[llvm] [RISCV] Recurse on second operand of two operand shuffles (PR #79197)
Philip Reames via llvm-commits
llvm-commits at lists.llvm.org
Tue Jan 23 11:55:19 PST 2024
https://github.com/preames created https://github.com/llvm/llvm-project/pull/79197
This builds on bdc41106ee48dce59c500c9a3957af947f30c8c3.
This change completes the migration to a recursive shuffle lowering strategy where when we encounter an unknown two argument shuffle, we lower each operand as a single source permute, and then use a vselect (i.e. a vmerge) to combine the results. This relies for code quality on the post-isel combine which will aggressively fold that vmerge back into the materialization of the second operand if possible.
Note: The change includes only the most immediately obvious of the stylistic cleanup. There's a bunch of code movement that this enables that I'll do as a separate patch as rolling it into this creates an unreadable diff.
>From 70e1ba53ec56a6f808d86b0afe14b8178aa9dd80 Mon Sep 17 00:00:00 2001
From: Philip Reames <preames at rivosinc.com>
Date: Tue, 23 Jan 2024 11:19:33 -0800
Subject: [PATCH] [RISCV] Recurse on second operand of two operand shuffles
This builds on bdc41106ee48dce59c500c9a3957af947f30c8c3.
This change completes the migration to a recursive shuffle lowering strategy
where when we encounter an unknown two argument shuffle, we lower each operand
as a single source permute, and then use a vselect (i.e. a vmerge) to combine
the results. This relies for code quality on the post-isel combine which
will aggressively fold that vmerge back into the materialization of the
second operand if possible.
Note: The change includes only the most immediately obvious of the stylistic
cleanup. There's a bunch of code movement that this enables that I'll do
as a separate patch as rolling it into this creates an unreadable diff.
---
llvm/lib/Target/RISCV/RISCVISelLowering.cpp | 79 +----
.../RISCV/rvv/fixed-vectors-fp-interleave.ll | 36 +-
.../RISCV/rvv/fixed-vectors-int-interleave.ll | 36 +-
.../RISCV/rvv/fixed-vectors-int-shuffles.ll | 23 +-
.../rvv/fixed-vectors-interleaved-access.ll | 333 ++++++++----------
.../rvv/fixed-vectors-shuffle-exact-vlen.ll | 7 +-
.../rvv/fixed-vectors-shuffle-transpose.ll | 129 +++----
.../rvv/fixed-vectors-shufflevector-vnsrl.ll | 36 +-
.../RISCV/rvv/vector-deinterleave-fixed.ll | 8 +-
9 files changed, 296 insertions(+), 391 deletions(-)
diff --git a/llvm/lib/Target/RISCV/RISCVISelLowering.cpp b/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
index e39888637062c6..c91a66e26f982b 100644
--- a/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
+++ b/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
@@ -4975,12 +4975,7 @@ static SDValue lowerVECTOR_SHUFFLE(SDValue Op, SelectionDAG &DAG,
// As a backup, shuffles can be lowered via a vrgather instruction, possibly
// merged with a second vrgather.
- SmallVector<SDValue> GatherIndicesLHS, GatherIndicesRHS;
-
- // Keep a track of which non-undef indices are used by each LHS/RHS shuffle
- // half.
- DenseMap<int, unsigned> LHSIndexCounts, RHSIndexCounts;
-
+ SmallVector<int> ShuffleMaskLHS, ShuffleMaskRHS;
SmallVector<SDValue> MaskVals;
// Now construct the mask that will be used by the blended vrgather operation.
@@ -4989,28 +4984,20 @@ static SDValue lowerVECTOR_SHUFFLE(SDValue Op, SelectionDAG &DAG,
bool SelectMaskVal = (MaskIndex < (int)NumElts) ^ !SwapOps;
MaskVals.push_back(DAG.getConstant(SelectMaskVal, DL, XLenVT));
bool IsLHSOrUndefIndex = MaskIndex < (int)NumElts;
- GatherIndicesLHS.push_back(IsLHSOrUndefIndex && MaskIndex >= 0
- ? DAG.getConstant(MaskIndex, DL, XLenVT)
- : DAG.getUNDEF(XLenVT));
- GatherIndicesRHS.push_back(
- IsLHSOrUndefIndex ? DAG.getUNDEF(XLenVT)
- : DAG.getConstant(MaskIndex - NumElts, DL, XLenVT));
- if (IsLHSOrUndefIndex && MaskIndex >= 0)
- ++LHSIndexCounts[MaskIndex];
- if (!IsLHSOrUndefIndex)
- ++RHSIndexCounts[MaskIndex - NumElts];
+ ShuffleMaskLHS.push_back(IsLHSOrUndefIndex && MaskIndex >= 0
+ ? MaskIndex : -1);
+ ShuffleMaskRHS.push_back(IsLHSOrUndefIndex ? -1 : (MaskIndex - NumElts));
}
if (SwapOps) {
std::swap(V1, V2);
- std::swap(GatherIndicesLHS, GatherIndicesRHS);
+ std::swap(ShuffleMaskLHS, ShuffleMaskRHS);
}
assert(MaskVals.size() == NumElts && "Unexpected select-like shuffle");
MVT MaskVT = MVT::getVectorVT(MVT::i1, NumElts);
SDValue SelectMask = DAG.getBuildVector(MaskVT, DL, MaskVals);
- unsigned GatherVXOpc = RISCVISD::VRGATHER_VX_VL;
unsigned GatherVVOpc = RISCVISD::VRGATHER_VV_VL;
MVT IndexVT = VT.changeTypeToInteger();
// Since we can't introduce illegal index types at this stage, use i16 and
@@ -5038,6 +5025,11 @@ static SDValue lowerVECTOR_SHUFFLE(SDValue Op, SelectionDAG &DAG,
// are handled above.
if (V2.isUndef()) {
V1 = convertToScalableVector(ContainerVT, V1, DAG, Subtarget);
+ SmallVector<SDValue> GatherIndicesLHS;
+ for (int ShuffleIdx : ShuffleMaskLHS)
+ GatherIndicesLHS.push_back(ShuffleIdx != -1
+ ? DAG.getConstant(ShuffleIdx, DL, XLenVT)
+ : DAG.getUNDEF(XLenVT));
SDValue LHSIndices = DAG.getBuildVector(IndexVT, DL, GatherIndicesLHS);
LHSIndices = convertToScalableVector(IndexContainerVT, LHSIndices, DAG,
Subtarget);
@@ -5046,50 +5038,13 @@ static SDValue lowerVECTOR_SHUFFLE(SDValue Op, SelectionDAG &DAG,
return convertFromScalableVector(VT, Gather, DAG, Subtarget);
}
- // Translate the gather index we computed above (and possibly swapped)
- // back to a shuffle mask. This step should disappear once we complete
- // the migration to recursive design.
- SmallVector<int> ShuffleMaskLHS;
- ShuffleMaskLHS.reserve(GatherIndicesLHS.size());
- for (SDValue GatherIndex : GatherIndicesLHS) {
- if (GatherIndex.isUndef()) {
- ShuffleMaskLHS.push_back(-1);
- continue;
- }
- auto *IdxC = cast<ConstantSDNode>(GatherIndex);
- ShuffleMaskLHS.push_back(IdxC->getZExtValue());
- }
-
- // Recursively invoke lowering for the LHS as if there were no RHS.
- // This allows us to leverage all of our single source permute tricks.
- SDValue Gather =
- DAG.getVectorShuffle(VT, DL, V1, DAG.getUNDEF(VT), ShuffleMaskLHS);
- Gather = convertToScalableVector(ContainerVT, Gather, DAG, Subtarget);
-
- // Blend in second vector source with an additional vrgather.
- V2 = convertToScalableVector(ContainerVT, V2, DAG, Subtarget);
-
- MVT MaskContainerVT = ContainerVT.changeVectorElementType(MVT::i1);
- SelectMask =
- convertToScalableVector(MaskContainerVT, SelectMask, DAG, Subtarget);
-
- // If only one index is used, we can use a "splat" vrgather.
