-NEXT: sw s10, 20(sp)
+; RV32-NEXT: sw zero, 8(sp)
+; RV32-NEXT: sw a7, 12(sp)
+; RV32-NEXT: lui a0, 61681
+; RV32-NEXT: addi a0, a0, -241
+; RV32-NEXT: vsetivli zero, 2, e32, m1, ta, ma
+; RV32-NEXT: vmv.v.x v3, a0
+; RV32-NEXT: lui a0, 209715
+; RV32-NEXT: addi a0, a0, 819
+; RV32-NEXT: vmv.v.x v2, a0
+; RV32-NEXT: lui a0, 349525
+; RV32-NEXT: addi a0, a0, 1365
+; RV32-NEXT: vmv.v.x v1, a0
+; RV32-NEXT: addi a0, sp, 272
+; RV32-NEXT: vsetivli zero, 1, e64, m1, ta, ma
+; RV32-NEXT: vlse64.v v0, (a0), zero
+; RV32-NEXT: addi a0, sp, 264
+; RV32-NEXT: vlse64.v v13, (a0), zero
+; RV32-NEXT: addi a0, sp, 256
+; RV32-NEXT: vlse64.v v14, (a0), zero
+; RV32-NEXT: addi a0, sp, 248
+; RV32-NEXT: vlse64.v v15, (a0), zero
+; RV32-NEXT: addi a0, sp, 240
+; RV32-NEXT: vlse64.v v16, (a0), zero
+; RV32-NEXT: addi a0, sp, 232
+; RV32-NEXT: vlse64.v v17, (a0), zero
+; RV32-NEXT: addi a0, sp, 224
+; RV32-NEXT: vlse64.v v18, (a0), zero
+; RV32-NEXT: addi a0, sp, 216
+; RV32-NEXT: vlse64.v v19, (a0), zero
+; RV32-NEXT: addi a0, sp, 208
+; RV32-NEXT: vlse64.v v20, (a0), zero
+; RV32-NEXT: addi a0, sp, 200
+; RV32-NEXT: vlse64.v v21, (a0), zero
+; RV32-NEXT: addi a0, sp, 192
+; RV32-NEXT: vlse64.v v22, (a0), zero
+; RV32-NEXT: addi a0, sp, 184
+; RV32-NEXT: vlse64.v v23, (a0), zero
+; RV32-NEXT: addi a0, sp, 176
+; RV32-NEXT: vlse64.v v24, (a0), zero
+; RV32-NEXT: addi a0, sp, 168
+; RV32-NEXT: vlse64.v v25, (a0), zero
+; RV32-NEXT: addi a0, sp, 160
+; RV32-NEXT: vlse64.v v26, (a0), zero
+; RV32-NEXT: addi a0, sp, 152
+; RV32-NEXT: vlse64.v v9, (a0), zero
+; RV32-NEXT: addi a0, sp, 144
+; RV32-NEXT: vlse64.v v10, (a0), zero
+; RV32-NEXT: addi a0, sp, 136
+; RV32-NEXT: vlse64.v v29, (a0), zero
+; RV32-NEXT: addi a0, sp, 128
+; RV32-NEXT: vlse64.v v30, (a0), zero
+; RV32-NEXT: addi a0, sp, 120
+; RV32-NEXT: vlse64.v v31, (a0), zero
+; RV32-NEXT: addi a0, sp, 112
+; RV32-NEXT: vlse64.v v11, (a0), zero
+; RV32-NEXT: addi a0, sp, 104
+; RV32-NEXT: vlse64.v v12, (a0), zero
+; RV32-NEXT: addi a0, sp, 96
+; RV32-NEXT: vlse64.v v5, (a0), zero
+; RV32-NEXT: addi a0, sp, 88
+; RV32-NEXT: vlse64.v v4, (a0), zero
+; RV32-NEXT: li a6, 56
+; RV32-NEXT: vsrl.vi v27, v8, 24
+; RV32-NEXT: vsrl.vx v28, v8, a6
+; RV32-NEXT: li ra, 40
+; RV32-NEXT: vsrl.vx v7, v8, ra
+; RV32-NEXT: vsll.vx v6, v8, a6
+; RV32-NEXT: addi a4, t3, -256
+; RV32-NEXT: vand.vx v7, v7, a4
+; RV32-NEXT: vor.vv v28, v7, v28
+; RV32-NEXT: vand.vx v7, v8, a4
+; RV32-NEXT: vsll.vx v7, v7, ra
+; RV32-NEXT: vor.vv v7, v6, v7
+; RV32-NEXT: vsrl.vi v6, v8, 8
+; RV32-NEXT: lui a5, 4080
+; RV32-NEXT: vand.vx v27, v27, a5
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v0, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v6, v6, v0
+; RV32-NEXT: vor.vv v27, v6, v27
+; RV32-NEXT: addi a3, sp, 80
+; RV32-NEXT: vlse64.v v6, (a3), zero
+; RV32-NEXT: vor.vv v27, v27, v28
+; RV32-NEXT: vand.vx v28, v8, a5
+; RV32-NEXT: vsll.vi v28, v28, 24
+; RV32-NEXT: vand.vv v8, v8, v0
+; RV32-NEXT: vsll.vi v8, v8, 8
+; RV32-NEXT: vor.vv v8, v28, v8
+; RV32-NEXT: addi a3, sp, 72
+; RV32-NEXT: vlse64.v v28, (a3), zero
+; RV32-NEXT: vor.vv v8, v7, v8
+; RV32-NEXT: addi a3, sp, 64
+; RV32-NEXT: vlse64.v v7, (a3), zero
+; RV32-NEXT: vor.vv v8, v8, v27
+; RV32-NEXT: vsrl.vi v27, v8, 4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v3, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v8, v8, v3
+; RV32-NEXT: vand.vv v27, v27, v3
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v27, v8
+; RV32-NEXT: vsrl.vi v27, v8, 2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v2, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v8, v8, v2
+; RV32-NEXT: vand.vv v27, v27, v2
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v8, v27, v8
+; RV32-NEXT: vsrl.vi v27, v8, 1
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v1, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v8, v8, v1
+; RV32-NEXT: vand.vv v27, v27, v1
+; RV32-NEXT: vadd.vv v8, v8, v8
+; RV32-NEXT: vor.vv v8, v27, v8
+; RV32-NEXT: addi a3, sp, 56
+; RV32-NEXT: vlse64.v v27, (a3), zero
+; RV32-NEXT: vand.vv v13, v8, v13
+; RV32-NEXT: vand.vv v14, v8, v14
+; RV32-NEXT: vand.vv v15, v8, v15
+; RV32-NEXT: vand.vv v16, v8, v16
+; RV32-NEXT: vand.vv v17, v8, v17
+; RV32-NEXT: vand.vv v18, v8, v18
+; RV32-NEXT: vand.vv v19, v8, v19
+; RV32-NEXT: vand.vv v20, v8, v20
+; RV32-NEXT: vand.vv v21, v8, v21
+; RV32-NEXT: vand.vv v22, v8, v22
+; RV32-NEXT: vand.vv v23, v8, v23
+; RV32-NEXT: vand.vv v24, v8, v24
+; RV32-NEXT: vand.vv v25, v8, v25
+; RV32-NEXT: vand.vv v26, v8, v26
+; RV32-NEXT: vand.vv v3, v8, v9
+; RV32-NEXT: vand.vv v2, v8, v10
+; RV32-NEXT: vand.vv v29, v8, v29
+; RV32-NEXT: vand.vv v30, v8, v30
+; RV32-NEXT: vand.vv v31, v8, v31
+; RV32-NEXT: vand.vv v0, v8, v11
+; RV32-NEXT: vand.vv v9, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v5, v8, v5
+; RV32-NEXT: vand.vv v4, v8, v4
+; RV32-NEXT: vand.vv v6, v8, v6
+; RV32-NEXT: vand.vv v9, v8, v28
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: addi a3, sp, 48
+; RV32-NEXT: addi a0, sp, 40
+; RV32-NEXT: vlse64.v v9, (a3), zero
+; RV32-NEXT: vlse64.v v10, (a0), zero
+; RV32-NEXT: vand.vv v11, v8, v7
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v11, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v11, v8, v27
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v11, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v9, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: addi a2, sp, 32
+; RV32-NEXT: addi a3, sp, 24
+; RV32-NEXT: addi a1, sp, 16
+; RV32-NEXT: addi a0, sp, 8
+; RV32-NEXT: vlse64.v v9, (a2), zero
+; RV32-NEXT: vlse64.v v10, (a3), zero
+; RV32-NEXT: vlse64.v v11, (a1), zero
+; RV32-NEXT: vlse64.v v12, (a0), zero
+; RV32-NEXT: vand.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 5
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v9, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v9, v8, v11
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 5
+; RV32-NEXT: sub a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v9, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vi v9, v8, 2
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vi v9, v8, 1
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vi v9, v8, 4
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vi v9, v8, 8
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: li a0, 16
+; RV32-NEXT: vand.vx v9, v8, a0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: li a0, 32
+; RV32-NEXT: vand.vx v9, v8, a0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: li a0, 64
+; RV32-NEXT: vand.vx v9, v8, a0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: li a0, 128
+; RV32-NEXT: vand.vx v9, v8, a0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: li a0, 256
+; RV32-NEXT: vand.vx v9, v8, a0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: li a0, 512
+; RV32-NEXT: vand.vx v9, v8, a0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: li a0, 1024
+; RV32-NEXT: vand.vx v9, v8, a0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s11
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: lui a0, 1
+; RV32-NEXT: vand.vx v9, v8, a0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, t0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 4
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, t1
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, t2
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 4
+; RV32-NEXT: sub a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, t3
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, t4
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, t5
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, t6
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s1
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 3
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s2
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s3
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 3
+; RV32-NEXT: sub a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s4
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s5
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 2
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s6
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s7
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 1
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s8
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s9
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v1, v8, s10
+; RV32-NEXT: vmul.vv v1, v8, v1
+; RV32-NEXT: vmul.vv v9, v8, v13
+; RV32-NEXT: addi a0, sp, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vmul.vv v10, v8, v14
+; RV32-NEXT: vmul.vv v11, v8, v15
+; RV32-NEXT: vmul.vv v12, v8, v16
+; RV32-NEXT: vmul.vv v13, v8, v17
+; RV32-NEXT: vmul.vv v14, v8, v18
+; RV32-NEXT: vmul.vv v15, v8, v19
+; RV32-NEXT: vmul.vv v16, v8, v20
+; RV32-NEXT: vmul.vv v17, v8, v21
+; RV32-NEXT: vmul.vv v18, v8, v22
+; RV32-NEXT: vmul.vv v19, v8, v23
+; RV32-NEXT: vmul.vv v20, v8, v24
+; RV32-NEXT: vmul.vv v21, v8, v25
+; RV32-NEXT: vmul.vv v22, v8, v26
+; RV32-NEXT: vmul.vv v23, v8, v3
+; RV32-NEXT: vmul.vv v24, v8, v2
+; RV32-NEXT: vmul.vv v25, v8, v29
+; RV32-NEXT: vmul.vv v26, v8, v30
+; RV32-NEXT: vmul.vv v27, v8, v31
+; RV32-NEXT: vmul.vv v28, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v29, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v29, v8, v29
+; RV32-NEXT: vmul.vv v30, v8, v5
+; RV32-NEXT: vmul.vv v31, v8, v4
+; RV32-NEXT: vmul.vv v7, v8, v6
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v6, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v6, v8, v6
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v5, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v5, v8, v5
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v4, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v4, v8, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v3, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v3, v8, v3
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v2, v8, v2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 5
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v0, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 5
+; RV32-NEXT: sub a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v8, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v8, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vi v8, v8, 0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 4
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 4
+; RV32-NEXT: sub a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 3
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 3
+; RV32-NEXT: sub a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 2
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 1
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: vxor.vv v8, v8, v1
+; RV32-NEXT: addi a0, sp, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: vxor.vv v8, v8, v11
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: vxor.vv v8, v8, v13
+; RV32-NEXT: vxor.vv v8, v8, v14
+; RV32-NEXT: vxor.vv v8, v8, v15
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: vxor.vv v8, v8, v17
+; RV32-NEXT: vxor.vv v8, v8, v18
+; RV32-NEXT: vxor.vv v8, v8, v19
+; RV32-NEXT: vxor.vv v8, v8, v20
+; RV32-NEXT: vxor.vv v8, v8, v21
+; RV32-NEXT: vxor.vv v8, v8, v22
+; RV32-NEXT: vxor.vv v8, v8, v23
+; RV32-NEXT: vxor.vv v8, v8, v24
+; RV32-NEXT: vxor.vv v8, v8, v25
+; RV32-NEXT: vxor.vv v8, v8, v26
+; RV32-NEXT: vxor.vv v8, v8, v27
+; RV32-NEXT: vxor.vv v8, v8, v28
+; RV32-NEXT: vxor.vv v8, v8, v29
+; RV32-NEXT: vxor.vv v8, v8, v30
+; RV32-NEXT: vxor.vv v8, v8, v31
+; RV32-NEXT: vxor.vv v8, v8, v7
+; RV32-NEXT: vxor.vv v8, v8, v6
+; RV32-NEXT: vxor.vv v8, v8, v5
+; RV32-NEXT: vxor.vv v8, v8, v4
+; RV32-NEXT: vxor.vv v8, v8, v3
+; RV32-NEXT: vxor.vv v8, v8, v2
+; RV32-NEXT: vxor.vv v8, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: vsrl.vx v9, v8, a6
+; RV32-NEXT: vsll.vx v10, v8, a6
+; RV32-NEXT: vsrl.vx v11, v8, ra
+; RV32-NEXT: vand.vx v12, v8, a4
+; RV32-NEXT: vand.vx v11, v11, a4
+; RV32-NEXT: vsrl.vi v13, v8, 24
+; RV32-NEXT: vand.vx v14, v8, a5
+; RV32-NEXT: vand.vx v13, v13, a5
+; RV32-NEXT: vsll.vx v12, v12, ra
+; RV32-NEXT: vsrl.vi v15, v8, 8
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v16, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v16
+; RV32-NEXT: vand.vv v15, v15, v16
+; RV32-NEXT: vor.vv v9, v11, v9
+; RV32-NEXT: vor.vv v11, v15, v13
+; RV32-NEXT: vsll.vi v8, v8, 8
+; RV32-NEXT: vsll.vi v13, v14, 24
+; RV32-NEXT: vor.vv v8, v13, v8
+; RV32-NEXT: vor.vv v10, v10, v12
+; RV32-NEXT: vor.vv v9, v11, v9
+; RV32-NEXT: vor.vv v8, v10, v8
+; RV32-NEXT: vor.vv v8, v8, v9
+; RV32-NEXT: vsrl.vi v9, v8, 4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v10, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v10
+; RV32-NEXT: vand.vv v9, v9, v10
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v9, v8
+; RV32-NEXT: vsrl.vi v9, v8, 2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v10, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v10
+; RV32-NEXT: vand.vv v9, v9, v10
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v8, v9, v8
+; RV32-NEXT: vsrl.vi v9, v8, 1
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v10, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v10
+; RV32-NEXT: vand.vv v9, v9, v10
+; RV32-NEXT: vadd.vv v8, v8, v8
+; RV32-NEXT: vor.vv v8, v9, v8
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add sp, sp, a0
+; RV32-NEXT: lw ra, 348(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s0, 344(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s1, 340(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s2, 336(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s3, 332(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s4, 328(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s5, 324(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s6, 320(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s7, 316(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s8, 312(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s9, 308(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s10, 304(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s11, 300(sp) # 4-byte Folded Reload
+; RV32-NEXT: addi sp, sp, 352
+; RV32-NEXT: ret
+;
+; RV64-LABEL: clmulr_v1i64:
+; RV64: # %bb.0:
+; RV64-NEXT: addi sp, sp, -224
+; RV64-NEXT: sd ra, 216(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s0, 208(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s1, 200(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s2, 192(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s3, 184(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s4, 176(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s5, 168(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s6, 160(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s7, 152(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s8, 144(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s9, 136(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s10, 128(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s11, 120(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: sub sp, sp, a0
+; RV64-NEXT: li s11, 56
+; RV64-NEXT: li ra, 40
+; RV64-NEXT: lui a0, 16
+; RV64-NEXT: vsetivli zero, 1, e64, m1, ta, ma
+; RV64-NEXT: vsrl.vi v10, v8, 24
+; RV64-NEXT: vsrl.vi v9, v8, 8
+; RV64-NEXT: li t2, 255
+; RV64-NEXT: lui t6, 61681
+; RV64-NEXT: lui s0, 209715
+; RV64-NEXT: lui s1, 349525
+; RV64-NEXT: li s10, 16
+; RV64-NEXT: li s9, 32
+; RV64-NEXT: li s8, 64
+; RV64-NEXT: li s7, 128
+; RV64-NEXT: li s5, 256
+; RV64-NEXT: li t5, 512
+; RV64-NEXT: li t3, 1024
+; RV64-NEXT: li t0, 1
+; RV64-NEXT: lui s6, 1
+; RV64-NEXT: lui s4, 2
+; RV64-NEXT: lui t4, 4
+; RV64-NEXT: lui t1, 8
+; RV64-NEXT: lui a7, 32
+; RV64-NEXT: lui a6, 64
+; RV64-NEXT: lui a5, 128
+; RV64-NEXT: lui a4, 256
+; RV64-NEXT: lui a3, 512
+; RV64-NEXT: lui a2, 1024
+; RV64-NEXT: vsrl.vx v11, v8, s11
+; RV64-NEXT: vsrl.vx v12, v8, ra
+; RV64-NEXT: addi t6, t6, -241
+; RV64-NEXT: addi s2, s0, 819
+; RV64-NEXT: addi s3, s1, 1365
+; RV64-NEXT: slli s1, t6, 32
+; RV64-NEXT: add s1, t6, s1
+; RV64-NEXT: slli t6, s2, 32
+; RV64-NEXT: add s2, s2, t6
+; RV64-NEXT: slli t6, s3, 32
+; RV64-NEXT: add s3, s3, t6
+; RV64-NEXT: addi s0, a0, -256
+; RV64-NEXT: lui a1, 16
+; RV64-NEXT: lui a0, 4080
+; RV64-NEXT: vand.vx v10, v10, a0
+; RV64-NEXT: slli t6, t2, 24
+; RV64-NEXT: vand.vx v13, v8, a0
+; RV64-NEXT: vsll.vx v14, v8, s11
+; RV64-NEXT: vand.vx v12, v12, s0
+; RV64-NEXT: vand.vx v9, v9, t6
+; RV64-NEXT: vsll.vi v13, v13, 24
+; RV64-NEXT: vand.vx v15, v8, t6
+; RV64-NEXT: vand.vx v8, v8, s0
+; RV64-NEXT: vor.vv v11, v12, v11
+; RV64-NEXT: vor.vv v9, v9, v10
+; RV64-NEXT: vsll.vi v10, v15, 8
+; RV64-NEXT: vsll.vx v8, v8, ra
+; RV64-NEXT: vor.vv v9, v9, v11
+; RV64-NEXT: vor.vv v10, v13, v10
+; RV64-NEXT: vor.vv v8, v14, v8
+; RV64-NEXT: vor.vv v8, v8, v10
+; RV64-NEXT: vor.vv v8, v8, v9
+; RV64-NEXT: vsrl.vi v9, v8, 4
+; RV64-NEXT: vand.vx v8, v8, s1
+; RV64-NEXT: vand.vx v9, v9, s1
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v9, v8
+; RV64-NEXT: vsrl.vi v9, v8, 2
+; RV64-NEXT: vand.vx v8, v8, s2
+; RV64-NEXT: vand.vx v9, v9, s2
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v9, v8
+; RV64-NEXT: vsrl.vi v9, v8, 1
+; RV64-NEXT: vand.vx v8, v8, s3
+; RV64-NEXT: vand.vx v9, v9, s3
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v9, v8
+; RV64-NEXT: vand.vx v9, v8, s10
+; RV64-NEXT: lui t2, 4096
+; RV64-NEXT: vand.vx v10, v8, s9
+; RV64-NEXT: lui s9, 8192
+; RV64-NEXT: vand.vx v11, v8, s8
+; RV64-NEXT: lui s8, 16384
+; RV64-NEXT: vand.vx v12, v8, s7
+; RV64-NEXT: lui s10, 32768
+; RV64-NEXT: vand.vx v13, v8, s5
+; RV64-NEXT: lui s11, 65536
+; RV64-NEXT: vand.vx v14, v8, t5
+; RV64-NEXT: lui t5, 131072
+; RV64-NEXT: vand.vx v15, v8, t3
+; RV64-NEXT: slli t3, t0, 11
+; RV64-NEXT: vand.vx v16, v8, t3
+; RV64-NEXT: lui t3, 262144
+; RV64-NEXT: vand.vx v17, v8, s6
+; RV64-NEXT: slli a0, t0, 31
+; RV64-NEXT: sd a0, 96(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v18, v8, s4
+; RV64-NEXT: slli a0, t0, 32
+; RV64-NEXT: sd a0, 88(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v19, v8, t4
+; RV64-NEXT: slli a0, t0, 33
+; RV64-NEXT: sd a0, 80(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v20, v8, t1
+; RV64-NEXT: slli a0, t0, 34
+; RV64-NEXT: sd a0, 72(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v21, v8, a1
+; RV64-NEXT: slli a0, t0, 35
+; RV64-NEXT: sd a0, 64(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v22, v8, a7
+; RV64-NEXT: slli a0, t0, 36
+; RV64-NEXT: sd a0, 56(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v23, v8, a6
+; RV64-NEXT: slli a0, t0, 37
+; RV64-NEXT: sd a0, 48(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v24, v8, a5
+; RV64-NEXT: slli a0, t0, 38
+; RV64-NEXT: sd a0, 40(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v25, v8, a4
+; RV64-NEXT: slli a0, t0, 39
+; RV64-NEXT: sd a0, 32(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v26, v8, a3
+; RV64-NEXT: slli a0, t0, 40
+; RV64-NEXT: sd a0, 24(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v27, v8, a2
+; RV64-NEXT: slli a0, t0, 41
+; RV64-NEXT: sd a0, 16(sp) # 8-byte Folded Spill
+; RV64-NEXT: lui a0, 2048
+; RV64-NEXT: vand.vx v28, v8, a0
+; RV64-NEXT: slli s5, t0, 42
+; RV64-NEXT: vand.vx v29, v8, t2
+; RV64-NEXT: slli s6, t0, 43
+; RV64-NEXT: vand.vx v30, v8, s9
+; RV64-NEXT: slli s7, t0, 44
+; RV64-NEXT: vand.vx v31, v8, s8
+; RV64-NEXT: slli s8, t0, 45
+; RV64-NEXT: vand.vx v7, v8, s10
+; RV64-NEXT: slli s9, t0, 46
+; RV64-NEXT: vand.vx v6, v8, s11
+; RV64-NEXT: slli s10, t0, 47
+; RV64-NEXT: vand.vx v5, v8, t5
+; RV64-NEXT: slli s11, t0, 48
+; RV64-NEXT: vand.vx v0, v8, t3
+; RV64-NEXT: slli ra, t0, 49
+; RV64-NEXT: slli t5, t0, 50
+; RV64-NEXT: slli t4, t0, 51
+; RV64-NEXT: slli t3, t0, 52
+; RV64-NEXT: slli t2, t0, 53
+; RV64-NEXT: slli t1, t0, 54
+; RV64-NEXT: slli a7, t0, 55
+; RV64-NEXT: slli a6, t0, 56
+; RV64-NEXT: slli a5, t0, 57
+; RV64-NEXT: slli a4, t0, 58
+; RV64-NEXT: slli a3, t0, 59
+; RV64-NEXT: slli a2, t0, 60
+; RV64-NEXT: slli a1, t0, 61
+; RV64-NEXT: slli t0, t0, 62
+; RV64-NEXT: li a0, -1
+; RV64-NEXT: slli a0, a0, 63
+; RV64-NEXT: vand.vi v4, v8, 2
+; RV64-NEXT: vand.vi v3, v8, 1
+; RV64-NEXT: vand.vi v2, v8, 4
+; RV64-NEXT: vand.vi v1, v8, 8
+; RV64-NEXT: vmul.vv v4, v8, v4
+; RV64-NEXT: sd t6, 8(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli s4, t6, 5
+; RV64-NEXT: add t6, s4, t6
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v4, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v4, v8, v3
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 5
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v4, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v4, v8, v2
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli s4, t6, 5
+; RV64-NEXT: sub t6, s4, t6
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v4, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v4, v8, v1
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v4, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v9
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v10
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v11
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v12
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v13
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 3
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v14
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 3
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v15
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v16
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v17
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v18
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v19
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 3
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v20
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 3
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v21
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli s4, t6, 4
+; RV64-NEXT: add t6, s4, t6
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v22
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v23
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli s4, t6, 4
+; RV64-NEXT: sub t6, s4, t6
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v24
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v25
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v26
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v27
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v28
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v29
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli s4, t6, 3
+; RV64-NEXT: add t6, s4, t6
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v30
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 3
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v31
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli s4, t6, 3
+; RV64-NEXT: sub t6, s4, t6
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v7
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v6
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli s4, t6, 2
+; RV64-NEXT: add t6, s4, t6
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v5
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v0
+; RV64-NEXT: csrr s4, vlenb
+; RV64-NEXT: slli t6, s4, 1
+; RV64-NEXT: add s4, t6, s4
+; RV64-NEXT: ld t6, 8(sp) # 8-byte Folded Reload
+; RV64-NEXT: add s4, sp, s4
+; RV64-NEXT: addi s4, s4, 112
+; RV64-NEXT: vs1r.v v9, (s4) # vscale x 8-byte Folded Spill
+; RV64-NEXT: ld s4, 96(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s4
+; RV64-NEXT: vmul.vv v9, v8, v9
+; RV64-NEXT: csrr s4, vlenb
+; RV64-NEXT: slli s4, s4, 1
+; RV64-NEXT: add s4, sp, s4
+; RV64-NEXT: addi s4, s4, 112
+; RV64-NEXT: vs1r.v v9, (s4) # vscale x 8-byte Folded Spill
+; RV64-NEXT: ld s4, 88(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s4
+; RV64-NEXT: vmul.vv v9, v8, v9
+; RV64-NEXT: csrr s4, vlenb
+; RV64-NEXT: add s4, sp, s4
+; RV64-NEXT: addi s4, s4, 112
+; RV64-NEXT: vs1r.v v9, (s4) # vscale x 8-byte Folded Spill
+; RV64-NEXT: ld s4, 80(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s4
+; RV64-NEXT: vmul.vv v9, v8, v9
+; RV64-NEXT: addi s4, sp, 112
+; RV64-NEXT: vs1r.v v9, (s4) # vscale x 8-byte Folded Spill
+; RV64-NEXT: ld s4, 72(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s4
+; RV64-NEXT: vmul.vv v3, v8, v9
+; RV64-NEXT: ld s4, 64(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s4
+; RV64-NEXT: vmul.vv v4, v8, v9
+; RV64-NEXT: ld s4, 56(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s4
+; RV64-NEXT: vmul.vv v5, v8, v9
+; RV64-NEXT: ld s4, 48(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s4
+; RV64-NEXT: vmul.vv v6, v8, v9
+; RV64-NEXT: ld s4, 40(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s4
+; RV64-NEXT: vmul.vv v7, v8, v9
+; RV64-NEXT: ld s4, 32(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s4
+; RV64-NEXT: vmul.vv v31, v8, v9
+; RV64-NEXT: ld s4, 24(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s4
+; RV64-NEXT: vmul.vv v30, v8, v9
+; RV64-NEXT: ld s4, 16(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s4
+; RV64-NEXT: vmul.vv v29, v8, v9
+; RV64-NEXT: vand.vx v9, v8, s5
+; RV64-NEXT: vmul.vv v28, v8, v9
+; RV64-NEXT: vand.vx v9, v8, s6
+; RV64-NEXT: vmul.vv v27, v8, v9
+; RV64-NEXT: vand.vx v9, v8, s7
+; RV64-NEXT: vmul.vv v26, v8, v9
+; RV64-NEXT: vand.vx v9, v8, s8
+; RV64-NEXT: vmul.vv v25, v8, v9
+; RV64-NEXT: vand.vx v9, v8, s9
+; RV64-NEXT: vmul.vv v24, v8, v9
+; RV64-NEXT: vand.vx v9, v8, s10
+; RV64-NEXT: vmul.vv v23, v8, v9
+; RV64-NEXT: vand.vx v9, v8, s11
+; RV64-NEXT: vmul.vv v22, v8, v9
+; RV64-NEXT: vand.vx v9, v8, ra
+; RV64-NEXT: vmul.vv v21, v8, v9
+; RV64-NEXT: vand.vx v9, v8, t5
+; RV64-NEXT: vmul.vv v20, v8, v9
+; RV64-NEXT: vand.vx v9, v8, t4
+; RV64-NEXT: vmul.vv v19, v8, v9
+; RV64-NEXT: vand.vx v9, v8, t3
+; RV64-NEXT: vmul.vv v18, v8, v9
+; RV64-NEXT: vand.vx v9, v8, t2
+; RV64-NEXT: vmul.vv v17, v8, v9
+; RV64-NEXT: vand.vx v9, v8, t1
+; RV64-NEXT: vmul.vv v16, v8, v9
+; RV64-NEXT: vand.vx v9, v8, a7
+; RV64-NEXT: vmul.vv v15, v8, v9
+; RV64-NEXT: vand.vx v9, v8, a6
+; RV64-NEXT: vmul.vv v14, v8, v9
+; RV64-NEXT: vand.vx v9, v8, a5
+; RV64-NEXT: vmul.vv v13, v8, v9
+; RV64-NEXT: vand.vx v9, v8, a4
+; RV64-NEXT: vmul.vv v12, v8, v9
+; RV64-NEXT: vand.vx v9, v8, a3
+; RV64-NEXT: vmul.vv v11, v8, v9
+; RV64-NEXT: vand.vx v9, v8, a2
+; RV64-NEXT: vmul.vv v10, v8, v9
+; RV64-NEXT: vand.vx v9, v8, a1
+; RV64-NEXT: vmul.vv v9, v8, v9
+; RV64-NEXT: vand.vx v0, v8, t0
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vand.vx v1, v8, a0
+; RV64-NEXT: vmul.vv v8, v8, v1
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a1, a0, 5
+; RV64-NEXT: add a0, a1, a0
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v1, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v2, v1
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a1, a0, 5
+; RV64-NEXT: sub a0, a1, a0
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a1, a0, 4
+; RV64-NEXT: add a0, a1, a0
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a1, a0, 4
+; RV64-NEXT: sub a0, a1, a0
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a1, a0, 3
+; RV64-NEXT: add a0, a1, a0
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a1, a0, 3
+; RV64-NEXT: sub a0, a1, a0
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a1, a0, 2
+; RV64-NEXT: add a0, a1, a0
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a1, a0, 1
+; RV64-NEXT: add a0, a1, a0
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: addi a0, sp, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v1, v2
+; RV64-NEXT: vxor.vv v3, v2, v3
+; RV64-NEXT: vxor.vv v4, v3, v4
+; RV64-NEXT: vxor.vv v5, v4, v5
+; RV64-NEXT: vxor.vv v6, v5, v6
+; RV64-NEXT: vxor.vv v7, v6, v7
+; RV64-NEXT: vxor.vv v31, v7, v31
+; RV64-NEXT: vxor.vv v30, v31, v30
+; RV64-NEXT: vxor.vv v29, v30, v29
+; RV64-NEXT: vxor.vv v28, v29, v28
+; RV64-NEXT: vxor.vv v27, v28, v27
+; RV64-NEXT: vxor.vv v26, v27, v26
+; RV64-NEXT: vxor.vv v25, v26, v25
+; RV64-NEXT: vxor.vv v24, v25, v24
+; RV64-NEXT: vxor.vv v23, v24, v23
+; RV64-NEXT: vxor.vv v22, v23, v22
+; RV64-NEXT: vxor.vv v21, v22, v21
+; RV64-NEXT: vxor.vv v20, v21, v20
+; RV64-NEXT: vxor.vv v19, v20, v19
+; RV64-NEXT: vxor.vv v18, v19, v18
+; RV64-NEXT: vxor.vv v17, v18, v17
+; RV64-NEXT: vxor.vv v16, v17, v16
+; RV64-NEXT: vxor.vv v15, v16, v15
+; RV64-NEXT: vxor.vv v14, v15, v14
+; RV64-NEXT: vxor.vv v13, v14, v13
+; RV64-NEXT: vxor.vv v12, v13, v12
+; RV64-NEXT: vxor.vv v11, v12, v11
+; RV64-NEXT: vxor.vv v10, v11, v10
+; RV64-NEXT: vxor.vv v9, v10, v9
+; RV64-NEXT: vxor.vv v9, v9, v0
+; RV64-NEXT: vxor.vv v8, v9, v8
+; RV64-NEXT: li a0, 56
+; RV64-NEXT: vsrl.vx v9, v8, a0
+; RV64-NEXT: li a1, 40
+; RV64-NEXT: vsrl.vx v10, v8, a1
+; RV64-NEXT: vsrl.vi v11, v8, 24
+; RV64-NEXT: vsrl.vi v12, v8, 8
+; RV64-NEXT: vand.vx v10, v10, s0
+; RV64-NEXT: vor.vv v9, v10, v9
+; RV64-NEXT: vand.vx v10, v8, t6
+; RV64-NEXT: lui a2, 4080
+; RV64-NEXT: vand.vx v11, v11, a2
+; RV64-NEXT: vand.vx v12, v12, t6
+; RV64-NEXT: vor.vv v11, v12, v11
+; RV64-NEXT: vand.vx v12, v8, a2
+; RV64-NEXT: vsll.vi v10, v10, 8
+; RV64-NEXT: vsll.vi v12, v12, 24
+; RV64-NEXT: vor.vv v10, v12, v10
+; RV64-NEXT: vsll.vx v12, v8, a0
+; RV64-NEXT: vand.vx v8, v8, s0
+; RV64-NEXT: vsll.vx v8, v8, a1
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vor.vv v9, v11, v9
+; RV64-NEXT: vor.vv v8, v8, v10
+; RV64-NEXT: vor.vv v8, v8, v9
+; RV64-NEXT: vsrl.vi v9, v8, 4
+; RV64-NEXT: vand.vx v8, v8, s1
+; RV64-NEXT: vand.vx v9, v9, s1
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v9, v8
+; RV64-NEXT: vsrl.vi v9, v8, 2
+; RV64-NEXT: vand.vx v8, v8, s2
+; RV64-NEXT: vand.vx v9, v9, s2
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v9, v8
+; RV64-NEXT: vsrl.vi v9, v8, 1
+; RV64-NEXT: vand.vx v8, v8, s3
+; RV64-NEXT: vand.vx v9, v9, s3
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v9, v8
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add sp, sp, a0
+; RV64-NEXT: ld ra, 216(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s0, 208(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s1, 200(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s2, 192(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s3, 184(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s4, 176(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s5, 168(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s6, 160(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s7, 152(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s8, 144(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s9, 136(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s10, 128(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s11, 120(sp) # 8-byte Folded Reload
+; RV64-NEXT: addi sp, sp, 224
+; RV64-NEXT: ret
+ %a = call <1 x i64> @llvm.clmulr.v1i64(<1 x i64> %x, <1 x i64> %y)
+ ret <1 x i64> %a
+}
+
+define <2 x i64> @clmulr_v2i64(<2 x i64> %x, <2 x i64> %y) nounwind {
+; RV32-LABEL: clmulr_v2i64:
+; RV32: # %bb.0:
+; RV32-NEXT: addi sp, sp, -352
+; RV32-NEXT: sw ra, 348(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s0, 344(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s1, 340(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s2, 336(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s3, 332(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s4, 328(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s5, 324(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s6, 320(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s7, 316(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s8, 312(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s9, 308(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s10, 304(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s11, 300(sp) # 4-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: sub sp, sp, a0
+; RV32-NEXT: lui s7, 1044480
+; RV32-NEXT: lui a7, 524288
+; RV32-NEXT: li s11, 1
+; RV32-NEXT: li s8, 2
+; RV32-NEXT: li s9, 4
+; RV32-NEXT: li s10, 8
+; RV32-NEXT: li a3, 16
+; RV32-NEXT: li a4, 32
+; RV32-NEXT: li a5, 64
+; RV32-NEXT: li a6, 128
+; RV32-NEXT: li ra, 256
+; RV32-NEXT: li a0, 512
+; RV32-NEXT: li a1, 1024
+; RV32-NEXT: lui a2, 1
+; RV32-NEXT: lui t0, 2
+; RV32-NEXT: lui t1, 4
+; RV32-NEXT: lui t2, 8
+; RV32-NEXT: lui t3, 16
+; RV32-NEXT: lui t4, 32
+; RV32-NEXT: lui t5, 64
+; RV32-NEXT: lui t6, 128
+; RV32-NEXT: lui s0, 256
+; RV32-NEXT: lui s1, 512
+; RV32-NEXT: lui s2, 1024
+; RV32-NEXT: lui s3, 2048
+; RV32-NEXT: lui s4, 4096
+; RV32-NEXT: lui s5, 8192
+; RV32-NEXT: lui s6, 16384
+; RV32-NEXT: sw s7, 272(sp)
+; RV32-NEXT: lui s7, 32768
+; RV32-NEXT: sw zero, 276(sp)
+; RV32-NEXT: sw a7, 264(sp)
+; RV32-NEXT: sw zero, 268(sp)
+; RV32-NEXT: sw zero, 256(sp)
+; RV32-NEXT: sw s11, 260(sp)
+; RV32-NEXT: sw zero, 248(sp)
+; RV32-NEXT: sw s8, 252(sp)
+; RV32-NEXT: lui s8, 65536
+; RV32-NEXT: sw zero, 240(sp)
+; RV32-NEXT: sw s9, 244(sp)
+; RV32-NEXT: lui s9, 131072
+; RV32-NEXT: sw zero, 232(sp)
+; RV32-NEXT: sw s10, 236(sp)
+; RV32-NEXT: lui s10, 262144
+; RV32-NEXT: sw zero, 224(sp)
+; RV32-NEXT: sw a3, 228(sp)
+; RV32-NEXT: sw zero, 216(sp)
+; RV32-NEXT: sw a4, 220(sp)
+; RV32-NEXT: sw zero, 208(sp)
+; RV32-NEXT: sw a5, 212(sp)
+; RV32-NEXT: sw zero, 200(sp)
+; RV32-NEXT: sw a6, 204(sp)
+; RV32-NEXT: sw zero, 192(sp)
+; RV32-NEXT: sw ra, 196(sp)
+; RV32-NEXT: sw zero, 184(sp)
+; RV32-NEXT: sw a0, 188(sp)
+; RV32-NEXT: sw zero, 176(sp)
+; RV32-NEXT: sw a1, 180(sp)
+; RV32-NEXT: slli s11, s11, 11
+; RV32-NEXT: sw zero, 168(sp)
+; RV32-NEXT: sw s11, 172(sp)
+; RV32-NEXT: sw zero, 160(sp)
+; RV32-NEXT: sw a2, 164(sp)
+; RV32-NEXT: sw zero, 152(sp)
+; RV32-NEXT: sw t0, 156(sp)
+; RV32-NEXT: sw zero, 144(sp)
+; RV32-NEXT: sw t1, 148(sp)
+; RV32-NEXT: sw zero, 136(sp)
+; RV32-NEXT: sw t2, 140(sp)
+; RV32-NEXT: sw zero, 128(sp)
+; RV32-NEXT: sw t3, 132(sp)
+; RV32-NEXT: sw zero, 120(sp)
+; RV32-NEXT: sw t4, 124(sp)
+; RV32-NEXT: sw zero, 112(sp)
+; RV32-NEXT: sw t5, 116(sp)
+; RV32-NEXT: sw zero, 104(sp)
+; RV32-NEXT: sw t6, 108(sp)
+; RV32-NEXT: sw zero, 96(sp)
+; RV32-NEXT: sw s0, 100(sp)
+; RV32-NEXT: sw zero, 88(sp)
+; RV32-NEXT: sw s1, 92(sp)
+; RV32-NEXT: sw zero, 80(sp)
+; RV32-NEXT: sw s2, 84(sp)
+; RV32-NEXT: sw zero, 72(sp)
+; RV32-NEXT: sw s3, 76(sp)
+; RV32-NEXT: sw zero, 64(sp)
+; RV32-NEXT: sw s4, 68(sp)
+; RV32-NEXT: sw zero, 56(sp)
+; RV32-NEXT: sw s5, 60(sp)
+; RV32-NEXT: sw zero, 48(sp)
+; RV32-NEXT: sw s6, 52(sp)
+; RV32-NEXT: sw zero, 40(sp)
+; RV32-NEXT: sw s7, 44(sp)
+; RV32-NEXT: sw zero, 32(sp)
+; RV32-NEXT: sw s8, 36(sp)
+; RV32-NEXT: sw zero, 24(sp)
+; RV32-NEXT: sw s9, 28(sp)
+; RV32-NEXT: sw zero, 16(sp)
+; RV32-NEXT: sw s10, 20(sp)
+; RV32-NEXT: sw zero, 8(sp)
+; RV32-NEXT: sw a7, 12(sp)
+; RV32-NEXT: lui a0, 61681
+; RV32-NEXT: addi a0, a0, -241
+; RV32-NEXT: vsetivli zero, 4, e32, m1, ta, ma
+; RV32-NEXT: vmv.v.x v3, a0
+; RV32-NEXT: lui a0, 209715
+; RV32-NEXT: addi a0, a0, 819
+; RV32-NEXT: vmv.v.x v2, a0
+; RV32-NEXT: lui a0, 349525
+; RV32-NEXT: addi a0, a0, 1365
+; RV32-NEXT: vmv.v.x v1, a0
+; RV32-NEXT: addi a0, sp, 272
+; RV32-NEXT: vsetivli zero, 2, e64, m1, ta, ma
+; RV32-NEXT: vlse64.v v0, (a0), zero
+; RV32-NEXT: addi a0, sp, 264
+; RV32-NEXT: vlse64.v v13, (a0), zero
+; RV32-NEXT: addi a0, sp, 256
+; RV32-NEXT: vlse64.v v14, (a0), zero
+; RV32-NEXT: addi a0, sp, 248
+; RV32-NEXT: vlse64.v v15, (a0), zero
+; RV32-NEXT: addi a0, sp, 240
+; RV32-NEXT: vlse64.v v16, (a0), zero
+; RV32-NEXT: addi a0, sp, 232
+; RV32-NEXT: vlse64.v v17, (a0), zero
+; RV32-NEXT: addi a0, sp, 224
+; RV32-NEXT: vlse64.v v18, (a0), zero
+; RV32-NEXT: addi a0, sp, 216
+; RV32-NEXT: vlse64.v v19, (a0), zero
+; RV32-NEXT: addi a0, sp, 208
+; RV32-NEXT: vlse64.v v20, (a0), zero
+; RV32-NEXT: addi a0, sp, 200
+; RV32-NEXT: vlse64.v v21, (a0), zero
+; RV32-NEXT: addi a0, sp, 192
+; RV32-NEXT: vlse64.v v22, (a0), zero
+; RV32-NEXT: addi a0, sp, 184
+; RV32-NEXT: vlse64.v v23, (a0), zero
+; RV32-NEXT: addi a0, sp, 176
+; RV32-NEXT: vlse64.v v24, (a0), zero
+; RV32-NEXT: addi a0, sp, 168
+; RV32-NEXT: vlse64.v v25, (a0), zero
+; RV32-NEXT: addi a0, sp, 160
+; RV32-NEXT: vlse64.v v26, (a0), zero
+; RV32-NEXT: addi a0, sp, 152
+; RV32-NEXT: vlse64.v v9, (a0), zero
+; RV32-NEXT: addi a0, sp, 144
+; RV32-NEXT: vlse64.v v10, (a0), zero
+; RV32-NEXT: addi a0, sp, 136
+; RV32-NEXT: vlse64.v v29, (a0), zero
+; RV32-NEXT: addi a0, sp, 128
+; RV32-NEXT: vlse64.v v30, (a0), zero
+; RV32-NEXT: addi a0, sp, 120
+; RV32-NEXT: vlse64.v v31, (a0), zero
+; RV32-NEXT: addi a0, sp, 112
+; RV32-NEXT: vlse64.v v11, (a0), zero
+; RV32-NEXT: addi a0, sp, 104
+; RV32-NEXT: vlse64.v v12, (a0), zero
+; RV32-NEXT: addi a0, sp, 96
+; RV32-NEXT: vlse64.v v5, (a0), zero
+; RV32-NEXT: addi a0, sp, 88
+; RV32-NEXT: vlse64.v v4, (a0), zero
+; RV32-NEXT: li a6, 56
+; RV32-NEXT: vsrl.vi v27, v8, 24
+; RV32-NEXT: vsrl.vx v28, v8, a6
+; RV32-NEXT: li ra, 40
+; RV32-NEXT: vsrl.vx v7, v8, ra
+; RV32-NEXT: vsll.vx v6, v8, a6
+; RV32-NEXT: addi a4, t3, -256
+; RV32-NEXT: vand.vx v7, v7, a4
+; RV32-NEXT: vor.vv v28, v7, v28
+; RV32-NEXT: vand.vx v7, v8, a4
+; RV32-NEXT: vsll.vx v7, v7, ra
+; RV32-NEXT: vor.vv v7, v6, v7
+; RV32-NEXT: vsrl.vi v6, v8, 8
+; RV32-NEXT: lui a5, 4080
+; RV32-NEXT: vand.vx v27, v27, a5
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v0, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v6, v6, v0
+; RV32-NEXT: vor.vv v27, v6, v27
+; RV32-NEXT: addi a3, sp, 80
+; RV32-NEXT: vlse64.v v6, (a3), zero
+; RV32-NEXT: vor.vv v27, v27, v28
+; RV32-NEXT: vand.vx v28, v8, a5
+; RV32-NEXT: vsll.vi v28, v28, 24
+; RV32-NEXT: vand.vv v8, v8, v0
+; RV32-NEXT: vsll.vi v8, v8, 8
+; RV32-NEXT: vor.vv v8, v28, v8
+; RV32-NEXT: addi a3, sp, 72
+; RV32-NEXT: vlse64.v v28, (a3), zero
+; RV32-NEXT: vor.vv v8, v7, v8
+; RV32-NEXT: addi a3, sp, 64
+; RV32-NEXT: vlse64.v v7, (a3), zero
+; RV32-NEXT: vor.vv v8, v8, v27
+; RV32-NEXT: vsrl.vi v27, v8, 4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v3, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v8, v8, v3
+; RV32-NEXT: vand.vv v27, v27, v3
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v27, v8
+; RV32-NEXT: vsrl.vi v27, v8, 2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v2, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v8, v8, v2
+; RV32-NEXT: vand.vv v27, v27, v2
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v8, v27, v8
+; RV32-NEXT: vsrl.vi v27, v8, 1
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v1, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v8, v8, v1
+; RV32-NEXT: vand.vv v27, v27, v1
+; RV32-NEXT: vadd.vv v8, v8, v8
+; RV32-NEXT: vor.vv v8, v27, v8
+; RV32-NEXT: addi a3, sp, 56
+; RV32-NEXT: vlse64.v v27, (a3), zero
+; RV32-NEXT: vand.vv v13, v8, v13
+; RV32-NEXT: vand.vv v14, v8, v14
+; RV32-NEXT: vand.vv v15, v8, v15
+; RV32-NEXT: vand.vv v16, v8, v16
+; RV32-NEXT: vand.vv v17, v8, v17
+; RV32-NEXT: vand.vv v18, v8, v18
+; RV32-NEXT: vand.vv v19, v8, v19
+; RV32-NEXT: vand.vv v20, v8, v20
+; RV32-NEXT: vand.vv v21, v8, v21
+; RV32-NEXT: vand.vv v22, v8, v22
+; RV32-NEXT: vand.vv v23, v8, v23
+; RV32-NEXT: vand.vv v24, v8, v24
+; RV32-NEXT: vand.vv v25, v8, v25
+; RV32-NEXT: vand.vv v26, v8, v26
+; RV32-NEXT: vand.vv v3, v8, v9
+; RV32-NEXT: vand.vv v2, v8, v10
+; RV32-NEXT: vand.vv v29, v8, v29
+; RV32-NEXT: vand.vv v30, v8, v30
+; RV32-NEXT: vand.vv v31, v8, v31
+; RV32-NEXT: vand.vv v0, v8, v11
+; RV32-NEXT: vand.vv v9, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v5, v8, v5
+; RV32-NEXT: vand.vv v4, v8, v4
+; RV32-NEXT: vand.vv v6, v8, v6
+; RV32-NEXT: vand.vv v9, v8, v28
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: addi a3, sp, 48
+; RV32-NEXT: addi a0, sp, 40
+; RV32-NEXT: vlse64.v v9, (a3), zero
+; RV32-NEXT: vlse64.v v10, (a0), zero
+; RV32-NEXT: vand.vv v11, v8, v7
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v11, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v11, v8, v27
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v11, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v9, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: addi a2, sp, 32
+; RV32-NEXT: addi a3, sp, 24
+; RV32-NEXT: addi a1, sp, 16