- // TODO: We can splat the most-common index and fix-up any stragglers, if
- // that's beneficial.
- if (RHSIndexCounts.size() == 1) {
- int SplatIndex = RHSIndexCounts.begin()->getFirst();
- Gather = DAG.getNode(GatherVXOpc, DL, ContainerVT, V2,
- DAG.getConstant(SplatIndex, DL, XLenVT), Gather,
- SelectMask, VL);
- } else {
- SDValue RHSIndices = DAG.getBuildVector(IndexVT, DL, GatherIndicesRHS);
- RHSIndices =
- convertToScalableVector(IndexContainerVT, RHSIndices, DAG, Subtarget);
- Gather = DAG.getNode(GatherVVOpc, DL, ContainerVT, V2, RHSIndices, Gather,
- SelectMask, VL);
- }
-
- return convertFromScalableVector(VT, Gather, DAG, Subtarget);
+ // Recursively invoke lowering for each operand if we had two
+ // independent single source permutes, and then combine the result via a
+ // vselect. Note that the vselect will likely be folded back into the
+ // second permute (vrgather, or other) by the post-isel combine.
+ V1 = DAG.getVectorShuffle(VT, DL, V1, DAG.getUNDEF(VT), ShuffleMaskLHS);
+ V2 = DAG.getVectorShuffle(VT, DL, V2, DAG.getUNDEF(VT), ShuffleMaskRHS);
+ return DAG.getNode(ISD::VSELECT, DL, VT, SelectMask, V2, V1);
}
bool RISCVTargetLowering::isShuffleMaskLegal(ArrayRef<int> M, EVT VT) const {
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp-interleave.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp-interleave.ll
index dab530751ef96b..6bfd0ac932672f 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp-interleave.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-fp-interleave.ll
@@ -238,26 +238,44 @@ define <64 x half> @interleave_v32f16(<32 x half> %x, <32 x half> %y) {
define <64 x float> @interleave_v32f32(<32 x float> %x, <32 x float> %y) {
; V128-LABEL: interleave_v32f32:
; V128: # %bb.0:
+; V128-NEXT: addi sp, sp, -16
+; V128-NEXT: .cfi_def_cfa_offset 16
+; V128-NEXT: csrr a0, vlenb
+; V128-NEXT: slli a0, a0, 3
+; V128-NEXT: sub sp, sp, a0
+; V128-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 8 * vlenb
+; V128-NEXT: vmv8r.v v0, v16
+; V128-NEXT: addi a0, sp, 16
+; V128-NEXT: vs8r.v v16, (a0) # Unknown-size Folded Spill
+; V128-NEXT: vmv8r.v v16, v8
; V128-NEXT: vsetivli zero, 16, e32, m8, ta, ma
-; V128-NEXT: vslidedown.vi v0, v8, 16
+; V128-NEXT: vslidedown.vi v8, v0, 16
; V128-NEXT: vsetivli zero, 16, e32, m4, ta, ma
; V128-NEXT: vwaddu.vv v24, v0, v8
; V128-NEXT: li a0, -1
; V128-NEXT: vwmaccu.vx v24, a0, v8
-; V128-NEXT: lui a1, %hi(.LCPI10_0)
-; V128-NEXT: addi a1, a1, %lo(.LCPI10_0)
-; V128-NEXT: li a2, 32
-; V128-NEXT: vsetvli zero, a2, e32, m8, ta, mu
-; V128-NEXT: vle16.v v12, (a1)
+; V128-NEXT: vsetivli zero, 16, e32, m8, ta, ma
+; V128-NEXT: vslidedown.vi v0, v16, 16
+; V128-NEXT: vsetivli zero, 16, e32, m4, ta, ma
+; V128-NEXT: vwaddu.vv v8, v0, v16
+; V128-NEXT: vwmaccu.vx v8, a0, v16
; V128-NEXT: lui a1, 699051
; V128-NEXT: addi a1, a1, -1366
+; V128-NEXT: li a2, 32
; V128-NEXT: vmv.s.x v0, a1
-; V128-NEXT: vrgatherei16.vv v24, v16, v12, v0.t
+; V128-NEXT: vsetvli zero, a2, e32, m8, ta, ma
+; V128-NEXT: vmerge.vvm v24, v8, v24, v0
; V128-NEXT: vsetivli zero, 16, e32, m4, ta, ma
-; V128-NEXT: vwaddu.vv v0, v8, v16
-; V128-NEXT: vwmaccu.vx v0, a0, v16
+; V128-NEXT: addi a1, sp, 16
+; V128-NEXT: vl8r.v v8, (a1) # Unknown-size Folded Reload
+; V128-NEXT: vwaddu.vv v0, v16, v8
+; V128-NEXT: vwmaccu.vx v0, a0, v8
; V128-NEXT: vmv8r.v v8, v0
; V128-NEXT: vmv8r.v v16, v24
+; V128-NEXT: csrr a0, vlenb
+; V128-NEXT: slli a0, a0, 3
+; V128-NEXT: add sp, sp, a0
+; V128-NEXT: addi sp, sp, 16
; V128-NEXT: ret
;
; V512-LABEL: interleave_v32f32:
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-interleave.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-interleave.ll
index 9e21cc9e3d624a..6da83644413bc2 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-interleave.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-interleave.ll
@@ -403,26 +403,44 @@ define <64 x i16> @interleave_v32i16(<32 x i16> %x, <32 x i16> %y) {
define <64 x i32> @interleave_v32i32(<32 x i32> %x, <32 x i32> %y) {
; V128-LABEL: interleave_v32i32:
; V128: # %bb.0:
+; V128-NEXT: addi sp, sp, -16
+; V128-NEXT: .cfi_def_cfa_offset 16
+; V128-NEXT: csrr a0, vlenb
+; V128-NEXT: slli a0, a0, 3
+; V128-NEXT: sub sp, sp, a0
+; V128-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 8 * vlenb
+; V128-NEXT: vmv8r.v v0, v16
+; V128-NEXT: addi a0, sp, 16
+; V128-NEXT: vs8r.v v16, (a0) # Unknown-size Folded Spill
+; V128-NEXT: vmv8r.v v16, v8
; V128-NEXT: vsetivli zero, 16, e32, m8, ta, ma
-; V128-NEXT: vslidedown.vi v0, v8, 16
+; V128-NEXT: vslidedown.vi v8, v0, 16
; V128-NEXT: vsetivli zero, 16, e32, m4, ta, ma
; V128-NEXT: vwaddu.vv v24, v0, v8
; V128-NEXT: li a0, -1
; V128-NEXT: vwmaccu.vx v24, a0, v8
-; V128-NEXT: lui a1, %hi(.LCPI17_0)
-; V128-NEXT: addi a1, a1, %lo(.LCPI17_0)
-; V128-NEXT: li a2, 32
-; V128-NEXT: vsetvli zero, a2, e32, m8, ta, mu
-; V128-NEXT: vle16.v v12, (a1)
+; V128-NEXT: vsetivli zero, 16, e32, m8, ta, ma
+; V128-NEXT: vslidedown.vi v0, v16, 16
+; V128-NEXT: vsetivli zero, 16, e32, m4, ta, ma
+; V128-NEXT: vwaddu.vv v8, v0, v16
+; V128-NEXT: vwmaccu.vx v8, a0, v16
; V128-NEXT: lui a1, 699051
; V128-NEXT: addi a1, a1, -1366
+; V128-NEXT: li a2, 32
; V128-NEXT: vmv.s.x v0, a1
-; V128-NEXT: vrgatherei16.vv v24, v16, v12, v0.t
+; V128-NEXT: vsetvli zero, a2, e32, m8, ta, ma
+; V128-NEXT: vmerge.vvm v24, v8, v24, v0
; V128-NEXT: vsetivli zero, 16, e32, m4, ta, ma
-; V128-NEXT: vwaddu.vv v0, v8, v16
-; V128-NEXT: vwmaccu.vx v0, a0, v16
+; V128-NEXT: addi a1, sp, 16
+; V128-NEXT: vl8r.v v8, (a1) # Unknown-size Folded Reload
+; V128-NEXT: vwaddu.vv v0, v16, v8
+; V128-NEXT: vwmaccu.vx v0, a0, v8
; V128-NEXT: vmv8r.v v8, v0
; V128-NEXT: vmv8r.v v16, v24
+; V128-NEXT: csrr a0, vlenb
+; V128-NEXT: slli a0, a0, 3
+; V128-NEXT: add sp, sp, a0
+; V128-NEXT: addi sp, sp, 16
; V128-NEXT: ret
;
; V512-LABEL: interleave_v32i32:
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-shuffles.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-shuffles.ll
index a26a87a1f3c139..23629ace4cf48c 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-shuffles.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-shuffles.ll
@@ -611,12 +611,10 @@ define <8 x i8> @concat_4xi8_start_undef(<8 x i8> %v, <8 x i8> %w) {
define <8 x i8> @concat_4xi8_start_undef_at_start(<8 x i8> %v, <8 x i8> %w) {
; CHECK-LABEL: concat_4xi8_start_undef_at_start:
; CHECK: # %bb.0:
-; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, mu
-; CHECK-NEXT: vid.v v10
; CHECK-NEXT: li a0, 224
+; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, mu
; CHECK-NEXT: vmv.s.x v0, a0
-; CHECK-NEXT: vadd.vi v10, v10, -4
-; CHECK-NEXT: vrgather.vv v8, v9, v10, v0.t
+; CHECK-NEXT: vslideup.vi v8, v9, 4, v0.t
; CHECK-NEXT: ret
%res = shufflevector <8 x i8> %v, <8 x i8> %w, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 9, i32 10, i32 11>
ret <8 x i8> %res
@@ -625,12 +623,10 @@ define <8 x i8> @concat_4xi8_start_undef_at_start(<8 x i8> %v, <8 x i8> %w) {
define <8 x i8> @merge_start_into_end_non_contiguous(<8 x i8> %v, <8 x i8> %w) {
; CHECK-LABEL: merge_start_into_end_non_contiguous:
; CHECK: # %bb.0:
-; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, mu
-; CHECK-NEXT: vid.v v10
; CHECK-NEXT: li a0, 144
+; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, mu
; CHECK-NEXT: vmv.s.x v0, a0
-; CHECK-NEXT: vadd.vi v10, v10, -4
-; CHECK-NEXT: vrgather.vv v8, v9, v10, v0.t
+; CHECK-NEXT: vslideup.vi v8, v9, 4, v0.t
; CHECK-NEXT: ret
%res = shufflevector <8 x i8> %v, <8 x i8> %w, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 5, i32 6, i32 11>
ret <8 x i8> %res
@@ -670,12 +666,11 @@ define <8 x i8> @merge_start_into_start(<8 x i8> %v, <8 x i8> %w) {
define <8 x i8> @merge_slidedown(<8 x i8> %v, <8 x i8> %w) {
; CHECK-LABEL: merge_slidedown:
; CHECK: # %bb.0:
-; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, mu
-; CHECK-NEXT: vslidedown.vi v8, v8, 1
+; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, ma
; CHECK-NEXT: li a0, 195
; CHECK-NEXT: vmv.s.x v0, a0
-; CHECK-NEXT: vid.v v10
-; CHECK-NEXT: vrgather.vv v8, v9, v10, v0.t
+; CHECK-NEXT: vslidedown.vi v8, v8, 1
+; CHECK-NEXT: vmerge.vvm v8, v8, v9, v0
; CHECK-NEXT: ret
%res = shufflevector <8 x i8> %v, <8 x i8> %w, <8 x i32> <i32 8, i32 9, i32 3, i32 4, i32 5, i32 6, i32 14, i32 15>
ret <8 x i8> %res
@@ -686,12 +681,10 @@ define <8 x i8> @merge_non_contiguous_slideup_slidedown(<8 x i8> %v, <8 x i8> %w
; CHECK-LABEL: merge_non_contiguous_slideup_slidedown:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, mu
-; CHECK-NEXT: vid.v v10
-; CHECK-NEXT: vadd.vi v10, v10, -1
; CHECK-NEXT: li a0, 234
; CHECK-NEXT: vmv.s.x v0, a0
; CHECK-NEXT: vslidedown.vi v8, v8, 2
-; CHECK-NEXT: vrgather.vv v8, v9, v10, v0.t
+; CHECK-NEXT: vslideup.vi v8, v9, 1, v0.t
; CHECK-NEXT: ret
%res = shufflevector <8 x i8> %v, <8 x i8> %w, <8 x i32> <i32 2, i32 8, i32 4, i32 10, i32 6, i32 12, i32 13, i32 14>
ret <8 x i8> %res
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-interleaved-access.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-interleaved-access.ll
index f889041647b235..e27ff0a573d5f2 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-interleaved-access.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-interleaved-access.ll
@@ -159,69 +159,57 @@ define {<8 x i64>, <8 x i64>, <8 x i64>, <8 x i64>, <8 x i64>, <8 x i64>} @load_
; RV32-NEXT: addi sp, sp, -16
; RV32-NEXT: .cfi_def_cfa_offset 16
; RV32-NEXT: csrr a2, vlenb
-; RV32-NEXT: li a3, 58
+; RV32-NEXT: li a3, 56
; RV32-NEXT: mul a2, a2, a3
; RV32-NEXT: sub sp, sp, a2
-; RV32-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x3a, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 58 * vlenb
+; RV32-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x38, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 56 * vlenb