+; RV32-NEXT: addi a0, sp, 8
+; RV32-NEXT: vlse64.v v9, (a2), zero
+; RV32-NEXT: vlse64.v v10, (a3), zero
+; RV32-NEXT: vlse64.v v11, (a1), zero
+; RV32-NEXT: vlse64.v v12, (a0), zero
+; RV32-NEXT: vand.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 5
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v9, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v9, v8, v11
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 5
+; RV32-NEXT: sub a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v9, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vi v9, v8, 2
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vi v9, v8, 1
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vi v9, v8, 4
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vi v9, v8, 8
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: li a0, 16
+; RV32-NEXT: vand.vx v9, v8, a0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: li a0, 32
+; RV32-NEXT: vand.vx v9, v8, a0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: li a0, 64
+; RV32-NEXT: vand.vx v9, v8, a0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: li a0, 128
+; RV32-NEXT: vand.vx v9, v8, a0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: li a0, 256
+; RV32-NEXT: vand.vx v9, v8, a0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: li a0, 512
+; RV32-NEXT: vand.vx v9, v8, a0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: li a0, 1024
+; RV32-NEXT: vand.vx v9, v8, a0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s11
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: lui a0, 1
+; RV32-NEXT: vand.vx v9, v8, a0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, t0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 4
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, t1
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, t2
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 4
+; RV32-NEXT: sub a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, t3
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, t4
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, t5
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, t6
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s1
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 3
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s2
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s3
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 3
+; RV32-NEXT: sub a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s4
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s5
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 2
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s6
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s7
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 1
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s8
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s9
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v1, v8, s10
+; RV32-NEXT: vmul.vv v1, v8, v1
+; RV32-NEXT: vmul.vv v9, v8, v13
+; RV32-NEXT: addi a0, sp, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vmul.vv v10, v8, v14
+; RV32-NEXT: vmul.vv v11, v8, v15
+; RV32-NEXT: vmul.vv v12, v8, v16
+; RV32-NEXT: vmul.vv v13, v8, v17
+; RV32-NEXT: vmul.vv v14, v8, v18
+; RV32-NEXT: vmul.vv v15, v8, v19
+; RV32-NEXT: vmul.vv v16, v8, v20
+; RV32-NEXT: vmul.vv v17, v8, v21
+; RV32-NEXT: vmul.vv v18, v8, v22
+; RV32-NEXT: vmul.vv v19, v8, v23
+; RV32-NEXT: vmul.vv v20, v8, v24
+; RV32-NEXT: vmul.vv v21, v8, v25
+; RV32-NEXT: vmul.vv v22, v8, v26
+; RV32-NEXT: vmul.vv v23, v8, v3
+; RV32-NEXT: vmul.vv v24, v8, v2
+; RV32-NEXT: vmul.vv v25, v8, v29
+; RV32-NEXT: vmul.vv v26, v8, v30
+; RV32-NEXT: vmul.vv v27, v8, v31
+; RV32-NEXT: vmul.vv v28, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v29, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v29, v8, v29
+; RV32-NEXT: vmul.vv v30, v8, v5
+; RV32-NEXT: vmul.vv v31, v8, v4
+; RV32-NEXT: vmul.vv v7, v8, v6
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v6, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v6, v8, v6
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v5, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v5, v8, v5
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v4, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v4, v8, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v3, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v3, v8, v3
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v2, v8, v2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 5
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v0, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 5
+; RV32-NEXT: sub a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v8, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v8, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vi v8, v8, 0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 4
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 4
+; RV32-NEXT: sub a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 3
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 3
+; RV32-NEXT: sub a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 2
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 1
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: vxor.vv v8, v8, v1
+; RV32-NEXT: addi a0, sp, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: vxor.vv v8, v8, v11
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: vxor.vv v8, v8, v13
+; RV32-NEXT: vxor.vv v8, v8, v14
+; RV32-NEXT: vxor.vv v8, v8, v15
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: vxor.vv v8, v8, v17
+; RV32-NEXT: vxor.vv v8, v8, v18
+; RV32-NEXT: vxor.vv v8, v8, v19
+; RV32-NEXT: vxor.vv v8, v8, v20
+; RV32-NEXT: vxor.vv v8, v8, v21
+; RV32-NEXT: vxor.vv v8, v8, v22
+; RV32-NEXT: vxor.vv v8, v8, v23
+; RV32-NEXT: vxor.vv v8, v8, v24
+; RV32-NEXT: vxor.vv v8, v8, v25
+; RV32-NEXT: vxor.vv v8, v8, v26
+; RV32-NEXT: vxor.vv v8, v8, v27
+; RV32-NEXT: vxor.vv v8, v8, v28
+; RV32-NEXT: vxor.vv v8, v8, v29
+; RV32-NEXT: vxor.vv v8, v8, v30
+; RV32-NEXT: vxor.vv v8, v8, v31
+; RV32-NEXT: vxor.vv v8, v8, v7
+; RV32-NEXT: vxor.vv v8, v8, v6
+; RV32-NEXT: vxor.vv v8, v8, v5
+; RV32-NEXT: vxor.vv v8, v8, v4
+; RV32-NEXT: vxor.vv v8, v8, v3
+; RV32-NEXT: vxor.vv v8, v8, v2
+; RV32-NEXT: vxor.vv v8, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: vsrl.vx v9, v8, a6
+; RV32-NEXT: vsll.vx v10, v8, a6
+; RV32-NEXT: vsrl.vx v11, v8, ra
+; RV32-NEXT: vand.vx v12, v8, a4
+; RV32-NEXT: vand.vx v11, v11, a4
+; RV32-NEXT: vsrl.vi v13, v8, 24
+; RV32-NEXT: vand.vx v14, v8, a5
+; RV32-NEXT: vand.vx v13, v13, a5
+; RV32-NEXT: vsll.vx v12, v12, ra
+; RV32-NEXT: vsrl.vi v15, v8, 8
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v16, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v16
+; RV32-NEXT: vand.vv v15, v15, v16
+; RV32-NEXT: vor.vv v9, v11, v9
+; RV32-NEXT: vor.vv v11, v15, v13
+; RV32-NEXT: vsll.vi v8, v8, 8
+; RV32-NEXT: vsll.vi v13, v14, 24
+; RV32-NEXT: vor.vv v8, v13, v8
+; RV32-NEXT: vor.vv v10, v10, v12
+; RV32-NEXT: vor.vv v9, v11, v9
+; RV32-NEXT: vor.vv v8, v10, v8
+; RV32-NEXT: vor.vv v8, v8, v9
+; RV32-NEXT: vsrl.vi v9, v8, 4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v10, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v10
+; RV32-NEXT: vand.vv v9, v9, v10
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v9, v8
+; RV32-NEXT: vsrl.vi v9, v8, 2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v10, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v10
+; RV32-NEXT: vand.vv v9, v9, v10
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v8, v9, v8
+; RV32-NEXT: vsrl.vi v9, v8, 1
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v10, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v10
+; RV32-NEXT: vand.vv v9, v9, v10
+; RV32-NEXT: vadd.vv v8, v8, v8
+; RV32-NEXT: vor.vv v8, v9, v8
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add sp, sp, a0
+; RV32-NEXT: lw ra, 348(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s0, 344(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s1, 340(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s2, 336(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s3, 332(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s4, 328(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s5, 324(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s6, 320(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s7, 316(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s8, 312(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s9, 308(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s10, 304(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s11, 300(sp) # 4-byte Folded Reload
+; RV32-NEXT: addi sp, sp, 352
+; RV32-NEXT: ret
+;
+; RV64-LABEL: clmulr_v2i64:
+; RV64: # %bb.0:
+; RV64-NEXT: addi sp, sp, -224
+; RV64-NEXT: sd ra, 216(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s0, 208(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s1, 200(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s2, 192(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s3, 184(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s4, 176(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s5, 168(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s6, 160(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s7, 152(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s8, 144(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s9, 136(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s10, 128(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s11, 120(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: sub sp, sp, a0
+; RV64-NEXT: li s11, 56
+; RV64-NEXT: li ra, 40
+; RV64-NEXT: lui a0, 16
+; RV64-NEXT: vsetivli zero, 2, e64, m1, ta, ma
+; RV64-NEXT: vsrl.vi v10, v8, 24
+; RV64-NEXT: vsrl.vi v9, v8, 8
+; RV64-NEXT: li t2, 255
+; RV64-NEXT: lui t6, 61681
+; RV64-NEXT: lui s0, 209715
+; RV64-NEXT: lui s1, 349525
+; RV64-NEXT: li s10, 16
+; RV64-NEXT: li s9, 32
+; RV64-NEXT: li s8, 64
+; RV64-NEXT: li s7, 128
+; RV64-NEXT: li s5, 256
+; RV64-NEXT: li t5, 512
+; RV64-NEXT: li t3, 1024
+; RV64-NEXT: li t0, 1
+; RV64-NEXT: lui s6, 1
+; RV64-NEXT: lui s4, 2
+; RV64-NEXT: lui t4, 4
+; RV64-NEXT: lui t1, 8
+; RV64-NEXT: lui a7, 32
+; RV64-NEXT: lui a6, 64
+; RV64-NEXT: lui a5, 128
+; RV64-NEXT: lui a4, 256
+; RV64-NEXT: lui a3, 512
+; RV64-NEXT: lui a2, 1024
+; RV64-NEXT: vsrl.vx v11, v8, s11
+; RV64-NEXT: vsrl.vx v12, v8, ra
+; RV64-NEXT: addi t6, t6, -241
+; RV64-NEXT: addi s2, s0, 819
+; RV64-NEXT: addi s3, s1, 1365
+; RV64-NEXT: slli s1, t6, 32
+; RV64-NEXT: add s1, t6, s1
+; RV64-NEXT: slli t6, s2, 32
+; RV64-NEXT: add s2, s2, t6
+; RV64-NEXT: slli t6, s3, 32
+; RV64-NEXT: add s3, s3, t6
+; RV64-NEXT: addi s0, a0, -256
+; RV64-NEXT: lui a1, 16
+; RV64-NEXT: lui a0, 4080
+; RV64-NEXT: vand.vx v10, v10, a0
+; RV64-NEXT: slli t6, t2, 24
+; RV64-NEXT: vand.vx v13, v8, a0
+; RV64-NEXT: vsll.vx v14, v8, s11
+; RV64-NEXT: vand.vx v12, v12, s0
+; RV64-NEXT: vand.vx v9, v9, t6
+; RV64-NEXT: vsll.vi v13, v13, 24
+; RV64-NEXT: vand.vx v15, v8, t6
+; RV64-NEXT: vand.vx v8, v8, s0
+; RV64-NEXT: vor.vv v11, v12, v11
+; RV64-NEXT: vor.vv v9, v9, v10
+; RV64-NEXT: vsll.vi v10, v15, 8
+; RV64-NEXT: vsll.vx v8, v8, ra
+; RV64-NEXT: vor.vv v9, v9, v11
+; RV64-NEXT: vor.vv v10, v13, v10
+; RV64-NEXT: vor.vv v8, v14, v8
+; RV64-NEXT: vor.vv v8, v8, v10
+; RV64-NEXT: vor.vv v8, v8, v9
+; RV64-NEXT: vsrl.vi v9, v8, 4
+; RV64-NEXT: vand.vx v8, v8, s1
+; RV64-NEXT: vand.vx v9, v9, s1
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v9, v8
+; RV64-NEXT: vsrl.vi v9, v8, 2
+; RV64-NEXT: vand.vx v8, v8, s2
+; RV64-NEXT: vand.vx v9, v9, s2
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v9, v8
+; RV64-NEXT: vsrl.vi v9, v8, 1
+; RV64-NEXT: vand.vx v8, v8, s3
+; RV64-NEXT: vand.vx v9, v9, s3
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v9, v8
+; RV64-NEXT: vand.vx v9, v8, s10
+; RV64-NEXT: lui t2, 4096
+; RV64-NEXT: vand.vx v10, v8, s9
+; RV64-NEXT: lui s9, 8192
+; RV64-NEXT: vand.vx v11, v8, s8
+; RV64-NEXT: lui s8, 16384
+; RV64-NEXT: vand.vx v12, v8, s7
+; RV64-NEXT: lui s10, 32768
+; RV64-NEXT: vand.vx v13, v8, s5
+; RV64-NEXT: lui s11, 65536
+; RV64-NEXT: vand.vx v14, v8, t5
+; RV64-NEXT: lui t5, 131072
+; RV64-NEXT: vand.vx v15, v8, t3
+; RV64-NEXT: slli t3, t0, 11
+; RV64-NEXT: vand.vx v16, v8, t3
+; RV64-NEXT: lui t3, 262144
+; RV64-NEXT: vand.vx v17, v8, s6
+; RV64-NEXT: slli a0, t0, 31
+; RV64-NEXT: sd a0, 96(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v18, v8, s4
+; RV64-NEXT: slli a0, t0, 32
+; RV64-NEXT: sd a0, 88(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v19, v8, t4
+; RV64-NEXT: slli a0, t0, 33
+; RV64-NEXT: sd a0, 80(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v20, v8, t1
+; RV64-NEXT: slli a0, t0, 34
+; RV64-NEXT: sd a0, 72(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v21, v8, a1
+; RV64-NEXT: slli a0, t0, 35
+; RV64-NEXT: sd a0, 64(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v22, v8, a7
+; RV64-NEXT: slli a0, t0, 36
+; RV64-NEXT: sd a0, 56(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v23, v8, a6
+; RV64-NEXT: slli a0, t0, 37
+; RV64-NEXT: sd a0, 48(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v24, v8, a5
+; RV64-NEXT: slli a0, t0, 38
+; RV64-NEXT: sd a0, 40(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v25, v8, a4
+; RV64-NEXT: slli a0, t0, 39
+; RV64-NEXT: sd a0, 32(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v26, v8, a3
+; RV64-NEXT: slli a0, t0, 40
+; RV64-NEXT: sd a0, 24(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v27, v8, a2
+; RV64-NEXT: slli a0, t0, 41
+; RV64-NEXT: sd a0, 16(sp) # 8-byte Folded Spill
+; RV64-NEXT: lui a0, 2048
+; RV64-NEXT: vand.vx v28, v8, a0
+; RV64-NEXT: slli s5, t0, 42
+; RV64-NEXT: vand.vx v29, v8, t2
+; RV64-NEXT: slli s6, t0, 43
+; RV64-NEXT: vand.vx v30, v8, s9
+; RV64-NEXT: slli s7, t0, 44
+; RV64-NEXT: vand.vx v31, v8, s8
+; RV64-NEXT: slli s8, t0, 45
+; RV64-NEXT: vand.vx v7, v8, s10
+; RV64-NEXT: slli s9, t0, 46
+; RV64-NEXT: vand.vx v6, v8, s11
+; RV64-NEXT: slli s10, t0, 47
+; RV64-NEXT: vand.vx v5, v8, t5
+; RV64-NEXT: slli s11, t0, 48
+; RV64-NEXT: vand.vx v0, v8, t3
+; RV64-NEXT: slli ra, t0, 49
+; RV64-NEXT: slli t5, t0, 50
+; RV64-NEXT: slli t4, t0, 51
+; RV64-NEXT: slli t3, t0, 52
+; RV64-NEXT: slli t2, t0, 53
+; RV64-NEXT: slli t1, t0, 54
+; RV64-NEXT: slli a7, t0, 55
+; RV64-NEXT: slli a6, t0, 56
+; RV64-NEXT: slli a5, t0, 57
+; RV64-NEXT: slli a4, t0, 58
+; RV64-NEXT: slli a3, t0, 59
+; RV64-NEXT: slli a2, t0, 60
+; RV64-NEXT: slli a1, t0, 61
+; RV64-NEXT: slli t0, t0, 62
+; RV64-NEXT: li a0, -1
+; RV64-NEXT: slli a0, a0, 63
+; RV64-NEXT: vand.vi v4, v8, 2
+; RV64-NEXT: vand.vi v3, v8, 1
+; RV64-NEXT: vand.vi v2, v8, 4
+; RV64-NEXT: vand.vi v1, v8, 8
+; RV64-NEXT: vmul.vv v4, v8, v4
+; RV64-NEXT: sd t6, 8(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli s4, t6, 5
+; RV64-NEXT: add t6, s4, t6
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v4, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v4, v8, v3
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 5
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v4, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v4, v8, v2
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli s4, t6, 5
+; RV64-NEXT: sub t6, s4, t6
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v4, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v4, v8, v1
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v4, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v9
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v10
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v11
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v12
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v13
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 3
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v14
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 3
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v15
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v16
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v17
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v18
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v19
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 3
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v20
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 3
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v21
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli s4, t6, 4
+; RV64-NEXT: add t6, s4, t6
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v22
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v23
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli s4, t6, 4
+; RV64-NEXT: sub t6, s4, t6
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v24
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v25
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v26
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v27
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v28
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v29
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli s4, t6, 3
+; RV64-NEXT: add t6, s4, t6
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v30
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 3
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v31
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli s4, t6, 3
+; RV64-NEXT: sub t6, s4, t6
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v7
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v6
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli s4, t6, 2
+; RV64-NEXT: add t6, s4, t6
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v5
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v0
+; RV64-NEXT: csrr s4, vlenb
+; RV64-NEXT: slli t6, s4, 1
+; RV64-NEXT: add s4, t6, s4
+; RV64-NEXT: ld t6, 8(sp) # 8-byte Folded Reload
+; RV64-NEXT: add s4, sp, s4
+; RV64-NEXT: addi s4, s4, 112
+; RV64-NEXT: vs1r.v v9, (s4) # vscale x 8-byte Folded Spill
+; RV64-NEXT: ld s4, 96(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s4
+; RV64-NEXT: vmul.vv v9, v8, v9
+; RV64-NEXT: csrr s4, vlenb
+; RV64-NEXT: slli s4, s4, 1
+; RV64-NEXT: add s4, sp, s4
+; RV64-NEXT: addi s4, s4, 112
+; RV64-NEXT: vs1r.v v9, (s4) # vscale x 8-byte Folded Spill
+; RV64-NEXT: ld s4, 88(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s4
+; RV64-NEXT: vmul.vv v9, v8, v9
+; RV64-NEXT: csrr s4, vlenb
+; RV64-NEXT: add s4, sp, s4
+; RV64-NEXT: addi s4, s4, 112
+; RV64-NEXT: vs1r.v v9, (s4) # vscale x 8-byte Folded Spill
+; RV64-NEXT: ld s4, 80(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s4
+; RV64-NEXT: vmul.vv v9, v8, v9
+; RV64-NEXT: addi s4, sp, 112
+; RV64-NEXT: vs1r.v v9, (s4) # vscale x 8-byte Folded Spill
+; RV64-NEXT: ld s4, 72(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s4
+; RV64-NEXT: vmul.vv v3, v8, v9
+; RV64-NEXT: ld s4, 64(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s4
+; RV64-NEXT: vmul.vv v4, v8, v9
+; RV64-NEXT: ld s4, 56(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s4
+; RV64-NEXT: vmul.vv v5, v8, v9
+; RV64-NEXT: ld s4, 48(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s4
+; RV64-NEXT: vmul.vv v6, v8, v9
+; RV64-NEXT: ld s4, 40(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s4
+; RV64-NEXT: vmul.vv v7, v8, v9
+; RV64-NEXT: ld s4, 32(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s4
+; RV64-NEXT: vmul.vv v31, v8, v9
+; RV64-NEXT: ld s4, 24(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s4
+; RV64-NEXT: vmul.vv v30, v8, v9
+; RV64-NEXT: ld s4, 16(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s4
+; RV64-NEXT: vmul.vv v29, v8, v9
+; RV64-NEXT: vand.vx v9, v8, s5
+; RV64-NEXT: vmul.vv v28, v8, v9
+; RV64-NEXT: vand.vx v9, v8, s6
+; RV64-NEXT: vmul.vv v27, v8, v9
+; RV64-NEXT: vand.vx v9, v8, s7
+; RV64-NEXT: vmul.vv v26, v8, v9
+; RV64-NEXT: vand.vx v9, v8, s8
+; RV64-NEXT: vmul.vv v25, v8, v9
+; RV64-NEXT: vand.vx v9, v8, s9
+; RV64-NEXT: vmul.vv v24, v8, v9
+; RV64-NEXT: vand.vx v9, v8, s10
+; RV64-NEXT: vmul.vv v23, v8, v9
+; RV64-NEXT: vand.vx v9, v8, s11
+; RV64-NEXT: vmul.vv v22, v8, v9
+; RV64-NEXT: vand.vx v9, v8, ra
+; RV64-NEXT: vmul.vv v21, v8, v9
+; RV64-NEXT: vand.vx v9, v8, t5
+; RV64-NEXT: vmul.vv v20, v8, v9
+; RV64-NEXT: vand.vx v9, v8, t4
+; RV64-NEXT: vmul.vv v19, v8, v9
+; RV64-NEXT: vand.vx v9, v8, t3
+; RV64-NEXT: vmul.vv v18, v8, v9
+; RV64-NEXT: vand.vx v9, v8, t2
+; RV64-NEXT: vmul.vv v17, v8, v9
+; RV64-NEXT: vand.vx v9, v8, t1
+; RV64-NEXT: vmul.vv v16, v8, v9
+; RV64-NEXT: vand.vx v9, v8, a7
+; RV64-NEXT: vmul.vv v15, v8, v9
+; RV64-NEXT: vand.vx v9, v8, a6
+; RV64-NEXT: vmul.vv v14, v8, v9
+; RV64-NEXT: vand.vx v9, v8, a5
+; RV64-NEXT: vmul.vv v13, v8, v9
+; RV64-NEXT: vand.vx v9, v8, a4
+; RV64-NEXT: vmul.vv v12, v8, v9
+; RV64-NEXT: vand.vx v9, v8, a3
+; RV64-NEXT: vmul.vv v11, v8, v9
+; RV64-NEXT: vand.vx v9, v8, a2
+; RV64-NEXT: vmul.vv v10, v8, v9
+; RV64-NEXT: vand.vx v9, v8, a1
+; RV64-NEXT: vmul.vv v9, v8, v9
+; RV64-NEXT: vand.vx v0, v8, t0
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vand.vx v1, v8, a0
+; RV64-NEXT: vmul.vv v8, v8, v1
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a1, a0, 5
+; RV64-NEXT: add a0, a1, a0
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v1, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v2, v1
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a1, a0, 5
+; RV64-NEXT: sub a0, a1, a0
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a1, a0, 4
+; RV64-NEXT: add a0, a1, a0
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a1, a0, 4
+; RV64-NEXT: sub a0, a1, a0
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a1, a0, 3
+; RV64-NEXT: add a0, a1, a0
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a1, a0, 3
+; RV64-NEXT: sub a0, a1, a0
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a1, a0, 2
+; RV64-NEXT: add a0, a1, a0
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a1, a0, 1
+; RV64-NEXT: add a0, a1, a0
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: addi a0, sp, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v1, v2
+; RV64-NEXT: vxor.vv v3, v2, v3
+; RV64-NEXT: vxor.vv v4, v3, v4
+; RV64-NEXT: vxor.vv v5, v4, v5
+; RV64-NEXT: vxor.vv v6, v5, v6
+; RV64-NEXT: vxor.vv v7, v6, v7
+; RV64-NEXT: vxor.vv v31, v7, v31
+; RV64-NEXT: vxor.vv v30, v31, v30
+; RV64-NEXT: vxor.vv v29, v30, v29
+; RV64-NEXT: vxor.vv v28, v29, v28
+; RV64-NEXT: vxor.vv v27, v28, v27
+; RV64-NEXT: vxor.vv v26, v27, v26
+; RV64-NEXT: vxor.vv v25, v26, v25
+; RV64-NEXT: vxor.vv v24, v25, v24
+; RV64-NEXT: vxor.vv v23, v24, v23
+; RV64-NEXT: vxor.vv v22, v23, v22
+; RV64-NEXT: vxor.vv v21, v22, v21
+; RV64-NEXT: vxor.vv v20, v21, v20
+; RV64-NEXT: vxor.vv v19, v20, v19
+; RV64-NEXT: vxor.vv v18, v19, v18
+; RV64-NEXT: vxor.vv v17, v18, v17
+; RV64-NEXT: vxor.vv v16, v17, v16
+; RV64-NEXT: vxor.vv v15, v16, v15
+; RV64-NEXT: vxor.vv v14, v15, v14
+; RV64-NEXT: vxor.vv v13, v14, v13
+; RV64-NEXT: vxor.vv v12, v13, v12
+; RV64-NEXT: vxor.vv v11, v12, v11
+; RV64-NEXT: vxor.vv v10, v11, v10
+; RV64-NEXT: vxor.vv v9, v10, v9
+; RV64-NEXT: vxor.vv v9, v9, v0
+; RV64-NEXT: vxor.vv v8, v9, v8
+; RV64-NEXT: li a0, 56
+; RV64-NEXT: vsrl.vx v9, v8, a0
+; RV64-NEXT: li a1, 40
+; RV64-NEXT: vsrl.vx v10, v8, a1
+; RV64-NEXT: vsrl.vi v11, v8, 24
+; RV64-NEXT: vsrl.vi v12, v8, 8
+; RV64-NEXT: vand.vx v10, v10, s0
+; RV64-NEXT: vor.vv v9, v10, v9
+; RV64-NEXT: vand.vx v10, v8, t6
+; RV64-NEXT: lui a2, 4080
+; RV64-NEXT: vand.vx v11, v11, a2
+; RV64-NEXT: vand.vx v12, v12, t6
+; RV64-NEXT: vor.vv v11, v12, v11
+; RV64-NEXT: vand.vx v12, v8, a2
+; RV64-NEXT: vsll.vi v10, v10, 8
+; RV64-NEXT: vsll.vi v12, v12, 24
+; RV64-NEXT: vor.vv v10, v12, v10
+; RV64-NEXT: vsll.vx v12, v8, a0
+; RV64-NEXT: vand.vx v8, v8, s0
+; RV64-NEXT: vsll.vx v8, v8, a1
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vor.vv v9, v11, v9
+; RV64-NEXT: vor.vv v8, v8, v10
+; RV64-NEXT: vor.vv v8, v8, v9
+; RV64-NEXT: vsrl.vi v9, v8, 4
+; RV64-NEXT: vand.vx v8, v8, s1
+; RV64-NEXT: vand.vx v9, v9, s1
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v9, v8
+; RV64-NEXT: vsrl.vi v9, v8, 2
+; RV64-NEXT: vand.vx v8, v8, s2
+; RV64-NEXT: vand.vx v9, v9, s2
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v9, v8
+; RV64-NEXT: vsrl.vi v9, v8, 1
+; RV64-NEXT: vand.vx v8, v8, s3
+; RV64-NEXT: vand.vx v9, v9, s3
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v9, v8
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add sp, sp, a0
+; RV64-NEXT: ld ra, 216(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s0, 208(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s1, 200(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s2, 192(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s3, 184(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s4, 176(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s5, 168(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s6, 160(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s7, 152(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s8, 144(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s9, 136(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s10, 128(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s11, 120(sp) # 8-byte Folded Reload
+; RV64-NEXT: addi sp, sp, 224
+; RV64-NEXT: ret
+ %a = call <2 x i64> @llvm.clmulr.v2i64(<2 x i64> %x, <2 x i64> %y)
+ ret <2 x i64> %a
+}
+
+define <4 x i64> @clmulr_v4i64(<4 x i64> %x, <4 x i64> %y) nounwind {
+; RV32-LABEL: clmulr_v4i64:
+; RV32: # %bb.0:
+; RV32-NEXT: addi sp, sp, -352
+; RV32-NEXT: sw ra, 348(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s0, 344(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s1, 340(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s2, 336(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s3, 332(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s4, 328(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s5, 324(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s6, 320(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s7, 316(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s8, 312(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s9, 308(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s10, 304(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s11, 300(sp) # 4-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: sub sp, sp, a0
+; RV32-NEXT: lui s7, 1044480
+; RV32-NEXT: lui a7, 524288
+; RV32-NEXT: li a1, 1
+; RV32-NEXT: li s8, 2
+; RV32-NEXT: li s9, 4
+; RV32-NEXT: li s10, 8
+; RV32-NEXT: li a3, 16
+; RV32-NEXT: li a4, 32
+; RV32-NEXT: li a5, 64
+; RV32-NEXT: li a6, 128
+; RV32-NEXT: li s11, 256
+; RV32-NEXT: li ra, 512
+; RV32-NEXT: li a0, 1024
+; RV32-NEXT: lui a2, 1
+; RV32-NEXT: lui t0, 2
+; RV32-NEXT: lui t1, 4
+; RV32-NEXT: lui t2, 8
+; RV32-NEXT: lui t3, 16
+; RV32-NEXT: lui t4, 32
+; RV32-NEXT: lui t5, 64
+; RV32-NEXT: lui t6, 128
+; RV32-NEXT: lui s0, 256
+; RV32-NEXT: lui s1, 512
+; RV32-NEXT: lui s2, 1024
+; RV32-NEXT: lui s3, 2048
+; RV32-NEXT: lui s4, 4096
+; RV32-NEXT: lui s5, 8192
+; RV32-NEXT: lui s6, 16384
+; RV32-NEXT: sw s7, 272(sp)
+; RV32-NEXT: lui s7, 32768
+; RV32-NEXT: sw zero, 276(sp)
+; RV32-NEXT: sw a7, 264(sp)
+; RV32-NEXT: sw zero, 268(sp)
+; RV32-NEXT: sw zero, 256(sp)
+; RV32-NEXT: sw a1, 260(sp)
+; RV32-NEXT: sw zero, 248(sp)
+; RV32-NEXT: sw s8, 252(sp)
+; RV32-NEXT: lui s8, 65536
+; RV32-NEXT: sw zero, 240(sp)
+; RV32-NEXT: sw s9, 244(sp)
+; RV32-NEXT: lui s9, 131072
+; RV32-NEXT: sw zero, 232(sp)
+; RV32-NEXT: sw s10, 236(sp)
+; RV32-NEXT: lui s10, 262144
+; RV32-NEXT: sw zero, 224(sp)
+; RV32-NEXT: sw a3, 228(sp)
+; RV32-NEXT: sw zero, 216(sp)
+; RV32-NEXT: sw a4, 220(sp)
+; RV32-NEXT: sw zero, 208(sp)
+; RV32-NEXT: sw a5, 212(sp)
+; RV32-NEXT: sw zero, 200(sp)
+; RV32-NEXT: sw a6, 204(sp)
+; RV32-NEXT: sw zero, 192(sp)
+; RV32-NEXT: sw s11, 196(sp)
+; RV32-NEXT: sw zero, 184(sp)
+; RV32-NEXT: sw ra, 188(sp)
+; RV32-NEXT: sw zero, 176(sp)
+; RV32-NEXT: sw a0, 180(sp)
+; RV32-NEXT: slli a5, a1, 11
+; RV32-NEXT: sw zero, 168(sp)
+; RV32-NEXT: sw a5, 172(sp)
+; RV32-NEXT: sw zero, 160(sp)
+; RV32-NEXT: sw a2, 164(sp)
+; RV32-NEXT: sw zero, 152(sp)
+; RV32-NEXT: sw t0, 156(sp)
+; RV32-NEXT: sw zero, 144(sp)
+; RV32-NEXT: sw t1, 148(sp)
+; RV32-NEXT: sw zero, 136(sp)
+; RV32-NEXT: sw t2, 140(sp)
+; RV32-NEXT: sw zero, 128(sp)
+; RV32-NEXT: sw t3, 132(sp)
+; RV32-NEXT: sw zero, 120(sp)
+; RV32-NEXT: sw t4, 124(sp)
+; RV32-NEXT: sw zero, 112(sp)
+; RV32-NEXT: sw t5, 116(sp)
+; RV32-NEXT: sw zero, 104(sp)
+; RV32-NEXT: sw t6, 108(sp)
+; RV32-NEXT: sw zero, 96(sp)
+; RV32-NEXT: sw s0, 100(sp)
+; RV32-NEXT: sw zero, 88(sp)
+; RV32-NEXT: sw s1, 92(sp)
+; RV32-NEXT: sw zero, 80(sp)
+; RV32-NEXT: sw s2, 84(sp)
+; RV32-NEXT: sw zero, 72(sp)
+; RV32-NEXT: sw s3, 76(sp)
+; RV32-NEXT: sw zero, 64(sp)
+; RV32-NEXT: sw s4, 68(sp)
+; RV32-NEXT: sw zero, 56(sp)
+; RV32-NEXT: sw s5, 60(sp)
+; RV32-NEXT: sw zero, 48(sp)
+; RV32-NEXT: sw s6, 52(sp)
+; RV32-NEXT: sw zero, 40(sp)
+; RV32-NEXT: sw s7, 44(sp)
+; RV32-NEXT: sw zero, 32(sp)
+; RV32-NEXT: sw s8, 36(sp)
+; RV32-NEXT: sw zero, 24(sp)
+; RV32-NEXT: sw s9, 28(sp)
+; RV32-NEXT: sw zero, 16(sp)
+; RV32-NEXT: sw s10, 20(sp)
+; RV32-NEXT: sw zero, 8(sp)
+; RV32-NEXT: sw a7, 12(sp)
+; RV32-NEXT: lui a0, 61681
+; RV32-NEXT: addi a0, a0, -241
+; RV32-NEXT: vsetivli zero, 8, e32, m2, ta, ma
+; RV32-NEXT: vmv.v.x v4, a0
+; RV32-NEXT: lui a0, 209715
+; RV32-NEXT: addi a0, a0, 819
+; RV32-NEXT: vmv.v.x v2, a0
+; RV32-NEXT: lui a0, 349525
+; RV32-NEXT: addi a0, a0, 1365
+; RV32-NEXT: vmv.v.x v0, a0
+; RV32-NEXT: addi a0, sp, 272
+; RV32-NEXT: vsetivli zero, 4, e64, m2, ta, ma
+; RV32-NEXT: vlse64.v v6, (a0), zero
+; RV32-NEXT: addi a0, sp, 264
+; RV32-NEXT: vlse64.v v10, (a0), zero
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 256
+; RV32-NEXT: vlse64.v v12, (a0), zero
+; RV32-NEXT: addi a0, sp, 248
+; RV32-NEXT: vlse64.v v14, (a0), zero
+; RV32-NEXT: addi a0, sp, 240
+; RV32-NEXT: vlse64.v v16, (a0), zero
+; RV32-NEXT: addi a0, sp, 232
+; RV32-NEXT: vlse64.v v18, (a0), zero
+; RV32-NEXT: addi a0, sp, 224
+; RV32-NEXT: vlse64.v v20, (a0), zero
+; RV32-NEXT: addi a0, sp, 216
+; RV32-NEXT: vlse64.v v22, (a0), zero
+; RV32-NEXT: li ra, 56
+; RV32-NEXT: vsrl.vi v24, v8, 24
+; RV32-NEXT: vsrl.vx v26, v8, ra
+; RV32-NEXT: li s11, 40
+; RV32-NEXT: vsrl.vx v28, v8, s11
+; RV32-NEXT: vsll.vx v30, v8, ra
+; RV32-NEXT: addi a4, t3, -256
+; RV32-NEXT: vand.vx v28, v28, a4
+; RV32-NEXT: vor.vv v26, v28, v26
+; RV32-NEXT: vand.vx v28, v8, a4
+; RV32-NEXT: vsll.vx v28, v28, s11
+; RV32-NEXT: vor.vv v30, v30, v28
+; RV32-NEXT: vsrl.vi v28, v8, 8
+; RV32-NEXT: lui a6, 4080
+; RV32-NEXT: vand.vx v24, v24, a6
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v6, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v28, v28, v6
+; RV32-NEXT: vor.vv v28, v28, v24
+; RV32-NEXT: addi a3, sp, 208
+; RV32-NEXT: vlse64.v v24, (a3), zero
+; RV32-NEXT: vor.vv v10, v28, v26
+; RV32-NEXT: vand.vx v26, v8, a6
+; RV32-NEXT: vsll.vi v26, v26, 24
+; RV32-NEXT: vand.vv v8, v8, v6
+; RV32-NEXT: vsll.vi v8, v8, 8
+; RV32-NEXT: vor.vv v8, v26, v8
+; RV32-NEXT: addi a3, sp, 200
+; RV32-NEXT: vlse64.v v28, (a3), zero
+; RV32-NEXT: vor.vv v8, v30, v8
+; RV32-NEXT: addi a3, sp, 192
+; RV32-NEXT: vlse64.v v26, (a3), zero
+; RV32-NEXT: vor.vv v8, v8, v10
+; RV32-NEXT: vsrl.vi v30, v8, 4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v4, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v8, v8, v4
+; RV32-NEXT: vand.vv v30, v30, v4
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v30, v8
+; RV32-NEXT: vsrl.vi v30, v8, 2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v2, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v8, v8, v2
+; RV32-NEXT: vand.vv v30, v30, v2
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v8, v30, v8
+; RV32-NEXT: vsrl.vi v30, v8, 1
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v0, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v8, v8, v0
+; RV32-NEXT: vand.vv v30, v30, v0
+; RV32-NEXT: vadd.vv v8, v8, v8
+; RV32-NEXT: vor.vv v8, v30, v8
+; RV32-NEXT: addi a3, sp, 184
+; RV32-NEXT: vlse64.v v30, (a3), zero
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vand.vv v6, v8, v10
+; RV32-NEXT: vand.vv v4, v8, v12
+; RV32-NEXT: vand.vv v2, v8, v14
+; RV32-NEXT: vand.vv v0, v8, v16
+; RV32-NEXT: vand.vv v10, v8, v18
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v22
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v28, v8, v28
+; RV32-NEXT: addi a3, sp, 176
+; RV32-NEXT: addi a0, sp, 168
+; RV32-NEXT: vlse64.v v10, (a3), zero
+; RV32-NEXT: vlse64.v v12, (a0), zero
+; RV32-NEXT: vand.vv v14, v8, v26
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v14, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v14, v8, v30
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v14, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: addi a2, sp, 160
+; RV32-NEXT: addi a3, sp, 152
+; RV32-NEXT: addi a1, sp, 144
+; RV32-NEXT: addi a0, sp, 136
+; RV32-NEXT: vlse64.v v10, (a2), zero
+; RV32-NEXT: vlse64.v v12, (a3), zero
+; RV32-NEXT: vlse64.v v14, (a1), zero
+; RV32-NEXT: vlse64.v v16, (a0), zero
+; RV32-NEXT: vand.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v14
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 128
+; RV32-NEXT: addi a1, sp, 120
+; RV32-NEXT: addi a2, sp, 112
+; RV32-NEXT: addi a3, sp, 104
+; RV32-NEXT: vlse64.v v10, (a0), zero
+; RV32-NEXT: vlse64.v v12, (a1), zero
+; RV32-NEXT: vlse64.v v14, (a2), zero
+; RV32-NEXT: vlse64.v v16, (a3), zero
+; RV32-NEXT: vand.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v14
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 96
+; RV32-NEXT: addi a1, sp, 88
+; RV32-NEXT: addi a2, sp, 80
+; RV32-NEXT: addi a3, sp, 72
+; RV32-NEXT: vlse64.v v10, (a0), zero
+; RV32-NEXT: vlse64.v v12, (a1), zero
+; RV32-NEXT: vlse64.v v14, (a2), zero
+; RV32-NEXT: vlse64.v v16, (a3), zero
+; RV32-NEXT: vand.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v14
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 64
+; RV32-NEXT: addi a1, sp, 56
+; RV32-NEXT: addi a2, sp, 48
+; RV32-NEXT: addi a3, sp, 40
+; RV32-NEXT: vlse64.v v10, (a0), zero
+; RV32-NEXT: vlse64.v v12, (a1), zero
+; RV32-NEXT: vlse64.v v14, (a2), zero
+; RV32-NEXT: vlse64.v v16, (a3), zero
+; RV32-NEXT: vand.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v14
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 32
+; RV32-NEXT: addi a1, sp, 24
+; RV32-NEXT: addi a2, sp, 16
+; RV32-NEXT: addi a3, sp, 8
+; RV32-NEXT: vlse64.v v10, (a0), zero
+; RV32-NEXT: vlse64.v v12, (a1), zero
+; RV32-NEXT: vlse64.v v14, (a2), zero
+; RV32-NEXT: vlse64.v v16, (a3), zero
+; RV32-NEXT: vand.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v14
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vi v10, v8, 2
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vi v10, v8, 1
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vi v10, v8, 4
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vi v10, v8, 8
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: li a0, 16
+; RV32-NEXT: vand.vx v10, v8, a0
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: li a0, 32
+; RV32-NEXT: vand.vx v10, v8, a0
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: li a0, 64
+; RV32-NEXT: vand.vx v10, v8, a0
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: li a0, 128
+; RV32-NEXT: vand.vx v10, v8, a0
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: li a0, 256
+; RV32-NEXT: vand.vx v10, v8, a0
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: li a0, 512
+; RV32-NEXT: vand.vx v10, v8, a0
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: li a0, 1024
+; RV32-NEXT: vand.vx v10, v8, a0
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, a5
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: lui a0, 1
+; RV32-NEXT: vand.vx v10, v8, a0
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, t0
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, t1
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, t2
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, t3
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, t4
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, t5
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, t6
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, s0
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, s1
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, s2
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, s3
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, s4
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, s5
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, s6
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, s7
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, s8
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, s9
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, s10
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: addi a0, sp, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v12, v8, v6
+; RV32-NEXT: vmul.vv v14, v8, v4
+; RV32-NEXT: vmul.vv v16, v8, v2
+; RV32-NEXT: vmul.vv v18, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v20, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v20, v8, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v22, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v22, v8, v22
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v24, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v26, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v26, v8, v26
+; RV32-NEXT: vmul.vv v28, v8, v28
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v30, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v30, v8, v30
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v6, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v6, v8, v6
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v4, v8, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v2, v8, v2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v0, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v8, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v8, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vi v8, v8, 0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: addi a0, sp, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: vxor.vv v8, v8, v14
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: vxor.vv v8, v8, v18
+; RV32-NEXT: vxor.vv v8, v8, v20
+; RV32-NEXT: vxor.vv v8, v8, v22
+; RV32-NEXT: vxor.vv v8, v8, v24
+; RV32-NEXT: vxor.vv v8, v8, v26
+; RV32-NEXT: vxor.vv v8, v8, v28
+; RV32-NEXT: vxor.vv v8, v8, v30
+; RV32-NEXT: vxor.vv v8, v8, v6
+; RV32-NEXT: vxor.vv v8, v8, v4
+; RV32-NEXT: vxor.vv v8, v8, v2
+; RV32-NEXT: vxor.vv v8, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: vsrl.vx v10, v8, ra
+; RV32-NEXT: vsll.vx v12, v8, ra
+; RV32-NEXT: vsrl.vx v14, v8, s11
+; RV32-NEXT: vand.vx v16, v8, a4
+; RV32-NEXT: vand.vx v14, v14, a4
+; RV32-NEXT: vsrl.vi v18, v8, 24
+; RV32-NEXT: vand.vx v20, v8, a6
+; RV32-NEXT: vand.vx v18, v18, a6
+; RV32-NEXT: vsll.vx v16, v16, s11
+; RV32-NEXT: vsrl.vi v22, v8, 8
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v24, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v24
+; RV32-NEXT: vand.vv v22, v22, v24
+; RV32-NEXT: vor.vv v10, v14, v10
+; RV32-NEXT: vor.vv v14, v22, v18
+; RV32-NEXT: vsll.vi v8, v8, 8
+; RV32-NEXT: vsll.vi v18, v20, 24
+; RV32-NEXT: vor.vv v8, v18, v8
+; RV32-NEXT: vor.vv v12, v12, v16
+; RV32-NEXT: vor.vv v10, v14, v10
+; RV32-NEXT: vor.vv v8, v12, v8
+; RV32-NEXT: vor.vv v8, v8, v10
+; RV32-NEXT: vsrl.vi v10, v8, 4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v12
+; RV32-NEXT: vand.vv v10, v10, v12
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v10, v8
+; RV32-NEXT: vsrl.vi v10, v8, 2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v12
+; RV32-NEXT: vand.vv v10, v10, v12
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v8, v10, v8
+; RV32-NEXT: vsrl.vi v10, v8, 1
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v12
+; RV32-NEXT: vand.vv v10, v10, v12
+; RV32-NEXT: vadd.vv v8, v8, v8
+; RV32-NEXT: vor.vv v8, v10, v8
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add sp, sp, a0
+; RV32-NEXT: lw ra, 348(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s0, 344(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s1, 340(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s2, 336(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s3, 332(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s4, 328(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s5, 324(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s6, 320(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s7, 316(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s8, 312(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s9, 308(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s10, 304(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s11, 300(sp) # 4-byte Folded Reload
+; RV32-NEXT: addi sp, sp, 352
+; RV32-NEXT: ret
+;
+; RV64-LABEL: clmulr_v4i64:
+; RV64: # %bb.0:
+; RV64-NEXT: addi sp, sp, -224
+; RV64-NEXT: sd ra, 216(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s0, 208(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s1, 200(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s2, 192(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s3, 184(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s4, 176(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s5, 168(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s6, 160(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s7, 152(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s8, 144(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s9, 136(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s10, 128(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s11, 120(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: sub sp, sp, a0
+; RV64-NEXT: li a7, 56
+; RV64-NEXT: li s1, 40
+; RV64-NEXT: lui s3, 16
+; RV64-NEXT: vsetivli zero, 4, e64, m2, ta, ma
+; RV64-NEXT: vsrl.vi v14, v8, 24
+; RV64-NEXT: lui t6, 4080
+; RV64-NEXT: vsrl.vi v10, v8, 8
+; RV64-NEXT: li s2, 255
+; RV64-NEXT: lui a5, 61681
+; RV64-NEXT: lui a6, 209715
+; RV64-NEXT: lui t5, 349525
+; RV64-NEXT: li t4, 16
+; RV64-NEXT: li t3, 32
+; RV64-NEXT: li t2, 64
+; RV64-NEXT: li t1, 128
+; RV64-NEXT: li t0, 256
+; RV64-NEXT: li a4, 512
+; RV64-NEXT: li a3, 1024
+; RV64-NEXT: li s0, 1
+; RV64-NEXT: lui a2, 1
+; RV64-NEXT: lui a1, 2
+; RV64-NEXT: lui a0, 4
+; RV64-NEXT: vsrl.vx v12, v8, a7
+; RV64-NEXT: vsrl.vx v18, v8, s1
+; RV64-NEXT: addi s4, s3, -256
+; RV64-NEXT: vand.vx v16, v14, t6
+; RV64-NEXT: slli s2, s2, 24
+; RV64-NEXT: vand.vx v20, v8, t6
+; RV64-NEXT: vsll.vx v14, v8, a7
+; RV64-NEXT: addi a7, a5, -241
+; RV64-NEXT: addi a6, a6, 819
+; RV64-NEXT: addi a5, t5, 1365
+; RV64-NEXT: slli t5, s0, 11
+; RV64-NEXT: slli t6, s0, 31
+; RV64-NEXT: sd t6, 96(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli t6, s0, 32
+; RV64-NEXT: sd t6, 88(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli t6, s0, 33
+; RV64-NEXT: sd t6, 80(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli t6, s0, 34
+; RV64-NEXT: sd t6, 72(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli t6, s0, 35
+; RV64-NEXT: sd t6, 64(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli t6, s0, 36
+; RV64-NEXT: sd t6, 56(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli t6, a7, 32
+; RV64-NEXT: add a7, a7, t6
+; RV64-NEXT: slli t6, a6, 32
+; RV64-NEXT: add a6, a6, t6
+; RV64-NEXT: slli t6, a5, 32
+; RV64-NEXT: add a5, a5, t6
+; RV64-NEXT: slli t6, s0, 37
+; RV64-NEXT: sd t6, 48(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v18, v18, s4
+; RV64-NEXT: vand.vx v10, v10, s2
+; RV64-NEXT: vsll.vi v20, v20, 24
+; RV64-NEXT: vand.vx v22, v8, s2
+; RV64-NEXT: vand.vx v8, v8, s4
+; RV64-NEXT: vor.vv v12, v18, v12
+; RV64-NEXT: vor.vv v10, v10, v16
+; RV64-NEXT: vsll.vi v16, v22, 8
+; RV64-NEXT: vsll.vx v8, v8, s1
+; RV64-NEXT: vor.vv v10, v10, v12
+; RV64-NEXT: vor.vv v12, v20, v16
+; RV64-NEXT: vor.vv v8, v14, v8
+; RV64-NEXT: vor.vv v8, v8, v12
+; RV64-NEXT: vor.vv v8, v8, v10
+; RV64-NEXT: vsrl.vi v10, v8, 4
+; RV64-NEXT: vand.vx v8, v8, a7
+; RV64-NEXT: vand.vx v10, v10, a7
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v10, v8
+; RV64-NEXT: vsrl.vi v10, v8, 2
+; RV64-NEXT: vand.vx v8, v8, a6
+; RV64-NEXT: vand.vx v10, v10, a6
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v10, v8
+; RV64-NEXT: vsrl.vi v10, v8, 1
+; RV64-NEXT: vand.vx v8, v8, a5
+; RV64-NEXT: vand.vx v10, v10, a5
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v10, v8
+; RV64-NEXT: vand.vx v10, v8, t4
+; RV64-NEXT: slli t4, s0, 38
+; RV64-NEXT: sd t4, 40(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t3
+; RV64-NEXT: slli t3, s0, 39
+; RV64-NEXT: sd t3, 32(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v14, v8, t2
+; RV64-NEXT: slli t2, s0, 40
+; RV64-NEXT: sd t2, 24(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, t1
+; RV64-NEXT: slli t1, s0, 41
+; RV64-NEXT: sd t1, 16(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v18, v8, t0
+; RV64-NEXT: slli s6, s0, 42
+; RV64-NEXT: vand.vx v20, v8, a4
+; RV64-NEXT: slli s7, s0, 43
+; RV64-NEXT: vand.vx v22, v8, a3
+; RV64-NEXT: slli s8, s0, 44
+; RV64-NEXT: vand.vx v24, v8, t5
+; RV64-NEXT: slli s9, s0, 45
+; RV64-NEXT: vand.vx v26, v8, a2
+; RV64-NEXT: slli s10, s0, 46
+; RV64-NEXT: vand.vx v28, v8, a1
+; RV64-NEXT: slli s11, s0, 47
+; RV64-NEXT: vand.vx v30, v8, a0
+; RV64-NEXT: slli ra, s0, 48
+; RV64-NEXT: slli s3, s0, 49
+; RV64-NEXT: slli s1, s0, 50
+; RV64-NEXT: slli t6, s0, 51
+; RV64-NEXT: slli t5, s0, 52
+; RV64-NEXT: slli t4, s0, 53
+; RV64-NEXT: slli t3, s0, 54
+; RV64-NEXT: slli t2, s0, 55
+; RV64-NEXT: slli t1, s0, 56
+; RV64-NEXT: slli t0, s0, 57
+; RV64-NEXT: slli a4, s0, 58
+; RV64-NEXT: slli a3, s0, 59
+; RV64-NEXT: slli a2, s0, 60
+; RV64-NEXT: slli a1, s0, 61
+; RV64-NEXT: slli s0, s0, 62
+; RV64-NEXT: li a0, -1
+; RV64-NEXT: slli a0, a0, 63
+; RV64-NEXT: vand.vi v6, v8, 2
+; RV64-NEXT: vand.vi v4, v8, 1
+; RV64-NEXT: vand.vi v2, v8, 4
+; RV64-NEXT: vand.vi v0, v8, 8
+; RV64-NEXT: vmul.vv v6, v8, v6
+; RV64-NEXT: sd a5, 8(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v6, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v6, v8, v4
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 5
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v6, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v6, v8, v2
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v6, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v6, v8, v0
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v6, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v14
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v16
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v18
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v20
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v22
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v24
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v26
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v28
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v30
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 8
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 16
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 5
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 32
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 6
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 64
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 128
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 256
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 512
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 1024
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 2048
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 4096
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 8192
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 16384
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 32768
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 65536
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 131072
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 262144
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: ld s5, 96(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: ld s5, 88(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: ld s5, 80(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: ld s5, 72(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: ld s5, 64(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: ld s5, 56(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: ld s5, 48(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: ld s5, 40(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: ld s5, 32(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: ld s5, 24(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: mv a5, s5
+; RV64-NEXT: slli s5, s5, 3
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: ld a5, 8(sp) # 8-byte Folded Reload
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 112
+; RV64-NEXT: vs2r.v v10, (s5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: ld s5, 16(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 4
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 112
+; RV64-NEXT: vs2r.v v10, (s5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, s6
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s6, s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 112
+; RV64-NEXT: vs2r.v v10, (s5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, s7
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 2
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 112
+; RV64-NEXT: vs2r.v v10, (s5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, s8
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 2
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 112
+; RV64-NEXT: vs2r.v v10, (s5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, s9
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 3
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 112
+; RV64-NEXT: vs2r.v v10, (s5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, s10
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 112
+; RV64-NEXT: vs2r.v v10, (s5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, s11
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 2
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 112
+; RV64-NEXT: vs2r.v v10, (s5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, ra
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 112
+; RV64-NEXT: vs2r.v v10, (s5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, s3
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: addi s3, sp, 112
+; RV64-NEXT: vs2r.v v10, (s3) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, s1
+; RV64-NEXT: vmul.vv v4, v8, v10
+; RV64-NEXT: vand.vx v10, v8, t6
+; RV64-NEXT: vmul.vv v6, v8, v10
+; RV64-NEXT: vand.vx v10, v8, t5
+; RV64-NEXT: vmul.vv v30, v8, v10
+; RV64-NEXT: vand.vx v10, v8, t4
+; RV64-NEXT: vmul.vv v28, v8, v10
+; RV64-NEXT: vand.vx v10, v8, t3
+; RV64-NEXT: vmul.vv v26, v8, v10
+; RV64-NEXT: vand.vx v10, v8, t2
+; RV64-NEXT: vmul.vv v24, v8, v10
+; RV64-NEXT: vand.vx v10, v8, t1
+; RV64-NEXT: vmul.vv v22, v8, v10
+; RV64-NEXT: vand.vx v10, v8, t0
+; RV64-NEXT: vmul.vv v20, v8, v10
+; RV64-NEXT: vand.vx v10, v8, a4
+; RV64-NEXT: vmul.vv v18, v8, v10
+; RV64-NEXT: vand.vx v10, v8, a3
+; RV64-NEXT: vmul.vv v16, v8, v10
+; RV64-NEXT: vand.vx v10, v8, a2
+; RV64-NEXT: vmul.vv v14, v8, v10
+; RV64-NEXT: vand.vx v10, v8, a1
+; RV64-NEXT: vmul.vv v12, v8, v10
+; RV64-NEXT: vand.vx v10, v8, s0
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: vand.vx v0, v8, a0
+; RV64-NEXT: vmul.vv v8, v8, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v0, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v2, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: addi a0, sp, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v0, v2
+; RV64-NEXT: vxor.vv v4, v2, v4
+; RV64-NEXT: vxor.vv v6, v4, v6
+; RV64-NEXT: vxor.vv v30, v6, v30
+; RV64-NEXT: vxor.vv v28, v30, v28
+; RV64-NEXT: vxor.vv v26, v28, v26
+; RV64-NEXT: vxor.vv v24, v26, v24
+; RV64-NEXT: vxor.vv v22, v24, v22
+; RV64-NEXT: vxor.vv v20, v22, v20
+; RV64-NEXT: vxor.vv v18, v20, v18
+; RV64-NEXT: vxor.vv v16, v18, v16
+; RV64-NEXT: vxor.vv v14, v16, v14
+; RV64-NEXT: vxor.vv v12, v14, v12
+; RV64-NEXT: vxor.vv v10, v12, v10
+; RV64-NEXT: vxor.vv v8, v10, v8
+; RV64-NEXT: li a0, 56
+; RV64-NEXT: vsrl.vx v10, v8, a0
+; RV64-NEXT: li a1, 40
+; RV64-NEXT: vsrl.vx v12, v8, a1
+; RV64-NEXT: vsrl.vi v14, v8, 24
+; RV64-NEXT: vsrl.vi v16, v8, 8
+; RV64-NEXT: vand.vx v12, v12, s4
+; RV64-NEXT: vor.vv v10, v12, v10
+; RV64-NEXT: vand.vx v12, v8, s2
+; RV64-NEXT: lui a2, 4080
+; RV64-NEXT: vand.vx v14, v14, a2
+; RV64-NEXT: vand.vx v16, v16, s2
+; RV64-NEXT: vor.vv v14, v16, v14
+; RV64-NEXT: vand.vx v16, v8, a2
+; RV64-NEXT: vsll.vi v12, v12, 8
+; RV64-NEXT: vsll.vi v16, v16, 24
+; RV64-NEXT: vor.vv v12, v16, v12
+; RV64-NEXT: vsll.vx v16, v8, a0
+; RV64-NEXT: vand.vx v8, v8, s4
+; RV64-NEXT: vsll.vx v8, v8, a1
+; RV64-NEXT: vor.vv v8, v16, v8
+; RV64-NEXT: vor.vv v10, v14, v10
+; RV64-NEXT: vor.vv v8, v8, v12
+; RV64-NEXT: vor.vv v8, v8, v10
+; RV64-NEXT: vsrl.vi v10, v8, 4
+; RV64-NEXT: vand.vx v8, v8, a7
+; RV64-NEXT: vand.vx v10, v10, a7
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v10, v8
+; RV64-NEXT: vsrl.vi v10, v8, 2
+; RV64-NEXT: vand.vx v8, v8, a6
+; RV64-NEXT: vand.vx v10, v10, a6
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v10, v8
+; RV64-NEXT: vsrl.vi v10, v8, 1
+; RV64-NEXT: vand.vx v8, v8, a5
+; RV64-NEXT: vand.vx v10, v10, a5
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v10, v8
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add sp, sp, a0
+; RV64-NEXT: ld ra, 216(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s0, 208(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s1, 200(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s2, 192(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s3, 184(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s4, 176(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s5, 168(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s6, 160(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s7, 152(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s8, 144(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s9, 136(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s10, 128(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s11, 120(sp) # 8-byte Folded Reload
+; RV64-NEXT: addi sp, sp, 224
+; RV64-NEXT: ret
+ %a = call <4 x i64> @llvm.clmulr.v4i64(<4 x i64> %x, <4 x i64> %y)
+ ret <4 x i64> %a
+}
+
+define <8 x i64> @clmulr_v8i64(<8 x i64> %x, <8 x i64> %y) nounwind {
+; RV32-LABEL: clmulr_v8i64:
+; RV32: # %bb.0:
+; RV32-NEXT: addi sp, sp, -352
+; RV32-NEXT: sw ra, 348(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s0, 344(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s1, 340(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s2, 336(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s3, 332(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s4, 328(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s5, 324(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s6, 320(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s7, 316(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s8, 312(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s9, 308(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s10, 304(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s11, 300(sp) # 4-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: sub sp, sp, a0
+; RV32-NEXT: lui s11, 1044480
+; RV32-NEXT: lui s0, 524288
+; RV32-NEXT: li a0, 1
+; RV32-NEXT: li ra, 2
+; RV32-NEXT: li t4, 4
+; RV32-NEXT: li t2, 8
+; RV32-NEXT: li t6, 16
+; RV32-NEXT: li t5, 32
+; RV32-NEXT: li t3, 64
+; RV32-NEXT: li t1, 128
+; RV32-NEXT: li t0, 256
+; RV32-NEXT: li a7, 512
+; RV32-NEXT: li a6, 1024
+; RV32-NEXT: lui a4, 1
+; RV32-NEXT: lui a3, 2
+; RV32-NEXT: lui a2, 4
+; RV32-NEXT: lui a5, 8
+; RV32-NEXT: lui s1, 16
+; RV32-NEXT: lui a1, 32
+; RV32-NEXT: lui s2, 64
+; RV32-NEXT: lui s3, 128
+; RV32-NEXT: lui s4, 256
+; RV32-NEXT: lui s5, 512
+; RV32-NEXT: lui s6, 1024
+; RV32-NEXT: lui s7, 2048
+; RV32-NEXT: lui s8, 4096
+; RV32-NEXT: lui s9, 8192
+; RV32-NEXT: lui s10, 16384
+; RV32-NEXT: sw s11, 272(sp)
+; RV32-NEXT: lui s11, 32768
+; RV32-NEXT: sw zero, 276(sp)
+; RV32-NEXT: sw s0, 264(sp)
+; RV32-NEXT: sw zero, 268(sp)
+; RV32-NEXT: sw zero, 256(sp)
+; RV32-NEXT: sw a0, 260(sp)
+; RV32-NEXT: sw zero, 248(sp)
+; RV32-NEXT: sw ra, 252(sp)
+; RV32-NEXT: lui ra, 65536
+; RV32-NEXT: sw zero, 240(sp)
+; RV32-NEXT: sw t4, 244(sp)
+; RV32-NEXT: lui t4, 131072
+; RV32-NEXT: sw zero, 232(sp)
+; RV32-NEXT: sw t2, 236(sp)
+; RV32-NEXT: lui t2, 262144
+; RV32-NEXT: sw zero, 224(sp)
+; RV32-NEXT: sw t6, 228(sp)
+; RV32-NEXT: sw zero, 216(sp)
+; RV32-NEXT: sw t5, 220(sp)
+; RV32-NEXT: sw zero, 208(sp)
+; RV32-NEXT: sw t3, 212(sp)
+; RV32-NEXT: sw zero, 200(sp)
+; RV32-NEXT: sw t1, 204(sp)
+; RV32-NEXT: sw zero, 192(sp)
+; RV32-NEXT: sw t0, 196(sp)
+; RV32-NEXT: sw zero, 184(sp)
+; RV32-NEXT: sw a7, 188(sp)
+; RV32-NEXT: sw zero, 176(sp)
+; RV32-NEXT: sw a6, 180(sp)
+; RV32-NEXT: li t1, 1024
+; RV32-NEXT: slli t6, a0, 11
+; RV32-NEXT: sw zero, 168(sp)
+; RV32-NEXT: sw t6, 172(sp)
+; RV32-NEXT: sw zero, 160(sp)
+; RV32-NEXT: sw a4, 164(sp)
+; RV32-NEXT: sw zero, 152(sp)
+; RV32-NEXT: sw a3, 156(sp)
+; RV32-NEXT: lui t3, 2
+; RV32-NEXT: sw zero, 144(sp)
+; RV32-NEXT: sw a2, 148(sp)
+; RV32-NEXT: lui t5, 4
+; RV32-NEXT: sw zero, 136(sp)
+; RV32-NEXT: sw a5, 140(sp)
+; RV32-NEXT: lui a4, 8
+; RV32-NEXT: sw zero, 128(sp)
+; RV32-NEXT: sw s1, 132(sp)
+; RV32-NEXT: sw zero, 120(sp)
+; RV32-NEXT: sw a1, 124(sp)
+; RV32-NEXT: sw zero, 112(sp)
+; RV32-NEXT: sw s2, 116(sp)
+; RV32-NEXT: sw zero, 104(sp)
+; RV32-NEXT: sw s3, 108(sp)
+; RV32-NEXT: sw zero, 96(sp)
+; RV32-NEXT: sw s4, 100(sp)
+; RV32-NEXT: sw zero, 88(sp)
+; RV32-NEXT: sw s5, 92(sp)
+; RV32-NEXT: sw zero, 80(sp)
+; RV32-NEXT: sw s6, 84(sp)
+; RV32-NEXT: sw zero, 72(sp)
+; RV32-NEXT: sw s7, 76(sp)
+; RV32-NEXT: sw zero, 64(sp)
+; RV32-NEXT: sw s8, 68(sp)
+; RV32-NEXT: sw zero, 56(sp)
+; RV32-NEXT: sw s9, 60(sp)
+; RV32-NEXT: sw zero, 48(sp)
+; RV32-NEXT: sw s10, 52(sp)
+; RV32-NEXT: sw zero, 40(sp)
+; RV32-NEXT: sw s11, 44(sp)
+; RV32-NEXT: sw zero, 32(sp)
+; RV32-NEXT: sw ra, 36(sp)
+; RV32-NEXT: sw zero, 24(sp)
+; RV32-NEXT: sw t4, 28(sp)
+; RV32-NEXT: sw zero, 16(sp)
+; RV32-NEXT: sw t2, 20(sp)
+; RV32-NEXT: sw zero, 8(sp)
+; RV32-NEXT: sw s0, 12(sp)
+; RV32-NEXT: lui a1, 61681
+; RV32-NEXT: addi a1, a1, -241
+; RV32-NEXT: vsetivli zero, 16, e32, m4, ta, ma
+; RV32-NEXT: vmv.v.x v28, a1
+; RV32-NEXT: lui a1, 209715
+; RV32-NEXT: addi a1, a1, 819
+; RV32-NEXT: vmv.v.x v4, a1
+; RV32-NEXT: addi a1, sp, 272
+; RV32-NEXT: vsetivli zero, 8, e64, m4, ta, ma
+; RV32-NEXT: vlse64.v v0, (a1), zero
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 8
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v0, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: li t0, 56
+; RV32-NEXT: vsrl.vi v20, v8, 24
+; RV32-NEXT: vsrl.vx v12, v8, t0
+; RV32-NEXT: li a6, 40
+; RV32-NEXT: vsrl.vx v16, v8, a6
+; RV32-NEXT: vsll.vx v24, v8, t0
+; RV32-NEXT: addi a3, s1, -256
+; RV32-NEXT: vand.vx v16, v16, a3
+; RV32-NEXT: vor.vv v16, v16, v12
+; RV32-NEXT: vand.vx v12, v8, a3
+; RV32-NEXT: vsll.vx v12, v12, a6
+; RV32-NEXT: vor.vv v12, v24, v12
+; RV32-NEXT: vsrl.vi v24, v8, 8
+; RV32-NEXT: lui a5, 4080
+; RV32-NEXT: vand.vx v20, v20, a5
+; RV32-NEXT: lui a7, 349525
+; RV32-NEXT: addi a7, a7, 1365
+; RV32-NEXT: vand.vv v24, v24, v0
+; RV32-NEXT: vor.vv v20, v24, v20
+; RV32-NEXT: vsetivli zero, 16, e32, m4, ta, ma
+; RV32-NEXT: vmv.v.x v24, a7
+; RV32-NEXT: vsetivli zero, 8, e64, m4, ta, ma
+; RV32-NEXT: vor.vv v16, v20, v16
+; RV32-NEXT: vand.vx v20, v8, a5
+; RV32-NEXT: vsll.vi v20, v20, 24
+; RV32-NEXT: vand.vv v8, v8, v0
+; RV32-NEXT: vsll.vi v8, v8, 8
+; RV32-NEXT: vor.vv v8, v20, v8
+; RV32-NEXT: addi a7, sp, 264
+; RV32-NEXT: vlse64.v v20, (a7), zero
+; RV32-NEXT: vor.vv v8, v12, v8
+; RV32-NEXT: addi a7, sp, 256
+; RV32-NEXT: vlse64.v v12, (a7), zero
+; RV32-NEXT: vor.vv v8, v8, v16
+; RV32-NEXT: vsrl.vi v16, v8, 4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v28, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v8, v8, v28
+; RV32-NEXT: vand.vv v16, v16, v28
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v16, v8
+; RV32-NEXT: vsrl.vi v16, v8, 2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v4, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v8, v8, v4
+; RV32-NEXT: vand.vv v16, v16, v4
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v8, v16, v8
+; RV32-NEXT: vsrl.vi v16, v8, 1
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v24, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v8, v8, v24
+; RV32-NEXT: vand.vv v16, v16, v24
+; RV32-NEXT: vadd.vv v8, v8, v8
+; RV32-NEXT: vor.vv v8, v16, v8
+; RV32-NEXT: addi a7, sp, 248
+; RV32-NEXT: vlse64.v v16, (a7), zero
+; RV32-NEXT: vand.vv v28, v8, v20
+; RV32-NEXT: addi a7, sp, 240
+; RV32-NEXT: addi a0, sp, 232
+; RV32-NEXT: vlse64.v v20, (a7), zero
+; RV32-NEXT: vlse64.v v24, (a0), zero
+; RV32-NEXT: vand.vv v4, v8, v12
+; RV32-NEXT: vand.vv v0, v8, v16
+; RV32-NEXT: vand.vv v12, v8, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: addi a2, sp, 224
+; RV32-NEXT: addi a7, sp, 216
+; RV32-NEXT: addi a1, sp, 208
+; RV32-NEXT: addi a0, sp, 200
+; RV32-NEXT: vlse64.v v12, (a2), zero
+; RV32-NEXT: vlse64.v v16, (a7), zero
+; RV32-NEXT: vlse64.v v20, (a1), zero
+; RV32-NEXT: vlse64.v v24, (a0), zero
+; RV32-NEXT: vand.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 192
+; RV32-NEXT: addi a1, sp, 184
+; RV32-NEXT: addi a2, sp, 176
+; RV32-NEXT: addi a7, sp, 168
+; RV32-NEXT: vlse64.v v12, (a0), zero
+; RV32-NEXT: vlse64.v v16, (a1), zero
+; RV32-NEXT: vlse64.v v20, (a2), zero
+; RV32-NEXT: vlse64.v v24, (a7), zero
+; RV32-NEXT: vand.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 160
+; RV32-NEXT: addi a1, sp, 152
+; RV32-NEXT: addi a2, sp, 144
+; RV32-NEXT: addi a7, sp, 136
+; RV32-NEXT: vlse64.v v12, (a0), zero
+; RV32-NEXT: vlse64.v v16, (a1), zero
+; RV32-NEXT: vlse64.v v20, (a2), zero
+; RV32-NEXT: vlse64.v v24, (a7), zero
+; RV32-NEXT: vand.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 128
+; RV32-NEXT: addi a1, sp, 120
+; RV32-NEXT: addi a2, sp, 112
+; RV32-NEXT: addi a7, sp, 104
+; RV32-NEXT: vlse64.v v12, (a0), zero
+; RV32-NEXT: vlse64.v v16, (a1), zero
+; RV32-NEXT: vlse64.v v20, (a2), zero
+; RV32-NEXT: vlse64.v v24, (a7), zero
+; RV32-NEXT: vand.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 96
+; RV32-NEXT: addi a1, sp, 88
+; RV32-NEXT: addi a2, sp, 80
+; RV32-NEXT: addi a7, sp, 72
+; RV32-NEXT: vlse64.v v12, (a0), zero
+; RV32-NEXT: vlse64.v v16, (a1), zero
+; RV32-NEXT: vlse64.v v20, (a2), zero
+; RV32-NEXT: vlse64.v v24, (a7), zero
+; RV32-NEXT: vand.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 64
+; RV32-NEXT: addi a1, sp, 56
+; RV32-NEXT: addi a2, sp, 48
+; RV32-NEXT: addi a7, sp, 40
+; RV32-NEXT: vlse64.v v12, (a0), zero
+; RV32-NEXT: vlse64.v v16, (a1), zero
+; RV32-NEXT: vlse64.v v20, (a2), zero
+; RV32-NEXT: vlse64.v v24, (a7), zero
+; RV32-NEXT: vand.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 32
+; RV32-NEXT: addi a1, sp, 24
+; RV32-NEXT: addi a2, sp, 16
+; RV32-NEXT: addi a7, sp, 8
+; RV32-NEXT: vlse64.v v12, (a0), zero
+; RV32-NEXT: vlse64.v v16, (a1), zero
+; RV32-NEXT: vlse64.v v20, (a2), zero
+; RV32-NEXT: vlse64.v v24, (a7), zero
+; RV32-NEXT: vand.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 7
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vi v12, v8, 2
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vi v12, v8, 1
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vi v12, v8, 4
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vi v12, v8, 8
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: li a0, 16
+; RV32-NEXT: vand.vx v12, v8, a0
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: li a0, 32
+; RV32-NEXT: vand.vx v12, v8, a0
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: li a0, 64
+; RV32-NEXT: vand.vx v12, v8, a0
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: li a0, 128
+; RV32-NEXT: vand.vx v12, v8, a0
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: li a0, 256
+; RV32-NEXT: vand.vx v12, v8, a0
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: li a0, 512
+; RV32-NEXT: vand.vx v12, v8, a0
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, t1
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, t6
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: lui a0, 1
+; RV32-NEXT: vand.vx v12, v8, a0
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, t3
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, t5
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, a4
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s1
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: lui a0, 32
+; RV32-NEXT: vand.vx v12, v8, a0
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s2
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s3
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s4
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s5
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s6
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s7
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s8
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s9
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s10
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s11
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, ra
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, t4
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, t2
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: addi a0, sp, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vmul.vv v16, v8, v28
+; RV32-NEXT: vmul.vv v20, v8, v4
+; RV32-NEXT: vmul.vv v24, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v28, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v28, v8, v28
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v4, v8, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v0, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 7
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v8, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v8, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vi v8, v8, 0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: addi a0, sp, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: vxor.vv v8, v8, v20
+; RV32-NEXT: vxor.vv v8, v8, v24
+; RV32-NEXT: vxor.vv v8, v8, v28
+; RV32-NEXT: vxor.vv v8, v8, v4
+; RV32-NEXT: vxor.vv v8, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: vsrl.vx v12, v8, t0
+; RV32-NEXT: vsrl.vx v16, v8, a6
+; RV32-NEXT: vsrl.vi v20, v8, 24
+; RV32-NEXT: vand.vx v16, v16, a3
+; RV32-NEXT: vor.vv v12, v16, v12
+; RV32-NEXT: vsrl.vi v16, v8, 8
+; RV32-NEXT: vand.vx v20, v20, a5
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 8
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vand.vv v16, v16, v24
+; RV32-NEXT: vor.vv v16, v16, v20
+; RV32-NEXT: vand.vx v20, v8, a5
+; RV32-NEXT: vand.vv v24, v8, v24
+; RV32-NEXT: vsll.vi v24, v24, 8
+; RV32-NEXT: vsll.vi v20, v20, 24
+; RV32-NEXT: vor.vv v20, v20, v24
+; RV32-NEXT: vsll.vx v24, v8, t0
+; RV32-NEXT: vand.vx v8, v8, a3
+; RV32-NEXT: vsll.vx v8, v8, a6
+; RV32-NEXT: vor.vv v8, v24, v8
+; RV32-NEXT: vor.vv v12, v16, v12
+; RV32-NEXT: vor.vv v8, v8, v20
+; RV32-NEXT: vor.vv v8, v8, v12
+; RV32-NEXT: vsrl.vi v12, v8, 4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v16
+; RV32-NEXT: vand.vv v12, v12, v16
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v12, v8
+; RV32-NEXT: vsrl.vi v12, v8, 2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v16
+; RV32-NEXT: vand.vv v12, v12, v16
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v8, v12, v8
+; RV32-NEXT: vsrl.vi v12, v8, 1
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v16
+; RV32-NEXT: vand.vv v12, v12, v16
+; RV32-NEXT: vadd.vv v8, v8, v8
+; RV32-NEXT: vor.vv v8, v12, v8
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add sp, sp, a0
+; RV32-NEXT: lw ra, 348(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s0, 344(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s1, 340(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s2, 336(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s3, 332(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s4, 328(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s5, 324(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s6, 320(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s7, 316(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s8, 312(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s9, 308(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s10, 304(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s11, 300(sp) # 4-byte Folded Reload
+; RV32-NEXT: addi sp, sp, 352
+; RV32-NEXT: ret
+;
+; RV64-LABEL: clmulr_v8i64:
+; RV64: # %bb.0:
+; RV64-NEXT: addi sp, sp, -240
+; RV64-NEXT: sd ra, 232(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s0, 224(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s1, 216(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s2, 208(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s3, 200(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s4, 192(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s5, 184(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s6, 176(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s7, 168(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s8, 160(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s9, 152(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s10, 144(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s11, 136(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: sub sp, sp, a0
+; RV64-NEXT: li a6, 56
+; RV64-NEXT: li t0, 40
+; RV64-NEXT: lui t1, 16
+; RV64-NEXT: vsetivli zero, 8, e64, m4, ta, ma
+; RV64-NEXT: vsrl.vi v20, v8, 24
+; RV64-NEXT: lui a7, 4080
+; RV64-NEXT: vsrl.vi v12, v8, 8
+; RV64-NEXT: li s0, 255
+; RV64-NEXT: lui a3, 61681
+; RV64-NEXT: lui a4, 209715
+; RV64-NEXT: lui a5, 349525
+; RV64-NEXT: li a2, 16
+; RV64-NEXT: li a1, 32
+; RV64-NEXT: li a0, 64
+; RV64-NEXT: li s9, 1
+; RV64-NEXT: vsrl.vx v16, v8, a6
+; RV64-NEXT: vsrl.vx v28, v8, t0
+; RV64-NEXT: addi s4, t1, -256
+; RV64-NEXT: vand.vx v24, v20, a7
+; RV64-NEXT: slli s0, s0, 24
+; RV64-NEXT: vand.vx v4, v8, a7
+; RV64-NEXT: vsll.vx v20, v8, a6
+; RV64-NEXT: addi a7, a3, -241
+; RV64-NEXT: addi a6, a4, 819
+; RV64-NEXT: addi a5, a5, 1365
+; RV64-NEXT: slli a3, s9, 11
+; RV64-NEXT: sd a3, 112(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a3, s9, 31
+; RV64-NEXT: sd a3, 104(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a3, s9, 32
+; RV64-NEXT: sd a3, 96(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a3, s9, 33
+; RV64-NEXT: sd a3, 88(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a3, s9, 34
+; RV64-NEXT: sd a3, 80(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a3, s9, 35
+; RV64-NEXT: sd a3, 72(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a3, s9, 36
+; RV64-NEXT: sd a3, 64(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a3, s9, 37
+; RV64-NEXT: sd a3, 56(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a3, s9, 38
+; RV64-NEXT: sd a3, 48(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a3, s9, 39
+; RV64-NEXT: sd a3, 40(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a3, s9, 40
+; RV64-NEXT: sd a3, 32(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a3, s9, 41
+; RV64-NEXT: sd a3, 24(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli s6, s9, 42
+; RV64-NEXT: slli s7, s9, 43
+; RV64-NEXT: slli a3, a7, 32
+; RV64-NEXT: add a7, a7, a3
+; RV64-NEXT: slli a3, a6, 32
+; RV64-NEXT: add a6, a6, a3
+; RV64-NEXT: slli a3, a5, 32
+; RV64-NEXT: add a5, a5, a3
+; RV64-NEXT: slli s8, s9, 44
+; RV64-NEXT: vand.vx v28, v28, s4
+; RV64-NEXT: vand.vx v12, v12, s0
+; RV64-NEXT: vsll.vi v4, v4, 24
+; RV64-NEXT: vand.vx v0, v8, s0
+; RV64-NEXT: vand.vx v8, v8, s4
+; RV64-NEXT: vor.vv v16, v28, v16
+; RV64-NEXT: vor.vv v12, v12, v24
+; RV64-NEXT: vsll.vi v24, v0, 8
+; RV64-NEXT: vsll.vx v8, v8, t0
+; RV64-NEXT: vor.vv v12, v12, v16
+; RV64-NEXT: vor.vv v16, v4, v24
+; RV64-NEXT: vor.vv v8, v20, v8
+; RV64-NEXT: vor.vv v8, v8, v16
+; RV64-NEXT: vor.vv v8, v8, v12
+; RV64-NEXT: vsrl.vi v12, v8, 4
+; RV64-NEXT: vand.vx v8, v8, a7
+; RV64-NEXT: vand.vx v12, v12, a7
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vsrl.vi v12, v8, 2
+; RV64-NEXT: vand.vx v8, v8, a6
+; RV64-NEXT: vand.vx v12, v12, a6
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vsrl.vi v12, v8, 1
+; RV64-NEXT: vand.vx v8, v8, a5
+; RV64-NEXT: vand.vx v12, v12, a5
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vand.vx v12, v8, a2
+; RV64-NEXT: slli s10, s9, 45
+; RV64-NEXT: vand.vx v16, v8, a1
+; RV64-NEXT: slli s11, s9, 46
+; RV64-NEXT: vand.vx v20, v8, a0
+; RV64-NEXT: slli ra, s9, 47
+; RV64-NEXT: slli s3, s9, 48
+; RV64-NEXT: slli s2, s9, 49
+; RV64-NEXT: slli s1, s9, 50
+; RV64-NEXT: slli t6, s9, 51
+; RV64-NEXT: slli t5, s9, 52
+; RV64-NEXT: slli t4, s9, 53
+; RV64-NEXT: slli t3, s9, 54
+; RV64-NEXT: slli t2, s9, 55
+; RV64-NEXT: slli t1, s9, 56
+; RV64-NEXT: slli t0, s9, 57
+; RV64-NEXT: slli a4, s9, 58
+; RV64-NEXT: slli a3, s9, 59
+; RV64-NEXT: slli a2, s9, 60
+; RV64-NEXT: slli a1, s9, 61
+; RV64-NEXT: slli s9, s9, 62
+; RV64-NEXT: li a0, -1
+; RV64-NEXT: slli a0, a0, 63
+; RV64-NEXT: vand.vi v24, v8, 2
+; RV64-NEXT: vand.vi v28, v8, 1
+; RV64-NEXT: vand.vi v4, v8, 4
+; RV64-NEXT: vand.vi v0, v8, 8
+; RV64-NEXT: vmul.vv v24, v8, v24
+; RV64-NEXT: sd a5, 8(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v24, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vmul.vv v24, v8, v28
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 5
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v24, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vmul.vv v24, v8, v4
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v24, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vmul.vv v24, v8, v0
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v24, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vmul.vv v12, v8, v16
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vmul.vv v12, v8, v20
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: li s5, 128
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: li s5, 256
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: li s5, 512
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 6
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: li s5, 1024
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: ld s5, 112(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 1
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 2
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 4
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 8
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 16
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 32
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 5
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 64
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 128
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 256
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 512
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 1024
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 2048
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 4096
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 5
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 8192
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 7
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 16384
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 32768
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 65536
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 131072
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 262144
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: ld s5, 104(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: ld s5, 96(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: ld s5, 88(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 5
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: ld s5, 80(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: ld s5, 72(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: ld s5, 64(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: ld s5, 56(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: ld s5, 48(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: ld s5, 40(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: ld s5, 32(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 2
+; RV64-NEXT: mv a5, s5
+; RV64-NEXT: slli s5, s5, 4
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: ld a5, 8(sp) # 8-byte Folded Reload
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 128
+; RV64-NEXT: vs4r.v v12, (s5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: ld s5, 24(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 128
+; RV64-NEXT: vs4r.v v12, (s5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s6
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 2
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s6, s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s6, s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 128
+; RV64-NEXT: vs4r.v v12, (s5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s7
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 3
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s6, s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 128
+; RV64-NEXT: vs4r.v v12, (s5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s8
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 2
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 2
+; RV64-NEXT: add s6, s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 128
+; RV64-NEXT: vs4r.v v12, (s5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s10
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 4
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 128
+; RV64-NEXT: vs4r.v v12, (s5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s11
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 2
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s6, s6, s5
+; RV64-NEXT: slli s5, s5, 2
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 128
+; RV64-NEXT: vs4r.v v12, (s5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, ra
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 3
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 2
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 128
+; RV64-NEXT: vs4r.v v12, (s5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s3
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr s3, vlenb
+; RV64-NEXT: slli s3, s3, 2
+; RV64-NEXT: mv s5, s3
+; RV64-NEXT: slli s3, s3, 3
+; RV64-NEXT: add s3, s3, s5
+; RV64-NEXT: add s3, sp, s3
+; RV64-NEXT: addi s3, s3, 128
+; RV64-NEXT: vs4r.v v12, (s3) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s2
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr s2, vlenb
+; RV64-NEXT: slli s2, s2, 5
+; RV64-NEXT: add s2, sp, s2
+; RV64-NEXT: addi s2, s2, 128
+; RV64-NEXT: vs4r.v v12, (s2) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s1
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr s1, vlenb
+; RV64-NEXT: slli s1, s1, 2
+; RV64-NEXT: mv s2, s1
+; RV64-NEXT: slli s1, s1, 1
+; RV64-NEXT: add s2, s2, s1
+; RV64-NEXT: slli s1, s1, 1
+; RV64-NEXT: add s1, s1, s2
+; RV64-NEXT: add s1, sp, s1
+; RV64-NEXT: addi s1, s1, 128
+; RV64-NEXT: vs4r.v v12, (s1) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t6
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 3
+; RV64-NEXT: mv s1, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s1
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 128
+; RV64-NEXT: vs4r.v v12, (t6) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr t5, vlenb
+; RV64-NEXT: slli t5, t5, 2
+; RV64-NEXT: mv t6, t5
+; RV64-NEXT: slli t5, t5, 2