; RV32-NEXT: addi a3, a1, 256
; RV32-NEXT: li a2, 32
; RV32-NEXT: vsetvli zero, a2, e32, m8, ta, ma
-; RV32-NEXT: vle32.v v8, (a3)
+; RV32-NEXT: vle32.v v16, (a3)
; RV32-NEXT: csrr a3, vlenb
-; RV32-NEXT: li a4, 25
-; RV32-NEXT: mul a3, a3, a4
+; RV32-NEXT: slli a3, a3, 5
; RV32-NEXT: add a3, sp, a3
; RV32-NEXT: addi a3, a3, 16
-; RV32-NEXT: vs8r.v v8, (a3) # Unknown-size Folded Spill
+; RV32-NEXT: vs8r.v v16, (a3) # Unknown-size Folded Spill
; RV32-NEXT: addi a3, a1, 128
; RV32-NEXT: vsetivli zero, 16, e32, m4, ta, ma
-; RV32-NEXT: vslideup.vi v16, v8, 4
+; RV32-NEXT: vslideup.vi v8, v16, 4
; RV32-NEXT: csrr a4, vlenb
-; RV32-NEXT: li a5, 12
-; RV32-NEXT: mul a4, a4, a5
-; RV32-NEXT: add a4, sp, a4
-; RV32-NEXT: addi a4, a4, 16
-; RV32-NEXT: vs4r.v v16, (a4) # Unknown-size Folded Spill
-; RV32-NEXT: vsetvli zero, zero, e16, m2, ta, ma
-; RV32-NEXT: vid.v v20
-; RV32-NEXT: vadd.vi v4, v20, -10
-; RV32-NEXT: vmv.v.v v2, v20
-; RV32-NEXT: csrr a4, vlenb
-; RV32-NEXT: slli a5, a4, 4
-; RV32-NEXT: add a4, a5, a4
+; RV32-NEXT: slli a4, a4, 4
; RV32-NEXT: add a4, sp, a4
; RV32-NEXT: addi a4, a4, 16
-; RV32-NEXT: vs2r.v v20, (a4) # Unknown-size Folded Spill
+; RV32-NEXT: vs4r.v v8, (a4) # Unknown-size Folded Spill
; RV32-NEXT: lui a4, 12
; RV32-NEXT: vmv.s.x v1, a4
; RV32-NEXT: vsetivli zero, 16, e32, m8, ta, ma
-; RV32-NEXT: vslidedown.vi v8, v8, 16
+; RV32-NEXT: vslidedown.vi v16, v16, 16
; RV32-NEXT: csrr a4, vlenb
-; RV32-NEXT: slli a5, a4, 5
-; RV32-NEXT: add a4, a5, a4
+; RV32-NEXT: li a5, 24
+; RV32-NEXT: mul a4, a4, a5
; RV32-NEXT: add a4, sp, a4
; RV32-NEXT: addi a4, a4, 16
-; RV32-NEXT: vs8r.v v8, (a4) # Unknown-size Folded Spill
+; RV32-NEXT: vs8r.v v16, (a4) # Unknown-size Folded Spill
; RV32-NEXT: vsetivli zero, 16, e32, m4, ta, mu
; RV32-NEXT: vmv1r.v v0, v1
; RV32-NEXT: csrr a4, vlenb
-; RV32-NEXT: slli a4, a4, 4
+; RV32-NEXT: slli a4, a4, 2
; RV32-NEXT: add a4, sp, a4
; RV32-NEXT: addi a4, a4, 16
; RV32-NEXT: vs1r.v v1, (a4) # Unknown-size Folded Spill
-; RV32-NEXT: vrgatherei16.vv v16, v8, v4, v0.t
+; RV32-NEXT: vslideup.vi v8, v16, 10, v0.t
; RV32-NEXT: csrr a4, vlenb
-; RV32-NEXT: li a5, 21
+; RV32-NEXT: li a5, 20
; RV32-NEXT: mul a4, a4, a5
; RV32-NEXT: add a4, sp, a4
; RV32-NEXT: addi a4, a4, 16
-; RV32-NEXT: vs4r.v v16, (a4) # Unknown-size Folded Spill
+; RV32-NEXT: vs4r.v v8, (a4) # Unknown-size Folded Spill
; RV32-NEXT: lui a4, %hi(.LCPI6_0)
; RV32-NEXT: addi a4, a4, %lo(.LCPI6_0)
; RV32-NEXT: vsetvli zero, a2, e32, m8, ta, mu
; RV32-NEXT: vle16.v v8, (a4)
; RV32-NEXT: csrr a4, vlenb
-; RV32-NEXT: slli a4, a4, 2
+; RV32-NEXT: slli a4, a4, 3
; RV32-NEXT: add a4, sp, a4
; RV32-NEXT: addi a4, a4, 16
; RV32-NEXT: vs4r.v v8, (a4) # Unknown-size Folded Spill
@@ -233,14 +221,14 @@ define {<8 x i64>, <8 x i64>, <8 x i64>, <8 x i64>, <8 x i64>, <8 x i64>} @load_
; RV32-NEXT: vs4r.v v8, (a4) # Unknown-size Folded Spill
; RV32-NEXT: vle32.v v16, (a1)
; RV32-NEXT: csrr a1, vlenb
-; RV32-NEXT: li a4, 49
+; RV32-NEXT: li a4, 40
; RV32-NEXT: mul a1, a1, a4
; RV32-NEXT: add a1, sp, a1
; RV32-NEXT: addi a1, a1, 16
; RV32-NEXT: vs8r.v v16, (a1) # Unknown-size Folded Spill
; RV32-NEXT: vle32.v v24, (a3)
; RV32-NEXT: csrr a1, vlenb
-; RV32-NEXT: li a3, 41
+; RV32-NEXT: li a3, 48
; RV32-NEXT: mul a1, a1, a3
; RV32-NEXT: add a1, sp, a1
; RV32-NEXT: addi a1, a1, 16
@@ -248,12 +236,13 @@ define {<8 x i64>, <8 x i64>, <8 x i64>, <8 x i64>, <8 x i64>, <8 x i64>} @load_
; RV32-NEXT: addi a1, a5, -64
; RV32-NEXT: vmv.s.x v0, a1
; RV32-NEXT: csrr a1, vlenb
-; RV32-NEXT: slli a1, a1, 3
+; RV32-NEXT: li a3, 12
+; RV32-NEXT: mul a1, a1, a3
; RV32-NEXT: add a1, sp, a1
; RV32-NEXT: addi a1, a1, 16
; RV32-NEXT: vs1r.v v0, (a1) # Unknown-size Folded Spill
; RV32-NEXT: csrr a1, vlenb
-; RV32-NEXT: slli a1, a1, 2
+; RV32-NEXT: slli a1, a1, 3
; RV32-NEXT: add a1, sp, a1
; RV32-NEXT: addi a1, a1, 16
; RV32-NEXT: vl4r.v v4, (a1) # Unknown-size Folded Reload
@@ -263,366 +252,330 @@ define {<8 x i64>, <8 x i64>, <8 x i64>, <8 x i64>, <8 x i64>, <8 x i64>} @load_
; RV32-NEXT: vrgatherei16.vv v8, v24, v16, v0.t
; RV32-NEXT: vsetivli zero, 12, e32, m4, tu, ma
; RV32-NEXT: csrr a1, vlenb
-; RV32-NEXT: li a3, 21
+; RV32-NEXT: li a3, 20
; RV32-NEXT: mul a1, a1, a3
; RV32-NEXT: add a1, sp, a1
; RV32-NEXT: addi a1, a1, 16
; RV32-NEXT: vl4r.v v12, (a1) # Unknown-size Folded Reload
; RV32-NEXT: vmv.v.v v12, v8
; RV32-NEXT: csrr a1, vlenb
-; RV32-NEXT: li a3, 21
+; RV32-NEXT: li a3, 20
; RV32-NEXT: mul a1, a1, a3
; RV32-NEXT: add a1, sp, a1
; RV32-NEXT: addi a1, a1, 16
; RV32-NEXT: vs4r.v v12, (a1) # Unknown-size Folded Spill
-; RV32-NEXT: vsetivli zero, 16, e32, m4, ta, ma
+; RV32-NEXT: vsetivli zero, 16, e32, m4, ta, mu
; RV32-NEXT: csrr a1, vlenb
-; RV32-NEXT: li a3, 25
-; RV32-NEXT: mul a1, a1, a3
+; RV32-NEXT: slli a1, a1, 5
; RV32-NEXT: add a1, sp, a1
; RV32-NEXT: addi a1, a1, 16
-; RV32-NEXT: vl8r.v v8, (a1) # Unknown-size Folded Reload