+; RV64-NEXT: add t5, t5, t6
+; RV64-NEXT: add t5, sp, t5
+; RV64-NEXT: addi t5, t5, 128
+; RV64-NEXT: vs4r.v v12, (t5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t4
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr t4, vlenb
+; RV64-NEXT: slli t4, t4, 4
+; RV64-NEXT: add t4, sp, t4
+; RV64-NEXT: addi t4, t4, 128
+; RV64-NEXT: vs4r.v v12, (t4) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t3
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr t3, vlenb
+; RV64-NEXT: slli t3, t3, 2
+; RV64-NEXT: mv t4, t3
+; RV64-NEXT: slli t3, t3, 1
+; RV64-NEXT: add t3, t3, t4
+; RV64-NEXT: add t3, sp, t3
+; RV64-NEXT: addi t3, t3, 128
+; RV64-NEXT: vs4r.v v12, (t3) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t2
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr t2, vlenb
+; RV64-NEXT: slli t2, t2, 3
+; RV64-NEXT: add t2, sp, t2
+; RV64-NEXT: addi t2, t2, 128
+; RV64-NEXT: vs4r.v v12, (t2) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t1
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr t1, vlenb
+; RV64-NEXT: slli t1, t1, 2
+; RV64-NEXT: add t1, sp, t1
+; RV64-NEXT: addi t1, t1, 128
+; RV64-NEXT: vs4r.v v12, (t1) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t0
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: addi t0, sp, 128
+; RV64-NEXT: vs4r.v v12, (t0) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, a4
+; RV64-NEXT: vmul.vv v28, v8, v12
+; RV64-NEXT: vand.vx v12, v8, a3
+; RV64-NEXT: vmul.vv v24, v8, v12
+; RV64-NEXT: vand.vx v12, v8, a2
+; RV64-NEXT: vmul.vv v20, v8, v12
+; RV64-NEXT: vand.vx v12, v8, a1
+; RV64-NEXT: vmul.vv v16, v8, v12
+; RV64-NEXT: vand.vx v12, v8, s9
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: vand.vx v0, v8, a0
+; RV64-NEXT: vmul.vv v8, v8, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v0, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v4, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 6
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 7
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: addi a0, sp, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v4, v0, v4
+; RV64-NEXT: vxor.vv v28, v4, v28
+; RV64-NEXT: vxor.vv v24, v28, v24
+; RV64-NEXT: vxor.vv v20, v24, v20
+; RV64-NEXT: vxor.vv v16, v20, v16
+; RV64-NEXT: vxor.vv v12, v16, v12
+; RV64-NEXT: vxor.vv v8, v12, v8
+; RV64-NEXT: li a0, 56
+; RV64-NEXT: vsrl.vx v12, v8, a0
+; RV64-NEXT: li a1, 40
+; RV64-NEXT: vsrl.vx v16, v8, a1
+; RV64-NEXT: vsrl.vi v20, v8, 24
+; RV64-NEXT: vsrl.vi v24, v8, 8
+; RV64-NEXT: vand.vx v16, v16, s4
+; RV64-NEXT: vor.vv v12, v16, v12
+; RV64-NEXT: vand.vx v16, v8, s0
+; RV64-NEXT: lui a2, 4080
+; RV64-NEXT: vand.vx v20, v20, a2
+; RV64-NEXT: vand.vx v24, v24, s0
+; RV64-NEXT: vor.vv v20, v24, v20
+; RV64-NEXT: vand.vx v24, v8, a2
+; RV64-NEXT: vsll.vi v16, v16, 8
+; RV64-NEXT: vsll.vi v24, v24, 24
+; RV64-NEXT: vor.vv v16, v24, v16
+; RV64-NEXT: vsll.vx v24, v8, a0
+; RV64-NEXT: vand.vx v8, v8, s4
+; RV64-NEXT: vsll.vx v8, v8, a1
+; RV64-NEXT: vor.vv v8, v24, v8
+; RV64-NEXT: vor.vv v12, v20, v12
+; RV64-NEXT: vor.vv v8, v8, v16
+; RV64-NEXT: vor.vv v8, v8, v12
+; RV64-NEXT: vsrl.vi v12, v8, 4
+; RV64-NEXT: vand.vx v8, v8, a7
+; RV64-NEXT: vand.vx v12, v12, a7
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vsrl.vi v12, v8, 2
+; RV64-NEXT: vand.vx v8, v8, a6
+; RV64-NEXT: vand.vx v12, v12, a6
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vsrl.vi v12, v8, 1
+; RV64-NEXT: vand.vx v8, v8, a5
+; RV64-NEXT: vand.vx v12, v12, a5
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add sp, sp, a0
+; RV64-NEXT: ld ra, 232(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s0, 224(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s1, 216(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s2, 208(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s3, 200(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s4, 192(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s5, 184(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s6, 176(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s7, 168(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s8, 160(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s9, 152(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s10, 144(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s11, 136(sp) # 8-byte Folded Reload
+; RV64-NEXT: addi sp, sp, 240
+; RV64-NEXT: ret
+ %a = call <8 x i64> @llvm.clmulr.v8i64(<8 x i64> %x, <8 x i64> %y)
+ ret <8 x i64> %a
+}
+
+define <1 x i32> @clmulh_v1i32(<1 x i32> %x, <1 x i32> %y) nounwind {
+; CHECK-LABEL: clmulh_v1i32:
+; CHECK: # %bb.0:
+; CHECK-NEXT: addi sp, sp, -16
+; CHECK-NEXT: csrr a0, vlenb
+; CHECK-NEXT: sub sp, sp, a0
+; CHECK-NEXT: vsetivli zero, 1, e32, mf2, ta, ma
+; CHECK-NEXT: vsrl.vi v9, v8, 8
+; CHECK-NEXT: lui a4, 16
+; CHECK-NEXT: vsrl.vi v10, v8, 24
+; CHECK-NEXT: vsll.vi v11, v8, 24
+; CHECK-NEXT: lui a0, 61681
+; CHECK-NEXT: lui a1, 209715
+; CHECK-NEXT: lui a5, 349525
+; CHECK-NEXT: li a6, 16
+; CHECK-NEXT: addi a3, a4, -256
+; CHECK-NEXT: addi a2, a0, -241
+; CHECK-NEXT: addi a1, a1, 819
+; CHECK-NEXT: addi a0, a5, 1365
+; CHECK-NEXT: vand.vx v9, v9, a3
+; CHECK-NEXT: vand.vx v8, v8, a3
+; CHECK-NEXT: vor.vv v9, v9, v10
+; CHECK-NEXT: vsll.vi v8, v8, 8
+; CHECK-NEXT: vor.vv v8, v11, v8
+; CHECK-NEXT: vor.vv v8, v8, v9
+; CHECK-NEXT: vsrl.vi v9, v8, 4
+; CHECK-NEXT: vand.vx v8, v8, a2
+; CHECK-NEXT: vand.vx v9, v9, a2
+; CHECK-NEXT: vsll.vi v8, v8, 4
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v9, v8, 2
+; CHECK-NEXT: vand.vx v8, v8, a1
+; CHECK-NEXT: vand.vx v9, v9, a1
+; CHECK-NEXT: vsll.vi v8, v8, 2
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v9, v8, 1
+; CHECK-NEXT: vand.vx v8, v8, a0
+; CHECK-NEXT: vand.vx v9, v9, a0
+; CHECK-NEXT: vadd.vv v8, v8, v8
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vand.vx v9, v8, a6
+; CHECK-NEXT: li a5, 32
+; CHECK-NEXT: vand.vx v10, v8, a5
+; CHECK-NEXT: li a5, 64
+; CHECK-NEXT: vand.vx v11, v8, a5
+; CHECK-NEXT: li a5, 128
+; CHECK-NEXT: vand.vx v12, v8, a5
+; CHECK-NEXT: li a5, 256
+; CHECK-NEXT: vand.vx v13, v8, a5
+; CHECK-NEXT: li a5, 512
+; CHECK-NEXT: vand.vx v14, v8, a5
+; CHECK-NEXT: li a5, 1024
+; CHECK-NEXT: vand.vx v15, v8, a5
+; CHECK-NEXT: li a5, 1
+; CHECK-NEXT: slli a5, a5, 11
+; CHECK-NEXT: vand.vx v16, v8, a5
+; CHECK-NEXT: lui a5, 1
+; CHECK-NEXT: vand.vx v17, v8, a5
+; CHECK-NEXT: lui a5, 2
+; CHECK-NEXT: vand.vx v18, v8, a5
+; CHECK-NEXT: lui a5, 4
+; CHECK-NEXT: vand.vx v19, v8, a5
+; CHECK-NEXT: lui a5, 8
+; CHECK-NEXT: vand.vx v20, v8, a5
+; CHECK-NEXT: lui a5, 32
+; CHECK-NEXT: vand.vx v21, v8, a4
+; CHECK-NEXT: lui a4, 64
+; CHECK-NEXT: vand.vx v22, v8, a5
+; CHECK-NEXT: lui a5, 128
+; CHECK-NEXT: vand.vx v23, v8, a4
+; CHECK-NEXT: lui a4, 256
+; CHECK-NEXT: vand.vx v24, v8, a5
+; CHECK-NEXT: lui a5, 512
+; CHECK-NEXT: vand.vx v25, v8, a4
+; CHECK-NEXT: lui a4, 1024
+; CHECK-NEXT: vand.vx v26, v8, a5
+; CHECK-NEXT: lui a5, 2048
+; CHECK-NEXT: vand.vx v27, v8, a4
+; CHECK-NEXT: lui a4, 4096
+; CHECK-NEXT: vand.vx v28, v8, a5
+; CHECK-NEXT: lui a5, 8192
+; CHECK-NEXT: vand.vx v29, v8, a4
+; CHECK-NEXT: lui a4, 16384
+; CHECK-NEXT: vand.vx v30, v8, a5
+; CHECK-NEXT: lui a5, 32768
+; CHECK-NEXT: vand.vx v31, v8, a4
+; CHECK-NEXT: lui a4, 65536
+; CHECK-NEXT: vand.vx v7, v8, a5
+; CHECK-NEXT: lui a5, 131072
+; CHECK-NEXT: vand.vx v6, v8, a4
+; CHECK-NEXT: lui a4, 262144
+; CHECK-NEXT: vand.vx v5, v8, a5
+; CHECK-NEXT: lui a5, 524288
+; CHECK-NEXT: vand.vi v4, v8, 2
+; CHECK-NEXT: vand.vi v3, v8, 1
+; CHECK-NEXT: vand.vi v2, v8, 4
+; CHECK-NEXT: vand.vi v1, v8, 8
+; CHECK-NEXT: vand.vx v0, v8, a4
+; CHECK-NEXT: vmul.vv v4, v8, v4
+; CHECK-NEXT: addi a4, sp, 16
+; CHECK-NEXT: vs1r.v v4, (a4) # vscale x 8-byte Folded Spill
+; CHECK-NEXT: vmul.vv v3, v8, v3
+; CHECK-NEXT: vmul.vv v2, v8, v2
+; CHECK-NEXT: vmul.vv v1, v8, v1
+; CHECK-NEXT: vmul.vv v9, v8, v9
+; CHECK-NEXT: vmul.vv v10, v8, v10
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vmul.vv v12, v8, v12
+; CHECK-NEXT: vmul.vv v13, v8, v13
+; CHECK-NEXT: vmul.vv v14, v8, v14
+; CHECK-NEXT: vmul.vv v15, v8, v15
+; CHECK-NEXT: vmul.vv v16, v8, v16
+; CHECK-NEXT: vmul.vv v17, v8, v17
+; CHECK-NEXT: vmul.vv v18, v8, v18
+; CHECK-NEXT: vmul.vv v19, v8, v19
+; CHECK-NEXT: vmul.vv v20, v8, v20
+; CHECK-NEXT: vmul.vv v21, v8, v21
+; CHECK-NEXT: vmul.vv v22, v8, v22
+; CHECK-NEXT: vmul.vv v23, v8, v23
+; CHECK-NEXT: vmul.vv v24, v8, v24
+; CHECK-NEXT: vmul.vv v25, v8, v25
+; CHECK-NEXT: vmul.vv v26, v8, v26
+; CHECK-NEXT: vmul.vv v27, v8, v27
+; CHECK-NEXT: vmul.vv v28, v8, v28
+; CHECK-NEXT: vmul.vv v29, v8, v29
+; CHECK-NEXT: vmul.vv v30, v8, v30
+; CHECK-NEXT: vmul.vv v31, v8, v31
+; CHECK-NEXT: vmul.vv v7, v8, v7
+; CHECK-NEXT: vmul.vv v6, v8, v6
+; CHECK-NEXT: vmul.vv v5, v8, v5
+; CHECK-NEXT: vmul.vv v0, v8, v0
+; CHECK-NEXT: vand.vx v4, v8, a5
+; CHECK-NEXT: vmul.vv v8, v8, v4
+; CHECK-NEXT: vl1r.v v4, (a4) # vscale x 8-byte Folded Reload
+; CHECK-NEXT: vxor.vv v4, v3, v4
+; CHECK-NEXT: vxor.vv v4, v4, v2
+; CHECK-NEXT: vxor.vv v4, v4, v1
+; CHECK-NEXT: vxor.vv v9, v4, v9
+; CHECK-NEXT: vxor.vv v9, v9, v10
+; CHECK-NEXT: vxor.vv v9, v9, v11
+; CHECK-NEXT: vxor.vv v9, v9, v12
+; CHECK-NEXT: vxor.vv v9, v9, v13
+; CHECK-NEXT: vxor.vv v9, v9, v14
+; CHECK-NEXT: vxor.vv v9, v9, v15
+; CHECK-NEXT: vxor.vv v9, v9, v16
+; CHECK-NEXT: vxor.vv v9, v9, v17
+; CHECK-NEXT: vxor.vv v9, v9, v18
+; CHECK-NEXT: vxor.vv v9, v9, v19
+; CHECK-NEXT: vxor.vv v9, v9, v20
+; CHECK-NEXT: vxor.vv v9, v9, v21
+; CHECK-NEXT: vxor.vv v9, v9, v22
+; CHECK-NEXT: vxor.vv v9, v9, v23
+; CHECK-NEXT: vxor.vv v9, v9, v24
+; CHECK-NEXT: vxor.vv v9, v9, v25
+; CHECK-NEXT: vxor.vv v9, v9, v26
+; CHECK-NEXT: vxor.vv v9, v9, v27
+; CHECK-NEXT: vxor.vv v9, v9, v28
+; CHECK-NEXT: vxor.vv v9, v9, v29
+; CHECK-NEXT: vxor.vv v9, v9, v30
+; CHECK-NEXT: vxor.vv v9, v9, v31
+; CHECK-NEXT: vxor.vv v9, v9, v7
+; CHECK-NEXT: vxor.vv v9, v9, v6
+; CHECK-NEXT: vxor.vv v9, v9, v5
+; CHECK-NEXT: vxor.vv v9, v9, v0
+; CHECK-NEXT: vxor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v9, v8, 8
+; CHECK-NEXT: vsrl.vi v10, v8, 24
+; CHECK-NEXT: vand.vx v9, v9, a3
+; CHECK-NEXT: vor.vv v9, v9, v10
+; CHECK-NEXT: vsll.vi v10, v8, 24
+; CHECK-NEXT: vand.vx v8, v8, a3
+; CHECK-NEXT: vsll.vi v8, v8, 8
+; CHECK-NEXT: vor.vv v8, v10, v8
+; CHECK-NEXT: vor.vv v8, v8, v9
+; CHECK-NEXT: vsrl.vi v9, v8, 4
+; CHECK-NEXT: vand.vx v8, v8, a2
+; CHECK-NEXT: vand.vx v9, v9, a2
+; CHECK-NEXT: vsll.vi v8, v8, 4
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v9, v8, 2
+; CHECK-NEXT: vand.vx v8, v8, a1
+; CHECK-NEXT: vand.vx v9, v9, a1
+; CHECK-NEXT: vsll.vi v8, v8, 2
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v9, v8, 1
+; CHECK-NEXT: vand.vx v8, v8, a0
+; CHECK-NEXT: vand.vx v9, v9, a0
+; CHECK-NEXT: vadd.vv v8, v8, v8
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v8, v8, 1
+; CHECK-NEXT: csrr a0, vlenb
+; CHECK-NEXT: add sp, sp, a0
+; CHECK-NEXT: addi sp, sp, 16
+; CHECK-NEXT: ret
+ %a = call <1 x i32> @llvm.clmulh.v1i32(<1 x i32> %x, <1 x i32> %y)
+ ret <1 x i32> %a
+}
+
+define <2 x i32> @clmulh_v2i32(<2 x i32> %x, <2 x i32> %y) nounwind {
+; CHECK-LABEL: clmulh_v2i32:
+; CHECK: # %bb.0:
+; CHECK-NEXT: addi sp, sp, -16
+; CHECK-NEXT: csrr a0, vlenb
+; CHECK-NEXT: sub sp, sp, a0
+; CHECK-NEXT: vsetivli zero, 2, e32, mf2, ta, ma
+; CHECK-NEXT: vsrl.vi v9, v8, 8
+; CHECK-NEXT: lui a4, 16
+; CHECK-NEXT: vsrl.vi v10, v8, 24
+; CHECK-NEXT: vsll.vi v11, v8, 24
+; CHECK-NEXT: lui a0, 61681
+; CHECK-NEXT: lui a1, 209715
+; CHECK-NEXT: lui a5, 349525
+; CHECK-NEXT: li a6, 16
+; CHECK-NEXT: addi a3, a4, -256
+; CHECK-NEXT: addi a2, a0, -241
+; CHECK-NEXT: addi a1, a1, 819
+; CHECK-NEXT: addi a0, a5, 1365
+; CHECK-NEXT: vand.vx v9, v9, a3
+; CHECK-NEXT: vand.vx v8, v8, a3
+; CHECK-NEXT: vor.vv v9, v9, v10
+; CHECK-NEXT: vsll.vi v8, v8, 8
+; CHECK-NEXT: vor.vv v8, v11, v8
+; CHECK-NEXT: vor.vv v8, v8, v9
+; CHECK-NEXT: vsrl.vi v9, v8, 4
+; CHECK-NEXT: vand.vx v8, v8, a2
+; CHECK-NEXT: vand.vx v9, v9, a2
+; CHECK-NEXT: vsll.vi v8, v8, 4
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v9, v8, 2
+; CHECK-NEXT: vand.vx v8, v8, a1
+; CHECK-NEXT: vand.vx v9, v9, a1
+; CHECK-NEXT: vsll.vi v8, v8, 2
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v9, v8, 1
+; CHECK-NEXT: vand.vx v8, v8, a0
+; CHECK-NEXT: vand.vx v9, v9, a0
+; CHECK-NEXT: vadd.vv v8, v8, v8
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vand.vx v9, v8, a6
+; CHECK-NEXT: li a5, 32
+; CHECK-NEXT: vand.vx v10, v8, a5
+; CHECK-NEXT: li a5, 64
+; CHECK-NEXT: vand.vx v11, v8, a5
+; CHECK-NEXT: li a5, 128
+; CHECK-NEXT: vand.vx v12, v8, a5
+; CHECK-NEXT: li a5, 256
+; CHECK-NEXT: vand.vx v13, v8, a5
+; CHECK-NEXT: li a5, 512
+; CHECK-NEXT: vand.vx v14, v8, a5
+; CHECK-NEXT: li a5, 1024
+; CHECK-NEXT: vand.vx v15, v8, a5
+; CHECK-NEXT: li a5, 1
+; CHECK-NEXT: slli a5, a5, 11
+; CHECK-NEXT: vand.vx v16, v8, a5
+; CHECK-NEXT: lui a5, 1
+; CHECK-NEXT: vand.vx v17, v8, a5
+; CHECK-NEXT: lui a5, 2
+; CHECK-NEXT: vand.vx v18, v8, a5
+; CHECK-NEXT: lui a5, 4
+; CHECK-NEXT: vand.vx v19, v8, a5
+; CHECK-NEXT: lui a5, 8
+; CHECK-NEXT: vand.vx v20, v8, a5
+; CHECK-NEXT: lui a5, 32
+; CHECK-NEXT: vand.vx v21, v8, a4
+; CHECK-NEXT: lui a4, 64
+; CHECK-NEXT: vand.vx v22, v8, a5
+; CHECK-NEXT: lui a5, 128
+; CHECK-NEXT: vand.vx v23, v8, a4
+; CHECK-NEXT: lui a4, 256
+; CHECK-NEXT: vand.vx v24, v8, a5
+; CHECK-NEXT: lui a5, 512
+; CHECK-NEXT: vand.vx v25, v8, a4
+; CHECK-NEXT: lui a4, 1024
+; CHECK-NEXT: vand.vx v26, v8, a5
+; CHECK-NEXT: lui a5, 2048
+; CHECK-NEXT: vand.vx v27, v8, a4
+; CHECK-NEXT: lui a4, 4096
+; CHECK-NEXT: vand.vx v28, v8, a5
+; CHECK-NEXT: lui a5, 8192
+; CHECK-NEXT: vand.vx v29, v8, a4
+; CHECK-NEXT: lui a4, 16384
+; CHECK-NEXT: vand.vx v30, v8, a5
+; CHECK-NEXT: lui a5, 32768
+; CHECK-NEXT: vand.vx v31, v8, a4
+; CHECK-NEXT: lui a4, 65536
+; CHECK-NEXT: vand.vx v7, v8, a5
+; CHECK-NEXT: lui a5, 131072
+; CHECK-NEXT: vand.vx v6, v8, a4
+; CHECK-NEXT: lui a4, 262144
+; CHECK-NEXT: vand.vx v5, v8, a5
+; CHECK-NEXT: lui a5, 524288
+; CHECK-NEXT: vand.vi v4, v8, 2
+; CHECK-NEXT: vand.vi v3, v8, 1
+; CHECK-NEXT: vand.vi v2, v8, 4
+; CHECK-NEXT: vand.vi v1, v8, 8
+; CHECK-NEXT: vand.vx v0, v8, a4
+; CHECK-NEXT: vmul.vv v4, v8, v4
+; CHECK-NEXT: addi a4, sp, 16
+; CHECK-NEXT: vs1r.v v4, (a4) # vscale x 8-byte Folded Spill
+; CHECK-NEXT: vmul.vv v3, v8, v3
+; CHECK-NEXT: vmul.vv v2, v8, v2
+; CHECK-NEXT: vmul.vv v1, v8, v1
+; CHECK-NEXT: vmul.vv v9, v8, v9
+; CHECK-NEXT: vmul.vv v10, v8, v10
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vmul.vv v12, v8, v12
+; CHECK-NEXT: vmul.vv v13, v8, v13
+; CHECK-NEXT: vmul.vv v14, v8, v14
+; CHECK-NEXT: vmul.vv v15, v8, v15
+; CHECK-NEXT: vmul.vv v16, v8, v16
+; CHECK-NEXT: vmul.vv v17, v8, v17
+; CHECK-NEXT: vmul.vv v18, v8, v18
+; CHECK-NEXT: vmul.vv v19, v8, v19
+; CHECK-NEXT: vmul.vv v20, v8, v20
+; CHECK-NEXT: vmul.vv v21, v8, v21
+; CHECK-NEXT: vmul.vv v22, v8, v22
+; CHECK-NEXT: vmul.vv v23, v8, v23
+; CHECK-NEXT: vmul.vv v24, v8, v24
+; CHECK-NEXT: vmul.vv v25, v8, v25
+; CHECK-NEXT: vmul.vv v26, v8, v26
+; CHECK-NEXT: vmul.vv v27, v8, v27
+; CHECK-NEXT: vmul.vv v28, v8, v28
+; CHECK-NEXT: vmul.vv v29, v8, v29
+; CHECK-NEXT: vmul.vv v30, v8, v30
+; CHECK-NEXT: vmul.vv v31, v8, v31
+; CHECK-NEXT: vmul.vv v7, v8, v7
+; CHECK-NEXT: vmul.vv v6, v8, v6
+; CHECK-NEXT: vmul.vv v5, v8, v5
+; CHECK-NEXT: vmul.vv v0, v8, v0
+; CHECK-NEXT: vand.vx v4, v8, a5
+; CHECK-NEXT: vmul.vv v8, v8, v4
+; CHECK-NEXT: vl1r.v v4, (a4) # vscale x 8-byte Folded Reload
+; CHECK-NEXT: vxor.vv v4, v3, v4
+; CHECK-NEXT: vxor.vv v4, v4, v2
+; CHECK-NEXT: vxor.vv v4, v4, v1
+; CHECK-NEXT: vxor.vv v9, v4, v9
+; CHECK-NEXT: vxor.vv v9, v9, v10
+; CHECK-NEXT: vxor.vv v9, v9, v11
+; CHECK-NEXT: vxor.vv v9, v9, v12
+; CHECK-NEXT: vxor.vv v9, v9, v13
+; CHECK-NEXT: vxor.vv v9, v9, v14
+; CHECK-NEXT: vxor.vv v9, v9, v15
+; CHECK-NEXT: vxor.vv v9, v9, v16
+; CHECK-NEXT: vxor.vv v9, v9, v17
+; CHECK-NEXT: vxor.vv v9, v9, v18
+; CHECK-NEXT: vxor.vv v9, v9, v19
+; CHECK-NEXT: vxor.vv v9, v9, v20
+; CHECK-NEXT: vxor.vv v9, v9, v21
+; CHECK-NEXT: vxor.vv v9, v9, v22
+; CHECK-NEXT: vxor.vv v9, v9, v23
+; CHECK-NEXT: vxor.vv v9, v9, v24
+; CHECK-NEXT: vxor.vv v9, v9, v25
+; CHECK-NEXT: vxor.vv v9, v9, v26
+; CHECK-NEXT: vxor.vv v9, v9, v27
+; CHECK-NEXT: vxor.vv v9, v9, v28
+; CHECK-NEXT: vxor.vv v9, v9, v29
+; CHECK-NEXT: vxor.vv v9, v9, v30
+; CHECK-NEXT: vxor.vv v9, v9, v31
+; CHECK-NEXT: vxor.vv v9, v9, v7
+; CHECK-NEXT: vxor.vv v9, v9, v6
+; CHECK-NEXT: vxor.vv v9, v9, v5
+; CHECK-NEXT: vxor.vv v9, v9, v0
+; CHECK-NEXT: vxor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v9, v8, 8
+; CHECK-NEXT: vsrl.vi v10, v8, 24
+; CHECK-NEXT: vand.vx v9, v9, a3
+; CHECK-NEXT: vor.vv v9, v9, v10
+; CHECK-NEXT: vsll.vi v10, v8, 24
+; CHECK-NEXT: vand.vx v8, v8, a3
+; CHECK-NEXT: vsll.vi v8, v8, 8
+; CHECK-NEXT: vor.vv v8, v10, v8
+; CHECK-NEXT: vor.vv v8, v8, v9
+; CHECK-NEXT: vsrl.vi v9, v8, 4
+; CHECK-NEXT: vand.vx v8, v8, a2
+; CHECK-NEXT: vand.vx v9, v9, a2
+; CHECK-NEXT: vsll.vi v8, v8, 4
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v9, v8, 2
+; CHECK-NEXT: vand.vx v8, v8, a1
+; CHECK-NEXT: vand.vx v9, v9, a1
+; CHECK-NEXT: vsll.vi v8, v8, 2
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v9, v8, 1
+; CHECK-NEXT: vand.vx v8, v8, a0
+; CHECK-NEXT: vand.vx v9, v9, a0
+; CHECK-NEXT: vadd.vv v8, v8, v8
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v8, v8, 1
+; CHECK-NEXT: csrr a0, vlenb
+; CHECK-NEXT: add sp, sp, a0
+; CHECK-NEXT: addi sp, sp, 16
+; CHECK-NEXT: ret
+ %a = call <2 x i32> @llvm.clmulh.v2i32(<2 x i32> %x, <2 x i32> %y)
+ ret <2 x i32> %a
+}
+
+define <4 x i32> @clmulh_v4i32(<4 x i32> %x, <4 x i32> %y) nounwind {
+; CHECK-LABEL: clmulh_v4i32:
+; CHECK: # %bb.0:
+; CHECK-NEXT: addi sp, sp, -16
+; CHECK-NEXT: csrr a0, vlenb
+; CHECK-NEXT: sub sp, sp, a0
+; CHECK-NEXT: vsetivli zero, 4, e32, m1, ta, ma
+; CHECK-NEXT: vsrl.vi v9, v8, 8
+; CHECK-NEXT: lui a4, 16
+; CHECK-NEXT: vsrl.vi v10, v8, 24
+; CHECK-NEXT: vsll.vi v11, v8, 24
+; CHECK-NEXT: lui a0, 61681
+; CHECK-NEXT: lui a1, 209715
+; CHECK-NEXT: lui a5, 349525
+; CHECK-NEXT: li a6, 16
+; CHECK-NEXT: addi a3, a4, -256
+; CHECK-NEXT: addi a2, a0, -241
+; CHECK-NEXT: addi a1, a1, 819
+; CHECK-NEXT: addi a0, a5, 1365
+; CHECK-NEXT: vand.vx v9, v9, a3
+; CHECK-NEXT: vand.vx v8, v8, a3
+; CHECK-NEXT: vor.vv v9, v9, v10
+; CHECK-NEXT: vsll.vi v8, v8, 8
+; CHECK-NEXT: vor.vv v8, v11, v8
+; CHECK-NEXT: vor.vv v8, v8, v9
+; CHECK-NEXT: vsrl.vi v9, v8, 4
+; CHECK-NEXT: vand.vx v8, v8, a2
+; CHECK-NEXT: vand.vx v9, v9, a2
+; CHECK-NEXT: vsll.vi v8, v8, 4
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v9, v8, 2
+; CHECK-NEXT: vand.vx v8, v8, a1
+; CHECK-NEXT: vand.vx v9, v9, a1
+; CHECK-NEXT: vsll.vi v8, v8, 2
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v9, v8, 1
+; CHECK-NEXT: vand.vx v8, v8, a0
+; CHECK-NEXT: vand.vx v9, v9, a0
+; CHECK-NEXT: vadd.vv v8, v8, v8
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vand.vx v9, v8, a6
+; CHECK-NEXT: li a5, 32
+; CHECK-NEXT: vand.vx v10, v8, a5
+; CHECK-NEXT: li a5, 64
+; CHECK-NEXT: vand.vx v11, v8, a5
+; CHECK-NEXT: li a5, 128
+; CHECK-NEXT: vand.vx v12, v8, a5
+; CHECK-NEXT: li a5, 256
+; CHECK-NEXT: vand.vx v13, v8, a5
+; CHECK-NEXT: li a5, 512
+; CHECK-NEXT: vand.vx v14, v8, a5
+; CHECK-NEXT: li a5, 1024
+; CHECK-NEXT: vand.vx v15, v8, a5
+; CHECK-NEXT: li a5, 1
+; CHECK-NEXT: slli a5, a5, 11
+; CHECK-NEXT: vand.vx v16, v8, a5
+; CHECK-NEXT: lui a5, 1
+; CHECK-NEXT: vand.vx v17, v8, a5
+; CHECK-NEXT: lui a5, 2
+; CHECK-NEXT: vand.vx v18, v8, a5
+; CHECK-NEXT: lui a5, 4
+; CHECK-NEXT: vand.vx v19, v8, a5
+; CHECK-NEXT: lui a5, 8
+; CHECK-NEXT: vand.vx v20, v8, a5
+; CHECK-NEXT: lui a5, 32
+; CHECK-NEXT: vand.vx v21, v8, a4
+; CHECK-NEXT: lui a4, 64
+; CHECK-NEXT: vand.vx v22, v8, a5
+; CHECK-NEXT: lui a5, 128
+; CHECK-NEXT: vand.vx v23, v8, a4
+; CHECK-NEXT: lui a4, 256
+; CHECK-NEXT: vand.vx v24, v8, a5
+; CHECK-NEXT: lui a5, 512
+; CHECK-NEXT: vand.vx v25, v8, a4
+; CHECK-NEXT: lui a4, 1024
+; CHECK-NEXT: vand.vx v26, v8, a5
+; CHECK-NEXT: lui a5, 2048
+; CHECK-NEXT: vand.vx v27, v8, a4
+; CHECK-NEXT: lui a4, 4096
+; CHECK-NEXT: vand.vx v28, v8, a5
+; CHECK-NEXT: lui a5, 8192
+; CHECK-NEXT: vand.vx v29, v8, a4
+; CHECK-NEXT: lui a4, 16384
+; CHECK-NEXT: vand.vx v30, v8, a5
+; CHECK-NEXT: lui a5, 32768
+; CHECK-NEXT: vand.vx v31, v8, a4
+; CHECK-NEXT: lui a4, 65536
+; CHECK-NEXT: vand.vx v7, v8, a5
+; CHECK-NEXT: lui a5, 131072
+; CHECK-NEXT: vand.vx v6, v8, a4
+; CHECK-NEXT: lui a4, 262144
+; CHECK-NEXT: vand.vx v5, v8, a5
+; CHECK-NEXT: lui a5, 524288
+; CHECK-NEXT: vand.vi v4, v8, 2
+; CHECK-NEXT: vand.vi v3, v8, 1
+; CHECK-NEXT: vand.vi v2, v8, 4
+; CHECK-NEXT: vand.vi v1, v8, 8
+; CHECK-NEXT: vand.vx v0, v8, a4
+; CHECK-NEXT: vmul.vv v4, v8, v4
+; CHECK-NEXT: addi a4, sp, 16
+; CHECK-NEXT: vs1r.v v4, (a4) # vscale x 8-byte Folded Spill
+; CHECK-NEXT: vmul.vv v3, v8, v3
+; CHECK-NEXT: vmul.vv v2, v8, v2
+; CHECK-NEXT: vmul.vv v1, v8, v1
+; CHECK-NEXT: vmul.vv v9, v8, v9
+; CHECK-NEXT: vmul.vv v10, v8, v10
+; CHECK-NEXT: vmul.vv v11, v8, v11
+; CHECK-NEXT: vmul.vv v12, v8, v12
+; CHECK-NEXT: vmul.vv v13, v8, v13
+; CHECK-NEXT: vmul.vv v14, v8, v14
+; CHECK-NEXT: vmul.vv v15, v8, v15
+; CHECK-NEXT: vmul.vv v16, v8, v16
+; CHECK-NEXT: vmul.vv v17, v8, v17
+; CHECK-NEXT: vmul.vv v18, v8, v18
+; CHECK-NEXT: vmul.vv v19, v8, v19
+; CHECK-NEXT: vmul.vv v20, v8, v20
+; CHECK-NEXT: vmul.vv v21, v8, v21
+; CHECK-NEXT: vmul.vv v22, v8, v22
+; CHECK-NEXT: vmul.vv v23, v8, v23
+; CHECK-NEXT: vmul.vv v24, v8, v24
+; CHECK-NEXT: vmul.vv v25, v8, v25
+; CHECK-NEXT: vmul.vv v26, v8, v26
+; CHECK-NEXT: vmul.vv v27, v8, v27
+; CHECK-NEXT: vmul.vv v28, v8, v28
+; CHECK-NEXT: vmul.vv v29, v8, v29
+; CHECK-NEXT: vmul.vv v30, v8, v30
+; CHECK-NEXT: vmul.vv v31, v8, v31
+; CHECK-NEXT: vmul.vv v7, v8, v7
+; CHECK-NEXT: vmul.vv v6, v8, v6
+; CHECK-NEXT: vmul.vv v5, v8, v5
+; CHECK-NEXT: vmul.vv v0, v8, v0
+; CHECK-NEXT: vand.vx v4, v8, a5
+; CHECK-NEXT: vmul.vv v8, v8, v4
+; CHECK-NEXT: vl1r.v v4, (a4) # vscale x 8-byte Folded Reload
+; CHECK-NEXT: vxor.vv v4, v3, v4
+; CHECK-NEXT: vxor.vv v4, v4, v2
+; CHECK-NEXT: vxor.vv v4, v4, v1
+; CHECK-NEXT: vxor.vv v9, v4, v9
+; CHECK-NEXT: vxor.vv v9, v9, v10
+; CHECK-NEXT: vxor.vv v9, v9, v11
+; CHECK-NEXT: vxor.vv v9, v9, v12
+; CHECK-NEXT: vxor.vv v9, v9, v13
+; CHECK-NEXT: vxor.vv v9, v9, v14
+; CHECK-NEXT: vxor.vv v9, v9, v15
+; CHECK-NEXT: vxor.vv v9, v9, v16
+; CHECK-NEXT: vxor.vv v9, v9, v17
+; CHECK-NEXT: vxor.vv v9, v9, v18
+; CHECK-NEXT: vxor.vv v9, v9, v19
+; CHECK-NEXT: vxor.vv v9, v9, v20
+; CHECK-NEXT: vxor.vv v9, v9, v21
+; CHECK-NEXT: vxor.vv v9, v9, v22
+; CHECK-NEXT: vxor.vv v9, v9, v23
+; CHECK-NEXT: vxor.vv v9, v9, v24
+; CHECK-NEXT: vxor.vv v9, v9, v25
+; CHECK-NEXT: vxor.vv v9, v9, v26
+; CHECK-NEXT: vxor.vv v9, v9, v27
+; CHECK-NEXT: vxor.vv v9, v9, v28
+; CHECK-NEXT: vxor.vv v9, v9, v29
+; CHECK-NEXT: vxor.vv v9, v9, v30
+; CHECK-NEXT: vxor.vv v9, v9, v31
+; CHECK-NEXT: vxor.vv v9, v9, v7
+; CHECK-NEXT: vxor.vv v9, v9, v6
+; CHECK-NEXT: vxor.vv v9, v9, v5
+; CHECK-NEXT: vxor.vv v9, v9, v0
+; CHECK-NEXT: vxor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v9, v8, 8
+; CHECK-NEXT: vsrl.vi v10, v8, 24
+; CHECK-NEXT: vand.vx v9, v9, a3
+; CHECK-NEXT: vor.vv v9, v9, v10
+; CHECK-NEXT: vsll.vi v10, v8, 24
+; CHECK-NEXT: vand.vx v8, v8, a3
+; CHECK-NEXT: vsll.vi v8, v8, 8
+; CHECK-NEXT: vor.vv v8, v10, v8
+; CHECK-NEXT: vor.vv v8, v8, v9
+; CHECK-NEXT: vsrl.vi v9, v8, 4
+; CHECK-NEXT: vand.vx v8, v8, a2
+; CHECK-NEXT: vand.vx v9, v9, a2
+; CHECK-NEXT: vsll.vi v8, v8, 4
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v9, v8, 2
+; CHECK-NEXT: vand.vx v8, v8, a1
+; CHECK-NEXT: vand.vx v9, v9, a1
+; CHECK-NEXT: vsll.vi v8, v8, 2
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v9, v8, 1
+; CHECK-NEXT: vand.vx v8, v8, a0
+; CHECK-NEXT: vand.vx v9, v9, a0
+; CHECK-NEXT: vadd.vv v8, v8, v8
+; CHECK-NEXT: vor.vv v8, v9, v8
+; CHECK-NEXT: vsrl.vi v8, v8, 1
+; CHECK-NEXT: csrr a0, vlenb
+; CHECK-NEXT: add sp, sp, a0
+; CHECK-NEXT: addi sp, sp, 16
+; CHECK-NEXT: ret
+ %a = call <4 x i32> @llvm.clmulh.v4i32(<4 x i32> %x, <4 x i32> %y)
+ ret <4 x i32> %a
+}
+
+define <8 x i32> @clmulh_v8i32(<8 x i32> %x, <8 x i32> %y) nounwind {
+; RV32-LABEL: clmulh_v8i32:
+; RV32: # %bb.0:
+; RV32-NEXT: addi sp, sp, -64
+; RV32-NEXT: sw s0, 60(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s1, 56(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s2, 52(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s3, 48(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s4, 44(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s5, 40(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s6, 36(sp) # 4-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: sub sp, sp, a0
+; RV32-NEXT: vsetivli zero, 8, e32, m2, ta, ma
+; RV32-NEXT: vsrl.vi v10, v8, 8
+; RV32-NEXT: lui a0, 16
+; RV32-NEXT: vsrl.vi v12, v8, 24
+; RV32-NEXT: vsll.vi v14, v8, 24
+; RV32-NEXT: lui a1, 61681
+; RV32-NEXT: lui a2, 209715
+; RV32-NEXT: lui s6, 349525
+; RV32-NEXT: li t2, 16
+; RV32-NEXT: li t6, 32
+; RV32-NEXT: li s3, 64
+; RV32-NEXT: li s5, 128
+; RV32-NEXT: li s4, 256
+; RV32-NEXT: li s2, 512
+; RV32-NEXT: li s1, 1024
+; RV32-NEXT: li s0, 1
+; RV32-NEXT: lui t5, 1
+; RV32-NEXT: lui t4, 2
+; RV32-NEXT: lui t3, 4
+; RV32-NEXT: lui a5, 8
+; RV32-NEXT: lui a6, 32
+; RV32-NEXT: lui a7, 64
+; RV32-NEXT: lui t0, 128
+; RV32-NEXT: lui t1, 256
+; RV32-NEXT: addi a4, a0, -256
+; RV32-NEXT: addi a3, a1, -241
+; RV32-NEXT: addi a2, a2, 819
+; RV32-NEXT: addi a1, s6, 1365
+; RV32-NEXT: vand.vx v10, v10, a4
+; RV32-NEXT: vand.vx v8, v8, a4
+; RV32-NEXT: vor.vv v10, v10, v12
+; RV32-NEXT: vsll.vi v8, v8, 8
+; RV32-NEXT: vor.vv v8, v14, v8
+; RV32-NEXT: vor.vv v8, v8, v10
+; RV32-NEXT: vsrl.vi v10, v8, 4
+; RV32-NEXT: vand.vx v8, v8, a3
+; RV32-NEXT: vand.vx v10, v10, a3
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v10, v8
+; RV32-NEXT: vsrl.vi v10, v8, 2
+; RV32-NEXT: vand.vx v8, v8, a2
+; RV32-NEXT: vand.vx v10, v10, a2
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v8, v10, v8
+; RV32-NEXT: vsrl.vi v10, v8, 1
+; RV32-NEXT: vand.vx v8, v8, a1
+; RV32-NEXT: vand.vx v10, v10, a1
+; RV32-NEXT: vadd.vv v8, v8, v8
+; RV32-NEXT: vor.vv v8, v10, v8
+; RV32-NEXT: vand.vx v10, v8, t2
+; RV32-NEXT: lui t2, 512
+; RV32-NEXT: vand.vx v12, v8, t6
+; RV32-NEXT: lui t6, 1024
+; RV32-NEXT: vand.vx v14, v8, s3
+; RV32-NEXT: lui s3, 2048
+; RV32-NEXT: vand.vx v16, v8, s5
+; RV32-NEXT: lui s5, 4096
+; RV32-NEXT: vand.vx v26, v8, s4
+; RV32-NEXT: lui s4, 8192
+; RV32-NEXT: vand.vx v28, v8, s2
+; RV32-NEXT: lui s2, 16384
+; RV32-NEXT: vand.vx v18, v8, s1
+; RV32-NEXT: lui s1, 32768
+; RV32-NEXT: slli s0, s0, 11
+; RV32-NEXT: vand.vx v20, v8, s0
+; RV32-NEXT: lui s0, 65536
+; RV32-NEXT: vand.vx v22, v8, t5
+; RV32-NEXT: lui t5, 131072
+; RV32-NEXT: vand.vx v24, v8, t4
+; RV32-NEXT: lui t4, 262144
+; RV32-NEXT: vand.vx v30, v8, t3
+; RV32-NEXT: lui t3, 524288
+; RV32-NEXT: vand.vi v6, v8, 2
+; RV32-NEXT: vand.vi v4, v8, 1
+; RV32-NEXT: vand.vi v2, v8, 4
+; RV32-NEXT: vand.vi v0, v8, 8
+; RV32-NEXT: vmul.vv v6, v8, v6
+; RV32-NEXT: sw a0, 4(sp) # 4-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv s6, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, s6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v6, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v6, v8, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v6, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v6, v8, v2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv s6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add s6, s6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add s6, s6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, s6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v6, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v6, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv s6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add s6, s6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, s6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v6, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv s6, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add s6, s6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, s6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v10, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv s6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, s6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v10, v8, v14
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv s6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add s6, s6, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, s6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v10, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv s6, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, s6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v10, v8, v26
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv s6, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, s6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v10, v8, v28
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v10, v8, v18
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv s6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add s6, s6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, s6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v10, v8, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv s6, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, s6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v10, v8, v22
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv s6, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, s6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v10, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v10, v8, v30
+; RV32-NEXT: csrr s6, vlenb
+; RV32-NEXT: slli s6, s6, 1
+; RV32-NEXT: mv a0, s6
+; RV32-NEXT: slli s6, s6, 1
+; RV32-NEXT: add s6, s6, a0
+; RV32-NEXT: lw a0, 4(sp) # 4-byte Folded Reload
+; RV32-NEXT: add s6, sp, s6
+; RV32-NEXT: addi s6, s6, 32
+; RV32-NEXT: vs2r.v v10, (s6) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, a5
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a5, vlenb
+; RV32-NEXT: slli a5, a5, 2
+; RV32-NEXT: add a5, sp, a5
+; RV32-NEXT: addi a5, a5, 32
+; RV32-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, a0
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, a6
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: addi a0, sp, 32
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, a7
+; RV32-NEXT: vmul.vv v6, v8, v10
+; RV32-NEXT: vand.vx v10, v8, t0
+; RV32-NEXT: vmul.vv v30, v8, v10
+; RV32-NEXT: vand.vx v10, v8, t1
+; RV32-NEXT: vmul.vv v28, v8, v10
+; RV32-NEXT: vand.vx v10, v8, t2
+; RV32-NEXT: vmul.vv v26, v8, v10
+; RV32-NEXT: vand.vx v10, v8, t6
+; RV32-NEXT: vmul.vv v24, v8, v10
+; RV32-NEXT: vand.vx v10, v8, s3
+; RV32-NEXT: vmul.vv v22, v8, v10
+; RV32-NEXT: vand.vx v10, v8, s5
+; RV32-NEXT: vmul.vv v20, v8, v10
+; RV32-NEXT: vand.vx v10, v8, s4
+; RV32-NEXT: vmul.vv v18, v8, v10
+; RV32-NEXT: vand.vx v10, v8, s2
+; RV32-NEXT: vmul.vv v16, v8, v10
+; RV32-NEXT: vand.vx v10, v8, s1
+; RV32-NEXT: vmul.vv v14, v8, v10
+; RV32-NEXT: vand.vx v10, v8, s0
+; RV32-NEXT: vmul.vv v12, v8, v10
+; RV32-NEXT: vand.vx v10, v8, t5
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: vand.vx v0, v8, t4
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: vand.vx v2, v8, t3
+; RV32-NEXT: vmul.vv v8, v8, v2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v4, v2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v2, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v2, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v2, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v2, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v2, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v2, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v2, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v2, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v2, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v2, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v2, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v2, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v2, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v2, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v2, v2, v4
+; RV32-NEXT: addi a0, sp, 32
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v4, v2, v4
+; RV32-NEXT: vxor.vv v6, v4, v6
+; RV32-NEXT: vxor.vv v30, v6, v30
+; RV32-NEXT: vxor.vv v28, v30, v28
+; RV32-NEXT: vxor.vv v26, v28, v26
+; RV32-NEXT: vxor.vv v24, v26, v24
+; RV32-NEXT: vxor.vv v22, v24, v22
+; RV32-NEXT: vxor.vv v20, v22, v20
+; RV32-NEXT: vxor.vv v18, v20, v18
+; RV32-NEXT: vxor.vv v16, v18, v16
+; RV32-NEXT: vxor.vv v14, v16, v14
+; RV32-NEXT: vxor.vv v12, v14, v12
+; RV32-NEXT: vxor.vv v10, v12, v10
+; RV32-NEXT: vxor.vv v10, v10, v0
+; RV32-NEXT: vxor.vv v8, v10, v8
+; RV32-NEXT: vsrl.vi v10, v8, 8
+; RV32-NEXT: vsrl.vi v12, v8, 24
+; RV32-NEXT: vand.vx v10, v10, a4
+; RV32-NEXT: vor.vv v10, v10, v12
+; RV32-NEXT: vsll.vi v12, v8, 24
+; RV32-NEXT: vand.vx v8, v8, a4
+; RV32-NEXT: vsll.vi v8, v8, 8
+; RV32-NEXT: vor.vv v8, v12, v8
+; RV32-NEXT: vor.vv v8, v8, v10
+; RV32-NEXT: vsrl.vi v10, v8, 4
+; RV32-NEXT: vand.vx v8, v8, a3
+; RV32-NEXT: vand.vx v10, v10, a3
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v10, v8
+; RV32-NEXT: vsrl.vi v10, v8, 2
+; RV32-NEXT: vand.vx v8, v8, a2
+; RV32-NEXT: vand.vx v10, v10, a2
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v8, v10, v8
+; RV32-NEXT: vsrl.vi v10, v8, 1
+; RV32-NEXT: vand.vx v8, v8, a1
+; RV32-NEXT: vand.vx v10, v10, a1
+; RV32-NEXT: vadd.vv v8, v8, v8
+; RV32-NEXT: vor.vv v8, v10, v8
+; RV32-NEXT: vsrl.vi v8, v8, 1
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add sp, sp, a0
+; RV32-NEXT: lw s0, 60(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s1, 56(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s2, 52(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s3, 48(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s4, 44(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s5, 40(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s6, 36(sp) # 4-byte Folded Reload
+; RV32-NEXT: addi sp, sp, 64
+; RV32-NEXT: ret
+;
+; RV64-LABEL: clmulh_v8i32:
+; RV64: # %bb.0:
+; RV64-NEXT: addi sp, sp, -96
+; RV64-NEXT: sd s0, 88(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s1, 80(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s2, 72(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s3, 64(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s4, 56(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s5, 48(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s6, 40(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: sub sp, sp, a0
+; RV64-NEXT: vsetivli zero, 8, e32, m2, ta, ma
+; RV64-NEXT: vsrl.vi v10, v8, 8
+; RV64-NEXT: lui a0, 16
+; RV64-NEXT: vsrl.vi v12, v8, 24
+; RV64-NEXT: vsll.vi v14, v8, 24
+; RV64-NEXT: lui a1, 61681
+; RV64-NEXT: lui a2, 209715
+; RV64-NEXT: lui s6, 349525
+; RV64-NEXT: li t2, 16
+; RV64-NEXT: li t6, 32
+; RV64-NEXT: li s3, 64
+; RV64-NEXT: li s5, 128
+; RV64-NEXT: li s4, 256
+; RV64-NEXT: li s2, 512
+; RV64-NEXT: li s1, 1024
+; RV64-NEXT: li s0, 1
+; RV64-NEXT: lui t5, 1
+; RV64-NEXT: lui t4, 2
+; RV64-NEXT: lui t3, 4
+; RV64-NEXT: lui a5, 8
+; RV64-NEXT: lui a6, 32
+; RV64-NEXT: lui a7, 64
+; RV64-NEXT: lui t0, 128
+; RV64-NEXT: lui t1, 256
+; RV64-NEXT: addi a4, a0, -256
+; RV64-NEXT: addi a3, a1, -241
+; RV64-NEXT: addi a2, a2, 819
+; RV64-NEXT: addi a1, s6, 1365
+; RV64-NEXT: vand.vx v10, v10, a4
+; RV64-NEXT: vand.vx v8, v8, a4
+; RV64-NEXT: vor.vv v10, v10, v12
+; RV64-NEXT: vsll.vi v8, v8, 8
+; RV64-NEXT: vor.vv v8, v14, v8
+; RV64-NEXT: vor.vv v8, v8, v10
+; RV64-NEXT: vsrl.vi v10, v8, 4
+; RV64-NEXT: vand.vx v8, v8, a3
+; RV64-NEXT: vand.vx v10, v10, a3
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v10, v8
+; RV64-NEXT: vsrl.vi v10, v8, 2
+; RV64-NEXT: vand.vx v8, v8, a2
+; RV64-NEXT: vand.vx v10, v10, a2
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v10, v8
+; RV64-NEXT: vsrl.vi v10, v8, 1
+; RV64-NEXT: vand.vx v8, v8, a1
+; RV64-NEXT: vand.vx v10, v10, a1
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v10, v8
+; RV64-NEXT: vand.vx v10, v8, t2
+; RV64-NEXT: lui t2, 512
+; RV64-NEXT: vand.vx v12, v8, t6
+; RV64-NEXT: lui t6, 1024
+; RV64-NEXT: vand.vx v14, v8, s3
+; RV64-NEXT: lui s3, 2048
+; RV64-NEXT: vand.vx v16, v8, s5
+; RV64-NEXT: lui s5, 4096
+; RV64-NEXT: vand.vx v26, v8, s4
+; RV64-NEXT: lui s4, 8192
+; RV64-NEXT: vand.vx v28, v8, s2
+; RV64-NEXT: lui s2, 16384
+; RV64-NEXT: vand.vx v18, v8, s1
+; RV64-NEXT: lui s1, 32768
+; RV64-NEXT: slli s0, s0, 11
+; RV64-NEXT: vand.vx v20, v8, s0
+; RV64-NEXT: lui s0, 65536
+; RV64-NEXT: vand.vx v22, v8, t5
+; RV64-NEXT: lui t5, 131072
+; RV64-NEXT: vand.vx v24, v8, t4
+; RV64-NEXT: lui t4, 262144
+; RV64-NEXT: vand.vx v30, v8, t3
+; RV64-NEXT: lui t3, 524288
+; RV64-NEXT: vand.vi v6, v8, 2
+; RV64-NEXT: vand.vi v4, v8, 1
+; RV64-NEXT: vand.vi v2, v8, 4
+; RV64-NEXT: vand.vi v0, v8, 8
+; RV64-NEXT: vmul.vv v6, v8, v6
+; RV64-NEXT: sd a0, 8(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv s6, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, a0, s6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v6, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v6, v8, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v6, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v6, v8, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv s6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add s6, s6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add s6, s6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, s6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v6, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v6, v8, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv s6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add s6, s6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, s6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v6, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv s6, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add s6, s6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, s6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v12
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv s6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, s6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v14
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv s6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add s6, s6, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, s6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv s6, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, s6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v26
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv s6, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, s6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v28
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v18
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv s6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add s6, s6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, s6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v20
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv s6, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, s6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v22
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv s6, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, s6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v24
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v30
+; RV64-NEXT: csrr s6, vlenb
+; RV64-NEXT: slli s6, s6, 1
+; RV64-NEXT: mv a0, s6
+; RV64-NEXT: slli s6, s6, 1
+; RV64-NEXT: add s6, s6, a0
+; RV64-NEXT: ld a0, 8(sp) # 8-byte Folded Reload
+; RV64-NEXT: add s6, sp, s6
+; RV64-NEXT: addi s6, s6, 32
+; RV64-NEXT: vs2r.v v10, (s6) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, a5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 32
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, a0
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, a6
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: addi a0, sp, 32
+; RV64-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, a7
+; RV64-NEXT: vmul.vv v6, v8, v10
+; RV64-NEXT: vand.vx v10, v8, t0
+; RV64-NEXT: vmul.vv v30, v8, v10
+; RV64-NEXT: vand.vx v10, v8, t1
+; RV64-NEXT: vmul.vv v28, v8, v10
+; RV64-NEXT: vand.vx v10, v8, t2
+; RV64-NEXT: vmul.vv v26, v8, v10
+; RV64-NEXT: vand.vx v10, v8, t6
+; RV64-NEXT: vmul.vv v24, v8, v10
+; RV64-NEXT: vand.vx v10, v8, s3
+; RV64-NEXT: vmul.vv v22, v8, v10
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v20, v8, v10
+; RV64-NEXT: vand.vx v10, v8, s4
+; RV64-NEXT: vmul.vv v18, v8, v10
+; RV64-NEXT: vand.vx v10, v8, s2
+; RV64-NEXT: vmul.vv v16, v8, v10
+; RV64-NEXT: vand.vx v10, v8, s1
+; RV64-NEXT: vmul.vv v14, v8, v10
+; RV64-NEXT: vand.vx v10, v8, s0
+; RV64-NEXT: vmul.vv v12, v8, v10
+; RV64-NEXT: vand.vx v10, v8, t5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: vand.vx v0, v8, t4
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vand.vx v2, v8, t3
+; RV64-NEXT: vmul.vv v8, v8, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v4, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v2, v4
+; RV64-NEXT: addi a0, sp, 32
+; RV64-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v4, v2, v4
+; RV64-NEXT: vxor.vv v6, v4, v6
+; RV64-NEXT: vxor.vv v30, v6, v30
+; RV64-NEXT: vxor.vv v28, v30, v28
+; RV64-NEXT: vxor.vv v26, v28, v26
+; RV64-NEXT: vxor.vv v24, v26, v24
+; RV64-NEXT: vxor.vv v22, v24, v22
+; RV64-NEXT: vxor.vv v20, v22, v20
+; RV64-NEXT: vxor.vv v18, v20, v18
+; RV64-NEXT: vxor.vv v16, v18, v16
+; RV64-NEXT: vxor.vv v14, v16, v14
+; RV64-NEXT: vxor.vv v12, v14, v12
+; RV64-NEXT: vxor.vv v10, v12, v10
+; RV64-NEXT: vxor.vv v10, v10, v0
+; RV64-NEXT: vxor.vv v8, v10, v8
+; RV64-NEXT: vsrl.vi v10, v8, 8
+; RV64-NEXT: vsrl.vi v12, v8, 24
+; RV64-NEXT: vand.vx v10, v10, a4
+; RV64-NEXT: vor.vv v10, v10, v12
+; RV64-NEXT: vsll.vi v12, v8, 24
+; RV64-NEXT: vand.vx v8, v8, a4
+; RV64-NEXT: vsll.vi v8, v8, 8
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vor.vv v8, v8, v10
+; RV64-NEXT: vsrl.vi v10, v8, 4
+; RV64-NEXT: vand.vx v8, v8, a3
+; RV64-NEXT: vand.vx v10, v10, a3
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v10, v8
+; RV64-NEXT: vsrl.vi v10, v8, 2
+; RV64-NEXT: vand.vx v8, v8, a2
+; RV64-NEXT: vand.vx v10, v10, a2
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v10, v8
+; RV64-NEXT: vsrl.vi v10, v8, 1
+; RV64-NEXT: vand.vx v8, v8, a1
+; RV64-NEXT: vand.vx v10, v10, a1
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v10, v8
+; RV64-NEXT: vsrl.vi v8, v8, 1
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add sp, sp, a0
+; RV64-NEXT: ld s0, 88(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s1, 80(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s2, 72(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s3, 64(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s4, 56(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s5, 48(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s6, 40(sp) # 8-byte Folded Reload
+; RV64-NEXT: addi sp, sp, 96
+; RV64-NEXT: ret
+ %a = call <8 x i32> @llvm.clmulh.v8i32(<8 x i32> %x, <8 x i32> %x)
+ ret <8 x i32> %a
+}
+
+define <16 x i32> @clmulh_v16i32(<16 x i32> %x, <16 x i32> %y) nounwind {
+; RV32-LABEL: clmulh_v16i32:
+; RV32: # %bb.0:
+; RV32-NEXT: addi sp, sp, -80
+; RV32-NEXT: sw ra, 76(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s0, 72(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s1, 68(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s2, 64(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s3, 60(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s4, 56(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s5, 52(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s6, 48(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s7, 44(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s8, 40(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s9, 36(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s10, 32(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s11, 28(sp) # 4-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: sub sp, sp, a0
+; RV32-NEXT: vsetivli zero, 16, e32, m4, ta, ma
+; RV32-NEXT: vsrl.vi v12, v8, 8
+; RV32-NEXT: lui a5, 16
+; RV32-NEXT: vsrl.vi v16, v8, 24
+; RV32-NEXT: vsll.vi v20, v8, 24
+; RV32-NEXT: lui a1, 61681
+; RV32-NEXT: lui a2, 209715
+; RV32-NEXT: lui ra, 349525
+; RV32-NEXT: li s11, 16
+; RV32-NEXT: li s10, 32
+; RV32-NEXT: li s9, 64
+; RV32-NEXT: li a7, 512
+; RV32-NEXT: li t0, 1024
+; RV32-NEXT: li a0, 1
+; RV32-NEXT: lui t1, 1
+; RV32-NEXT: lui t2, 2
+; RV32-NEXT: lui t3, 4
+; RV32-NEXT: lui t4, 8
+; RV32-NEXT: lui t5, 32
+; RV32-NEXT: lui t6, 64
+; RV32-NEXT: lui s0, 128
+; RV32-NEXT: lui s1, 256
+; RV32-NEXT: lui s2, 512
+; RV32-NEXT: lui s3, 1024
+; RV32-NEXT: lui s4, 2048
+; RV32-NEXT: lui s5, 4096
+; RV32-NEXT: lui s6, 8192
+; RV32-NEXT: lui s7, 16384
+; RV32-NEXT: lui s8, 32768
+; RV32-NEXT: addi a4, a5, -256
+; RV32-NEXT: addi a3, a1, -241
+; RV32-NEXT: addi a2, a2, 819
+; RV32-NEXT: addi a1, ra, 1365
+; RV32-NEXT: vand.vx v12, v12, a4
+; RV32-NEXT: vand.vx v8, v8, a4
+; RV32-NEXT: vor.vv v12, v12, v16
+; RV32-NEXT: vsll.vi v8, v8, 8
+; RV32-NEXT: vor.vv v8, v20, v8
+; RV32-NEXT: vor.vv v8, v8, v12
+; RV32-NEXT: vsrl.vi v12, v8, 4
+; RV32-NEXT: vand.vx v8, v8, a3
+; RV32-NEXT: vand.vx v12, v12, a3
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v12, v8
+; RV32-NEXT: vsrl.vi v12, v8, 2
+; RV32-NEXT: vand.vx v8, v8, a2
+; RV32-NEXT: vand.vx v12, v12, a2
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v8, v12, v8
+; RV32-NEXT: vsrl.vi v12, v8, 1
+; RV32-NEXT: vand.vx v8, v8, a1
+; RV32-NEXT: vand.vx v12, v12, a1
+; RV32-NEXT: vadd.vv v8, v8, v8
+; RV32-NEXT: vor.vv v8, v12, v8
+; RV32-NEXT: vand.vx v12, v8, s11
+; RV32-NEXT: lui s11, 65536
+; RV32-NEXT: vand.vx v16, v8, s10
+; RV32-NEXT: lui s10, 131072
+; RV32-NEXT: vand.vx v20, v8, s9
+; RV32-NEXT: lui s9, 262144
+; RV32-NEXT: slli ra, a0, 11
+; RV32-NEXT: vand.vi v24, v8, 2
+; RV32-NEXT: vand.vi v28, v8, 1
+; RV32-NEXT: vand.vi v4, v8, 4
+; RV32-NEXT: vand.vi v0, v8, 8
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: sw a4, 4(sp) # 4-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a4, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a4, a4, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs4r.v v24, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vmul.vv v24, v8, v28
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a4, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs4r.v v24, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vmul.vv v24, v8, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a4, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a4, a4, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a4, a4, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs4r.v v24, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vmul.vv v24, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a4, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a4, a4, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs4r.v v24, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a4, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a4, a4, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vmul.vv v12, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a4, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vmul.vv v12, v8, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a4, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a4, a4, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: lui a0, 524288
+; RV32-NEXT: li a6, 128
+; RV32-NEXT: vand.vx v12, v8, a6
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a4, vlenb
+; RV32-NEXT: slli a4, a4, 3
+; RV32-NEXT: mv a6, a4
+; RV32-NEXT: slli a4, a4, 3
+; RV32-NEXT: add a4, a4, a6
+; RV32-NEXT: add a4, sp, a4
+; RV32-NEXT: addi a4, a4, 16
+; RV32-NEXT: vs4r.v v12, (a4) # vscale x 32-byte Folded Spill
+; RV32-NEXT: li a6, 256
+; RV32-NEXT: vand.vx v12, v8, a6
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 2
+; RV32-NEXT: mv a4, a6
+; RV32-NEXT: slli a6, a6, 4
+; RV32-NEXT: add a6, a6, a4
+; RV32-NEXT: lw a4, 4(sp) # 4-byte Folded Reload
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 16
+; RV32-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, a7
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 6
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 16
+; RV32-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, t0
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 2
+; RV32-NEXT: mv a7, a6
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: add a7, a7, a6
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: add a7, a7, a6
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: add a6, a6, a7
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 16
+; RV32-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, ra
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 3
+; RV32-NEXT: mv a7, a6
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: add a7, a7, a6
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: add a6, a6, a7
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 16
+; RV32-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, t1
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 2
+; RV32-NEXT: mv a7, a6
+; RV32-NEXT: slli a6, a6, 2
+; RV32-NEXT: add a7, a7, a6
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: add a6, a6, a7
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 16
+; RV32-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, t2
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 4
+; RV32-NEXT: mv a7, a6
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: add a6, a6, a7
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 16
+; RV32-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, t3
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 2
+; RV32-NEXT: mv a7, a6
+; RV32-NEXT: slli a6, a6, 1
+; RV32-NEXT: add a7, a7, a6
+; RV32-NEXT: slli a6, a6, 2
+; RV32-NEXT: add a6, a6, a7
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 16
+; RV32-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, t4
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a6, vlenb
+; RV32-NEXT: slli a6, a6, 3
+; RV32-NEXT: mv a7, a6
+; RV32-NEXT: slli a6, a6, 2
+; RV32-NEXT: add a6, a6, a7
+; RV32-NEXT: add a6, sp, a6
+; RV32-NEXT: addi a6, a6, 16
+; RV32-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, a5
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a5, vlenb
+; RV32-NEXT: slli a5, a5, 2
+; RV32-NEXT: mv a6, a5
+; RV32-NEXT: slli a5, a5, 3
+; RV32-NEXT: add a5, a5, a6
+; RV32-NEXT: add a5, sp, a5
+; RV32-NEXT: addi a5, a5, 16
+; RV32-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, t5
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a5, vlenb
+; RV32-NEXT: slli a5, a5, 5
+; RV32-NEXT: add a5, sp, a5
+; RV32-NEXT: addi a5, a5, 16
+; RV32-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, t6
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a5, vlenb
+; RV32-NEXT: slli a5, a5, 2
+; RV32-NEXT: mv a6, a5
+; RV32-NEXT: slli a5, a5, 1
+; RV32-NEXT: add a6, a6, a5
+; RV32-NEXT: slli a5, a5, 1
+; RV32-NEXT: add a5, a5, a6
+; RV32-NEXT: add a5, sp, a5
+; RV32-NEXT: addi a5, a5, 16
+; RV32-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s0
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a5, vlenb
+; RV32-NEXT: slli a5, a5, 3
+; RV32-NEXT: mv a6, a5
+; RV32-NEXT: slli a5, a5, 1
+; RV32-NEXT: add a5, a5, a6
+; RV32-NEXT: add a5, sp, a5
+; RV32-NEXT: addi a5, a5, 16
+; RV32-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s1
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a5, vlenb
+; RV32-NEXT: slli a5, a5, 2
+; RV32-NEXT: mv a6, a5
+; RV32-NEXT: slli a5, a5, 2
+; RV32-NEXT: add a5, a5, a6
+; RV32-NEXT: add a5, sp, a5
+; RV32-NEXT: addi a5, a5, 16
+; RV32-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s2
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a5, vlenb
+; RV32-NEXT: slli a5, a5, 4
+; RV32-NEXT: add a5, sp, a5
+; RV32-NEXT: addi a5, a5, 16
+; RV32-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s3
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a5, vlenb
+; RV32-NEXT: slli a5, a5, 2
+; RV32-NEXT: mv a6, a5
+; RV32-NEXT: slli a5, a5, 1
+; RV32-NEXT: add a5, a5, a6
+; RV32-NEXT: add a5, sp, a5
+; RV32-NEXT: addi a5, a5, 16
+; RV32-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s4
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a5, vlenb
+; RV32-NEXT: slli a5, a5, 3
+; RV32-NEXT: add a5, sp, a5
+; RV32-NEXT: addi a5, a5, 16
+; RV32-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s5
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a5, vlenb
+; RV32-NEXT: slli a5, a5, 2
+; RV32-NEXT: add a5, sp, a5
+; RV32-NEXT: addi a5, a5, 16
+; RV32-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s6
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: addi a5, sp, 16
+; RV32-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s7
+; RV32-NEXT: vmul.vv v28, v8, v12
+; RV32-NEXT: vand.vx v12, v8, s8
+; RV32-NEXT: vmul.vv v24, v8, v12
+; RV32-NEXT: vand.vx v12, v8, s11
+; RV32-NEXT: vmul.vv v20, v8, v12
+; RV32-NEXT: vand.vx v12, v8, s10
+; RV32-NEXT: vmul.vv v16, v8, v12
+; RV32-NEXT: vand.vx v12, v8, s9
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: vand.vx v0, v8, a0
+; RV32-NEXT: vmul.vv v8, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v0, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v4, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a5, a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a5, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 16
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v0, v0, v4
+; RV32-NEXT: addi a0, sp, 16
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v4, v0, v4
+; RV32-NEXT: vxor.vv v28, v4, v28
+; RV32-NEXT: vxor.vv v24, v28, v24
+; RV32-NEXT: vxor.vv v20, v24, v20
+; RV32-NEXT: vxor.vv v16, v20, v16
+; RV32-NEXT: vxor.vv v12, v16, v12
+; RV32-NEXT: vxor.vv v8, v12, v8
+; RV32-NEXT: vsrl.vi v12, v8, 8
+; RV32-NEXT: vsrl.vi v16, v8, 24
+; RV32-NEXT: vand.vx v12, v12, a4
+; RV32-NEXT: vor.vv v12, v12, v16
+; RV32-NEXT: vsll.vi v16, v8, 24
+; RV32-NEXT: vand.vx v8, v8, a4
+; RV32-NEXT: vsll.vi v8, v8, 8
+; RV32-NEXT: vor.vv v8, v16, v8
+; RV32-NEXT: vor.vv v8, v8, v12
+; RV32-NEXT: vsrl.vi v12, v8, 4
+; RV32-NEXT: vand.vx v8, v8, a3
+; RV32-NEXT: vand.vx v12, v12, a3
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v12, v8
+; RV32-NEXT: vsrl.vi v12, v8, 2
+; RV32-NEXT: vand.vx v8, v8, a2
+; RV32-NEXT: vand.vx v12, v12, a2
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v8, v12, v8
+; RV32-NEXT: vsrl.vi v12, v8, 1
+; RV32-NEXT: vand.vx v8, v8, a1
+; RV32-NEXT: vand.vx v12, v12, a1
+; RV32-NEXT: vadd.vv v8, v8, v8
+; RV32-NEXT: vor.vv v8, v12, v8
+; RV32-NEXT: vsrl.vi v8, v8, 1
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add sp, sp, a0
+; RV32-NEXT: lw ra, 76(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s0, 72(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s1, 68(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s2, 64(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s3, 60(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s4, 56(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s5, 52(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s6, 48(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s7, 44(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s8, 40(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s9, 36(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s10, 32(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s11, 28(sp) # 4-byte Folded Reload
+; RV32-NEXT: addi sp, sp, 80
+; RV32-NEXT: ret
+;
+; RV64-LABEL: clmulh_v16i32:
+; RV64: # %bb.0:
+; RV64-NEXT: addi sp, sp, -144
+; RV64-NEXT: sd ra, 136(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s0, 128(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s1, 120(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s2, 112(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s3, 104(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s4, 96(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s5, 88(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s6, 80(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s7, 72(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s8, 64(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s9, 56(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s10, 48(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s11, 40(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: sub sp, sp, a0
+; RV64-NEXT: vsetivli zero, 16, e32, m4, ta, ma
+; RV64-NEXT: vsrl.vi v12, v8, 8
+; RV64-NEXT: lui a5, 16
+; RV64-NEXT: vsrl.vi v16, v8, 24
+; RV64-NEXT: vsll.vi v20, v8, 24
+; RV64-NEXT: lui a1, 61681
+; RV64-NEXT: lui a2, 209715
+; RV64-NEXT: lui ra, 349525
+; RV64-NEXT: li s11, 16
+; RV64-NEXT: li s10, 32
+; RV64-NEXT: li s9, 64
+; RV64-NEXT: li a7, 512
+; RV64-NEXT: li t0, 1024
+; RV64-NEXT: li a0, 1
+; RV64-NEXT: lui t1, 1
+; RV64-NEXT: lui t2, 2
+; RV64-NEXT: lui t3, 4
+; RV64-NEXT: lui t4, 8
+; RV64-NEXT: lui t5, 32
+; RV64-NEXT: lui t6, 64
+; RV64-NEXT: lui s0, 128
+; RV64-NEXT: lui s1, 256
+; RV64-NEXT: lui s2, 512
+; RV64-NEXT: lui s3, 1024
+; RV64-NEXT: lui s4, 2048
+; RV64-NEXT: lui s5, 4096
+; RV64-NEXT: lui s6, 8192
+; RV64-NEXT: lui s7, 16384
+; RV64-NEXT: lui s8, 32768
+; RV64-NEXT: addi a4, a5, -256
+; RV64-NEXT: addi a3, a1, -241
+; RV64-NEXT: addi a2, a2, 819
+; RV64-NEXT: addi a1, ra, 1365
+; RV64-NEXT: vand.vx v12, v12, a4
+; RV64-NEXT: vand.vx v8, v8, a4
+; RV64-NEXT: vor.vv v12, v12, v16
+; RV64-NEXT: vsll.vi v8, v8, 8
+; RV64-NEXT: vor.vv v8, v20, v8
+; RV64-NEXT: vor.vv v8, v8, v12
+; RV64-NEXT: vsrl.vi v12, v8, 4
+; RV64-NEXT: vand.vx v8, v8, a3
+; RV64-NEXT: vand.vx v12, v12, a3
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vsrl.vi v12, v8, 2
+; RV64-NEXT: vand.vx v8, v8, a2
+; RV64-NEXT: vand.vx v12, v12, a2
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vsrl.vi v12, v8, 1
+; RV64-NEXT: vand.vx v8, v8, a1
+; RV64-NEXT: vand.vx v12, v12, a1
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vand.vx v12, v8, s11
+; RV64-NEXT: lui s11, 65536
+; RV64-NEXT: vand.vx v16, v8, s10
+; RV64-NEXT: lui s10, 131072
+; RV64-NEXT: vand.vx v20, v8, s9
+; RV64-NEXT: lui s9, 262144
+; RV64-NEXT: slli ra, a0, 11
+; RV64-NEXT: vand.vi v24, v8, 2
+; RV64-NEXT: vand.vi v28, v8, 1
+; RV64-NEXT: vand.vi v4, v8, 4
+; RV64-NEXT: vand.vi v0, v8, 8
+; RV64-NEXT: vmul.vv v24, v8, v24
+; RV64-NEXT: sd a4, 8(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a4, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a4, a4, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs4r.v v24, (a0) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vmul.vv v24, v8, v28
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: mv a4, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs4r.v v24, (a0) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vmul.vv v24, v8, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a4, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a4, a4, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a4, a4, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs4r.v v24, (a0) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vmul.vv v24, v8, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a4, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a4, a4, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs4r.v v24, (a0) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a4, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a4, a4, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vmul.vv v12, v8, v16
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a4, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vmul.vv v12, v8, v20
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a4, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a4, a4, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui a0, 524288
+; RV64-NEXT: li a6, 128
+; RV64-NEXT: vand.vx v12, v8, a6
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a4, vlenb
+; RV64-NEXT: slli a4, a4, 3
+; RV64-NEXT: mv a6, a4
+; RV64-NEXT: slli a4, a4, 3
+; RV64-NEXT: add a4, a4, a6
+; RV64-NEXT: add a4, sp, a4
+; RV64-NEXT: addi a4, a4, 32
+; RV64-NEXT: vs4r.v v12, (a4) # vscale x 32-byte Folded Spill
+; RV64-NEXT: li a6, 256
+; RV64-NEXT: vand.vx v12, v8, a6
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a6, vlenb
+; RV64-NEXT: slli a6, a6, 2
+; RV64-NEXT: mv a4, a6
+; RV64-NEXT: slli a6, a6, 4
+; RV64-NEXT: add a6, a6, a4
+; RV64-NEXT: ld a4, 8(sp) # 8-byte Folded Reload
+; RV64-NEXT: add a6, sp, a6
+; RV64-NEXT: addi a6, a6, 32
+; RV64-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, a7
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a6, vlenb
+; RV64-NEXT: slli a6, a6, 6
+; RV64-NEXT: add a6, sp, a6
+; RV64-NEXT: addi a6, a6, 32
+; RV64-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t0
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a6, vlenb
+; RV64-NEXT: slli a6, a6, 2
+; RV64-NEXT: mv a7, a6
+; RV64-NEXT: slli a6, a6, 1
+; RV64-NEXT: add a7, a7, a6
+; RV64-NEXT: slli a6, a6, 1
+; RV64-NEXT: add a7, a7, a6
+; RV64-NEXT: slli a6, a6, 1
+; RV64-NEXT: add a6, a6, a7
+; RV64-NEXT: add a6, sp, a6
+; RV64-NEXT: addi a6, a6, 32
+; RV64-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, ra
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a6, vlenb
+; RV64-NEXT: slli a6, a6, 3
+; RV64-NEXT: mv a7, a6
+; RV64-NEXT: slli a6, a6, 1
+; RV64-NEXT: add a7, a7, a6
+; RV64-NEXT: slli a6, a6, 1
+; RV64-NEXT: add a6, a6, a7
+; RV64-NEXT: add a6, sp, a6
+; RV64-NEXT: addi a6, a6, 32
+; RV64-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t1
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a6, vlenb
+; RV64-NEXT: slli a6, a6, 2
+; RV64-NEXT: mv a7, a6
+; RV64-NEXT: slli a6, a6, 2
+; RV64-NEXT: add a7, a7, a6
+; RV64-NEXT: slli a6, a6, 1
+; RV64-NEXT: add a6, a6, a7
+; RV64-NEXT: add a6, sp, a6
+; RV64-NEXT: addi a6, a6, 32
+; RV64-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t2
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a6, vlenb
+; RV64-NEXT: slli a6, a6, 4
+; RV64-NEXT: mv a7, a6
+; RV64-NEXT: slli a6, a6, 1
+; RV64-NEXT: add a6, a6, a7
+; RV64-NEXT: add a6, sp, a6
+; RV64-NEXT: addi a6, a6, 32
+; RV64-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t3
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a6, vlenb
+; RV64-NEXT: slli a6, a6, 2
+; RV64-NEXT: mv a7, a6
+; RV64-NEXT: slli a6, a6, 1
+; RV64-NEXT: add a7, a7, a6
+; RV64-NEXT: slli a6, a6, 2
+; RV64-NEXT: add a6, a6, a7
+; RV64-NEXT: add a6, sp, a6
+; RV64-NEXT: addi a6, a6, 32
+; RV64-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t4
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a6, vlenb
+; RV64-NEXT: slli a6, a6, 3
+; RV64-NEXT: mv a7, a6
+; RV64-NEXT: slli a6, a6, 2
+; RV64-NEXT: add a6, a6, a7
+; RV64-NEXT: add a6, sp, a6
+; RV64-NEXT: addi a6, a6, 32
+; RV64-NEXT: vs4r.v v12, (a6) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, a5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv a6, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, a5, a6
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 32
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 32
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t6
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv a6, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a6, a6, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, a6
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 32
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s0
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv a6, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, a6
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 32
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s1
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv a6, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, a6
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 32
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s2
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 32
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s3
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv a6, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, a6
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 32
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s4
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 32
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 32
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s6
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: addi a5, sp, 32
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s7
+; RV64-NEXT: vmul.vv v28, v8, v12
+; RV64-NEXT: vand.vx v12, v8, s8
+; RV64-NEXT: vmul.vv v24, v8, v12
+; RV64-NEXT: vand.vx v12, v8, s11
+; RV64-NEXT: vmul.vv v20, v8, v12
+; RV64-NEXT: vand.vx v12, v8, s10
+; RV64-NEXT: vmul.vv v16, v8, v12
+; RV64-NEXT: vand.vx v12, v8, s9
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: vand.vx v0, v8, a0
+; RV64-NEXT: vmul.vv v8, v8, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v0, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v4, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a5, a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a5, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 32
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: addi a0, sp, 32
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v4, v0, v4
+; RV64-NEXT: vxor.vv v28, v4, v28
+; RV64-NEXT: vxor.vv v24, v28, v24
+; RV64-NEXT: vxor.vv v20, v24, v20
+; RV64-NEXT: vxor.vv v16, v20, v16
+; RV64-NEXT: vxor.vv v12, v16, v12
+; RV64-NEXT: vxor.vv v8, v12, v8
+; RV64-NEXT: vsrl.vi v12, v8, 8
+; RV64-NEXT: vsrl.vi v16, v8, 24
+; RV64-NEXT: vand.vx v12, v12, a4
+; RV64-NEXT: vor.vv v12, v12, v16
+; RV64-NEXT: vsll.vi v16, v8, 24
+; RV64-NEXT: vand.vx v8, v8, a4
+; RV64-NEXT: vsll.vi v8, v8, 8
+; RV64-NEXT: vor.vv v8, v16, v8
+; RV64-NEXT: vor.vv v8, v8, v12
+; RV64-NEXT: vsrl.vi v12, v8, 4
+; RV64-NEXT: vand.vx v8, v8, a3
+; RV64-NEXT: vand.vx v12, v12, a3
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vsrl.vi v12, v8, 2
+; RV64-NEXT: vand.vx v8, v8, a2
+; RV64-NEXT: vand.vx v12, v12, a2
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vsrl.vi v12, v8, 1
+; RV64-NEXT: vand.vx v8, v8, a1
+; RV64-NEXT: vand.vx v12, v12, a1
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vsrl.vi v8, v8, 1
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add sp, sp, a0
+; RV64-NEXT: ld ra, 136(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s0, 128(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s1, 120(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s2, 112(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s3, 104(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s4, 96(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s5, 88(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s6, 80(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s7, 72(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s8, 64(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s9, 56(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s10, 48(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s11, 40(sp) # 8-byte Folded Reload
+; RV64-NEXT: addi sp, sp, 144
+; RV64-NEXT: ret
+ %a = call <16 x i32> @llvm.clmulh.v16i32(<16 x i32> %x, <16 x i32> %y)
+ ret <16 x i32> %a
+}
+
+define <1 x i64> @clmulh_v1i64(<1 x i64> %x, <1 x i64> %y) nounwind {
+; RV32-LABEL: clmulh_v1i64:
+; RV32: # %bb.0:
+; RV32-NEXT: addi sp, sp, -352
+; RV32-NEXT: sw ra, 348(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s0, 344(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s1, 340(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s2, 336(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s3, 332(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s4, 328(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s5, 324(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s6, 320(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s7, 316(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s8, 312(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s9, 308(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s10, 304(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s11, 300(sp) # 4-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: sub sp, sp, a0
+; RV32-NEXT: lui s7, 1044480
+; RV32-NEXT: lui a7, 524288
+; RV32-NEXT: li s11, 1
+; RV32-NEXT: li s8, 2
+; RV32-NEXT: li s9, 4
+; RV32-NEXT: li s10, 8
+; RV32-NEXT: li a3, 16
+; RV32-NEXT: li a4, 32
+; RV32-NEXT: li a5, 64
+; RV32-NEXT: li a6, 128
+; RV32-NEXT: li ra, 256
+; RV32-NEXT: li a0, 512
+; RV32-NEXT: li a1, 1024
+; RV32-NEXT: lui a2, 1
+; RV32-NEXT: lui t0, 2
+; RV32-NEXT: lui t1, 4
+; RV32-NEXT: lui t2, 8
+; RV32-NEXT: lui t3, 16
+; RV32-NEXT: lui t4, 32
+; RV32-NEXT: lui t5, 64
+; RV32-NEXT: lui t6, 128
+; RV32-NEXT: lui s0, 256
+; RV32-NEXT: lui s1, 512
+; RV32-NEXT: lui s2, 1024
+; RV32-NEXT: lui s3, 2048
+; RV32-NEXT: lui s4, 4096
+; RV32-NEXT: lui s5, 8192
+; RV32-NEXT: lui s6, 16384
+; RV32-NEXT: sw s7, 272(sp)
+; RV32-NEXT: lui s7, 32768
+; RV32-NEXT: sw zero, 276(sp)
+; RV32-NEXT: sw a7, 264(sp)
+; RV32-NEXT: sw zero, 268(sp)
+; RV32-NEXT: sw zero, 256(sp)
+; RV32-NEXT: sw s11, 260(sp)
+; RV32-NEXT: sw zero, 248(sp)
+; RV32-NEXT: sw s8, 252(sp)
+; RV32-NEXT: lui s8, 65536
+; RV32-NEXT: sw zero, 240(sp)
+; RV32-NEXT: sw s9, 244(sp)
+; RV32-NEXT: lui s9, 131072
+; RV32-NEXT: sw zero, 232(sp)
+; RV32-NEXT: sw s10, 236(sp)
+; RV32-NEXT: lui s10, 262144
+; RV32-NEXT: sw zero, 224(sp)
+; RV32-NEXT: sw a3, 228(sp)
+; RV32-NEXT: sw zero, 216(sp)
+; RV32-NEXT: sw a4, 220(sp)
+; RV32-NEXT: sw zero, 208(sp)
+; RV32-NEXT: sw a5, 212(sp)
+; RV32-NEXT: sw zero, 200(sp)
+; RV32-NEXT: sw a6, 204(sp)
+; RV32-NEXT: sw zero, 192(sp)
+; RV32-NEXT: sw ra, 196(sp)
+; RV32-NEXT: sw zero, 184(sp)
+; RV32-NEXT: sw a0, 188(sp)
+; RV32-NEXT: sw zero, 176(sp)
+; RV32-NEXT: sw a1, 180(sp)
+; RV32-NEXT: slli s11, s11, 11
+; RV32-NEXT: sw zero, 168(sp)
+; RV32-NEXT: sw s11, 172(sp)
+; RV32-NEXT: sw zero, 160(sp)
+; RV32-NEXT: sw a2, 164(sp)
+; RV32-NEXT: sw zero, 152(sp)
+; RV32-NEXT: sw t0, 156(sp)
+; RV32-NEXT: sw zero, 144(sp)
+; RV32-NEXT: sw t1, 148(sp)
+; RV32-NEXT: sw zero, 136(sp)
+; RV32-NEXT: sw t2, 140(sp)
+; RV32-NEXT: sw zero, 128(sp)
+; RV32-NEXT: sw t3, 132(sp)
+; RV32-NEXT: sw zero, 120(sp)
+; RV32-NEXT: sw t4, 124(sp)
+; RV32-NEXT: sw zero, 112(sp)
+; RV32-NEXT: sw t5, 116(sp)
+; RV32-NEXT: sw zero, 104(sp)
+; RV32-NEXT: sw t6, 108(sp)
+; RV32-NEXT: sw zero, 96(sp)
+; RV32-NEXT: sw s0, 100(sp)
+; RV32-NEXT: sw zero, 88(sp)
+; RV32-NEXT: sw s1, 92(sp)
+; RV32-NEXT: sw zero, 80(sp)
+; RV32-NEXT: sw s2, 84(sp)
+; RV32-NEXT: sw zero, 72(sp)
+; RV32-NEXT: sw s3, 76(sp)
+; RV32-NEXT: sw zero, 64(sp)
+; RV32-NEXT: sw s4, 68(sp)
+; RV32-NEXT: sw zero, 56(sp)
+; RV32-NEXT: sw s5, 60(sp)
+; RV32-NEXT: sw zero, 48(sp)
+; RV32-NEXT: sw s6, 52(sp)
+; RV32-NEXT: sw zero, 40(sp)
+; RV32-NEXT: sw s7, 44(sp)
+; RV32-NEXT: sw zero, 32(sp)
+; RV32-NEXT: sw s8, 36(sp)
+; RV32-NEXT: sw zero, 24(sp)
+; RV32-NEXT: sw s9, 28(sp)
+; RV32-NEXT: sw zero, 16(sp)
+; RV32-NEXT: sw s10, 20(sp)
+; RV32-NEXT: sw zero, 8(sp)
+; RV32-NEXT: sw a7, 12(sp)
+; RV32-NEXT: lui a0, 61681
+; RV32-NEXT: addi a0, a0, -241
+; RV32-NEXT: vsetivli zero, 2, e32, m1, ta, ma
+; RV32-NEXT: vmv.v.x v3, a0
+; RV32-NEXT: lui a0, 209715
+; RV32-NEXT: addi a0, a0, 819
+; RV32-NEXT: vmv.v.x v2, a0
+; RV32-NEXT: lui a0, 349525
+; RV32-NEXT: addi a0, a0, 1365
+; RV32-NEXT: vmv.v.x v1, a0
+; RV32-NEXT: addi a0, sp, 272
+; RV32-NEXT: vsetivli zero, 1, e64, m1, ta, ma
+; RV32-NEXT: vlse64.v v0, (a0), zero
+; RV32-NEXT: addi a0, sp, 264
+; RV32-NEXT: vlse64.v v13, (a0), zero
+; RV32-NEXT: addi a0, sp, 256
+; RV32-NEXT: vlse64.v v14, (a0), zero
+; RV32-NEXT: addi a0, sp, 248
+; RV32-NEXT: vlse64.v v15, (a0), zero
+; RV32-NEXT: addi a0, sp, 240
+; RV32-NEXT: vlse64.v v16, (a0), zero
+; RV32-NEXT: addi a0, sp, 232
+; RV32-NEXT: vlse64.v v17, (a0), zero
+; RV32-NEXT: addi a0, sp, 224
+; RV32-NEXT: vlse64.v v18, (a0), zero
+; RV32-NEXT: addi a0, sp, 216
+; RV32-NEXT: vlse64.v v19, (a0), zero
+; RV32-NEXT: addi a0, sp, 208
+; RV32-NEXT: vlse64.v v20, (a0), zero
+; RV32-NEXT: addi a0, sp, 200
+; RV32-NEXT: vlse64.v v21, (a0), zero
+; RV32-NEXT: addi a0, sp, 192
+; RV32-NEXT: vlse64.v v22, (a0), zero
+; RV32-NEXT: addi a0, sp, 184
+; RV32-NEXT: vlse64.v v23, (a0), zero
+; RV32-NEXT: addi a0, sp, 176
+; RV32-NEXT: vlse64.v v24, (a0), zero
+; RV32-NEXT: addi a0, sp, 168
+; RV32-NEXT: vlse64.v v25, (a0), zero
+; RV32-NEXT: addi a0, sp, 160
+; RV32-NEXT: vlse64.v v26, (a0), zero
+; RV32-NEXT: addi a0, sp, 152
+; RV32-NEXT: vlse64.v v9, (a0), zero
+; RV32-NEXT: addi a0, sp, 144
+; RV32-NEXT: vlse64.v v10, (a0), zero
+; RV32-NEXT: addi a0, sp, 136
+; RV32-NEXT: vlse64.v v29, (a0), zero
+; RV32-NEXT: addi a0, sp, 128
+; RV32-NEXT: vlse64.v v30, (a0), zero
+; RV32-NEXT: addi a0, sp, 120
+; RV32-NEXT: vlse64.v v31, (a0), zero
+; RV32-NEXT: addi a0, sp, 112
+; RV32-NEXT: vlse64.v v11, (a0), zero
+; RV32-NEXT: addi a0, sp, 104
+; RV32-NEXT: vlse64.v v12, (a0), zero
+; RV32-NEXT: addi a0, sp, 96
+; RV32-NEXT: vlse64.v v5, (a0), zero
+; RV32-NEXT: addi a0, sp, 88
+; RV32-NEXT: vlse64.v v4, (a0), zero
+; RV32-NEXT: li a6, 56
+; RV32-NEXT: vsrl.vi v27, v8, 24
+; RV32-NEXT: vsrl.vx v28, v8, a6
+; RV32-NEXT: li ra, 40
+; RV32-NEXT: vsrl.vx v7, v8, ra
+; RV32-NEXT: vsll.vx v6, v8, a6
+; RV32-NEXT: addi a4, t3, -256
+; RV32-NEXT: vand.vx v7, v7, a4
+; RV32-NEXT: vor.vv v28, v7, v28
+; RV32-NEXT: vand.vx v7, v8, a4
+; RV32-NEXT: vsll.vx v7, v7, ra
+; RV32-NEXT: vor.vv v7, v6, v7
+; RV32-NEXT: vsrl.vi v6, v8, 8
+; RV32-NEXT: lui a5, 4080
+; RV32-NEXT: vand.vx v27, v27, a5
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v0, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v6, v6, v0
+; RV32-NEXT: vor.vv v27, v6, v27
+; RV32-NEXT: addi a3, sp, 80
+; RV32-NEXT: vlse64.v v6, (a3), zero
+; RV32-NEXT: vor.vv v27, v27, v28
+; RV32-NEXT: vand.vx v28, v8, a5
+; RV32-NEXT: vsll.vi v28, v28, 24
+; RV32-NEXT: vand.vv v8, v8, v0
+; RV32-NEXT: vsll.vi v8, v8, 8
+; RV32-NEXT: vor.vv v8, v28, v8
+; RV32-NEXT: addi a3, sp, 72
+; RV32-NEXT: vlse64.v v28, (a3), zero
+; RV32-NEXT: vor.vv v8, v7, v8
+; RV32-NEXT: addi a3, sp, 64
+; RV32-NEXT: vlse64.v v7, (a3), zero
+; RV32-NEXT: vor.vv v8, v8, v27
+; RV32-NEXT: vsrl.vi v27, v8, 4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v3, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v8, v8, v3
+; RV32-NEXT: vand.vv v27, v27, v3
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v27, v8
+; RV32-NEXT: vsrl.vi v27, v8, 2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v2, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v8, v8, v2
+; RV32-NEXT: vand.vv v27, v27, v2
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v8, v27, v8
+; RV32-NEXT: vsrl.vi v27, v8, 1
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v1, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v8, v8, v1
+; RV32-NEXT: vand.vv v27, v27, v1
+; RV32-NEXT: vadd.vv v8, v8, v8
+; RV32-NEXT: vor.vv v8, v27, v8
+; RV32-NEXT: addi a3, sp, 56
+; RV32-NEXT: vlse64.v v27, (a3), zero
+; RV32-NEXT: vand.vv v13, v8, v13
+; RV32-NEXT: vand.vv v14, v8, v14
+; RV32-NEXT: vand.vv v15, v8, v15
+; RV32-NEXT: vand.vv v16, v8, v16
+; RV32-NEXT: vand.vv v17, v8, v17
+; RV32-NEXT: vand.vv v18, v8, v18
+; RV32-NEXT: vand.vv v19, v8, v19
+; RV32-NEXT: vand.vv v20, v8, v20
+; RV32-NEXT: vand.vv v21, v8, v21
+; RV32-NEXT: vand.vv v22, v8, v22
+; RV32-NEXT: vand.vv v23, v8, v23
+; RV32-NEXT: vand.vv v24, v8, v24
+; RV32-NEXT: vand.vv v25, v8, v25
+; RV32-NEXT: vand.vv v26, v8, v26
+; RV32-NEXT: vand.vv v3, v8, v9
+; RV32-NEXT: vand.vv v2, v8, v10
+; RV32-NEXT: vand.vv v29, v8, v29
+; RV32-NEXT: vand.vv v30, v8, v30
+; RV32-NEXT: vand.vv v31, v8, v31
+; RV32-NEXT: vand.vv v0, v8, v11
+; RV32-NEXT: vand.vv v9, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v5, v8, v5
+; RV32-NEXT: vand.vv v4, v8, v4
+; RV32-NEXT: vand.vv v6, v8, v6
+; RV32-NEXT: vand.vv v9, v8, v28
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: addi a3, sp, 48
+; RV32-NEXT: addi a0, sp, 40
+; RV32-NEXT: vlse64.v v9, (a3), zero
+; RV32-NEXT: vlse64.v v10, (a0), zero
+; RV32-NEXT: vand.vv v11, v8, v7
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v11, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v11, v8, v27
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v11, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v9, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: addi a2, sp, 32
+; RV32-NEXT: addi a3, sp, 24
+; RV32-NEXT: addi a1, sp, 16
+; RV32-NEXT: addi a0, sp, 8
+; RV32-NEXT: vlse64.v v9, (a2), zero
+; RV32-NEXT: vlse64.v v10, (a3), zero
+; RV32-NEXT: vlse64.v v11, (a1), zero
+; RV32-NEXT: vlse64.v v12, (a0), zero
+; RV32-NEXT: vand.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 5
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v9, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v9, v8, v11
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 5
+; RV32-NEXT: sub a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v9, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vi v9, v8, 2
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vi v9, v8, 1
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vi v9, v8, 4
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vi v9, v8, 8
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: li a0, 16
+; RV32-NEXT: vand.vx v9, v8, a0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: li a0, 32
+; RV32-NEXT: vand.vx v9, v8, a0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: li a0, 64
+; RV32-NEXT: vand.vx v9, v8, a0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: li a0, 128
+; RV32-NEXT: vand.vx v9, v8, a0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: li a0, 256
+; RV32-NEXT: vand.vx v9, v8, a0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: li a0, 512
+; RV32-NEXT: vand.vx v9, v8, a0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: li a0, 1024
+; RV32-NEXT: vand.vx v9, v8, a0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s11
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: lui a0, 1
+; RV32-NEXT: vand.vx v9, v8, a0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, t0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 4
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, t1
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, t2
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 4
+; RV32-NEXT: sub a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, t3
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, t4
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, t5
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, t6
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s1
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 3
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s2
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s3
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 3
+; RV32-NEXT: sub a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s4
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s5
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 2
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s6
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s7
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 1
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s8
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s9
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v1, v8, s10
+; RV32-NEXT: vmul.vv v1, v8, v1
+; RV32-NEXT: vmul.vv v9, v8, v13
+; RV32-NEXT: addi a0, sp, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vmul.vv v10, v8, v14
+; RV32-NEXT: vmul.vv v11, v8, v15
+; RV32-NEXT: vmul.vv v12, v8, v16
+; RV32-NEXT: vmul.vv v13, v8, v17
+; RV32-NEXT: vmul.vv v14, v8, v18
+; RV32-NEXT: vmul.vv v15, v8, v19
+; RV32-NEXT: vmul.vv v16, v8, v20
+; RV32-NEXT: vmul.vv v17, v8, v21