-; RV32-NEXT: vslideup.vi v12, v8, 2
-; RV32-NEXT: vsetvli zero, zero, e16, m2, ta, ma
-; RV32-NEXT: vadd.vi v8, v2, -8
-; RV32-NEXT: vsetvli zero, zero, e32, m4, ta, mu
+; RV32-NEXT: vl8r.v v16, (a1) # Unknown-size Folded Reload
+; RV32-NEXT: vslideup.vi v8, v16, 2
; RV32-NEXT: vmv1r.v v0, v1
; RV32-NEXT: csrr a1, vlenb
-; RV32-NEXT: slli a3, a1, 5
-; RV32-NEXT: add a1, a3, a1
+; RV32-NEXT: li a3, 24
+; RV32-NEXT: mul a1, a1, a3
; RV32-NEXT: add a1, sp, a1
; RV32-NEXT: addi a1, a1, 16
; RV32-NEXT: vl8r.v v16, (a1) # Unknown-size Folded Reload
-; RV32-NEXT: vrgatherei16.vv v12, v16, v8, v0.t
-; RV32-NEXT: vmv.v.v v20, v12
+; RV32-NEXT: vslideup.vi v8, v16, 8, v0.t
+; RV32-NEXT: vmv.v.v v20, v8
; RV32-NEXT: lui a1, %hi(.LCPI6_2)
; RV32-NEXT: addi a1, a1, %lo(.LCPI6_2)
; RV32-NEXT: vsetvli zero, a2, e32, m8, ta, mu
; RV32-NEXT: lui a3, %hi(.LCPI6_3)
; RV32-NEXT: addi a3, a3, %lo(.LCPI6_3)
-; RV32-NEXT: vle16.v v16, (a1)
+; RV32-NEXT: vle16.v v24, (a1)
; RV32-NEXT: vle16.v v8, (a3)
; RV32-NEXT: csrr a1, vlenb
-; RV32-NEXT: slli a1, a1, 2
+; RV32-NEXT: slli a1, a1, 3
; RV32-NEXT: add a1, sp, a1
; RV32-NEXT: addi a1, a1, 16
; RV32-NEXT: vs4r.v v8, (a1) # Unknown-size Folded Spill
; RV32-NEXT: csrr a1, vlenb
-; RV32-NEXT: li a3, 49
+; RV32-NEXT: li a3, 40
; RV32-NEXT: mul a1, a1, a3
; RV32-NEXT: add a1, sp, a1
; RV32-NEXT: addi a1, a1, 16
; RV32-NEXT: vl8r.v v0, (a1) # Unknown-size Folded Reload
-; RV32-NEXT: vrgatherei16.vv v8, v0, v16
+; RV32-NEXT: vrgatherei16.vv v8, v0, v24
; RV32-NEXT: csrr a1, vlenb
-; RV32-NEXT: slli a1, a1, 3
+; RV32-NEXT: li a3, 12
+; RV32-NEXT: mul a1, a1, a3
; RV32-NEXT: add a1, sp, a1
; RV32-NEXT: addi a1, a1, 16
; RV32-NEXT: vl1r.v v0, (a1) # Unknown-size Folded Reload
; RV32-NEXT: csrr a1, vlenb
-; RV32-NEXT: li a3, 41
+; RV32-NEXT: li a3, 48
; RV32-NEXT: mul a1, a1, a3
; RV32-NEXT: add a1, sp, a1
; RV32-NEXT: addi a1, a1, 16
; RV32-NEXT: vl8r.v v24, (a1) # Unknown-size Folded Reload
; RV32-NEXT: csrr a1, vlenb
-; RV32-NEXT: slli a1, a1, 2
+; RV32-NEXT: slli a1, a1, 3
; RV32-NEXT: add a1, sp, a1
; RV32-NEXT: addi a1, a1, 16
-; RV32-NEXT: vl4r.v v16, (a1) # Unknown-size Folded Reload
-; RV32-NEXT: vrgatherei16.vv v8, v24, v16, v0.t
+; RV32-NEXT: vl4r.v v4, (a1) # Unknown-size Folded Reload
+; RV32-NEXT: vrgatherei16.vv v8, v24, v4, v0.t
; RV32-NEXT: vsetivli zero, 12, e32, m4, tu, ma
; RV32-NEXT: vmv.v.v v20, v8
; RV32-NEXT: csrr a1, vlenb
-; RV32-NEXT: slli a1, a1, 3
+; RV32-NEXT: li a3, 12
+; RV32-NEXT: mul a1, a1, a3
; RV32-NEXT: add a1, sp, a1
; RV32-NEXT: addi a1, a1, 16
; RV32-NEXT: vs4r.v v20, (a1) # Unknown-size Folded Spill
; RV32-NEXT: lui a1, %hi(.LCPI6_4)
; RV32-NEXT: addi a1, a1, %lo(.LCPI6_4)
-; RV32-NEXT: vsetivli zero, 16, e32, m4, ta, ma
+; RV32-NEXT: vsetivli zero, 16, e32, m4, ta, mu
; RV32-NEXT: vle16.v v8, (a1)
; RV32-NEXT: csrr a1, vlenb
-; RV32-NEXT: li a3, 25
-; RV32-NEXT: mul a1, a1, a3
-; RV32-NEXT: add a1, sp, a1
-; RV32-NEXT: addi a1, a1, 16
-; RV32-NEXT: vl8r.v v16, (a1) # Unknown-size Folded Reload
-; RV32-NEXT: vrgatherei16.vv v24, v16, v8
-; RV32-NEXT: vsetvli zero, zero, e16, m2, ta, ma
-; RV32-NEXT: csrr a1, vlenb
-; RV32-NEXT: slli a3, a1, 4
-; RV32-NEXT: add a1, a3, a1
+; RV32-NEXT: slli a1, a1, 5
; RV32-NEXT: add a1, sp, a1
; RV32-NEXT: addi a1, a1, 16
-; RV32-NEXT: vl2r.v v8, (a1) # Unknown-size Folded Reload
-; RV32-NEXT: vadd.vi v8, v8, -6
-; RV32-NEXT: vsetvli zero, zero, e32, m4, ta, mu
-; RV32-NEXT: csrr a1, vlenb
-; RV32-NEXT: slli a1, a1, 4
-; RV32-NEXT: add a1, sp, a1
-; RV32-NEXT: addi a1, a1, 16
-; RV32-NEXT: vl1r.v v0, (a1) # Unknown-size Folded Reload
+; RV32-NEXT: vl8r.v v24, (a1) # Unknown-size Folded Reload
+; RV32-NEXT: vrgatherei16.vv v12, v24, v8
; RV32-NEXT: csrr a1, vlenb
-; RV32-NEXT: slli a3, a1, 5
-; RV32-NEXT: add a1, a3, a1
+; RV32-NEXT: slli a1, a1, 2
; RV32-NEXT: add a1, sp, a1
; RV32-NEXT: addi a1, a1, 16
-; RV32-NEXT: vl8r.v v16, (a1) # Unknown-size Folded Reload
-; RV32-NEXT: vrgatherei16.vv v24, v16, v8, v0.t
+; RV32-NEXT: vl1r.v v1, (a1) # Unknown-size Folded Reload
+; RV32-NEXT: vmv1r.v v0, v1
+; RV32-NEXT: vslideup.vi v12, v16, 6, v0.t
+; RV32-NEXT: vmv.v.v v4, v12
; RV32-NEXT: lui a1, %hi(.LCPI6_5)
; RV32-NEXT: addi a1, a1, %lo(.LCPI6_5)
; RV32-NEXT: vsetvli zero, a2, e32, m8, ta, mu
; RV32-NEXT: lui a3, %hi(.LCPI6_6)
; RV32-NEXT: addi a3, a3, %lo(.LCPI6_6)
-; RV32-NEXT: vle16.v v16, (a1)
-; RV32-NEXT: vle16.v v28, (a3)
-; RV32-NEXT: li a1, 960
-; RV32-NEXT: vmv.s.x v20, a1
-; RV32-NEXT: addi a1, sp, 16
-; RV32-NEXT: vs1r.v v20, (a1) # Unknown-size Folded Spill
+; RV32-NEXT: vle16.v v24, (a1)
+; RV32-NEXT: vle16.v v8, (a3)
; RV32-NEXT: csrr a1, vlenb
-; RV32-NEXT: li a3, 49
-; RV32-NEXT: mul a1, a1, a3
+; RV32-NEXT: slli a1, a1, 3
; RV32-NEXT: add a1, sp, a1
; RV32-NEXT: addi a1, a1, 16
-; RV32-NEXT: vl8r.v v0, (a1) # Unknown-size Folded Reload
-; RV32-NEXT: vrgatherei16.vv v8, v0, v16
-; RV32-NEXT: vmv1r.v v0, v20