+; RV32-NEXT: vmul.vv v18, v8, v22
+; RV32-NEXT: vmul.vv v19, v8, v23
+; RV32-NEXT: vmul.vv v20, v8, v24
+; RV32-NEXT: vmul.vv v21, v8, v25
+; RV32-NEXT: vmul.vv v22, v8, v26
+; RV32-NEXT: vmul.vv v23, v8, v3
+; RV32-NEXT: vmul.vv v24, v8, v2
+; RV32-NEXT: vmul.vv v25, v8, v29
+; RV32-NEXT: vmul.vv v26, v8, v30
+; RV32-NEXT: vmul.vv v27, v8, v31
+; RV32-NEXT: vmul.vv v28, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v29, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v29, v8, v29
+; RV32-NEXT: vmul.vv v30, v8, v5
+; RV32-NEXT: vmul.vv v31, v8, v4
+; RV32-NEXT: vmul.vv v7, v8, v6
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v6, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v6, v8, v6
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v5, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v5, v8, v5
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v4, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v4, v8, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v3, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v3, v8, v3
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v2, v8, v2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 5
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v0, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 5
+; RV32-NEXT: sub a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v8, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v8, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vi v8, v8, 0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 4
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 4
+; RV32-NEXT: sub a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 3
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 3
+; RV32-NEXT: sub a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 2
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 1
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: vxor.vv v8, v8, v1
+; RV32-NEXT: addi a0, sp, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: vxor.vv v8, v8, v11
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: vxor.vv v8, v8, v13
+; RV32-NEXT: vxor.vv v8, v8, v14
+; RV32-NEXT: vxor.vv v8, v8, v15
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: vxor.vv v8, v8, v17
+; RV32-NEXT: vxor.vv v8, v8, v18
+; RV32-NEXT: vxor.vv v8, v8, v19
+; RV32-NEXT: vxor.vv v8, v8, v20
+; RV32-NEXT: vxor.vv v8, v8, v21
+; RV32-NEXT: vxor.vv v8, v8, v22
+; RV32-NEXT: vxor.vv v8, v8, v23
+; RV32-NEXT: vxor.vv v8, v8, v24
+; RV32-NEXT: vxor.vv v8, v8, v25
+; RV32-NEXT: vxor.vv v8, v8, v26
+; RV32-NEXT: vxor.vv v8, v8, v27
+; RV32-NEXT: vxor.vv v8, v8, v28
+; RV32-NEXT: vxor.vv v8, v8, v29
+; RV32-NEXT: vxor.vv v8, v8, v30
+; RV32-NEXT: vxor.vv v8, v8, v31
+; RV32-NEXT: vxor.vv v8, v8, v7
+; RV32-NEXT: vxor.vv v8, v8, v6
+; RV32-NEXT: vxor.vv v8, v8, v5
+; RV32-NEXT: vxor.vv v8, v8, v4
+; RV32-NEXT: vxor.vv v8, v8, v3
+; RV32-NEXT: vxor.vv v8, v8, v2
+; RV32-NEXT: vxor.vv v8, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: vsrl.vx v9, v8, a6
+; RV32-NEXT: vsll.vx v10, v8, a6
+; RV32-NEXT: vsrl.vx v11, v8, ra
+; RV32-NEXT: vand.vx v12, v8, a4
+; RV32-NEXT: vand.vx v11, v11, a4
+; RV32-NEXT: vsrl.vi v13, v8, 24
+; RV32-NEXT: vand.vx v14, v8, a5
+; RV32-NEXT: vand.vx v13, v13, a5
+; RV32-NEXT: vsll.vx v12, v12, ra
+; RV32-NEXT: vsrl.vi v15, v8, 8
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v16, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v16
+; RV32-NEXT: vand.vv v15, v15, v16
+; RV32-NEXT: vor.vv v9, v11, v9
+; RV32-NEXT: vor.vv v11, v15, v13
+; RV32-NEXT: vsll.vi v8, v8, 8
+; RV32-NEXT: vsll.vi v13, v14, 24
+; RV32-NEXT: vor.vv v8, v13, v8
+; RV32-NEXT: vor.vv v10, v10, v12
+; RV32-NEXT: vor.vv v9, v11, v9
+; RV32-NEXT: vor.vv v8, v10, v8
+; RV32-NEXT: vor.vv v8, v8, v9
+; RV32-NEXT: vsrl.vi v9, v8, 4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v10, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v10
+; RV32-NEXT: vand.vv v9, v9, v10
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v9, v8
+; RV32-NEXT: vsrl.vi v9, v8, 2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v10, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v10
+; RV32-NEXT: vand.vv v9, v9, v10
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v8, v9, v8
+; RV32-NEXT: vsrl.vi v9, v8, 1
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v10, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v10
+; RV32-NEXT: vand.vv v9, v9, v10
+; RV32-NEXT: vadd.vv v8, v8, v8
+; RV32-NEXT: vor.vv v8, v9, v8
+; RV32-NEXT: vsrl.vi v8, v8, 1
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add sp, sp, a0
+; RV32-NEXT: lw ra, 348(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s0, 344(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s1, 340(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s2, 336(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s3, 332(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s4, 328(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s5, 324(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s6, 320(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s7, 316(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s8, 312(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s9, 308(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s10, 304(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s11, 300(sp) # 4-byte Folded Reload
+; RV32-NEXT: addi sp, sp, 352
+; RV32-NEXT: ret
+;
+; RV64-LABEL: clmulh_v1i64:
+; RV64: # %bb.0:
+; RV64-NEXT: addi sp, sp, -224
+; RV64-NEXT: sd ra, 216(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s0, 208(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s1, 200(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s2, 192(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s3, 184(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s4, 176(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s5, 168(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s6, 160(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s7, 152(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s8, 144(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s9, 136(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s10, 128(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s11, 120(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: sub sp, sp, a0
+; RV64-NEXT: li s11, 56
+; RV64-NEXT: li ra, 40
+; RV64-NEXT: lui a0, 16
+; RV64-NEXT: vsetivli zero, 1, e64, m1, ta, ma
+; RV64-NEXT: vsrl.vi v10, v8, 24
+; RV64-NEXT: vsrl.vi v9, v8, 8
+; RV64-NEXT: li t2, 255
+; RV64-NEXT: lui t6, 61681
+; RV64-NEXT: lui s0, 209715
+; RV64-NEXT: lui s1, 349525
+; RV64-NEXT: li s10, 16
+; RV64-NEXT: li s9, 32
+; RV64-NEXT: li s8, 64
+; RV64-NEXT: li s7, 128
+; RV64-NEXT: li s5, 256
+; RV64-NEXT: li t5, 512
+; RV64-NEXT: li t3, 1024
+; RV64-NEXT: li t0, 1
+; RV64-NEXT: lui s6, 1
+; RV64-NEXT: lui s4, 2
+; RV64-NEXT: lui t4, 4
+; RV64-NEXT: lui t1, 8
+; RV64-NEXT: lui a7, 32
+; RV64-NEXT: lui a6, 64
+; RV64-NEXT: lui a5, 128
+; RV64-NEXT: lui a4, 256
+; RV64-NEXT: lui a3, 512
+; RV64-NEXT: lui a2, 1024
+; RV64-NEXT: vsrl.vx v11, v8, s11
+; RV64-NEXT: vsrl.vx v12, v8, ra
+; RV64-NEXT: addi t6, t6, -241
+; RV64-NEXT: addi s2, s0, 819
+; RV64-NEXT: addi s3, s1, 1365
+; RV64-NEXT: slli s1, t6, 32
+; RV64-NEXT: add s1, t6, s1
+; RV64-NEXT: slli t6, s2, 32
+; RV64-NEXT: add s2, s2, t6
+; RV64-NEXT: slli t6, s3, 32
+; RV64-NEXT: add s3, s3, t6
+; RV64-NEXT: addi s0, a0, -256
+; RV64-NEXT: lui a1, 16
+; RV64-NEXT: lui a0, 4080
+; RV64-NEXT: vand.vx v10, v10, a0
+; RV64-NEXT: slli t6, t2, 24
+; RV64-NEXT: vand.vx v13, v8, a0
+; RV64-NEXT: vsll.vx v14, v8, s11
+; RV64-NEXT: vand.vx v12, v12, s0
+; RV64-NEXT: vand.vx v9, v9, t6
+; RV64-NEXT: vsll.vi v13, v13, 24
+; RV64-NEXT: vand.vx v15, v8, t6
+; RV64-NEXT: vand.vx v8, v8, s0
+; RV64-NEXT: vor.vv v11, v12, v11
+; RV64-NEXT: vor.vv v9, v9, v10
+; RV64-NEXT: vsll.vi v10, v15, 8
+; RV64-NEXT: vsll.vx v8, v8, ra
+; RV64-NEXT: vor.vv v9, v9, v11
+; RV64-NEXT: vor.vv v10, v13, v10
+; RV64-NEXT: vor.vv v8, v14, v8
+; RV64-NEXT: vor.vv v8, v8, v10
+; RV64-NEXT: vor.vv v8, v8, v9
+; RV64-NEXT: vsrl.vi v9, v8, 4
+; RV64-NEXT: vand.vx v8, v8, s1
+; RV64-NEXT: vand.vx v9, v9, s1
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v9, v8
+; RV64-NEXT: vsrl.vi v9, v8, 2
+; RV64-NEXT: vand.vx v8, v8, s2
+; RV64-NEXT: vand.vx v9, v9, s2
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v9, v8
+; RV64-NEXT: vsrl.vi v9, v8, 1
+; RV64-NEXT: vand.vx v8, v8, s3
+; RV64-NEXT: vand.vx v9, v9, s3
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v9, v8
+; RV64-NEXT: vand.vx v9, v8, s10
+; RV64-NEXT: lui t2, 4096
+; RV64-NEXT: vand.vx v10, v8, s9
+; RV64-NEXT: lui s9, 8192
+; RV64-NEXT: vand.vx v11, v8, s8
+; RV64-NEXT: lui s8, 16384
+; RV64-NEXT: vand.vx v12, v8, s7
+; RV64-NEXT: lui s10, 32768
+; RV64-NEXT: vand.vx v13, v8, s5
+; RV64-NEXT: lui s11, 65536
+; RV64-NEXT: vand.vx v14, v8, t5
+; RV64-NEXT: lui t5, 131072
+; RV64-NEXT: vand.vx v15, v8, t3
+; RV64-NEXT: slli t3, t0, 11
+; RV64-NEXT: vand.vx v16, v8, t3
+; RV64-NEXT: lui t3, 262144
+; RV64-NEXT: vand.vx v17, v8, s6
+; RV64-NEXT: slli a0, t0, 31
+; RV64-NEXT: sd a0, 96(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v18, v8, s4
+; RV64-NEXT: slli a0, t0, 32
+; RV64-NEXT: sd a0, 88(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v19, v8, t4
+; RV64-NEXT: slli a0, t0, 33
+; RV64-NEXT: sd a0, 80(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v20, v8, t1
+; RV64-NEXT: slli a0, t0, 34
+; RV64-NEXT: sd a0, 72(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v21, v8, a1
+; RV64-NEXT: slli a0, t0, 35
+; RV64-NEXT: sd a0, 64(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v22, v8, a7
+; RV64-NEXT: slli a0, t0, 36
+; RV64-NEXT: sd a0, 56(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v23, v8, a6
+; RV64-NEXT: slli a0, t0, 37
+; RV64-NEXT: sd a0, 48(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v24, v8, a5
+; RV64-NEXT: slli a0, t0, 38
+; RV64-NEXT: sd a0, 40(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v25, v8, a4
+; RV64-NEXT: slli a0, t0, 39
+; RV64-NEXT: sd a0, 32(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v26, v8, a3
+; RV64-NEXT: slli a0, t0, 40
+; RV64-NEXT: sd a0, 24(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v27, v8, a2
+; RV64-NEXT: slli a0, t0, 41
+; RV64-NEXT: sd a0, 16(sp) # 8-byte Folded Spill
+; RV64-NEXT: lui a0, 2048
+; RV64-NEXT: vand.vx v28, v8, a0
+; RV64-NEXT: slli s5, t0, 42
+; RV64-NEXT: vand.vx v29, v8, t2
+; RV64-NEXT: slli s6, t0, 43
+; RV64-NEXT: vand.vx v30, v8, s9
+; RV64-NEXT: slli s7, t0, 44
+; RV64-NEXT: vand.vx v31, v8, s8
+; RV64-NEXT: slli s8, t0, 45
+; RV64-NEXT: vand.vx v7, v8, s10
+; RV64-NEXT: slli s9, t0, 46
+; RV64-NEXT: vand.vx v6, v8, s11
+; RV64-NEXT: slli s10, t0, 47
+; RV64-NEXT: vand.vx v5, v8, t5
+; RV64-NEXT: slli s11, t0, 48
+; RV64-NEXT: vand.vx v0, v8, t3
+; RV64-NEXT: slli ra, t0, 49
+; RV64-NEXT: slli t5, t0, 50
+; RV64-NEXT: slli t4, t0, 51
+; RV64-NEXT: slli t3, t0, 52
+; RV64-NEXT: slli t2, t0, 53
+; RV64-NEXT: slli t1, t0, 54
+; RV64-NEXT: slli a7, t0, 55
+; RV64-NEXT: slli a6, t0, 56
+; RV64-NEXT: slli a5, t0, 57
+; RV64-NEXT: slli a4, t0, 58
+; RV64-NEXT: slli a3, t0, 59
+; RV64-NEXT: slli a2, t0, 60
+; RV64-NEXT: slli a1, t0, 61
+; RV64-NEXT: slli t0, t0, 62
+; RV64-NEXT: li a0, -1
+; RV64-NEXT: slli a0, a0, 63
+; RV64-NEXT: vand.vi v4, v8, 2
+; RV64-NEXT: vand.vi v3, v8, 1
+; RV64-NEXT: vand.vi v2, v8, 4
+; RV64-NEXT: vand.vi v1, v8, 8
+; RV64-NEXT: vmul.vv v4, v8, v4
+; RV64-NEXT: sd t6, 8(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli s4, t6, 5
+; RV64-NEXT: add t6, s4, t6
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v4, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v4, v8, v3
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 5
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v4, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v4, v8, v2
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli s4, t6, 5
+; RV64-NEXT: sub t6, s4, t6
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v4, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v4, v8, v1
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v4, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v9
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v10
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v11
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v12
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v13
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 3
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v14
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 3
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v15
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v16
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v17
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v18
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v19
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 3
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v20
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 3
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v21
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli s4, t6, 4
+; RV64-NEXT: add t6, s4, t6
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v22
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v23
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli s4, t6, 4
+; RV64-NEXT: sub t6, s4, t6
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v24
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v25
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v26
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v27
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v28
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v29
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli s4, t6, 3
+; RV64-NEXT: add t6, s4, t6
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v30
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 3
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v31
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli s4, t6, 3
+; RV64-NEXT: sub t6, s4, t6
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v7
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v6
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli s4, t6, 2
+; RV64-NEXT: add t6, s4, t6
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v5
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v0
+; RV64-NEXT: csrr s4, vlenb
+; RV64-NEXT: slli t6, s4, 1
+; RV64-NEXT: add s4, t6, s4
+; RV64-NEXT: ld t6, 8(sp) # 8-byte Folded Reload
+; RV64-NEXT: add s4, sp, s4
+; RV64-NEXT: addi s4, s4, 112
+; RV64-NEXT: vs1r.v v9, (s4) # vscale x 8-byte Folded Spill
+; RV64-NEXT: ld s4, 96(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s4
+; RV64-NEXT: vmul.vv v9, v8, v9
+; RV64-NEXT: csrr s4, vlenb
+; RV64-NEXT: slli s4, s4, 1
+; RV64-NEXT: add s4, sp, s4
+; RV64-NEXT: addi s4, s4, 112
+; RV64-NEXT: vs1r.v v9, (s4) # vscale x 8-byte Folded Spill
+; RV64-NEXT: ld s4, 88(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s4
+; RV64-NEXT: vmul.vv v9, v8, v9
+; RV64-NEXT: csrr s4, vlenb
+; RV64-NEXT: add s4, sp, s4
+; RV64-NEXT: addi s4, s4, 112
+; RV64-NEXT: vs1r.v v9, (s4) # vscale x 8-byte Folded Spill
+; RV64-NEXT: ld s4, 80(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s4
+; RV64-NEXT: vmul.vv v9, v8, v9
+; RV64-NEXT: addi s4, sp, 112
+; RV64-NEXT: vs1r.v v9, (s4) # vscale x 8-byte Folded Spill
+; RV64-NEXT: ld s4, 72(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s4
+; RV64-NEXT: vmul.vv v3, v8, v9
+; RV64-NEXT: ld s4, 64(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s4
+; RV64-NEXT: vmul.vv v4, v8, v9
+; RV64-NEXT: ld s4, 56(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s4
+; RV64-NEXT: vmul.vv v5, v8, v9
+; RV64-NEXT: ld s4, 48(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s4
+; RV64-NEXT: vmul.vv v6, v8, v9
+; RV64-NEXT: ld s4, 40(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s4
+; RV64-NEXT: vmul.vv v7, v8, v9
+; RV64-NEXT: ld s4, 32(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s4
+; RV64-NEXT: vmul.vv v31, v8, v9
+; RV64-NEXT: ld s4, 24(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s4
+; RV64-NEXT: vmul.vv v30, v8, v9
+; RV64-NEXT: ld s4, 16(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s4
+; RV64-NEXT: vmul.vv v29, v8, v9
+; RV64-NEXT: vand.vx v9, v8, s5
+; RV64-NEXT: vmul.vv v28, v8, v9
+; RV64-NEXT: vand.vx v9, v8, s6
+; RV64-NEXT: vmul.vv v27, v8, v9
+; RV64-NEXT: vand.vx v9, v8, s7
+; RV64-NEXT: vmul.vv v26, v8, v9
+; RV64-NEXT: vand.vx v9, v8, s8
+; RV64-NEXT: vmul.vv v25, v8, v9
+; RV64-NEXT: vand.vx v9, v8, s9
+; RV64-NEXT: vmul.vv v24, v8, v9
+; RV64-NEXT: vand.vx v9, v8, s10
+; RV64-NEXT: vmul.vv v23, v8, v9
+; RV64-NEXT: vand.vx v9, v8, s11
+; RV64-NEXT: vmul.vv v22, v8, v9
+; RV64-NEXT: vand.vx v9, v8, ra
+; RV64-NEXT: vmul.vv v21, v8, v9
+; RV64-NEXT: vand.vx v9, v8, t5
+; RV64-NEXT: vmul.vv v20, v8, v9
+; RV64-NEXT: vand.vx v9, v8, t4
+; RV64-NEXT: vmul.vv v19, v8, v9
+; RV64-NEXT: vand.vx v9, v8, t3
+; RV64-NEXT: vmul.vv v18, v8, v9
+; RV64-NEXT: vand.vx v9, v8, t2
+; RV64-NEXT: vmul.vv v17, v8, v9
+; RV64-NEXT: vand.vx v9, v8, t1
+; RV64-NEXT: vmul.vv v16, v8, v9
+; RV64-NEXT: vand.vx v9, v8, a7
+; RV64-NEXT: vmul.vv v15, v8, v9
+; RV64-NEXT: vand.vx v9, v8, a6
+; RV64-NEXT: vmul.vv v14, v8, v9
+; RV64-NEXT: vand.vx v9, v8, a5
+; RV64-NEXT: vmul.vv v13, v8, v9
+; RV64-NEXT: vand.vx v9, v8, a4
+; RV64-NEXT: vmul.vv v12, v8, v9
+; RV64-NEXT: vand.vx v9, v8, a3
+; RV64-NEXT: vmul.vv v11, v8, v9
+; RV64-NEXT: vand.vx v9, v8, a2
+; RV64-NEXT: vmul.vv v10, v8, v9
+; RV64-NEXT: vand.vx v9, v8, a1
+; RV64-NEXT: vmul.vv v9, v8, v9
+; RV64-NEXT: vand.vx v0, v8, t0
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vand.vx v1, v8, a0
+; RV64-NEXT: vmul.vv v8, v8, v1
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a1, a0, 5
+; RV64-NEXT: add a0, a1, a0
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v1, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v2, v1
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a1, a0, 5
+; RV64-NEXT: sub a0, a1, a0
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a1, a0, 4
+; RV64-NEXT: add a0, a1, a0
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a1, a0, 4
+; RV64-NEXT: sub a0, a1, a0
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a1, a0, 3
+; RV64-NEXT: add a0, a1, a0
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a1, a0, 3
+; RV64-NEXT: sub a0, a1, a0
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a1, a0, 2
+; RV64-NEXT: add a0, a1, a0
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a1, a0, 1
+; RV64-NEXT: add a0, a1, a0
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: addi a0, sp, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v1, v2
+; RV64-NEXT: vxor.vv v3, v2, v3
+; RV64-NEXT: vxor.vv v4, v3, v4
+; RV64-NEXT: vxor.vv v5, v4, v5
+; RV64-NEXT: vxor.vv v6, v5, v6
+; RV64-NEXT: vxor.vv v7, v6, v7
+; RV64-NEXT: vxor.vv v31, v7, v31
+; RV64-NEXT: vxor.vv v30, v31, v30
+; RV64-NEXT: vxor.vv v29, v30, v29
+; RV64-NEXT: vxor.vv v28, v29, v28
+; RV64-NEXT: vxor.vv v27, v28, v27
+; RV64-NEXT: vxor.vv v26, v27, v26
+; RV64-NEXT: vxor.vv v25, v26, v25
+; RV64-NEXT: vxor.vv v24, v25, v24
+; RV64-NEXT: vxor.vv v23, v24, v23
+; RV64-NEXT: vxor.vv v22, v23, v22
+; RV64-NEXT: vxor.vv v21, v22, v21
+; RV64-NEXT: vxor.vv v20, v21, v20
+; RV64-NEXT: vxor.vv v19, v20, v19
+; RV64-NEXT: vxor.vv v18, v19, v18
+; RV64-NEXT: vxor.vv v17, v18, v17
+; RV64-NEXT: vxor.vv v16, v17, v16
+; RV64-NEXT: vxor.vv v15, v16, v15
+; RV64-NEXT: vxor.vv v14, v15, v14
+; RV64-NEXT: vxor.vv v13, v14, v13
+; RV64-NEXT: vxor.vv v12, v13, v12
+; RV64-NEXT: vxor.vv v11, v12, v11
+; RV64-NEXT: vxor.vv v10, v11, v10
+; RV64-NEXT: vxor.vv v9, v10, v9
+; RV64-NEXT: vxor.vv v9, v9, v0
+; RV64-NEXT: vxor.vv v8, v9, v8
+; RV64-NEXT: li a0, 56
+; RV64-NEXT: vsrl.vx v9, v8, a0
+; RV64-NEXT: li a1, 40
+; RV64-NEXT: vsrl.vx v10, v8, a1
+; RV64-NEXT: vsrl.vi v11, v8, 24
+; RV64-NEXT: vsrl.vi v12, v8, 8
+; RV64-NEXT: vand.vx v10, v10, s0
+; RV64-NEXT: vor.vv v9, v10, v9
+; RV64-NEXT: vand.vx v10, v8, t6
+; RV64-NEXT: lui a2, 4080
+; RV64-NEXT: vand.vx v11, v11, a2
+; RV64-NEXT: vand.vx v12, v12, t6
+; RV64-NEXT: vor.vv v11, v12, v11
+; RV64-NEXT: vand.vx v12, v8, a2
+; RV64-NEXT: vsll.vi v10, v10, 8
+; RV64-NEXT: vsll.vi v12, v12, 24
+; RV64-NEXT: vor.vv v10, v12, v10
+; RV64-NEXT: vsll.vx v12, v8, a0
+; RV64-NEXT: vand.vx v8, v8, s0
+; RV64-NEXT: vsll.vx v8, v8, a1
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vor.vv v9, v11, v9
+; RV64-NEXT: vor.vv v8, v8, v10
+; RV64-NEXT: vor.vv v8, v8, v9
+; RV64-NEXT: vsrl.vi v9, v8, 4
+; RV64-NEXT: vand.vx v8, v8, s1
+; RV64-NEXT: vand.vx v9, v9, s1
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v9, v8
+; RV64-NEXT: vsrl.vi v9, v8, 2
+; RV64-NEXT: vand.vx v8, v8, s2
+; RV64-NEXT: vand.vx v9, v9, s2
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v9, v8
+; RV64-NEXT: vsrl.vi v9, v8, 1
+; RV64-NEXT: vand.vx v8, v8, s3
+; RV64-NEXT: vand.vx v9, v9, s3
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v9, v8
+; RV64-NEXT: vsrl.vi v8, v8, 1
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add sp, sp, a0
+; RV64-NEXT: ld ra, 216(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s0, 208(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s1, 200(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s2, 192(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s3, 184(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s4, 176(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s5, 168(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s6, 160(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s7, 152(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s8, 144(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s9, 136(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s10, 128(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s11, 120(sp) # 8-byte Folded Reload
+; RV64-NEXT: addi sp, sp, 224
+; RV64-NEXT: ret
+ %a = call <1 x i64> @llvm.clmulh.v1i64(<1 x i64> %x, <1 x i64> %y)
+ ret <1 x i64> %a
+}
+
+define <2 x i64> @clmulh_v2i64(<2 x i64> %x, <2 x i64> %y) nounwind {
+; RV32-LABEL: clmulh_v2i64:
+; RV32: # %bb.0:
+; RV32-NEXT: addi sp, sp, -352
+; RV32-NEXT: sw ra, 348(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s0, 344(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s1, 340(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s2, 336(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s3, 332(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s4, 328(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s5, 324(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s6, 320(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s7, 316(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s8, 312(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s9, 308(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s10, 304(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s11, 300(sp) # 4-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: sub sp, sp, a0
+; RV32-NEXT: lui s7, 1044480
+; RV32-NEXT: lui a7, 524288
+; RV32-NEXT: li s11, 1
+; RV32-NEXT: li s8, 2
+; RV32-NEXT: li s9, 4
+; RV32-NEXT: li s10, 8
+; RV32-NEXT: li a3, 16
+; RV32-NEXT: li a4, 32
+; RV32-NEXT: li a5, 64
+; RV32-NEXT: li a6, 128
+; RV32-NEXT: li ra, 256
+; RV32-NEXT: li a0, 512
+; RV32-NEXT: li a1, 1024
+; RV32-NEXT: lui a2, 1
+; RV32-NEXT: lui t0, 2
+; RV32-NEXT: lui t1, 4
+; RV32-NEXT: lui t2, 8
+; RV32-NEXT: lui t3, 16
+; RV32-NEXT: lui t4, 32
+; RV32-NEXT: lui t5, 64
+; RV32-NEXT: lui t6, 128
+; RV32-NEXT: lui s0, 256
+; RV32-NEXT: lui s1, 512
+; RV32-NEXT: lui s2, 1024
+; RV32-NEXT: lui s3, 2048
+; RV32-NEXT: lui s4, 4096
+; RV32-NEXT: lui s5, 8192
+; RV32-NEXT: lui s6, 16384
+; RV32-NEXT: sw s7, 272(sp)
+; RV32-NEXT: lui s7, 32768
+; RV32-NEXT: sw zero, 276(sp)
+; RV32-NEXT: sw a7, 264(sp)
+; RV32-NEXT: sw zero, 268(sp)
+; RV32-NEXT: sw zero, 256(sp)
+; RV32-NEXT: sw s11, 260(sp)
+; RV32-NEXT: sw zero, 248(sp)
+; RV32-NEXT: sw s8, 252(sp)
+; RV32-NEXT: lui s8, 65536
+; RV32-NEXT: sw zero, 240(sp)
+; RV32-NEXT: sw s9, 244(sp)
+; RV32-NEXT: lui s9, 131072
+; RV32-NEXT: sw zero, 232(sp)
+; RV32-NEXT: sw s10, 236(sp)
+; RV32-NEXT: lui s10, 262144
+; RV32-NEXT: sw zero, 224(sp)
+; RV32-NEXT: sw a3, 228(sp)
+; RV32-NEXT: sw zero, 216(sp)
+; RV32-NEXT: sw a4, 220(sp)
+; RV32-NEXT: sw zero, 208(sp)
+; RV32-NEXT: sw a5, 212(sp)
+; RV32-NEXT: sw zero, 200(sp)
+; RV32-NEXT: sw a6, 204(sp)
+; RV32-NEXT: sw zero, 192(sp)
+; RV32-NEXT: sw ra, 196(sp)
+; RV32-NEXT: sw zero, 184(sp)
+; RV32-NEXT: sw a0, 188(sp)
+; RV32-NEXT: sw zero, 176(sp)
+; RV32-NEXT: sw a1, 180(sp)
+; RV32-NEXT: slli s11, s11, 11
+; RV32-NEXT: sw zero, 168(sp)
+; RV32-NEXT: sw s11, 172(sp)
+; RV32-NEXT: sw zero, 160(sp)
+; RV32-NEXT: sw a2, 164(sp)
+; RV32-NEXT: sw zero, 152(sp)
+; RV32-NEXT: sw t0, 156(sp)
+; RV32-NEXT: sw zero, 144(sp)
+; RV32-NEXT: sw t1, 148(sp)
+; RV32-NEXT: sw zero, 136(sp)
+; RV32-NEXT: sw t2, 140(sp)
+; RV32-NEXT: sw zero, 128(sp)
+; RV32-NEXT: sw t3, 132(sp)
+; RV32-NEXT: sw zero, 120(sp)
+; RV32-NEXT: sw t4, 124(sp)
+; RV32-NEXT: sw zero, 112(sp)
+; RV32-NEXT: sw t5, 116(sp)
+; RV32-NEXT: sw zero, 104(sp)
+; RV32-NEXT: sw t6, 108(sp)
+; RV32-NEXT: sw zero, 96(sp)
+; RV32-NEXT: sw s0, 100(sp)
+; RV32-NEXT: sw zero, 88(sp)
+; RV32-NEXT: sw s1, 92(sp)
+; RV32-NEXT: sw zero, 80(sp)
+; RV32-NEXT: sw s2, 84(sp)
+; RV32-NEXT: sw zero, 72(sp)
+; RV32-NEXT: sw s3, 76(sp)
+; RV32-NEXT: sw zero, 64(sp)
+; RV32-NEXT: sw s4, 68(sp)
+; RV32-NEXT: sw zero, 56(sp)
+; RV32-NEXT: sw s5, 60(sp)
+; RV32-NEXT: sw zero, 48(sp)
+; RV32-NEXT: sw s6, 52(sp)
+; RV32-NEXT: sw zero, 40(sp)
+; RV32-NEXT: sw s7, 44(sp)
+; RV32-NEXT: sw zero, 32(sp)
+; RV32-NEXT: sw s8, 36(sp)
+; RV32-NEXT: sw zero, 24(sp)
+; RV32-NEXT: sw s9, 28(sp)
+; RV32-NEXT: sw zero, 16(sp)
+; RV32-NEXT: sw s10, 20(sp)
+; RV32-NEXT: sw zero, 8(sp)
+; RV32-NEXT: sw a7, 12(sp)
+; RV32-NEXT: lui a0, 61681
+; RV32-NEXT: addi a0, a0, -241
+; RV32-NEXT: vsetivli zero, 4, e32, m1, ta, ma
+; RV32-NEXT: vmv.v.x v3, a0
+; RV32-NEXT: lui a0, 209715
+; RV32-NEXT: addi a0, a0, 819
+; RV32-NEXT: vmv.v.x v2, a0
+; RV32-NEXT: lui a0, 349525
+; RV32-NEXT: addi a0, a0, 1365
+; RV32-NEXT: vmv.v.x v1, a0
+; RV32-NEXT: addi a0, sp, 272
+; RV32-NEXT: vsetivli zero, 2, e64, m1, ta, ma
+; RV32-NEXT: vlse64.v v0, (a0), zero
+; RV32-NEXT: addi a0, sp, 264
+; RV32-NEXT: vlse64.v v13, (a0), zero
+; RV32-NEXT: addi a0, sp, 256
+; RV32-NEXT: vlse64.v v14, (a0), zero
+; RV32-NEXT: addi a0, sp, 248
+; RV32-NEXT: vlse64.v v15, (a0), zero
+; RV32-NEXT: addi a0, sp, 240
+; RV32-NEXT: vlse64.v v16, (a0), zero
+; RV32-NEXT: addi a0, sp, 232
+; RV32-NEXT: vlse64.v v17, (a0), zero
+; RV32-NEXT: addi a0, sp, 224
+; RV32-NEXT: vlse64.v v18, (a0), zero
+; RV32-NEXT: addi a0, sp, 216
+; RV32-NEXT: vlse64.v v19, (a0), zero
+; RV32-NEXT: addi a0, sp, 208
+; RV32-NEXT: vlse64.v v20, (a0), zero
+; RV32-NEXT: addi a0, sp, 200
+; RV32-NEXT: vlse64.v v21, (a0), zero
+; RV32-NEXT: addi a0, sp, 192
+; RV32-NEXT: vlse64.v v22, (a0), zero
+; RV32-NEXT: addi a0, sp, 184
+; RV32-NEXT: vlse64.v v23, (a0), zero
+; RV32-NEXT: addi a0, sp, 176
+; RV32-NEXT: vlse64.v v24, (a0), zero
+; RV32-NEXT: addi a0, sp, 168
+; RV32-NEXT: vlse64.v v25, (a0), zero
+; RV32-NEXT: addi a0, sp, 160
+; RV32-NEXT: vlse64.v v26, (a0), zero
+; RV32-NEXT: addi a0, sp, 152
+; RV32-NEXT: vlse64.v v9, (a0), zero
+; RV32-NEXT: addi a0, sp, 144
+; RV32-NEXT: vlse64.v v10, (a0), zero
+; RV32-NEXT: addi a0, sp, 136
+; RV32-NEXT: vlse64.v v29, (a0), zero
+; RV32-NEXT: addi a0, sp, 128
+; RV32-NEXT: vlse64.v v30, (a0), zero
+; RV32-NEXT: addi a0, sp, 120
+; RV32-NEXT: vlse64.v v31, (a0), zero
+; RV32-NEXT: addi a0, sp, 112
+; RV32-NEXT: vlse64.v v11, (a0), zero
+; RV32-NEXT: addi a0, sp, 104
+; RV32-NEXT: vlse64.v v12, (a0), zero
+; RV32-NEXT: addi a0, sp, 96
+; RV32-NEXT: vlse64.v v5, (a0), zero
+; RV32-NEXT: addi a0, sp, 88
+; RV32-NEXT: vlse64.v v4, (a0), zero
+; RV32-NEXT: li a6, 56
+; RV32-NEXT: vsrl.vi v27, v8, 24
+; RV32-NEXT: vsrl.vx v28, v8, a6
+; RV32-NEXT: li ra, 40
+; RV32-NEXT: vsrl.vx v7, v8, ra
+; RV32-NEXT: vsll.vx v6, v8, a6
+; RV32-NEXT: addi a4, t3, -256
+; RV32-NEXT: vand.vx v7, v7, a4
+; RV32-NEXT: vor.vv v28, v7, v28
+; RV32-NEXT: vand.vx v7, v8, a4
+; RV32-NEXT: vsll.vx v7, v7, ra
+; RV32-NEXT: vor.vv v7, v6, v7
+; RV32-NEXT: vsrl.vi v6, v8, 8
+; RV32-NEXT: lui a5, 4080
+; RV32-NEXT: vand.vx v27, v27, a5
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v0, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v6, v6, v0
+; RV32-NEXT: vor.vv v27, v6, v27
+; RV32-NEXT: addi a3, sp, 80
+; RV32-NEXT: vlse64.v v6, (a3), zero
+; RV32-NEXT: vor.vv v27, v27, v28
+; RV32-NEXT: vand.vx v28, v8, a5
+; RV32-NEXT: vsll.vi v28, v28, 24
+; RV32-NEXT: vand.vv v8, v8, v0
+; RV32-NEXT: vsll.vi v8, v8, 8
+; RV32-NEXT: vor.vv v8, v28, v8
+; RV32-NEXT: addi a3, sp, 72
+; RV32-NEXT: vlse64.v v28, (a3), zero
+; RV32-NEXT: vor.vv v8, v7, v8
+; RV32-NEXT: addi a3, sp, 64
+; RV32-NEXT: vlse64.v v7, (a3), zero
+; RV32-NEXT: vor.vv v8, v8, v27
+; RV32-NEXT: vsrl.vi v27, v8, 4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v3, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v8, v8, v3
+; RV32-NEXT: vand.vv v27, v27, v3
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v27, v8
+; RV32-NEXT: vsrl.vi v27, v8, 2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v2, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v8, v8, v2
+; RV32-NEXT: vand.vv v27, v27, v2
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v8, v27, v8
+; RV32-NEXT: vsrl.vi v27, v8, 1
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v1, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v8, v8, v1
+; RV32-NEXT: vand.vv v27, v27, v1
+; RV32-NEXT: vadd.vv v8, v8, v8
+; RV32-NEXT: vor.vv v8, v27, v8
+; RV32-NEXT: addi a3, sp, 56
+; RV32-NEXT: vlse64.v v27, (a3), zero
+; RV32-NEXT: vand.vv v13, v8, v13
+; RV32-NEXT: vand.vv v14, v8, v14
+; RV32-NEXT: vand.vv v15, v8, v15
+; RV32-NEXT: vand.vv v16, v8, v16
+; RV32-NEXT: vand.vv v17, v8, v17
+; RV32-NEXT: vand.vv v18, v8, v18
+; RV32-NEXT: vand.vv v19, v8, v19
+; RV32-NEXT: vand.vv v20, v8, v20
+; RV32-NEXT: vand.vv v21, v8, v21
+; RV32-NEXT: vand.vv v22, v8, v22
+; RV32-NEXT: vand.vv v23, v8, v23
+; RV32-NEXT: vand.vv v24, v8, v24
+; RV32-NEXT: vand.vv v25, v8, v25
+; RV32-NEXT: vand.vv v26, v8, v26
+; RV32-NEXT: vand.vv v3, v8, v9
+; RV32-NEXT: vand.vv v2, v8, v10
+; RV32-NEXT: vand.vv v29, v8, v29
+; RV32-NEXT: vand.vv v30, v8, v30
+; RV32-NEXT: vand.vv v31, v8, v31
+; RV32-NEXT: vand.vv v0, v8, v11
+; RV32-NEXT: vand.vv v9, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v5, v8, v5
+; RV32-NEXT: vand.vv v4, v8, v4
+; RV32-NEXT: vand.vv v6, v8, v6
+; RV32-NEXT: vand.vv v9, v8, v28
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: addi a3, sp, 48
+; RV32-NEXT: addi a0, sp, 40
+; RV32-NEXT: vlse64.v v9, (a3), zero
+; RV32-NEXT: vlse64.v v10, (a0), zero
+; RV32-NEXT: vand.vv v11, v8, v7
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v11, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v11, v8, v27
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v11, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v9, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: addi a2, sp, 32
+; RV32-NEXT: addi a3, sp, 24
+; RV32-NEXT: addi a1, sp, 16
+; RV32-NEXT: addi a0, sp, 8
+; RV32-NEXT: vlse64.v v9, (a2), zero
+; RV32-NEXT: vlse64.v v10, (a3), zero
+; RV32-NEXT: vlse64.v v11, (a1), zero
+; RV32-NEXT: vlse64.v v12, (a0), zero
+; RV32-NEXT: vand.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 5
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v9, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v9, v8, v11
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 5
+; RV32-NEXT: sub a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vv v9, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vi v9, v8, 2
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vi v9, v8, 1
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vi v9, v8, 4
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vi v9, v8, 8
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: li a0, 16
+; RV32-NEXT: vand.vx v9, v8, a0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: li a0, 32
+; RV32-NEXT: vand.vx v9, v8, a0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: li a0, 64
+; RV32-NEXT: vand.vx v9, v8, a0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: li a0, 128
+; RV32-NEXT: vand.vx v9, v8, a0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: li a0, 256
+; RV32-NEXT: vand.vx v9, v8, a0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: li a0, 512
+; RV32-NEXT: vand.vx v9, v8, a0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: li a0, 1024
+; RV32-NEXT: vand.vx v9, v8, a0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s11
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: lui a0, 1
+; RV32-NEXT: vand.vx v9, v8, a0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, t0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 4
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, t1
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, t2
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 4
+; RV32-NEXT: sub a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, t3
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, t4
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, t5
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, t6
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s0
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s1
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 3
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s2
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s3
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 3
+; RV32-NEXT: sub a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s4
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s5
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 2
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s6
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s7
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 1
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s8
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v9, v8, s9
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vand.vx v1, v8, s10
+; RV32-NEXT: vmul.vv v1, v8, v1
+; RV32-NEXT: vmul.vv v9, v8, v13
+; RV32-NEXT: addi a0, sp, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: vmul.vv v10, v8, v14
+; RV32-NEXT: vmul.vv v11, v8, v15
+; RV32-NEXT: vmul.vv v12, v8, v16
+; RV32-NEXT: vmul.vv v13, v8, v17
+; RV32-NEXT: vmul.vv v14, v8, v18
+; RV32-NEXT: vmul.vv v15, v8, v19
+; RV32-NEXT: vmul.vv v16, v8, v20
+; RV32-NEXT: vmul.vv v17, v8, v21
+; RV32-NEXT: vmul.vv v18, v8, v22
+; RV32-NEXT: vmul.vv v19, v8, v23
+; RV32-NEXT: vmul.vv v20, v8, v24
+; RV32-NEXT: vmul.vv v21, v8, v25
+; RV32-NEXT: vmul.vv v22, v8, v26
+; RV32-NEXT: vmul.vv v23, v8, v3
+; RV32-NEXT: vmul.vv v24, v8, v2
+; RV32-NEXT: vmul.vv v25, v8, v29
+; RV32-NEXT: vmul.vv v26, v8, v30
+; RV32-NEXT: vmul.vv v27, v8, v31
+; RV32-NEXT: vmul.vv v28, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v29, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v29, v8, v29
+; RV32-NEXT: vmul.vv v30, v8, v5
+; RV32-NEXT: vmul.vv v31, v8, v4
+; RV32-NEXT: vmul.vv v7, v8, v6
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v6, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v6, v8, v6
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v5, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v5, v8, v5
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v4, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v4, v8, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v3, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v3, v8, v3
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v2, v8, v2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 5
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v0, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 5
+; RV32-NEXT: sub a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v9, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v9, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vmul.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs1r.v v8, (a0) # vscale x 8-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v8, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vi v8, v8, 0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 4
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 4
+; RV32-NEXT: sub a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 3
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 3
+; RV32-NEXT: sub a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 2
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a1, a0, 1
+; RV32-NEXT: add a0, a1, a0
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: vxor.vv v8, v8, v1
+; RV32-NEXT: addi a0, sp, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: vxor.vv v8, v8, v11
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: vxor.vv v8, v8, v13
+; RV32-NEXT: vxor.vv v8, v8, v14
+; RV32-NEXT: vxor.vv v8, v8, v15
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: vxor.vv v8, v8, v17
+; RV32-NEXT: vxor.vv v8, v8, v18
+; RV32-NEXT: vxor.vv v8, v8, v19
+; RV32-NEXT: vxor.vv v8, v8, v20
+; RV32-NEXT: vxor.vv v8, v8, v21
+; RV32-NEXT: vxor.vv v8, v8, v22
+; RV32-NEXT: vxor.vv v8, v8, v23
+; RV32-NEXT: vxor.vv v8, v8, v24
+; RV32-NEXT: vxor.vv v8, v8, v25
+; RV32-NEXT: vxor.vv v8, v8, v26
+; RV32-NEXT: vxor.vv v8, v8, v27
+; RV32-NEXT: vxor.vv v8, v8, v28
+; RV32-NEXT: vxor.vv v8, v8, v29
+; RV32-NEXT: vxor.vv v8, v8, v30
+; RV32-NEXT: vxor.vv v8, v8, v31
+; RV32-NEXT: vxor.vv v8, v8, v7
+; RV32-NEXT: vxor.vv v8, v8, v6
+; RV32-NEXT: vxor.vv v8, v8, v5
+; RV32-NEXT: vxor.vv v8, v8, v4
+; RV32-NEXT: vxor.vv v8, v8, v3
+; RV32-NEXT: vxor.vv v8, v8, v2
+; RV32-NEXT: vxor.vv v8, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v9, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v9
+; RV32-NEXT: vsrl.vx v9, v8, a6
+; RV32-NEXT: vsll.vx v10, v8, a6
+; RV32-NEXT: vsrl.vx v11, v8, ra
+; RV32-NEXT: vand.vx v12, v8, a4
+; RV32-NEXT: vand.vx v11, v11, a4
+; RV32-NEXT: vsrl.vi v13, v8, 24
+; RV32-NEXT: vand.vx v14, v8, a5
+; RV32-NEXT: vand.vx v13, v13, a5
+; RV32-NEXT: vsll.vx v12, v12, ra
+; RV32-NEXT: vsrl.vi v15, v8, 8
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v16, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v16
+; RV32-NEXT: vand.vv v15, v15, v16
+; RV32-NEXT: vor.vv v9, v11, v9
+; RV32-NEXT: vor.vv v11, v15, v13
+; RV32-NEXT: vsll.vi v8, v8, 8
+; RV32-NEXT: vsll.vi v13, v14, 24
+; RV32-NEXT: vor.vv v8, v13, v8
+; RV32-NEXT: vor.vv v10, v10, v12
+; RV32-NEXT: vor.vv v9, v11, v9
+; RV32-NEXT: vor.vv v8, v10, v8
+; RV32-NEXT: vor.vv v8, v8, v9
+; RV32-NEXT: vsrl.vi v9, v8, 4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v10, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v10
+; RV32-NEXT: vand.vv v9, v9, v10
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v9, v8
+; RV32-NEXT: vsrl.vi v9, v8, 2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v10, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v10
+; RV32-NEXT: vand.vv v9, v9, v10
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v8, v9, v8
+; RV32-NEXT: vsrl.vi v9, v8, 1
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl1r.v v10, (a0) # vscale x 8-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v10
+; RV32-NEXT: vand.vv v9, v9, v10
+; RV32-NEXT: vadd.vv v8, v8, v8
+; RV32-NEXT: vor.vv v8, v9, v8
+; RV32-NEXT: vsrl.vi v8, v8, 1
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add sp, sp, a0
+; RV32-NEXT: lw ra, 348(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s0, 344(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s1, 340(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s2, 336(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s3, 332(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s4, 328(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s5, 324(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s6, 320(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s7, 316(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s8, 312(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s9, 308(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s10, 304(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s11, 300(sp) # 4-byte Folded Reload
+; RV32-NEXT: addi sp, sp, 352
+; RV32-NEXT: ret
+;
+; RV64-LABEL: clmulh_v2i64:
+; RV64: # %bb.0:
+; RV64-NEXT: addi sp, sp, -224
+; RV64-NEXT: sd ra, 216(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s0, 208(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s1, 200(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s2, 192(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s3, 184(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s4, 176(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s5, 168(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s6, 160(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s7, 152(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s8, 144(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s9, 136(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s10, 128(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s11, 120(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: sub sp, sp, a0
+; RV64-NEXT: li s11, 56
+; RV64-NEXT: li ra, 40
+; RV64-NEXT: lui a0, 16
+; RV64-NEXT: vsetivli zero, 2, e64, m1, ta, ma
+; RV64-NEXT: vsrl.vi v10, v8, 24
+; RV64-NEXT: vsrl.vi v9, v8, 8
+; RV64-NEXT: li t2, 255
+; RV64-NEXT: lui t6, 61681
+; RV64-NEXT: lui s0, 209715
+; RV64-NEXT: lui s1, 349525
+; RV64-NEXT: li s10, 16
+; RV64-NEXT: li s9, 32
+; RV64-NEXT: li s8, 64
+; RV64-NEXT: li s7, 128
+; RV64-NEXT: li s5, 256
+; RV64-NEXT: li t5, 512
+; RV64-NEXT: li t3, 1024
+; RV64-NEXT: li t0, 1
+; RV64-NEXT: lui s6, 1
+; RV64-NEXT: lui s4, 2
+; RV64-NEXT: lui t4, 4
+; RV64-NEXT: lui t1, 8
+; RV64-NEXT: lui a7, 32
+; RV64-NEXT: lui a6, 64
+; RV64-NEXT: lui a5, 128
+; RV64-NEXT: lui a4, 256
+; RV64-NEXT: lui a3, 512
+; RV64-NEXT: lui a2, 1024
+; RV64-NEXT: vsrl.vx v11, v8, s11
+; RV64-NEXT: vsrl.vx v12, v8, ra
+; RV64-NEXT: addi t6, t6, -241
+; RV64-NEXT: addi s2, s0, 819
+; RV64-NEXT: addi s3, s1, 1365
+; RV64-NEXT: slli s1, t6, 32
+; RV64-NEXT: add s1, t6, s1
+; RV64-NEXT: slli t6, s2, 32
+; RV64-NEXT: add s2, s2, t6
+; RV64-NEXT: slli t6, s3, 32
+; RV64-NEXT: add s3, s3, t6
+; RV64-NEXT: addi s0, a0, -256
+; RV64-NEXT: lui a1, 16
+; RV64-NEXT: lui a0, 4080
+; RV64-NEXT: vand.vx v10, v10, a0
+; RV64-NEXT: slli t6, t2, 24
+; RV64-NEXT: vand.vx v13, v8, a0
+; RV64-NEXT: vsll.vx v14, v8, s11
+; RV64-NEXT: vand.vx v12, v12, s0
+; RV64-NEXT: vand.vx v9, v9, t6
+; RV64-NEXT: vsll.vi v13, v13, 24
+; RV64-NEXT: vand.vx v15, v8, t6
+; RV64-NEXT: vand.vx v8, v8, s0
+; RV64-NEXT: vor.vv v11, v12, v11
+; RV64-NEXT: vor.vv v9, v9, v10
+; RV64-NEXT: vsll.vi v10, v15, 8
+; RV64-NEXT: vsll.vx v8, v8, ra
+; RV64-NEXT: vor.vv v9, v9, v11
+; RV64-NEXT: vor.vv v10, v13, v10
+; RV64-NEXT: vor.vv v8, v14, v8
+; RV64-NEXT: vor.vv v8, v8, v10
+; RV64-NEXT: vor.vv v8, v8, v9
+; RV64-NEXT: vsrl.vi v9, v8, 4
+; RV64-NEXT: vand.vx v8, v8, s1
+; RV64-NEXT: vand.vx v9, v9, s1
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v9, v8
+; RV64-NEXT: vsrl.vi v9, v8, 2
+; RV64-NEXT: vand.vx v8, v8, s2
+; RV64-NEXT: vand.vx v9, v9, s2
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v9, v8
+; RV64-NEXT: vsrl.vi v9, v8, 1
+; RV64-NEXT: vand.vx v8, v8, s3
+; RV64-NEXT: vand.vx v9, v9, s3
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v9, v8
+; RV64-NEXT: vand.vx v9, v8, s10
+; RV64-NEXT: lui t2, 4096
+; RV64-NEXT: vand.vx v10, v8, s9
+; RV64-NEXT: lui s9, 8192
+; RV64-NEXT: vand.vx v11, v8, s8
+; RV64-NEXT: lui s8, 16384
+; RV64-NEXT: vand.vx v12, v8, s7
+; RV64-NEXT: lui s10, 32768
+; RV64-NEXT: vand.vx v13, v8, s5
+; RV64-NEXT: lui s11, 65536
+; RV64-NEXT: vand.vx v14, v8, t5
+; RV64-NEXT: lui t5, 131072
+; RV64-NEXT: vand.vx v15, v8, t3
+; RV64-NEXT: slli t3, t0, 11
+; RV64-NEXT: vand.vx v16, v8, t3
+; RV64-NEXT: lui t3, 262144
+; RV64-NEXT: vand.vx v17, v8, s6
+; RV64-NEXT: slli a0, t0, 31
+; RV64-NEXT: sd a0, 96(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v18, v8, s4
+; RV64-NEXT: slli a0, t0, 32
+; RV64-NEXT: sd a0, 88(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v19, v8, t4
+; RV64-NEXT: slli a0, t0, 33
+; RV64-NEXT: sd a0, 80(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v20, v8, t1
+; RV64-NEXT: slli a0, t0, 34
+; RV64-NEXT: sd a0, 72(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v21, v8, a1
+; RV64-NEXT: slli a0, t0, 35
+; RV64-NEXT: sd a0, 64(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v22, v8, a7
+; RV64-NEXT: slli a0, t0, 36
+; RV64-NEXT: sd a0, 56(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v23, v8, a6
+; RV64-NEXT: slli a0, t0, 37
+; RV64-NEXT: sd a0, 48(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v24, v8, a5
+; RV64-NEXT: slli a0, t0, 38
+; RV64-NEXT: sd a0, 40(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v25, v8, a4
+; RV64-NEXT: slli a0, t0, 39
+; RV64-NEXT: sd a0, 32(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v26, v8, a3
+; RV64-NEXT: slli a0, t0, 40
+; RV64-NEXT: sd a0, 24(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v27, v8, a2
+; RV64-NEXT: slli a0, t0, 41
+; RV64-NEXT: sd a0, 16(sp) # 8-byte Folded Spill
+; RV64-NEXT: lui a0, 2048
+; RV64-NEXT: vand.vx v28, v8, a0
+; RV64-NEXT: slli s5, t0, 42
+; RV64-NEXT: vand.vx v29, v8, t2
+; RV64-NEXT: slli s6, t0, 43
+; RV64-NEXT: vand.vx v30, v8, s9
+; RV64-NEXT: slli s7, t0, 44
+; RV64-NEXT: vand.vx v31, v8, s8
+; RV64-NEXT: slli s8, t0, 45
+; RV64-NEXT: vand.vx v7, v8, s10
+; RV64-NEXT: slli s9, t0, 46
+; RV64-NEXT: vand.vx v6, v8, s11
+; RV64-NEXT: slli s10, t0, 47
+; RV64-NEXT: vand.vx v5, v8, t5
+; RV64-NEXT: slli s11, t0, 48
+; RV64-NEXT: vand.vx v0, v8, t3
+; RV64-NEXT: slli ra, t0, 49
+; RV64-NEXT: slli t5, t0, 50
+; RV64-NEXT: slli t4, t0, 51
+; RV64-NEXT: slli t3, t0, 52
+; RV64-NEXT: slli t2, t0, 53
+; RV64-NEXT: slli t1, t0, 54
+; RV64-NEXT: slli a7, t0, 55
+; RV64-NEXT: slli a6, t0, 56
+; RV64-NEXT: slli a5, t0, 57
+; RV64-NEXT: slli a4, t0, 58
+; RV64-NEXT: slli a3, t0, 59
+; RV64-NEXT: slli a2, t0, 60
+; RV64-NEXT: slli a1, t0, 61
+; RV64-NEXT: slli t0, t0, 62
+; RV64-NEXT: li a0, -1
+; RV64-NEXT: slli a0, a0, 63
+; RV64-NEXT: vand.vi v4, v8, 2
+; RV64-NEXT: vand.vi v3, v8, 1
+; RV64-NEXT: vand.vi v2, v8, 4
+; RV64-NEXT: vand.vi v1, v8, 8
+; RV64-NEXT: vmul.vv v4, v8, v4
+; RV64-NEXT: sd t6, 8(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli s4, t6, 5
+; RV64-NEXT: add t6, s4, t6
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v4, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v4, v8, v3
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 5
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v4, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v4, v8, v2
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli s4, t6, 5
+; RV64-NEXT: sub t6, s4, t6
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v4, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v4, v8, v1
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v4, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v9
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v10
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v11
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v12
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v13
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 3
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v14
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 3
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v15
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v16
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v17
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v18
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v19
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 3
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v20
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 3
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v21
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli s4, t6, 4
+; RV64-NEXT: add t6, s4, t6
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v22
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v23
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli s4, t6, 4
+; RV64-NEXT: sub t6, s4, t6
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v24
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v25
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v26
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v27
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add s4, s4, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v28
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v29
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli s4, t6, 3
+; RV64-NEXT: add t6, s4, t6
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v30
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 3
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v31
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli s4, t6, 3
+; RV64-NEXT: sub t6, s4, t6
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v7
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: mv s4, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s4
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v6
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli s4, t6, 2
+; RV64-NEXT: add t6, s4, t6
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v5
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 2
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 112
+; RV64-NEXT: vs1r.v v9, (t6) # vscale x 8-byte Folded Spill
+; RV64-NEXT: vmul.vv v9, v8, v0
+; RV64-NEXT: csrr s4, vlenb
+; RV64-NEXT: slli t6, s4, 1
+; RV64-NEXT: add s4, t6, s4
+; RV64-NEXT: ld t6, 8(sp) # 8-byte Folded Reload
+; RV64-NEXT: add s4, sp, s4
+; RV64-NEXT: addi s4, s4, 112
+; RV64-NEXT: vs1r.v v9, (s4) # vscale x 8-byte Folded Spill
+; RV64-NEXT: ld s4, 96(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s4
+; RV64-NEXT: vmul.vv v9, v8, v9
+; RV64-NEXT: csrr s4, vlenb
+; RV64-NEXT: slli s4, s4, 1
+; RV64-NEXT: add s4, sp, s4
+; RV64-NEXT: addi s4, s4, 112
+; RV64-NEXT: vs1r.v v9, (s4) # vscale x 8-byte Folded Spill
+; RV64-NEXT: ld s4, 88(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s4
+; RV64-NEXT: vmul.vv v9, v8, v9
+; RV64-NEXT: csrr s4, vlenb
+; RV64-NEXT: add s4, sp, s4
+; RV64-NEXT: addi s4, s4, 112
+; RV64-NEXT: vs1r.v v9, (s4) # vscale x 8-byte Folded Spill
+; RV64-NEXT: ld s4, 80(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s4
+; RV64-NEXT: vmul.vv v9, v8, v9
+; RV64-NEXT: addi s4, sp, 112
+; RV64-NEXT: vs1r.v v9, (s4) # vscale x 8-byte Folded Spill
+; RV64-NEXT: ld s4, 72(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s4
+; RV64-NEXT: vmul.vv v3, v8, v9
+; RV64-NEXT: ld s4, 64(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s4
+; RV64-NEXT: vmul.vv v4, v8, v9
+; RV64-NEXT: ld s4, 56(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s4
+; RV64-NEXT: vmul.vv v5, v8, v9
+; RV64-NEXT: ld s4, 48(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s4
+; RV64-NEXT: vmul.vv v6, v8, v9
+; RV64-NEXT: ld s4, 40(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s4
+; RV64-NEXT: vmul.vv v7, v8, v9
+; RV64-NEXT: ld s4, 32(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s4
+; RV64-NEXT: vmul.vv v31, v8, v9
+; RV64-NEXT: ld s4, 24(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s4
+; RV64-NEXT: vmul.vv v30, v8, v9
+; RV64-NEXT: ld s4, 16(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v9, v8, s4
+; RV64-NEXT: vmul.vv v29, v8, v9
+; RV64-NEXT: vand.vx v9, v8, s5
+; RV64-NEXT: vmul.vv v28, v8, v9
+; RV64-NEXT: vand.vx v9, v8, s6
+; RV64-NEXT: vmul.vv v27, v8, v9
+; RV64-NEXT: vand.vx v9, v8, s7
+; RV64-NEXT: vmul.vv v26, v8, v9
+; RV64-NEXT: vand.vx v9, v8, s8
+; RV64-NEXT: vmul.vv v25, v8, v9
+; RV64-NEXT: vand.vx v9, v8, s9
+; RV64-NEXT: vmul.vv v24, v8, v9
+; RV64-NEXT: vand.vx v9, v8, s10
+; RV64-NEXT: vmul.vv v23, v8, v9
+; RV64-NEXT: vand.vx v9, v8, s11
+; RV64-NEXT: vmul.vv v22, v8, v9
+; RV64-NEXT: vand.vx v9, v8, ra
+; RV64-NEXT: vmul.vv v21, v8, v9
+; RV64-NEXT: vand.vx v9, v8, t5
+; RV64-NEXT: vmul.vv v20, v8, v9
+; RV64-NEXT: vand.vx v9, v8, t4
+; RV64-NEXT: vmul.vv v19, v8, v9
+; RV64-NEXT: vand.vx v9, v8, t3
+; RV64-NEXT: vmul.vv v18, v8, v9
+; RV64-NEXT: vand.vx v9, v8, t2
+; RV64-NEXT: vmul.vv v17, v8, v9
+; RV64-NEXT: vand.vx v9, v8, t1
+; RV64-NEXT: vmul.vv v16, v8, v9
+; RV64-NEXT: vand.vx v9, v8, a7
+; RV64-NEXT: vmul.vv v15, v8, v9
+; RV64-NEXT: vand.vx v9, v8, a6
+; RV64-NEXT: vmul.vv v14, v8, v9
+; RV64-NEXT: vand.vx v9, v8, a5
+; RV64-NEXT: vmul.vv v13, v8, v9
+; RV64-NEXT: vand.vx v9, v8, a4
+; RV64-NEXT: vmul.vv v12, v8, v9
+; RV64-NEXT: vand.vx v9, v8, a3
+; RV64-NEXT: vmul.vv v11, v8, v9
+; RV64-NEXT: vand.vx v9, v8, a2
+; RV64-NEXT: vmul.vv v10, v8, v9
+; RV64-NEXT: vand.vx v9, v8, a1
+; RV64-NEXT: vmul.vv v9, v8, v9
+; RV64-NEXT: vand.vx v0, v8, t0
+; RV64-NEXT: vmul.vv v0, v8, v0
+; RV64-NEXT: vand.vx v1, v8, a0
+; RV64-NEXT: vmul.vv v8, v8, v1
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a1, a0, 5
+; RV64-NEXT: add a0, a1, a0
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v1, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v2, v1
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a1, a0, 5
+; RV64-NEXT: sub a0, a1, a0
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a1, a0, 4
+; RV64-NEXT: add a0, a1, a0
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a1, a0, 4
+; RV64-NEXT: sub a0, a1, a0
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a1, a0, 3
+; RV64-NEXT: add a0, a1, a0
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a1, a0, 3
+; RV64-NEXT: sub a0, a1, a0
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a1, a0, 2
+; RV64-NEXT: add a0, a1, a0
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a1, a0, 1
+; RV64-NEXT: add a0, a1, a0
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v1, v1, v2
+; RV64-NEXT: addi a0, sp, 112
+; RV64-NEXT: vl1r.v v2, (a0) # vscale x 8-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v1, v2
+; RV64-NEXT: vxor.vv v3, v2, v3
+; RV64-NEXT: vxor.vv v4, v3, v4
+; RV64-NEXT: vxor.vv v5, v4, v5
+; RV64-NEXT: vxor.vv v6, v5, v6
+; RV64-NEXT: vxor.vv v7, v6, v7
+; RV64-NEXT: vxor.vv v31, v7, v31
+; RV64-NEXT: vxor.vv v30, v31, v30
+; RV64-NEXT: vxor.vv v29, v30, v29
+; RV64-NEXT: vxor.vv v28, v29, v28
+; RV64-NEXT: vxor.vv v27, v28, v27
+; RV64-NEXT: vxor.vv v26, v27, v26
+; RV64-NEXT: vxor.vv v25, v26, v25
+; RV64-NEXT: vxor.vv v24, v25, v24
+; RV64-NEXT: vxor.vv v23, v24, v23
+; RV64-NEXT: vxor.vv v22, v23, v22
+; RV64-NEXT: vxor.vv v21, v22, v21
+; RV64-NEXT: vxor.vv v20, v21, v20
+; RV64-NEXT: vxor.vv v19, v20, v19
+; RV64-NEXT: vxor.vv v18, v19, v18
+; RV64-NEXT: vxor.vv v17, v18, v17
+; RV64-NEXT: vxor.vv v16, v17, v16
+; RV64-NEXT: vxor.vv v15, v16, v15
+; RV64-NEXT: vxor.vv v14, v15, v14
+; RV64-NEXT: vxor.vv v13, v14, v13
+; RV64-NEXT: vxor.vv v12, v13, v12
+; RV64-NEXT: vxor.vv v11, v12, v11
+; RV64-NEXT: vxor.vv v10, v11, v10
+; RV64-NEXT: vxor.vv v9, v10, v9
+; RV64-NEXT: vxor.vv v9, v9, v0
+; RV64-NEXT: vxor.vv v8, v9, v8
+; RV64-NEXT: li a0, 56
+; RV64-NEXT: vsrl.vx v9, v8, a0
+; RV64-NEXT: li a1, 40
+; RV64-NEXT: vsrl.vx v10, v8, a1
+; RV64-NEXT: vsrl.vi v11, v8, 24
+; RV64-NEXT: vsrl.vi v12, v8, 8
+; RV64-NEXT: vand.vx v10, v10, s0
+; RV64-NEXT: vor.vv v9, v10, v9
+; RV64-NEXT: vand.vx v10, v8, t6
+; RV64-NEXT: lui a2, 4080
+; RV64-NEXT: vand.vx v11, v11, a2
+; RV64-NEXT: vand.vx v12, v12, t6
+; RV64-NEXT: vor.vv v11, v12, v11
+; RV64-NEXT: vand.vx v12, v8, a2
+; RV64-NEXT: vsll.vi v10, v10, 8
+; RV64-NEXT: vsll.vi v12, v12, 24
+; RV64-NEXT: vor.vv v10, v12, v10
+; RV64-NEXT: vsll.vx v12, v8, a0
+; RV64-NEXT: vand.vx v8, v8, s0
+; RV64-NEXT: vsll.vx v8, v8, a1
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vor.vv v9, v11, v9
+; RV64-NEXT: vor.vv v8, v8, v10
+; RV64-NEXT: vor.vv v8, v8, v9
+; RV64-NEXT: vsrl.vi v9, v8, 4
+; RV64-NEXT: vand.vx v8, v8, s1
+; RV64-NEXT: vand.vx v9, v9, s1
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v9, v8
+; RV64-NEXT: vsrl.vi v9, v8, 2
+; RV64-NEXT: vand.vx v8, v8, s2
+; RV64-NEXT: vand.vx v9, v9, s2
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v9, v8
+; RV64-NEXT: vsrl.vi v9, v8, 1
+; RV64-NEXT: vand.vx v8, v8, s3
+; RV64-NEXT: vand.vx v9, v9, s3
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v9, v8
+; RV64-NEXT: vsrl.vi v8, v8, 1
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add sp, sp, a0
+; RV64-NEXT: ld ra, 216(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s0, 208(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s1, 200(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s2, 192(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s3, 184(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s4, 176(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s5, 168(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s6, 160(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s7, 152(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s8, 144(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s9, 136(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s10, 128(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s11, 120(sp) # 8-byte Folded Reload
+; RV64-NEXT: addi sp, sp, 224
+; RV64-NEXT: ret
+ %a = call <2 x i64> @llvm.clmulh.v2i64(<2 x i64> %x, <2 x i64> %y)
+ ret <2 x i64> %a
+}
+
+define <4 x i64> @clmulh_v4i64(<4 x i64> %x, <4 x i64> %y) nounwind {
+; RV32-LABEL: clmulh_v4i64:
+; RV32: # %bb.0:
+; RV32-NEXT: addi sp, sp, -352
+; RV32-NEXT: sw ra, 348(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s0, 344(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s1, 340(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s2, 336(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s3, 332(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s4, 328(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s5, 324(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s6, 320(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s7, 316(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s8, 312(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s9, 308(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s10, 304(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s11, 300(sp) # 4-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: sub sp, sp, a0
+; RV32-NEXT: lui s7, 1044480
+; RV32-NEXT: lui a7, 524288
+; RV32-NEXT: li a1, 1
+; RV32-NEXT: li s8, 2
+; RV32-NEXT: li s9, 4
+; RV32-NEXT: li s10, 8
+; RV32-NEXT: li a3, 16
+; RV32-NEXT: li a4, 32
+; RV32-NEXT: li a5, 64
+; RV32-NEXT: li a6, 128
+; RV32-NEXT: li s11, 256
+; RV32-NEXT: li ra, 512
+; RV32-NEXT: li a0, 1024
+; RV32-NEXT: lui a2, 1
+; RV32-NEXT: lui t0, 2
+; RV32-NEXT: lui t1, 4
+; RV32-NEXT: lui t2, 8
+; RV32-NEXT: lui t3, 16
+; RV32-NEXT: lui t4, 32
+; RV32-NEXT: lui t5, 64
+; RV32-NEXT: lui t6, 128
+; RV32-NEXT: lui s0, 256
+; RV32-NEXT: lui s1, 512
+; RV32-NEXT: lui s2, 1024
+; RV32-NEXT: lui s3, 2048
+; RV32-NEXT: lui s4, 4096
+; RV32-NEXT: lui s5, 8192
+; RV32-NEXT: lui s6, 16384
+; RV32-NEXT: sw s7, 272(sp)
+; RV32-NEXT: lui s7, 32768
+; RV32-NEXT: sw zero, 276(sp)
+; RV32-NEXT: sw a7, 264(sp)
+; RV32-NEXT: sw zero, 268(sp)
+; RV32-NEXT: sw zero, 256(sp)
+; RV32-NEXT: sw a1, 260(sp)
+; RV32-NEXT: sw zero, 248(sp)
+; RV32-NEXT: sw s8, 252(sp)
+; RV32-NEXT: lui s8, 65536
+; RV32-NEXT: sw zero, 240(sp)
+; RV32-NEXT: sw s9, 244(sp)
+; RV32-NEXT: lui s9, 131072
+; RV32-NEXT: sw zero, 232(sp)
+; RV32-NEXT: sw s10, 236(sp)
+; RV32-NEXT: lui s10, 262144
+; RV32-NEXT: sw zero, 224(sp)
+; RV32-NEXT: sw a3, 228(sp)
+; RV32-NEXT: sw zero, 216(sp)
+; RV32-NEXT: sw a4, 220(sp)
+; RV32-NEXT: sw zero, 208(sp)
+; RV32-NEXT: sw a5, 212(sp)
+; RV32-NEXT: sw zero, 200(sp)
+; RV32-NEXT: sw a6, 204(sp)
+; RV32-NEXT: sw zero, 192(sp)
+; RV32-NEXT: sw s11, 196(sp)
+; RV32-NEXT: sw zero, 184(sp)
+; RV32-NEXT: sw ra, 188(sp)
+; RV32-NEXT: sw zero, 176(sp)
+; RV32-NEXT: sw a0, 180(sp)
+; RV32-NEXT: slli a5, a1, 11
+; RV32-NEXT: sw zero, 168(sp)
+; RV32-NEXT: sw a5, 172(sp)
+; RV32-NEXT: sw zero, 160(sp)
+; RV32-NEXT: sw a2, 164(sp)
+; RV32-NEXT: sw zero, 152(sp)
+; RV32-NEXT: sw t0, 156(sp)
+; RV32-NEXT: sw zero, 144(sp)
+; RV32-NEXT: sw t1, 148(sp)
+; RV32-NEXT: sw zero, 136(sp)
+; RV32-NEXT: sw t2, 140(sp)
+; RV32-NEXT: sw zero, 128(sp)
+; RV32-NEXT: sw t3, 132(sp)
+; RV32-NEXT: sw zero, 120(sp)
+; RV32-NEXT: sw t4, 124(sp)
+; RV32-NEXT: sw zero, 112(sp)
+; RV32-NEXT: sw t5, 116(sp)
+; RV32-NEXT: sw zero, 104(sp)
+; RV32-NEXT: sw t6, 108(sp)
+; RV32-NEXT: sw zero, 96(sp)
+; RV32-NEXT: sw s0, 100(sp)
+; RV32-NEXT: sw zero, 88(sp)
+; RV32-NEXT: sw s1, 92(sp)
+; RV32-NEXT: sw zero, 80(sp)
+; RV32-NEXT: sw s2, 84(sp)
+; RV32-NEXT: sw zero, 72(sp)
+; RV32-NEXT: sw s3, 76(sp)
+; RV32-NEXT: sw zero, 64(sp)
+; RV32-NEXT: sw s4, 68(sp)
+; RV32-NEXT: sw zero, 56(sp)
+; RV32-NEXT: sw s5, 60(sp)
+; RV32-NEXT: sw zero, 48(sp)
+; RV32-NEXT: sw s6, 52(sp)
+; RV32-NEXT: sw zero, 40(sp)
+; RV32-NEXT: sw s7, 44(sp)
+; RV32-NEXT: sw zero, 32(sp)
+; RV32-NEXT: sw s8, 36(sp)
+; RV32-NEXT: sw zero, 24(sp)
+; RV32-NEXT: sw s9, 28(sp)
+; RV32-NEXT: sw zero, 16(sp)
+; RV32-NEXT: sw s10, 20(sp)
+; RV32-NEXT: sw zero, 8(sp)
+; RV32-NEXT: sw a7, 12(sp)
+; RV32-NEXT: lui a0, 61681
+; RV32-NEXT: addi a0, a0, -241
+; RV32-NEXT: vsetivli zero, 8, e32, m2, ta, ma
+; RV32-NEXT: vmv.v.x v4, a0
+; RV32-NEXT: lui a0, 209715
+; RV32-NEXT: addi a0, a0, 819
+; RV32-NEXT: vmv.v.x v2, a0
+; RV32-NEXT: lui a0, 349525
+; RV32-NEXT: addi a0, a0, 1365
+; RV32-NEXT: vmv.v.x v0, a0
+; RV32-NEXT: addi a0, sp, 272
+; RV32-NEXT: vsetivli zero, 4, e64, m2, ta, ma
+; RV32-NEXT: vlse64.v v6, (a0), zero
+; RV32-NEXT: addi a0, sp, 264
+; RV32-NEXT: vlse64.v v10, (a0), zero
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 256
+; RV32-NEXT: vlse64.v v12, (a0), zero
+; RV32-NEXT: addi a0, sp, 248
+; RV32-NEXT: vlse64.v v14, (a0), zero
+; RV32-NEXT: addi a0, sp, 240
+; RV32-NEXT: vlse64.v v16, (a0), zero
+; RV32-NEXT: addi a0, sp, 232
+; RV32-NEXT: vlse64.v v18, (a0), zero
+; RV32-NEXT: addi a0, sp, 224
+; RV32-NEXT: vlse64.v v20, (a0), zero
+; RV32-NEXT: addi a0, sp, 216
+; RV32-NEXT: vlse64.v v22, (a0), zero
+; RV32-NEXT: li ra, 56
+; RV32-NEXT: vsrl.vi v24, v8, 24
+; RV32-NEXT: vsrl.vx v26, v8, ra
+; RV32-NEXT: li s11, 40
+; RV32-NEXT: vsrl.vx v28, v8, s11
+; RV32-NEXT: vsll.vx v30, v8, ra
+; RV32-NEXT: addi a4, t3, -256
+; RV32-NEXT: vand.vx v28, v28, a4
+; RV32-NEXT: vor.vv v26, v28, v26
+; RV32-NEXT: vand.vx v28, v8, a4
+; RV32-NEXT: vsll.vx v28, v28, s11
+; RV32-NEXT: vor.vv v30, v30, v28
+; RV32-NEXT: vsrl.vi v28, v8, 8
+; RV32-NEXT: lui a6, 4080
+; RV32-NEXT: vand.vx v24, v24, a6
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v6, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v28, v28, v6
+; RV32-NEXT: vor.vv v28, v28, v24
+; RV32-NEXT: addi a3, sp, 208
+; RV32-NEXT: vlse64.v v24, (a3), zero
+; RV32-NEXT: vor.vv v10, v28, v26
+; RV32-NEXT: vand.vx v26, v8, a6
+; RV32-NEXT: vsll.vi v26, v26, 24
+; RV32-NEXT: vand.vv v8, v8, v6
+; RV32-NEXT: vsll.vi v8, v8, 8
+; RV32-NEXT: vor.vv v8, v26, v8
+; RV32-NEXT: addi a3, sp, 200
+; RV32-NEXT: vlse64.v v28, (a3), zero
+; RV32-NEXT: vor.vv v8, v30, v8
+; RV32-NEXT: addi a3, sp, 192
+; RV32-NEXT: vlse64.v v26, (a3), zero
+; RV32-NEXT: vor.vv v8, v8, v10
+; RV32-NEXT: vsrl.vi v30, v8, 4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v4, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v8, v8, v4
+; RV32-NEXT: vand.vv v30, v30, v4
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v30, v8
+; RV32-NEXT: vsrl.vi v30, v8, 2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v2, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v8, v8, v2
+; RV32-NEXT: vand.vv v30, v30, v2
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v8, v30, v8
+; RV32-NEXT: vsrl.vi v30, v8, 1
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v0, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v8, v8, v0
+; RV32-NEXT: vand.vv v30, v30, v0
+; RV32-NEXT: vadd.vv v8, v8, v8
+; RV32-NEXT: vor.vv v8, v30, v8
+; RV32-NEXT: addi a3, sp, 184
+; RV32-NEXT: vlse64.v v30, (a3), zero
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vand.vv v6, v8, v10
+; RV32-NEXT: vand.vv v4, v8, v12
+; RV32-NEXT: vand.vv v2, v8, v14
+; RV32-NEXT: vand.vv v0, v8, v16
+; RV32-NEXT: vand.vv v10, v8, v18
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v22
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v28, v8, v28
+; RV32-NEXT: addi a3, sp, 176
+; RV32-NEXT: addi a0, sp, 168
+; RV32-NEXT: vlse64.v v10, (a3), zero
+; RV32-NEXT: vlse64.v v12, (a0), zero
+; RV32-NEXT: vand.vv v14, v8, v26
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v14, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v14, v8, v30
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v14, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: addi a2, sp, 160
+; RV32-NEXT: addi a3, sp, 152
+; RV32-NEXT: addi a1, sp, 144
+; RV32-NEXT: addi a0, sp, 136
+; RV32-NEXT: vlse64.v v10, (a2), zero
+; RV32-NEXT: vlse64.v v12, (a3), zero
+; RV32-NEXT: vlse64.v v14, (a1), zero
+; RV32-NEXT: vlse64.v v16, (a0), zero
+; RV32-NEXT: vand.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v14
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 128
+; RV32-NEXT: addi a1, sp, 120
+; RV32-NEXT: addi a2, sp, 112
+; RV32-NEXT: addi a3, sp, 104
+; RV32-NEXT: vlse64.v v10, (a0), zero
+; RV32-NEXT: vlse64.v v12, (a1), zero
+; RV32-NEXT: vlse64.v v14, (a2), zero
+; RV32-NEXT: vlse64.v v16, (a3), zero
+; RV32-NEXT: vand.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v14
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 96
+; RV32-NEXT: addi a1, sp, 88
+; RV32-NEXT: addi a2, sp, 80
+; RV32-NEXT: addi a3, sp, 72
+; RV32-NEXT: vlse64.v v10, (a0), zero
+; RV32-NEXT: vlse64.v v12, (a1), zero
+; RV32-NEXT: vlse64.v v14, (a2), zero
+; RV32-NEXT: vlse64.v v16, (a3), zero
+; RV32-NEXT: vand.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v14
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 64
+; RV32-NEXT: addi a1, sp, 56
+; RV32-NEXT: addi a2, sp, 48
+; RV32-NEXT: addi a3, sp, 40
+; RV32-NEXT: vlse64.v v10, (a0), zero
+; RV32-NEXT: vlse64.v v12, (a1), zero
+; RV32-NEXT: vlse64.v v14, (a2), zero
+; RV32-NEXT: vlse64.v v16, (a3), zero
+; RV32-NEXT: vand.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v14
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 32
+; RV32-NEXT: addi a1, sp, 24
+; RV32-NEXT: addi a2, sp, 16
+; RV32-NEXT: addi a3, sp, 8
+; RV32-NEXT: vlse64.v v10, (a0), zero
+; RV32-NEXT: vlse64.v v12, (a1), zero
+; RV32-NEXT: vlse64.v v14, (a2), zero
+; RV32-NEXT: vlse64.v v16, (a3), zero
+; RV32-NEXT: vand.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v14
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vv v10, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vi v10, v8, 2
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vi v10, v8, 1
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vi v10, v8, 4
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vi v10, v8, 8
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: li a0, 16
+; RV32-NEXT: vand.vx v10, v8, a0
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: li a0, 32
+; RV32-NEXT: vand.vx v10, v8, a0
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: li a0, 64
+; RV32-NEXT: vand.vx v10, v8, a0
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: li a0, 128
+; RV32-NEXT: vand.vx v10, v8, a0
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: li a0, 256
+; RV32-NEXT: vand.vx v10, v8, a0
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: li a0, 512
+; RV32-NEXT: vand.vx v10, v8, a0
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: li a0, 1024
+; RV32-NEXT: vand.vx v10, v8, a0
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, a5
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: lui a0, 1
+; RV32-NEXT: vand.vx v10, v8, a0
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, t0
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, t1
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, t2
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, t3
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, t4
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, t5
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, t6
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, s0
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, s1
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, s2
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, s3
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, s4
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, s5
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, s6
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, s7
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, s8
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, s9
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vand.vx v10, v8, s10
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: addi a0, sp, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: vmul.vv v12, v8, v6
+; RV32-NEXT: vmul.vv v14, v8, v4
+; RV32-NEXT: vmul.vv v16, v8, v2
+; RV32-NEXT: vmul.vv v18, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v20, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v20, v8, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v22, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v22, v8, v22
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v24, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v24, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v26, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v26, v8, v26
+; RV32-NEXT: vmul.vv v28, v8, v28
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v30, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v30, v8, v30
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v6, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v6, v8, v6
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v4, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v4, v8, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v2, v8, v2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v0, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v10, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v10, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vmul.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs2r.v v8, (a0) # vscale x 16-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v8, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vi v8, v8, 0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: addi a0, sp, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: vxor.vv v8, v8, v14
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: vxor.vv v8, v8, v18
+; RV32-NEXT: vxor.vv v8, v8, v20
+; RV32-NEXT: vxor.vv v8, v8, v22
+; RV32-NEXT: vxor.vv v8, v8, v24
+; RV32-NEXT: vxor.vv v8, v8, v26
+; RV32-NEXT: vxor.vv v8, v8, v28
+; RV32-NEXT: vxor.vv v8, v8, v30
+; RV32-NEXT: vxor.vv v8, v8, v6
+; RV32-NEXT: vxor.vv v8, v8, v4
+; RV32-NEXT: vxor.vv v8, v8, v2
+; RV32-NEXT: vxor.vv v8, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v10, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v10
+; RV32-NEXT: vsrl.vx v10, v8, ra
+; RV32-NEXT: vsll.vx v12, v8, ra
+; RV32-NEXT: vsrl.vx v14, v8, s11
+; RV32-NEXT: vand.vx v16, v8, a4
+; RV32-NEXT: vand.vx v14, v14, a4
+; RV32-NEXT: vsrl.vi v18, v8, 24
+; RV32-NEXT: vand.vx v20, v8, a6
+; RV32-NEXT: vand.vx v18, v18, a6
+; RV32-NEXT: vsll.vx v16, v16, s11
+; RV32-NEXT: vsrl.vi v22, v8, 8
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v24, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v24
+; RV32-NEXT: vand.vv v22, v22, v24
+; RV32-NEXT: vor.vv v10, v14, v10
+; RV32-NEXT: vor.vv v14, v22, v18
+; RV32-NEXT: vsll.vi v8, v8, 8
+; RV32-NEXT: vsll.vi v18, v20, 24
+; RV32-NEXT: vor.vv v8, v18, v8
+; RV32-NEXT: vor.vv v12, v12, v16
+; RV32-NEXT: vor.vv v10, v14, v10
+; RV32-NEXT: vor.vv v8, v12, v8
+; RV32-NEXT: vor.vv v8, v8, v10
+; RV32-NEXT: vsrl.vi v10, v8, 4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v12
+; RV32-NEXT: vand.vv v10, v10, v12
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v10, v8
+; RV32-NEXT: vsrl.vi v10, v8, 2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v12
+; RV32-NEXT: vand.vv v10, v10, v12
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v8, v10, v8
+; RV32-NEXT: vsrl.vi v10, v8, 1
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl2r.v v12, (a0) # vscale x 16-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v12
+; RV32-NEXT: vand.vv v10, v10, v12
+; RV32-NEXT: vadd.vv v8, v8, v8
+; RV32-NEXT: vor.vv v8, v10, v8
+; RV32-NEXT: vsrl.vi v8, v8, 1
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add sp, sp, a0
+; RV32-NEXT: lw ra, 348(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s0, 344(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s1, 340(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s2, 336(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s3, 332(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s4, 328(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s5, 324(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s6, 320(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s7, 316(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s8, 312(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s9, 308(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s10, 304(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s11, 300(sp) # 4-byte Folded Reload
+; RV32-NEXT: addi sp, sp, 352
+; RV32-NEXT: ret
+;
+; RV64-LABEL: clmulh_v4i64:
+; RV64: # %bb.0:
+; RV64-NEXT: addi sp, sp, -224
+; RV64-NEXT: sd ra, 216(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s0, 208(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s1, 200(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s2, 192(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s3, 184(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s4, 176(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s5, 168(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s6, 160(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s7, 152(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s8, 144(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s9, 136(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s10, 128(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s11, 120(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: sub sp, sp, a0
+; RV64-NEXT: li a7, 56
+; RV64-NEXT: li s1, 40
+; RV64-NEXT: lui s3, 16
+; RV64-NEXT: vsetivli zero, 4, e64, m2, ta, ma
+; RV64-NEXT: vsrl.vi v14, v8, 24
+; RV64-NEXT: lui t6, 4080
+; RV64-NEXT: vsrl.vi v10, v8, 8
+; RV64-NEXT: li s2, 255
+; RV64-NEXT: lui a5, 61681
+; RV64-NEXT: lui a6, 209715
+; RV64-NEXT: lui t5, 349525
+; RV64-NEXT: li t4, 16
+; RV64-NEXT: li t3, 32
+; RV64-NEXT: li t2, 64
+; RV64-NEXT: li t1, 128
+; RV64-NEXT: li t0, 256
+; RV64-NEXT: li a4, 512
+; RV64-NEXT: li a3, 1024
+; RV64-NEXT: li s0, 1
+; RV64-NEXT: lui a2, 1
+; RV64-NEXT: lui a1, 2
+; RV64-NEXT: lui a0, 4
+; RV64-NEXT: vsrl.vx v12, v8, a7
+; RV64-NEXT: vsrl.vx v18, v8, s1
+; RV64-NEXT: addi s4, s3, -256
+; RV64-NEXT: vand.vx v16, v14, t6
+; RV64-NEXT: slli s2, s2, 24
+; RV64-NEXT: vand.vx v20, v8, t6
+; RV64-NEXT: vsll.vx v14, v8, a7
+; RV64-NEXT: addi a7, a5, -241
+; RV64-NEXT: addi a6, a6, 819
+; RV64-NEXT: addi a5, t5, 1365
+; RV64-NEXT: slli t5, s0, 11
+; RV64-NEXT: slli t6, s0, 31
+; RV64-NEXT: sd t6, 96(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli t6, s0, 32
+; RV64-NEXT: sd t6, 88(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli t6, s0, 33
+; RV64-NEXT: sd t6, 80(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli t6, s0, 34
+; RV64-NEXT: sd t6, 72(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli t6, s0, 35
+; RV64-NEXT: sd t6, 64(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli t6, s0, 36
+; RV64-NEXT: sd t6, 56(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli t6, a7, 32
+; RV64-NEXT: add a7, a7, t6
+; RV64-NEXT: slli t6, a6, 32
+; RV64-NEXT: add a6, a6, t6
+; RV64-NEXT: slli t6, a5, 32
+; RV64-NEXT: add a5, a5, t6
+; RV64-NEXT: slli t6, s0, 37
+; RV64-NEXT: sd t6, 48(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v18, v18, s4
+; RV64-NEXT: vand.vx v10, v10, s2
+; RV64-NEXT: vsll.vi v20, v20, 24
+; RV64-NEXT: vand.vx v22, v8, s2
+; RV64-NEXT: vand.vx v8, v8, s4
+; RV64-NEXT: vor.vv v12, v18, v12
+; RV64-NEXT: vor.vv v10, v10, v16
+; RV64-NEXT: vsll.vi v16, v22, 8
+; RV64-NEXT: vsll.vx v8, v8, s1
+; RV64-NEXT: vor.vv v10, v10, v12
+; RV64-NEXT: vor.vv v12, v20, v16
+; RV64-NEXT: vor.vv v8, v14, v8
+; RV64-NEXT: vor.vv v8, v8, v12
+; RV64-NEXT: vor.vv v8, v8, v10
+; RV64-NEXT: vsrl.vi v10, v8, 4
+; RV64-NEXT: vand.vx v8, v8, a7
+; RV64-NEXT: vand.vx v10, v10, a7
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v10, v8
+; RV64-NEXT: vsrl.vi v10, v8, 2
+; RV64-NEXT: vand.vx v8, v8, a6
+; RV64-NEXT: vand.vx v10, v10, a6
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v10, v8
+; RV64-NEXT: vsrl.vi v10, v8, 1
+; RV64-NEXT: vand.vx v8, v8, a5
+; RV64-NEXT: vand.vx v10, v10, a5
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v10, v8
+; RV64-NEXT: vand.vx v10, v8, t4
+; RV64-NEXT: slli t4, s0, 38
+; RV64-NEXT: sd t4, 40(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t3
+; RV64-NEXT: slli t3, s0, 39
+; RV64-NEXT: sd t3, 32(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v14, v8, t2
+; RV64-NEXT: slli t2, s0, 40
+; RV64-NEXT: sd t2, 24(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v16, v8, t1
+; RV64-NEXT: slli t1, s0, 41
+; RV64-NEXT: sd t1, 16(sp) # 8-byte Folded Spill
+; RV64-NEXT: vand.vx v18, v8, t0
+; RV64-NEXT: slli s6, s0, 42
+; RV64-NEXT: vand.vx v20, v8, a4
+; RV64-NEXT: slli s7, s0, 43
+; RV64-NEXT: vand.vx v22, v8, a3
+; RV64-NEXT: slli s8, s0, 44
+; RV64-NEXT: vand.vx v24, v8, t5
+; RV64-NEXT: slli s9, s0, 45
+; RV64-NEXT: vand.vx v26, v8, a2
+; RV64-NEXT: slli s10, s0, 46
+; RV64-NEXT: vand.vx v28, v8, a1
+; RV64-NEXT: slli s11, s0, 47
+; RV64-NEXT: vand.vx v30, v8, a0
+; RV64-NEXT: slli ra, s0, 48
+; RV64-NEXT: slli s3, s0, 49
+; RV64-NEXT: slli s1, s0, 50
+; RV64-NEXT: slli t6, s0, 51
+; RV64-NEXT: slli t5, s0, 52
+; RV64-NEXT: slli t4, s0, 53
+; RV64-NEXT: slli t3, s0, 54
+; RV64-NEXT: slli t2, s0, 55
+; RV64-NEXT: slli t1, s0, 56
+; RV64-NEXT: slli t0, s0, 57
+; RV64-NEXT: slli a4, s0, 58
+; RV64-NEXT: slli a3, s0, 59
+; RV64-NEXT: slli a2, s0, 60
+; RV64-NEXT: slli a1, s0, 61
+; RV64-NEXT: slli s0, s0, 62
+; RV64-NEXT: li a0, -1
+; RV64-NEXT: slli a0, a0, 63
+; RV64-NEXT: vand.vi v6, v8, 2
+; RV64-NEXT: vand.vi v4, v8, 1
+; RV64-NEXT: vand.vi v2, v8, 4
+; RV64-NEXT: vand.vi v0, v8, 8
+; RV64-NEXT: vmul.vv v6, v8, v6
+; RV64-NEXT: sd a5, 8(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v6, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v6, v8, v4
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 5
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v6, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v6, v8, v2
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v6, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v6, v8, v0
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v6, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v14
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v16
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v18
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v20
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v22
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v24
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v26
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v28
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vmul.vv v10, v8, v30
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 8
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 16
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 5
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 32
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 6