+; RV32-NEXT: vs4r.v v8, (a1) # Unknown-size Folded Spill
+; RV32-NEXT: li a1, 960
+; RV32-NEXT: vmv.s.x v2, a1
; RV32-NEXT: csrr a1, vlenb
-; RV32-NEXT: li a3, 41
+; RV32-NEXT: li a3, 40
; RV32-NEXT: mul a1, a1, a3
; RV32-NEXT: add a1, sp, a1
; RV32-NEXT: addi a1, a1, 16
; RV32-NEXT: vl8r.v v16, (a1) # Unknown-size Folded Reload
-; RV32-NEXT: vrgatherei16.vv v8, v16, v28, v0.t
-; RV32-NEXT: vsetivli zero, 10, e32, m4, tu, ma
-; RV32-NEXT: vmv.v.v v24, v8
+; RV32-NEXT: vrgatherei16.vv v8, v16, v24
+; RV32-NEXT: vmv1r.v v0, v2
; RV32-NEXT: csrr a1, vlenb
-; RV32-NEXT: slli a1, a1, 2
+; RV32-NEXT: li a3, 48
+; RV32-NEXT: mul a1, a1, a3
; RV32-NEXT: add a1, sp, a1
; RV32-NEXT: addi a1, a1, 16
-; RV32-NEXT: vs4r.v v24, (a1) # Unknown-size Folded Spill
-; RV32-NEXT: lui a1, %hi(.LCPI6_7)
-; RV32-NEXT: addi a1, a1, %lo(.LCPI6_7)
-; RV32-NEXT: vsetivli zero, 16, e32, m4, ta, ma
-; RV32-NEXT: vle16.v v8, (a1)
+; RV32-NEXT: vl8r.v v24, (a1) # Unknown-size Folded Reload
; RV32-NEXT: csrr a1, vlenb
-; RV32-NEXT: li a3, 25
-; RV32-NEXT: mul a1, a1, a3
+; RV32-NEXT: slli a1, a1, 3
; RV32-NEXT: add a1, sp, a1
; RV32-NEXT: addi a1, a1, 16
-; RV32-NEXT: vl8r.v v16, (a1) # Unknown-size Folded Reload
-; RV32-NEXT: vrgatherei16.vv v12, v16, v8
-; RV32-NEXT: vsetvli zero, zero, e16, m2, ta, ma
+; RV32-NEXT: vl4r.v v16, (a1) # Unknown-size Folded Reload
+; RV32-NEXT: vrgatherei16.vv v8, v24, v16, v0.t
+; RV32-NEXT: vsetivli zero, 10, e32, m4, tu, ma
+; RV32-NEXT: vmv.v.v v4, v8
; RV32-NEXT: csrr a1, vlenb
-; RV32-NEXT: slli a3, a1, 4
-; RV32-NEXT: add a1, a3, a1
+; RV32-NEXT: slli a1, a1, 3
; RV32-NEXT: add a1, sp, a1
; RV32-NEXT: addi a1, a1, 16
-; RV32-NEXT: vl2r.v v8, (a1) # Unknown-size Folded Reload
-; RV32-NEXT: vadd.vi v8, v8, -4
-; RV32-NEXT: vsetvli zero, zero, e32, m4, ta, mu
+; RV32-NEXT: vs4r.v v4, (a1) # Unknown-size Folded Spill
+; RV32-NEXT: lui a1, %hi(.LCPI6_7)
+; RV32-NEXT: addi a1, a1, %lo(.LCPI6_7)
+; RV32-NEXT: vsetivli zero, 16, e32, m4, ta, mu
+; RV32-NEXT: vle16.v v8, (a1)
; RV32-NEXT: csrr a1, vlenb
-; RV32-NEXT: slli a1, a1, 4
+; RV32-NEXT: slli a1, a1, 5
; RV32-NEXT: add a1, sp, a1
; RV32-NEXT: addi a1, a1, 16
-; RV32-NEXT: vl1r.v v0, (a1) # Unknown-size Folded Reload
+; RV32-NEXT: vl8r.v v24, (a1) # Unknown-size Folded Reload
+; RV32-NEXT: vrgatherei16.vv v28, v24, v8
+; RV32-NEXT: vmv1r.v v0, v1
; RV32-NEXT: csrr a1, vlenb
-; RV32-NEXT: slli a3, a1, 5
-; RV32-NEXT: add a1, a3, a1
+; RV32-NEXT: li a3, 24
+; RV32-NEXT: mul a1, a1, a3
; RV32-NEXT: add a1, sp, a1
; RV32-NEXT: addi a1, a1, 16
-; RV32-NEXT: vl8r.v v16, (a1) # Unknown-size Folded Reload
-; RV32-NEXT: vrgatherei16.vv v12, v16, v8, v0.t
-; RV32-NEXT: vmv.v.v v24, v12
+; RV32-NEXT: vl8r.v v8, (a1) # Unknown-size Folded Reload
+; RV32-NEXT: vslideup.vi v28, v8, 4, v0.t
+; RV32-NEXT: vmv.v.v v4, v28
; RV32-NEXT: lui a1, %hi(.LCPI6_8)
; RV32-NEXT: addi a1, a1, %lo(.LCPI6_8)
; RV32-NEXT: vsetvli zero, a2, e32, m8, ta, mu
; RV32-NEXT: lui a3, %hi(.LCPI6_9)
; RV32-NEXT: addi a3, a3, %lo(.LCPI6_9)
-; RV32-NEXT: vle16.v v16, (a1)
-; RV32-NEXT: vle16.v v28, (a3)
+; RV32-NEXT: vle16.v v28, (a1)
+; RV32-NEXT: vle16.v v24, (a3)
; RV32-NEXT: csrr a1, vlenb
-; RV32-NEXT: li a3, 49
+; RV32-NEXT: li a3, 40
; RV32-NEXT: mul a1, a1, a3
; RV32-NEXT: add a1, sp, a1
; RV32-NEXT: addi a1, a1, 16
-; RV32-NEXT: vl8r.v v0, (a1) # Unknown-size Folded Reload
-; RV32-NEXT: vrgatherei16.vv v8, v0, v16
-; RV32-NEXT: addi a1, sp, 16
-; RV32-NEXT: vl1r.v v0, (a1) # Unknown-size Folded Reload
+; RV32-NEXT: vl8r.v v16, (a1) # Unknown-size Folded Reload
+; RV32-NEXT: vrgatherei16.vv v8, v16, v28
+; RV32-NEXT: vmv1r.v v0, v2
; RV32-NEXT: csrr a1, vlenb
-; RV32-NEXT: li a3, 41
+; RV32-NEXT: li a3, 48
; RV32-NEXT: mul a1, a1, a3
; RV32-NEXT: add a1, sp, a1
; RV32-NEXT: addi a1, a1, 16
; RV32-NEXT: vl8r.v v16, (a1) # Unknown-size Folded Reload
-; RV32-NEXT: vrgatherei16.vv v8, v16, v28, v0.t
+; RV32-NEXT: vrgatherei16.vv v8, v16, v24, v0.t
; RV32-NEXT: vsetivli zero, 10, e32, m4, tu, ma
-; RV32-NEXT: vmv.v.v v24, v8
+; RV32-NEXT: vmv.v.v v4, v8
; RV32-NEXT: csrr a1, vlenb
-; RV32-NEXT: slli a3, a1, 4
-; RV32-NEXT: add a1, a3, a1
+; RV32-NEXT: slli a1, a1, 2
; RV32-NEXT: add a1, sp, a1
; RV32-NEXT: addi a1, a1, 16
-; RV32-NEXT: vs4r.v v24, (a1) # Unknown-size Folded Spill
+; RV32-NEXT: vs4r.v v4, (a1) # Unknown-size Folded Spill
; RV32-NEXT: vsetivli zero, 16, e32, m4, ta, mu
; RV32-NEXT: lui a1, %hi(.LCPI6_10)
; RV32-NEXT: addi a1, a1, %lo(.LCPI6_10)
-; RV32-NEXT: vle16.v v8, (a1)
+; RV32-NEXT: vle16.v v2, (a1)
; RV32-NEXT: lui a1, 15
-; RV32-NEXT: vmv.s.x v0, a1
+; RV32-NEXT: vmv.s.x v5, a1
; RV32-NEXT: csrr a1, vlenb
-; RV32-NEXT: slli a1, a1, 4
+; RV32-NEXT: slli a1, a1, 5
; RV32-NEXT: add a1, sp, a1
; RV32-NEXT: addi a1, a1, 16
-; RV32-NEXT: vs1r.v v0, (a1) # Unknown-size Folded Spill
+; RV32-NEXT: vl8r.v v24, (a1) # Unknown-size Folded Reload
+; RV32-NEXT: vslideup.vi v28, v24, 6