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 64
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 128
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 256
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 512
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 1024
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 2048
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 4096
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 8192
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 16384
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 32768
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 65536
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 131072
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: lui s5, 262144
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: ld s5, 96(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: ld s5, 88(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: ld s5, 80(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: ld s5, 72(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: ld s5, 64(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: ld s5, 56(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: ld s5, 48(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: ld s5, 40(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: ld s5, 32(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 112
+; RV64-NEXT: vs2r.v v10, (a5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: ld s5, 24(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: mv a5, s5
+; RV64-NEXT: slli s5, s5, 3
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: ld a5, 8(sp) # 8-byte Folded Reload
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 112
+; RV64-NEXT: vs2r.v v10, (s5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: ld s5, 16(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v10, v8, s5
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 4
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 112
+; RV64-NEXT: vs2r.v v10, (s5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, s6
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s6, s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 112
+; RV64-NEXT: vs2r.v v10, (s5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, s7
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 2
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 112
+; RV64-NEXT: vs2r.v v10, (s5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, s8
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 2
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 112
+; RV64-NEXT: vs2r.v v10, (s5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, s9
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 3
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 112
+; RV64-NEXT: vs2r.v v10, (s5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, s10
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 112
+; RV64-NEXT: vs2r.v v10, (s5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, s11
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 2
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 112
+; RV64-NEXT: vs2r.v v10, (s5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, ra
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 112
+; RV64-NEXT: vs2r.v v10, (s5) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, s3
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: addi s3, sp, 112
+; RV64-NEXT: vs2r.v v10, (s3) # vscale x 16-byte Folded Spill
+; RV64-NEXT: vand.vx v10, v8, s1
+; RV64-NEXT: vmul.vv v4, v8, v10
+; RV64-NEXT: vand.vx v10, v8, t6
+; RV64-NEXT: vmul.vv v6, v8, v10
+; RV64-NEXT: vand.vx v10, v8, t5
+; RV64-NEXT: vmul.vv v30, v8, v10
+; RV64-NEXT: vand.vx v10, v8, t4
+; RV64-NEXT: vmul.vv v28, v8, v10
+; RV64-NEXT: vand.vx v10, v8, t3
+; RV64-NEXT: vmul.vv v26, v8, v10
+; RV64-NEXT: vand.vx v10, v8, t2
+; RV64-NEXT: vmul.vv v24, v8, v10
+; RV64-NEXT: vand.vx v10, v8, t1
+; RV64-NEXT: vmul.vv v22, v8, v10
+; RV64-NEXT: vand.vx v10, v8, t0
+; RV64-NEXT: vmul.vv v20, v8, v10
+; RV64-NEXT: vand.vx v10, v8, a4
+; RV64-NEXT: vmul.vv v18, v8, v10
+; RV64-NEXT: vand.vx v10, v8, a3
+; RV64-NEXT: vmul.vv v16, v8, v10
+; RV64-NEXT: vand.vx v10, v8, a2
+; RV64-NEXT: vmul.vv v14, v8, v10
+; RV64-NEXT: vand.vx v10, v8, a1
+; RV64-NEXT: vmul.vv v12, v8, v10
+; RV64-NEXT: vand.vx v10, v8, s0
+; RV64-NEXT: vmul.vv v10, v8, v10
+; RV64-NEXT: vand.vx v0, v8, a0
+; RV64-NEXT: vmul.vv v8, v8, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v0, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v2, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v2
+; RV64-NEXT: addi a0, sp, 112
+; RV64-NEXT: vl2r.v v2, (a0) # vscale x 16-byte Folded Reload
+; RV64-NEXT: vxor.vv v2, v0, v2
+; RV64-NEXT: vxor.vv v4, v2, v4
+; RV64-NEXT: vxor.vv v6, v4, v6
+; RV64-NEXT: vxor.vv v30, v6, v30
+; RV64-NEXT: vxor.vv v28, v30, v28
+; RV64-NEXT: vxor.vv v26, v28, v26
+; RV64-NEXT: vxor.vv v24, v26, v24
+; RV64-NEXT: vxor.vv v22, v24, v22
+; RV64-NEXT: vxor.vv v20, v22, v20
+; RV64-NEXT: vxor.vv v18, v20, v18
+; RV64-NEXT: vxor.vv v16, v18, v16
+; RV64-NEXT: vxor.vv v14, v16, v14
+; RV64-NEXT: vxor.vv v12, v14, v12
+; RV64-NEXT: vxor.vv v10, v12, v10
+; RV64-NEXT: vxor.vv v8, v10, v8
+; RV64-NEXT: li a0, 56
+; RV64-NEXT: vsrl.vx v10, v8, a0
+; RV64-NEXT: li a1, 40
+; RV64-NEXT: vsrl.vx v12, v8, a1
+; RV64-NEXT: vsrl.vi v14, v8, 24
+; RV64-NEXT: vsrl.vi v16, v8, 8
+; RV64-NEXT: vand.vx v12, v12, s4
+; RV64-NEXT: vor.vv v10, v12, v10
+; RV64-NEXT: vand.vx v12, v8, s2
+; RV64-NEXT: lui a2, 4080
+; RV64-NEXT: vand.vx v14, v14, a2
+; RV64-NEXT: vand.vx v16, v16, s2
+; RV64-NEXT: vor.vv v14, v16, v14
+; RV64-NEXT: vand.vx v16, v8, a2
+; RV64-NEXT: vsll.vi v12, v12, 8
+; RV64-NEXT: vsll.vi v16, v16, 24
+; RV64-NEXT: vor.vv v12, v16, v12
+; RV64-NEXT: vsll.vx v16, v8, a0
+; RV64-NEXT: vand.vx v8, v8, s4
+; RV64-NEXT: vsll.vx v8, v8, a1
+; RV64-NEXT: vor.vv v8, v16, v8
+; RV64-NEXT: vor.vv v10, v14, v10
+; RV64-NEXT: vor.vv v8, v8, v12
+; RV64-NEXT: vor.vv v8, v8, v10
+; RV64-NEXT: vsrl.vi v10, v8, 4
+; RV64-NEXT: vand.vx v8, v8, a7
+; RV64-NEXT: vand.vx v10, v10, a7
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v10, v8
+; RV64-NEXT: vsrl.vi v10, v8, 2
+; RV64-NEXT: vand.vx v8, v8, a6
+; RV64-NEXT: vand.vx v10, v10, a6
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v10, v8
+; RV64-NEXT: vsrl.vi v10, v8, 1
+; RV64-NEXT: vand.vx v8, v8, a5
+; RV64-NEXT: vand.vx v10, v10, a5
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v10, v8
+; RV64-NEXT: vsrl.vi v8, v8, 1
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add sp, sp, a0
+; RV64-NEXT: ld ra, 216(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s0, 208(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s1, 200(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s2, 192(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s3, 184(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s4, 176(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s5, 168(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s6, 160(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s7, 152(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s8, 144(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s9, 136(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s10, 128(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s11, 120(sp) # 8-byte Folded Reload
+; RV64-NEXT: addi sp, sp, 224
+; RV64-NEXT: ret
+ %a = call <4 x i64> @llvm.clmulh.v4i64(<4 x i64> %x, <4 x i64> %y)
+ ret <4 x i64> %a
+}
+
+define <8 x i64> @clmulh_v8i64(<8 x i64> %x, <8 x i64> %y) nounwind {
+; RV32-LABEL: clmulh_v8i64:
+; RV32: # %bb.0:
+; RV32-NEXT: addi sp, sp, -352
+; RV32-NEXT: sw ra, 348(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s0, 344(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s1, 340(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s2, 336(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s3, 332(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s4, 328(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s5, 324(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s6, 320(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s7, 316(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s8, 312(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s9, 308(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s10, 304(sp) # 4-byte Folded Spill
+; RV32-NEXT: sw s11, 300(sp) # 4-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: sub sp, sp, a0
+; RV32-NEXT: lui s11, 1044480
+; RV32-NEXT: lui s0, 524288
+; RV32-NEXT: li a0, 1
+; RV32-NEXT: li ra, 2
+; RV32-NEXT: li t4, 4
+; RV32-NEXT: li t2, 8
+; RV32-NEXT: li t6, 16
+; RV32-NEXT: li t5, 32
+; RV32-NEXT: li t3, 64
+; RV32-NEXT: li t1, 128
+; RV32-NEXT: li t0, 256
+; RV32-NEXT: li a7, 512
+; RV32-NEXT: li a6, 1024
+; RV32-NEXT: lui a4, 1
+; RV32-NEXT: lui a3, 2
+; RV32-NEXT: lui a2, 4
+; RV32-NEXT: lui a5, 8
+; RV32-NEXT: lui s1, 16
+; RV32-NEXT: lui a1, 32
+; RV32-NEXT: lui s2, 64
+; RV32-NEXT: lui s3, 128
+; RV32-NEXT: lui s4, 256
+; RV32-NEXT: lui s5, 512
+; RV32-NEXT: lui s6, 1024
+; RV32-NEXT: lui s7, 2048
+; RV32-NEXT: lui s8, 4096
+; RV32-NEXT: lui s9, 8192
+; RV32-NEXT: lui s10, 16384
+; RV32-NEXT: sw s11, 272(sp)
+; RV32-NEXT: lui s11, 32768
+; RV32-NEXT: sw zero, 276(sp)
+; RV32-NEXT: sw s0, 264(sp)
+; RV32-NEXT: sw zero, 268(sp)
+; RV32-NEXT: sw zero, 256(sp)
+; RV32-NEXT: sw a0, 260(sp)
+; RV32-NEXT: sw zero, 248(sp)
+; RV32-NEXT: sw ra, 252(sp)
+; RV32-NEXT: lui ra, 65536
+; RV32-NEXT: sw zero, 240(sp)
+; RV32-NEXT: sw t4, 244(sp)
+; RV32-NEXT: lui t4, 131072
+; RV32-NEXT: sw zero, 232(sp)
+; RV32-NEXT: sw t2, 236(sp)
+; RV32-NEXT: lui t2, 262144
+; RV32-NEXT: sw zero, 224(sp)
+; RV32-NEXT: sw t6, 228(sp)
+; RV32-NEXT: sw zero, 216(sp)
+; RV32-NEXT: sw t5, 220(sp)
+; RV32-NEXT: sw zero, 208(sp)
+; RV32-NEXT: sw t3, 212(sp)
+; RV32-NEXT: sw zero, 200(sp)
+; RV32-NEXT: sw t1, 204(sp)
+; RV32-NEXT: sw zero, 192(sp)
+; RV32-NEXT: sw t0, 196(sp)
+; RV32-NEXT: sw zero, 184(sp)
+; RV32-NEXT: sw a7, 188(sp)
+; RV32-NEXT: sw zero, 176(sp)
+; RV32-NEXT: sw a6, 180(sp)
+; RV32-NEXT: li t1, 1024
+; RV32-NEXT: slli t6, a0, 11
+; RV32-NEXT: sw zero, 168(sp)
+; RV32-NEXT: sw t6, 172(sp)
+; RV32-NEXT: sw zero, 160(sp)
+; RV32-NEXT: sw a4, 164(sp)
+; RV32-NEXT: sw zero, 152(sp)
+; RV32-NEXT: sw a3, 156(sp)
+; RV32-NEXT: lui t3, 2
+; RV32-NEXT: sw zero, 144(sp)
+; RV32-NEXT: sw a2, 148(sp)
+; RV32-NEXT: lui t5, 4
+; RV32-NEXT: sw zero, 136(sp)
+; RV32-NEXT: sw a5, 140(sp)
+; RV32-NEXT: lui a4, 8
+; RV32-NEXT: sw zero, 128(sp)
+; RV32-NEXT: sw s1, 132(sp)
+; RV32-NEXT: sw zero, 120(sp)
+; RV32-NEXT: sw a1, 124(sp)
+; RV32-NEXT: sw zero, 112(sp)
+; RV32-NEXT: sw s2, 116(sp)
+; RV32-NEXT: sw zero, 104(sp)
+; RV32-NEXT: sw s3, 108(sp)
+; RV32-NEXT: sw zero, 96(sp)
+; RV32-NEXT: sw s4, 100(sp)
+; RV32-NEXT: sw zero, 88(sp)
+; RV32-NEXT: sw s5, 92(sp)
+; RV32-NEXT: sw zero, 80(sp)
+; RV32-NEXT: sw s6, 84(sp)
+; RV32-NEXT: sw zero, 72(sp)
+; RV32-NEXT: sw s7, 76(sp)
+; RV32-NEXT: sw zero, 64(sp)
+; RV32-NEXT: sw s8, 68(sp)
+; RV32-NEXT: sw zero, 56(sp)
+; RV32-NEXT: sw s9, 60(sp)
+; RV32-NEXT: sw zero, 48(sp)
+; RV32-NEXT: sw s10, 52(sp)
+; RV32-NEXT: sw zero, 40(sp)
+; RV32-NEXT: sw s11, 44(sp)
+; RV32-NEXT: sw zero, 32(sp)
+; RV32-NEXT: sw ra, 36(sp)
+; RV32-NEXT: sw zero, 24(sp)
+; RV32-NEXT: sw t4, 28(sp)
+; RV32-NEXT: sw zero, 16(sp)
+; RV32-NEXT: sw t2, 20(sp)
+; RV32-NEXT: sw zero, 8(sp)
+; RV32-NEXT: sw s0, 12(sp)
+; RV32-NEXT: lui a1, 61681
+; RV32-NEXT: addi a1, a1, -241
+; RV32-NEXT: vsetivli zero, 16, e32, m4, ta, ma
+; RV32-NEXT: vmv.v.x v28, a1
+; RV32-NEXT: lui a1, 209715
+; RV32-NEXT: addi a1, a1, 819
+; RV32-NEXT: vmv.v.x v4, a1
+; RV32-NEXT: addi a1, sp, 272
+; RV32-NEXT: vsetivli zero, 8, e64, m4, ta, ma
+; RV32-NEXT: vlse64.v v0, (a1), zero
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 8
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v0, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: li t0, 56
+; RV32-NEXT: vsrl.vi v20, v8, 24
+; RV32-NEXT: vsrl.vx v12, v8, t0
+; RV32-NEXT: li a6, 40
+; RV32-NEXT: vsrl.vx v16, v8, a6
+; RV32-NEXT: vsll.vx v24, v8, t0
+; RV32-NEXT: addi a3, s1, -256
+; RV32-NEXT: vand.vx v16, v16, a3
+; RV32-NEXT: vor.vv v16, v16, v12
+; RV32-NEXT: vand.vx v12, v8, a3
+; RV32-NEXT: vsll.vx v12, v12, a6
+; RV32-NEXT: vor.vv v12, v24, v12
+; RV32-NEXT: vsrl.vi v24, v8, 8
+; RV32-NEXT: lui a5, 4080
+; RV32-NEXT: vand.vx v20, v20, a5
+; RV32-NEXT: lui a7, 349525
+; RV32-NEXT: addi a7, a7, 1365
+; RV32-NEXT: vand.vv v24, v24, v0
+; RV32-NEXT: vor.vv v20, v24, v20
+; RV32-NEXT: vsetivli zero, 16, e32, m4, ta, ma
+; RV32-NEXT: vmv.v.x v24, a7
+; RV32-NEXT: vsetivli zero, 8, e64, m4, ta, ma
+; RV32-NEXT: vor.vv v16, v20, v16
+; RV32-NEXT: vand.vx v20, v8, a5
+; RV32-NEXT: vsll.vi v20, v20, 24
+; RV32-NEXT: vand.vv v8, v8, v0
+; RV32-NEXT: vsll.vi v8, v8, 8
+; RV32-NEXT: vor.vv v8, v20, v8
+; RV32-NEXT: addi a7, sp, 264
+; RV32-NEXT: vlse64.v v20, (a7), zero
+; RV32-NEXT: vor.vv v8, v12, v8
+; RV32-NEXT: addi a7, sp, 256
+; RV32-NEXT: vlse64.v v12, (a7), zero
+; RV32-NEXT: vor.vv v8, v8, v16
+; RV32-NEXT: vsrl.vi v16, v8, 4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v28, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v8, v8, v28
+; RV32-NEXT: vand.vv v16, v16, v28
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v16, v8
+; RV32-NEXT: vsrl.vi v16, v8, 2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v4, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v8, v8, v4
+; RV32-NEXT: vand.vv v16, v16, v4
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v8, v16, v8
+; RV32-NEXT: vsrl.vi v16, v8, 1
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v24, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v8, v8, v24
+; RV32-NEXT: vand.vv v16, v16, v24
+; RV32-NEXT: vadd.vv v8, v8, v8
+; RV32-NEXT: vor.vv v8, v16, v8
+; RV32-NEXT: addi a7, sp, 248
+; RV32-NEXT: vlse64.v v16, (a7), zero
+; RV32-NEXT: vand.vv v28, v8, v20
+; RV32-NEXT: addi a7, sp, 240
+; RV32-NEXT: addi a0, sp, 232
+; RV32-NEXT: vlse64.v v20, (a7), zero
+; RV32-NEXT: vlse64.v v24, (a0), zero
+; RV32-NEXT: vand.vv v4, v8, v12
+; RV32-NEXT: vand.vv v0, v8, v16
+; RV32-NEXT: vand.vv v12, v8, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: addi a2, sp, 224
+; RV32-NEXT: addi a7, sp, 216
+; RV32-NEXT: addi a1, sp, 208
+; RV32-NEXT: addi a0, sp, 200
+; RV32-NEXT: vlse64.v v12, (a2), zero
+; RV32-NEXT: vlse64.v v16, (a7), zero
+; RV32-NEXT: vlse64.v v20, (a1), zero
+; RV32-NEXT: vlse64.v v24, (a0), zero
+; RV32-NEXT: vand.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 192
+; RV32-NEXT: addi a1, sp, 184
+; RV32-NEXT: addi a2, sp, 176
+; RV32-NEXT: addi a7, sp, 168
+; RV32-NEXT: vlse64.v v12, (a0), zero
+; RV32-NEXT: vlse64.v v16, (a1), zero
+; RV32-NEXT: vlse64.v v20, (a2), zero
+; RV32-NEXT: vlse64.v v24, (a7), zero
+; RV32-NEXT: vand.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 160
+; RV32-NEXT: addi a1, sp, 152
+; RV32-NEXT: addi a2, sp, 144
+; RV32-NEXT: addi a7, sp, 136
+; RV32-NEXT: vlse64.v v12, (a0), zero
+; RV32-NEXT: vlse64.v v16, (a1), zero
+; RV32-NEXT: vlse64.v v20, (a2), zero
+; RV32-NEXT: vlse64.v v24, (a7), zero
+; RV32-NEXT: vand.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 128
+; RV32-NEXT: addi a1, sp, 120
+; RV32-NEXT: addi a2, sp, 112
+; RV32-NEXT: addi a7, sp, 104
+; RV32-NEXT: vlse64.v v12, (a0), zero
+; RV32-NEXT: vlse64.v v16, (a1), zero
+; RV32-NEXT: vlse64.v v20, (a2), zero
+; RV32-NEXT: vlse64.v v24, (a7), zero
+; RV32-NEXT: vand.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 96
+; RV32-NEXT: addi a1, sp, 88
+; RV32-NEXT: addi a2, sp, 80
+; RV32-NEXT: addi a7, sp, 72
+; RV32-NEXT: vlse64.v v12, (a0), zero
+; RV32-NEXT: vlse64.v v16, (a1), zero
+; RV32-NEXT: vlse64.v v20, (a2), zero
+; RV32-NEXT: vlse64.v v24, (a7), zero
+; RV32-NEXT: vand.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 64
+; RV32-NEXT: addi a1, sp, 56
+; RV32-NEXT: addi a2, sp, 48
+; RV32-NEXT: addi a7, sp, 40
+; RV32-NEXT: vlse64.v v12, (a0), zero
+; RV32-NEXT: vlse64.v v16, (a1), zero
+; RV32-NEXT: vlse64.v v20, (a2), zero
+; RV32-NEXT: vlse64.v v24, (a7), zero
+; RV32-NEXT: vand.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: addi a0, sp, 32
+; RV32-NEXT: addi a1, sp, 24
+; RV32-NEXT: addi a2, sp, 16
+; RV32-NEXT: addi a7, sp, 8
+; RV32-NEXT: vlse64.v v12, (a0), zero
+; RV32-NEXT: vlse64.v v16, (a1), zero
+; RV32-NEXT: vlse64.v v20, (a2), zero
+; RV32-NEXT: vlse64.v v24, (a7), zero
+; RV32-NEXT: vand.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v16
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 7
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v20
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vv v12, v8, v24
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vi v12, v8, 2
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vi v12, v8, 1
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vi v12, v8, 4
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vi v12, v8, 8
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: li a0, 16
+; RV32-NEXT: vand.vx v12, v8, a0
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: li a0, 32
+; RV32-NEXT: vand.vx v12, v8, a0
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: li a0, 64
+; RV32-NEXT: vand.vx v12, v8, a0
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: li a0, 128
+; RV32-NEXT: vand.vx v12, v8, a0
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: li a0, 256
+; RV32-NEXT: vand.vx v12, v8, a0
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: li a0, 512
+; RV32-NEXT: vand.vx v12, v8, a0
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, t1
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, t6
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: lui a0, 1
+; RV32-NEXT: vand.vx v12, v8, a0
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, t3
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, t5
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, a4
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s1
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: lui a0, 32
+; RV32-NEXT: vand.vx v12, v8, a0
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s2
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s3
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s4
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s5
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s6
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s7
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s8
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s9
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s10
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, s11
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, ra
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, t4
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vand.vx v12, v8, t2
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: addi a0, sp, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: vmul.vv v16, v8, v28
+; RV32-NEXT: vmul.vv v20, v8, v4
+; RV32-NEXT: vmul.vv v24, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v28, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v28, v8, v28
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v4, v8, v4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v0, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v0, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 7
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v12, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v12, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vmul.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vs4r.v v8, (a0) # vscale x 32-byte Folded Spill
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v8, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vi v8, v8, 0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: addi a0, sp, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: vxor.vv v8, v8, v16
+; RV32-NEXT: vxor.vv v8, v8, v20
+; RV32-NEXT: vxor.vv v8, v8, v24
+; RV32-NEXT: vxor.vv v8, v8, v28
+; RV32-NEXT: vxor.vv v8, v8, v4
+; RV32-NEXT: vxor.vv v8, v8, v0
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 4
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v12, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vxor.vv v8, v8, v12
+; RV32-NEXT: vsrl.vx v12, v8, t0
+; RV32-NEXT: vsrl.vx v16, v8, a6
+; RV32-NEXT: vsrl.vi v20, v8, 24
+; RV32-NEXT: vand.vx v16, v16, a3
+; RV32-NEXT: vor.vv v12, v16, v12
+; RV32-NEXT: vsrl.vi v16, v8, 8
+; RV32-NEXT: vand.vx v20, v20, a5
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 8
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v24, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vand.vv v16, v16, v24
+; RV32-NEXT: vor.vv v16, v16, v20
+; RV32-NEXT: vand.vx v20, v8, a5
+; RV32-NEXT: vand.vv v24, v8, v24
+; RV32-NEXT: vsll.vi v24, v24, 8
+; RV32-NEXT: vsll.vi v20, v20, 24
+; RV32-NEXT: vor.vv v20, v20, v24
+; RV32-NEXT: vsll.vx v24, v8, t0
+; RV32-NEXT: vand.vx v8, v8, a3
+; RV32-NEXT: vsll.vx v8, v8, a6
+; RV32-NEXT: vor.vv v8, v24, v8
+; RV32-NEXT: vor.vv v12, v16, v12
+; RV32-NEXT: vor.vv v8, v8, v20
+; RV32-NEXT: vor.vv v8, v8, v12
+; RV32-NEXT: vsrl.vi v12, v8, 4
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v16
+; RV32-NEXT: vand.vv v12, v12, v16
+; RV32-NEXT: vsll.vi v8, v8, 4
+; RV32-NEXT: vor.vv v8, v12, v8
+; RV32-NEXT: vsrl.vi v12, v8, 2
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 3
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v16
+; RV32-NEXT: vand.vv v12, v12, v16
+; RV32-NEXT: vsll.vi v8, v8, 2
+; RV32-NEXT: vor.vv v8, v12, v8
+; RV32-NEXT: vsrl.vi v12, v8, 1
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a1, a1, a0
+; RV32-NEXT: slli a0, a0, 1
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add a0, sp, a0
+; RV32-NEXT: addi a0, a0, 288
+; RV32-NEXT: vl4r.v v16, (a0) # vscale x 32-byte Folded Reload
+; RV32-NEXT: vand.vv v8, v8, v16
+; RV32-NEXT: vand.vv v12, v12, v16
+; RV32-NEXT: vadd.vv v8, v8, v8
+; RV32-NEXT: vor.vv v8, v12, v8
+; RV32-NEXT: vsrl.vi v8, v8, 1
+; RV32-NEXT: csrr a0, vlenb
+; RV32-NEXT: slli a0, a0, 2
+; RV32-NEXT: mv a1, a0
+; RV32-NEXT: slli a0, a0, 6
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: add sp, sp, a0
+; RV32-NEXT: lw ra, 348(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s0, 344(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s1, 340(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s2, 336(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s3, 332(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s4, 328(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s5, 324(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s6, 320(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s7, 316(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s8, 312(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s9, 308(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s10, 304(sp) # 4-byte Folded Reload
+; RV32-NEXT: lw s11, 300(sp) # 4-byte Folded Reload
+; RV32-NEXT: addi sp, sp, 352
+; RV32-NEXT: ret
+;
+; RV64-LABEL: clmulh_v8i64:
+; RV64: # %bb.0:
+; RV64-NEXT: addi sp, sp, -240
+; RV64-NEXT: sd ra, 232(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s0, 224(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s1, 216(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s2, 208(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s3, 200(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s4, 192(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s5, 184(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s6, 176(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s7, 168(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s8, 160(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s9, 152(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s10, 144(sp) # 8-byte Folded Spill
+; RV64-NEXT: sd s11, 136(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: sub sp, sp, a0
+; RV64-NEXT: li a6, 56
+; RV64-NEXT: li t0, 40
+; RV64-NEXT: lui t1, 16
+; RV64-NEXT: vsetivli zero, 8, e64, m4, ta, ma
+; RV64-NEXT: vsrl.vi v20, v8, 24
+; RV64-NEXT: lui a7, 4080
+; RV64-NEXT: vsrl.vi v12, v8, 8
+; RV64-NEXT: li s0, 255
+; RV64-NEXT: lui a3, 61681
+; RV64-NEXT: lui a4, 209715
+; RV64-NEXT: lui a5, 349525
+; RV64-NEXT: li a2, 16
+; RV64-NEXT: li a1, 32
+; RV64-NEXT: li a0, 64
+; RV64-NEXT: li s9, 1
+; RV64-NEXT: vsrl.vx v16, v8, a6
+; RV64-NEXT: vsrl.vx v28, v8, t0
+; RV64-NEXT: addi s4, t1, -256
+; RV64-NEXT: vand.vx v24, v20, a7
+; RV64-NEXT: slli s0, s0, 24
+; RV64-NEXT: vand.vx v4, v8, a7
+; RV64-NEXT: vsll.vx v20, v8, a6
+; RV64-NEXT: addi a7, a3, -241
+; RV64-NEXT: addi a6, a4, 819
+; RV64-NEXT: addi a5, a5, 1365
+; RV64-NEXT: slli a3, s9, 11
+; RV64-NEXT: sd a3, 112(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a3, s9, 31
+; RV64-NEXT: sd a3, 104(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a3, s9, 32
+; RV64-NEXT: sd a3, 96(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a3, s9, 33
+; RV64-NEXT: sd a3, 88(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a3, s9, 34
+; RV64-NEXT: sd a3, 80(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a3, s9, 35
+; RV64-NEXT: sd a3, 72(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a3, s9, 36
+; RV64-NEXT: sd a3, 64(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a3, s9, 37
+; RV64-NEXT: sd a3, 56(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a3, s9, 38
+; RV64-NEXT: sd a3, 48(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a3, s9, 39
+; RV64-NEXT: sd a3, 40(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a3, s9, 40
+; RV64-NEXT: sd a3, 32(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli a3, s9, 41
+; RV64-NEXT: sd a3, 24(sp) # 8-byte Folded Spill
+; RV64-NEXT: slli s6, s9, 42
+; RV64-NEXT: slli s7, s9, 43
+; RV64-NEXT: slli a3, a7, 32
+; RV64-NEXT: add a7, a7, a3
+; RV64-NEXT: slli a3, a6, 32
+; RV64-NEXT: add a6, a6, a3
+; RV64-NEXT: slli a3, a5, 32
+; RV64-NEXT: add a5, a5, a3
+; RV64-NEXT: slli s8, s9, 44
+; RV64-NEXT: vand.vx v28, v28, s4
+; RV64-NEXT: vand.vx v12, v12, s0
+; RV64-NEXT: vsll.vi v4, v4, 24
+; RV64-NEXT: vand.vx v0, v8, s0
+; RV64-NEXT: vand.vx v8, v8, s4
+; RV64-NEXT: vor.vv v16, v28, v16
+; RV64-NEXT: vor.vv v12, v12, v24
+; RV64-NEXT: vsll.vi v24, v0, 8
+; RV64-NEXT: vsll.vx v8, v8, t0
+; RV64-NEXT: vor.vv v12, v12, v16
+; RV64-NEXT: vor.vv v16, v4, v24
+; RV64-NEXT: vor.vv v8, v20, v8
+; RV64-NEXT: vor.vv v8, v8, v16
+; RV64-NEXT: vor.vv v8, v8, v12
+; RV64-NEXT: vsrl.vi v12, v8, 4
+; RV64-NEXT: vand.vx v8, v8, a7
+; RV64-NEXT: vand.vx v12, v12, a7
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vsrl.vi v12, v8, 2
+; RV64-NEXT: vand.vx v8, v8, a6
+; RV64-NEXT: vand.vx v12, v12, a6
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vsrl.vi v12, v8, 1
+; RV64-NEXT: vand.vx v8, v8, a5
+; RV64-NEXT: vand.vx v12, v12, a5
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vand.vx v12, v8, a2
+; RV64-NEXT: slli s10, s9, 45
+; RV64-NEXT: vand.vx v16, v8, a1
+; RV64-NEXT: slli s11, s9, 46
+; RV64-NEXT: vand.vx v20, v8, a0
+; RV64-NEXT: slli ra, s9, 47
+; RV64-NEXT: slli s3, s9, 48
+; RV64-NEXT: slli s2, s9, 49
+; RV64-NEXT: slli s1, s9, 50
+; RV64-NEXT: slli t6, s9, 51
+; RV64-NEXT: slli t5, s9, 52
+; RV64-NEXT: slli t4, s9, 53
+; RV64-NEXT: slli t3, s9, 54
+; RV64-NEXT: slli t2, s9, 55
+; RV64-NEXT: slli t1, s9, 56
+; RV64-NEXT: slli t0, s9, 57
+; RV64-NEXT: slli a4, s9, 58
+; RV64-NEXT: slli a3, s9, 59
+; RV64-NEXT: slli a2, s9, 60
+; RV64-NEXT: slli a1, s9, 61
+; RV64-NEXT: slli s9, s9, 62
+; RV64-NEXT: li a0, -1
+; RV64-NEXT: slli a0, a0, 63
+; RV64-NEXT: vand.vi v24, v8, 2
+; RV64-NEXT: vand.vi v28, v8, 1
+; RV64-NEXT: vand.vi v4, v8, 4
+; RV64-NEXT: vand.vi v0, v8, 8
+; RV64-NEXT: vmul.vv v24, v8, v24
+; RV64-NEXT: sd a5, 8(sp) # 8-byte Folded Spill
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v24, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vmul.vv v24, v8, v28
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 5
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v24, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vmul.vv v24, v8, v4
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v24, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vmul.vv v24, v8, v0
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v24, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vmul.vv v12, v8, v16
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vmul.vv v12, v8, v20
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: li s5, 128
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: li s5, 256
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: li s5, 512
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 6
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: li s5, 1024
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: ld s5, 112(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 1
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 2
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 4
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 8
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 16
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 32
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 5
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 64
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 128
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 256
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 512
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 1024
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 2048
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 4096
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 5
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 8192
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 7
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 16384
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 32768
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 65536
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 131072
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: lui s5, 262144
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: ld s5, 104(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: ld s5, 96(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: ld s5, 88(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 5
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: ld s5, 80(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: ld s5, 72(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: ld s5, 64(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: ld s5, 56(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 4
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: ld s5, 48(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 2
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 1
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: ld s5, 40(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr a5, vlenb
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: mv s5, a5
+; RV64-NEXT: slli a5, a5, 3
+; RV64-NEXT: add a5, a5, s5
+; RV64-NEXT: add a5, sp, a5
+; RV64-NEXT: addi a5, a5, 128
+; RV64-NEXT: vs4r.v v12, (a5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: ld s5, 32(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 2
+; RV64-NEXT: mv a5, s5
+; RV64-NEXT: slli s5, s5, 4
+; RV64-NEXT: add s5, s5, a5
+; RV64-NEXT: ld a5, 8(sp) # 8-byte Folded Reload
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 128
+; RV64-NEXT: vs4r.v v12, (s5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: ld s5, 24(sp) # 8-byte Folded Reload
+; RV64-NEXT: vand.vx v12, v8, s5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 128
+; RV64-NEXT: vs4r.v v12, (s5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s6
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 2
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s6, s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s6, s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 128
+; RV64-NEXT: vs4r.v v12, (s5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s7
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 3
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s6, s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 128
+; RV64-NEXT: vs4r.v v12, (s5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s8
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 2
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 2
+; RV64-NEXT: add s6, s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 128
+; RV64-NEXT: vs4r.v v12, (s5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s10
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 4
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 128
+; RV64-NEXT: vs4r.v v12, (s5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s11
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 2
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 1
+; RV64-NEXT: add s6, s6, s5
+; RV64-NEXT: slli s5, s5, 2
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 128
+; RV64-NEXT: vs4r.v v12, (s5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, ra
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr s5, vlenb
+; RV64-NEXT: slli s5, s5, 3
+; RV64-NEXT: mv s6, s5
+; RV64-NEXT: slli s5, s5, 2
+; RV64-NEXT: add s5, s5, s6
+; RV64-NEXT: add s5, sp, s5
+; RV64-NEXT: addi s5, s5, 128
+; RV64-NEXT: vs4r.v v12, (s5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s3
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr s3, vlenb
+; RV64-NEXT: slli s3, s3, 2
+; RV64-NEXT: mv s5, s3
+; RV64-NEXT: slli s3, s3, 3
+; RV64-NEXT: add s3, s3, s5
+; RV64-NEXT: add s3, sp, s3
+; RV64-NEXT: addi s3, s3, 128
+; RV64-NEXT: vs4r.v v12, (s3) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s2
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr s2, vlenb
+; RV64-NEXT: slli s2, s2, 5
+; RV64-NEXT: add s2, sp, s2
+; RV64-NEXT: addi s2, s2, 128
+; RV64-NEXT: vs4r.v v12, (s2) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, s1
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr s1, vlenb
+; RV64-NEXT: slli s1, s1, 2
+; RV64-NEXT: mv s2, s1
+; RV64-NEXT: slli s1, s1, 1
+; RV64-NEXT: add s2, s2, s1
+; RV64-NEXT: slli s1, s1, 1
+; RV64-NEXT: add s1, s1, s2
+; RV64-NEXT: add s1, sp, s1
+; RV64-NEXT: addi s1, s1, 128
+; RV64-NEXT: vs4r.v v12, (s1) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t6
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr t6, vlenb
+; RV64-NEXT: slli t6, t6, 3
+; RV64-NEXT: mv s1, t6
+; RV64-NEXT: slli t6, t6, 1
+; RV64-NEXT: add t6, t6, s1
+; RV64-NEXT: add t6, sp, t6
+; RV64-NEXT: addi t6, t6, 128
+; RV64-NEXT: vs4r.v v12, (t6) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t5
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr t5, vlenb
+; RV64-NEXT: slli t5, t5, 2
+; RV64-NEXT: mv t6, t5
+; RV64-NEXT: slli t5, t5, 2
+; RV64-NEXT: add t5, t5, t6
+; RV64-NEXT: add t5, sp, t5
+; RV64-NEXT: addi t5, t5, 128
+; RV64-NEXT: vs4r.v v12, (t5) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t4
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr t4, vlenb
+; RV64-NEXT: slli t4, t4, 4
+; RV64-NEXT: add t4, sp, t4
+; RV64-NEXT: addi t4, t4, 128
+; RV64-NEXT: vs4r.v v12, (t4) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t3
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr t3, vlenb
+; RV64-NEXT: slli t3, t3, 2
+; RV64-NEXT: mv t4, t3
+; RV64-NEXT: slli t3, t3, 1
+; RV64-NEXT: add t3, t3, t4
+; RV64-NEXT: add t3, sp, t3
+; RV64-NEXT: addi t3, t3, 128
+; RV64-NEXT: vs4r.v v12, (t3) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t2
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr t2, vlenb
+; RV64-NEXT: slli t2, t2, 3
+; RV64-NEXT: add t2, sp, t2
+; RV64-NEXT: addi t2, t2, 128
+; RV64-NEXT: vs4r.v v12, (t2) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t1
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: csrr t1, vlenb
+; RV64-NEXT: slli t1, t1, 2
+; RV64-NEXT: add t1, sp, t1
+; RV64-NEXT: addi t1, t1, 128
+; RV64-NEXT: vs4r.v v12, (t1) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, t0
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: addi t0, sp, 128
+; RV64-NEXT: vs4r.v v12, (t0) # vscale x 32-byte Folded Spill
+; RV64-NEXT: vand.vx v12, v8, a4
+; RV64-NEXT: vmul.vv v28, v8, v12
+; RV64-NEXT: vand.vx v12, v8, a3
+; RV64-NEXT: vmul.vv v24, v8, v12
+; RV64-NEXT: vand.vx v12, v8, a2
+; RV64-NEXT: vmul.vv v20, v8, v12
+; RV64-NEXT: vand.vx v12, v8, a1
+; RV64-NEXT: vmul.vv v16, v8, v12
+; RV64-NEXT: vand.vx v12, v8, s9
+; RV64-NEXT: vmul.vv v12, v8, v12
+; RV64-NEXT: vand.vx v0, v8, a0
+; RV64-NEXT: vmul.vv v8, v8, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v0, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v4, v0
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 6
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 7
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 6
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 5
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 4
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a0, sp, a0
+; RV64-NEXT: addi a0, a0, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v0, v0, v4
+; RV64-NEXT: addi a0, sp, 128
+; RV64-NEXT: vl4r.v v4, (a0) # vscale x 32-byte Folded Reload
+; RV64-NEXT: vxor.vv v4, v0, v4
+; RV64-NEXT: vxor.vv v28, v4, v28
+; RV64-NEXT: vxor.vv v24, v28, v24
+; RV64-NEXT: vxor.vv v20, v24, v20
+; RV64-NEXT: vxor.vv v16, v20, v16
+; RV64-NEXT: vxor.vv v12, v16, v12
+; RV64-NEXT: vxor.vv v8, v12, v8
+; RV64-NEXT: li a0, 56
+; RV64-NEXT: vsrl.vx v12, v8, a0
+; RV64-NEXT: li a1, 40
+; RV64-NEXT: vsrl.vx v16, v8, a1
+; RV64-NEXT: vsrl.vi v20, v8, 24
+; RV64-NEXT: vsrl.vi v24, v8, 8
+; RV64-NEXT: vand.vx v16, v16, s4
+; RV64-NEXT: vor.vv v12, v16, v12
+; RV64-NEXT: vand.vx v16, v8, s0
+; RV64-NEXT: lui a2, 4080
+; RV64-NEXT: vand.vx v20, v20, a2
+; RV64-NEXT: vand.vx v24, v24, s0
+; RV64-NEXT: vor.vv v20, v24, v20
+; RV64-NEXT: vand.vx v24, v8, a2
+; RV64-NEXT: vsll.vi v16, v16, 8
+; RV64-NEXT: vsll.vi v24, v24, 24
+; RV64-NEXT: vor.vv v16, v24, v16
+; RV64-NEXT: vsll.vx v24, v8, a0
+; RV64-NEXT: vand.vx v8, v8, s4
+; RV64-NEXT: vsll.vx v8, v8, a1
+; RV64-NEXT: vor.vv v8, v24, v8
+; RV64-NEXT: vor.vv v12, v20, v12
+; RV64-NEXT: vor.vv v8, v8, v16
+; RV64-NEXT: vor.vv v8, v8, v12
+; RV64-NEXT: vsrl.vi v12, v8, 4
+; RV64-NEXT: vand.vx v8, v8, a7
+; RV64-NEXT: vand.vx v12, v12, a7
+; RV64-NEXT: vsll.vi v8, v8, 4
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vsrl.vi v12, v8, 2
+; RV64-NEXT: vand.vx v8, v8, a6
+; RV64-NEXT: vand.vx v12, v12, a6
+; RV64-NEXT: vsll.vi v8, v8, 2
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vsrl.vi v12, v8, 1
+; RV64-NEXT: vand.vx v8, v8, a5
+; RV64-NEXT: vand.vx v12, v12, a5
+; RV64-NEXT: vadd.vv v8, v8, v8
+; RV64-NEXT: vor.vv v8, v12, v8
+; RV64-NEXT: vsrl.vi v8, v8, 1
+; RV64-NEXT: csrr a0, vlenb
+; RV64-NEXT: slli a0, a0, 3
+; RV64-NEXT: mv a1, a0
+; RV64-NEXT: slli a0, a0, 2
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a1, a1, a0
+; RV64-NEXT: slli a0, a0, 1
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: add sp, sp, a0
+; RV64-NEXT: ld ra, 232(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s0, 224(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s1, 216(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s2, 208(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s3, 200(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s4, 192(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s5, 184(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s6, 176(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s7, 168(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s8, 160(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s9, 152(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s10, 144(sp) # 8-byte Folded Reload
+; RV64-NEXT: ld s11, 136(sp) # 8-byte Folded Reload
+; RV64-NEXT: addi sp, sp, 240
+; RV64-NEXT: ret
+ %a = call <8 x i64> @llvm.clmulh.v8i64(<8 x i64> %x, <8 x i64> %y)
+ ret <8 x i64> %a
+}
More information about the llvm-commits
mailing list