+; RV32-NEXT: vmv1r.v v0, v5
; RV32-NEXT: csrr a1, vlenb
-; RV32-NEXT: li a3, 25
+; RV32-NEXT: li a3, 24
; RV32-NEXT: mul a1, a1, a3
; RV32-NEXT: add a1, sp, a1
; RV32-NEXT: addi a1, a1, 16
-; RV32-NEXT: vl8r.v v16, (a1) # Unknown-size Folded Reload
-; RV32-NEXT: vslideup.vi v20, v16, 6
-; RV32-NEXT: csrr a1, vlenb
-; RV32-NEXT: slli a3, a1, 5
-; RV32-NEXT: add a1, a3, a1
-; RV32-NEXT: add a1, sp, a1
-; RV32-NEXT: addi a1, a1, 16
-; RV32-NEXT: vl8r.v v24, (a1) # Unknown-size Folded Reload
-; RV32-NEXT: vrgatherei16.vv v20, v24, v8, v0.t
+; RV32-NEXT: vl8r.v v8, (a1) # Unknown-size Folded Reload
+; RV32-NEXT: vrgatherei16.vv v28, v8, v2, v0.t
; RV32-NEXT: lui a1, %hi(.LCPI6_11)
; RV32-NEXT: addi a1, a1, %lo(.LCPI6_11)
; RV32-NEXT: vsetvli zero, a2, e32, m8, ta, mu
; RV32-NEXT: lui a3, %hi(.LCPI6_12)
; RV32-NEXT: addi a3, a3, %lo(.LCPI6_12)
-; RV32-NEXT: vle16.v v24, (a1)
-; RV32-NEXT: vle16.v v16, (a3)
+; RV32-NEXT: vle16.v v0, (a1)
+; RV32-NEXT: vle16.v v24, (a3)
; RV32-NEXT: li a1, 1008
-; RV32-NEXT: vmv.s.x v28, a1
+; RV32-NEXT: vmv.s.x v4, a1
; RV32-NEXT: csrr a1, vlenb
-; RV32-NEXT: li a3, 25
-; RV32-NEXT: mul a1, a1, a3
+; RV32-NEXT: slli a1, a1, 5
; RV32-NEXT: add a1, sp, a1
; RV32-NEXT: addi a1, a1, 16
-; RV32-NEXT: vs1r.v v28, (a1) # Unknown-size Folded Spill
+; RV32-NEXT: vs1r.v v4, (a1) # Unknown-size Folded Spill
; RV32-NEXT: csrr a1, vlenb
-; RV32-NEXT: li a3, 49
+; RV32-NEXT: li a3, 40
; RV32-NEXT: mul a1, a1, a3
; RV32-NEXT: add a1, sp, a1
; RV32-NEXT: addi a1, a1, 16
-; RV32-NEXT: vl8r.v v0, (a1) # Unknown-size Folded Reload
-; RV32-NEXT: vrgatherei16.vv v8, v0, v24
-; RV32-NEXT: vmv1r.v v0, v28
+; RV32-NEXT: vl8r.v v16, (a1) # Unknown-size Folded Reload
+; RV32-NEXT: vrgatherei16.vv v8, v16, v0
+; RV32-NEXT: vmv1r.v v0, v4
; RV32-NEXT: csrr a1, vlenb
-; RV32-NEXT: li a3, 41
+; RV32-NEXT: li a3, 48
; RV32-NEXT: mul a1, a1, a3
; RV32-NEXT: add a1, sp, a1
; RV32-NEXT: addi a1, a1, 16
-; RV32-NEXT: vl8r.v v24, (a1) # Unknown-size Folded Reload
-; RV32-NEXT: vrgatherei16.vv v8, v24, v16, v0.t
+; RV32-NEXT: vl8r.v v16, (a1) # Unknown-size Folded Reload
+; RV32-NEXT: vrgatherei16.vv v8, v16, v24, v0.t
; RV32-NEXT: vsetivli zero, 10, e32, m4, tu, ma
-; RV32-NEXT: vmv.v.v v20, v8
+; RV32-NEXT: vmv.v.v v28, v8
; RV32-NEXT: lui a1, %hi(.LCPI6_13)
; RV32-NEXT: addi a1, a1, %lo(.LCPI6_13)
; RV32-NEXT: vsetivli zero, 16, e32, m4, ta, mu
; RV32-NEXT: vle16.v v8, (a1)
+; RV32-NEXT: vmv1r.v v0, v5
; RV32-NEXT: csrr a1, vlenb
; RV32-NEXT: slli a1, a1, 4
; RV32-NEXT: add a1, sp, a1
; RV32-NEXT: addi a1, a1, 16
-; RV32-NEXT: vl1r.v v0, (a1) # Unknown-size Folded Reload
+; RV32-NEXT: vl4r.v v24, (a1) # Unknown-size Folded Reload
; RV32-NEXT: csrr a1, vlenb
-; RV32-NEXT: li a3, 12
+; RV32-NEXT: li a3, 24
; RV32-NEXT: mul a1, a1, a3
; RV32-NEXT: add a1, sp, a1
; RV32-NEXT: addi a1, a1, 16
-; RV32-NEXT: vl4r.v v16, (a1) # Unknown-size Folded Reload
-; RV32-NEXT: csrr a1, vlenb
-; RV32-NEXT: slli a3, a1, 5
-; RV32-NEXT: add a1, a3, a1
-; RV32-NEXT: add a1, sp, a1
-; RV32-NEXT: addi a1, a1, 16
-; RV32-NEXT: vl8r.v v24, (a1) # Unknown-size Folded Reload
-; RV32-NEXT: vrgatherei16.vv v16, v24, v8, v0.t
+; RV32-NEXT: vl8r.v v16, (a1) # Unknown-size Folded Reload
+; RV32-NEXT: vrgatherei16.vv v24, v16, v8, v0.t
; RV32-NEXT: lui a1, %hi(.LCPI6_14)
; RV32-NEXT: addi a1, a1, %lo(.LCPI6_14)
; RV32-NEXT: vsetvli zero, a2, e32, m8, ta, mu
; RV32-NEXT: lui a2, %hi(.LCPI6_15)
; RV32-NEXT: addi a2, a2, %lo(.LCPI6_15)
-; RV32-NEXT: vle16.v v24, (a1)
+; RV32-NEXT: vle16.v v16, (a1)
; RV32-NEXT: vle16.v v8, (a2)
; RV32-NEXT: csrr a1, vlenb
-; RV32-NEXT: slli a2, a1, 5
-; RV32-NEXT: add a1, a2, a1
+; RV32-NEXT: li a2, 24
+; RV32-NEXT: mul a1, a1, a2
; RV32-NEXT: add a1, sp, a1
; RV32-NEXT: addi a1, a1, 16
; RV32-NEXT: vs4r.v v8, (a1) # Unknown-size Folded Spill
; RV32-NEXT: csrr a1, vlenb
-; RV32-NEXT: li a2, 49
+; RV32-NEXT: li a2, 40
; RV32-NEXT: mul a1, a1, a2
; RV32-NEXT: add a1, sp, a1
; RV32-NEXT: addi a1, a1, 16
; RV32-NEXT: vl8r.v v0, (a1) # Unknown-size Folded Reload
-; RV32-NEXT: vrgatherei16.vv v8, v0, v24
+; RV32-NEXT: vrgatherei16.vv v8, v0, v16
; RV32-NEXT: csrr a1, vlenb
-; RV32-NEXT: li a2, 25
-; RV32-NEXT: mul a1, a1, a2
+; RV32-NEXT: slli a1, a1, 5
; RV32-NEXT: add a1, sp, a1
; RV32-NEXT: addi a1, a1, 16
; RV32-NEXT: vl1r.v v0, (a1) # Unknown-size Folded Reload
; RV32-NEXT: csrr a1, vlenb
-; RV32-NEXT: li a2, 41
+; RV32-NEXT: li a2, 48
; RV32-NEXT: mul a1, a1, a2
; RV32-NEXT: add a1, sp, a1
; RV32-NEXT: addi a1, a1, 16
-; RV32-NEXT: vl8r.v v24, (a1) # Unknown-size Folded Reload
+; RV32-NEXT: vl8r.v v16, (a1) # Unknown-size Folded Reload
; RV32-NEXT: csrr a1, vlenb
-; RV32-NEXT: slli a2, a1, 5
-; RV32-NEXT: add a1, a2, a1
+; RV32-NEXT: li a2, 24
+; RV32-NEXT: mul a1, a1, a2
; RV32-NEXT: add a1, sp, a1
; RV32-NEXT: addi a1, a1, 16
; RV32-NEXT: vl4r.v v4, (a1) # Unknown-size Folded Reload
-; RV32-NEXT: vrgatherei16.vv v8, v24, v4, v0.t
+; RV32-NEXT: vrgatherei16.vv v8, v16, v4, v0.t
; RV32-NEXT: vsetivli zero, 10, e32, m4, tu, ma
-; RV32-NEXT: vmv.v.v v16, v8
+; RV32-NEXT: vmv.v.v v24, v8
; RV32-NEXT: addi a1, a0, 320
; RV32-NEXT: vsetivli zero, 16, e32, m4, ta, ma
-; RV32-NEXT: vse32.v v16, (a1)
+; RV32-NEXT: vse32.v v24, (a1)
; RV32-NEXT: addi a1, a0, 256
-; RV32-NEXT: vse32.v v20, (a1)
+; RV32-NEXT: vse32.v v28, (a1)
; RV32-NEXT: addi a1, a0, 192
; RV32-NEXT: csrr a2, vlenb
-; RV32-NEXT: slli a3, a2, 4
-; RV32-NEXT: add a2, a3, a2
+; RV32-NEXT: slli a2, a2, 2
; RV32-NEXT: add a2, sp, a2
; RV32-NEXT: addi a2, a2, 16
; RV32-NEXT: vl4r.v v8, (a2) # Unknown-size Folded Reload
; RV32-NEXT: vse32.v v8, (a1)
; RV32-NEXT: addi a1, a0, 128
; RV32-NEXT: csrr a2, vlenb
-; RV32-NEXT: slli a2, a2, 2
+; RV32-NEXT: slli a2, a2, 3
; RV32-NEXT: add a2, sp, a2
; RV32-NEXT: addi a2, a2, 16
; RV32-NEXT: vl4r.v v8, (a2) # Unknown-size Folded Reload
; RV32-NEXT: vse32.v v8, (a1)
; RV32-NEXT: addi a1, a0, 64
; RV32-NEXT: csrr a2, vlenb
-; RV32-NEXT: slli a2, a2, 3
+; RV32-NEXT: li a3, 12
+; RV32-NEXT: mul a2, a2, a3
; RV32-NEXT: add a2, sp, a2
; RV32-NEXT: addi a2, a2, 16
; RV32-NEXT: vl4r.v v8, (a2) # Unknown-size Folded Reload
; RV32-NEXT: vse32.v v8, (a1)
; RV32-NEXT: csrr a1, vlenb
-; RV32-NEXT: li a2, 21
+; RV32-NEXT: li a2, 20
; RV32-NEXT: mul a1, a1, a2
; RV32-NEXT: add a1, sp, a1
; RV32-NEXT: addi a1, a1, 16
; RV32-NEXT: vl4r.v v8, (a1) # Unknown-size Folded Reload
; RV32-NEXT: vse32.v v8, (a0)
; RV32-NEXT: csrr a0, vlenb
-; RV32-NEXT: li a1, 58
+; RV32-NEXT: li a1, 56
; RV32-NEXT: mul a0, a0, a1
; RV32-NEXT: add sp, sp, a0
; RV32-NEXT: addi sp, sp, 16
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-shuffle-exact-vlen.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-shuffle-exact-vlen.ll
index f53b51e05c5726..c8c08ab1a987b3 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-shuffle-exact-vlen.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-shuffle-exact-vlen.ll
@@ -152,15 +152,12 @@ define <4 x i64> @m2_splat_into_identity_two_source(<4 x i64> %v1, <4 x i64> %v2
define <4 x i64> @m2_splat_into_slide_two_source(<4 x i64> %v1, <4 x i64> %v2) vscale_range(2,2) {
; CHECK-LABEL: m2_splat_into_slide_two_source:
; CHECK: # %bb.0:
-; CHECK-NEXT: vsetivli zero, 4, e16, mf2, ta, ma
-; CHECK-NEXT: vid.v v12
-; CHECK-NEXT: vadd.vi v14, v12, -1
-; CHECK-NEXT: vsetvli zero, zero, e64, m2, ta, ma
+; CHECK-NEXT: vsetivli zero, 4, e64, m2, ta, ma
; CHECK-NEXT: vrgather.vi v12, v8, 0
; CHECK-NEXT: vsetivli zero, 1, e8, mf8, ta, ma
; CHECK-NEXT: vmv.v.i v0, 12
; CHECK-NEXT: vsetivli zero, 4, e64, m2, ta, mu
-; CHECK-NEXT: vrgatherei16.vv v12, v10, v14, v0.t
+; CHECK-NEXT: vslideup.vi v12, v10, 1, v0.t
; CHECK-NEXT: vmv.v.v v8, v12
; CHECK-NEXT: ret
%res = shufflevector <4 x i64> %v1, <4 x i64> %v2, <4 x i32> <i32 0, i32 0, i32 5, i32 6>
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-shuffle-transpose.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-shuffle-transpose.ll
index a34fa9502d93b3..038fead011d899 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-shuffle-transpose.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-shuffle-transpose.ll
@@ -7,12 +7,10 @@ target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
define <8 x i8> @trn1.v8i8(<8 x i8> %v0, <8 x i8> %v1) {
; CHECK-LABEL: trn1.v8i8:
; CHECK: # %bb.0:
-; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, mu
-; CHECK-NEXT: vid.v v10
; CHECK-NEXT: li a0, 170
+; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, mu
; CHECK-NEXT: vmv.s.x v0, a0
-; CHECK-NEXT: vadd.vi v10, v10, -1
-; CHECK-NEXT: vrgather.vv v8, v9, v10, v0.t
+; CHECK-NEXT: vslideup.vi v8, v9, 1, v0.t
; CHECK-NEXT: ret
%tmp0 = shufflevector <8 x i8> %v0, <8 x i8> %v1, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
ret <8 x i8> %tmp0
@@ -21,12 +19,11 @@ define <8 x i8> @trn1.v8i8(<8 x i8> %v0, <8 x i8> %v1) {
define <8 x i8> @trn2.v8i8(<8 x i8> %v0, <8 x i8> %v1) {
; CHECK-LABEL: trn2.v8i8:
; CHECK: # %bb.0:
-; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, mu
-; CHECK-NEXT: vslidedown.vi v8, v8, 1
+; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, ma
; CHECK-NEXT: li a0, 170
; CHECK-NEXT: vmv.s.x v0, a0
-; CHECK-NEXT: vid.v v10
-; CHECK-NEXT: vrgather.vv v8, v9, v10, v0.t
+; CHECK-NEXT: vslidedown.vi v8, v8, 1
+; CHECK-NEXT: vmerge.vvm v8, v8, v9, v0
; CHECK-NEXT: ret
%tmp0 = shufflevector <8 x i8> %v0, <8 x i8> %v1, <8 x i32> <i32 1, i32 9, i32 3, i32 11, i32 5, i32 13, i32 7, i32 15>
ret <8 x i8> %tmp0
@@ -35,15 +32,12 @@ define <8 x i8> @trn2.v8i8(<8 x i8> %v0, <8 x i8> %v1) {
define <16 x i8> @trn1.v16i8(<16 x i8> %v0, <16 x i8> %v1) {
; CHECK-LABEL: trn1.v16i8:
; CHECK: # %bb.0:
-; CHECK-NEXT: vsetivli zero, 16, e8, m1, ta, ma
-; CHECK-NEXT: vid.v v10
-; CHECK-NEXT: vadd.vi v10, v10, -1
; CHECK-NEXT: lui a0, 11
; CHECK-NEXT: addi a0, a0, -1366
-; CHECK-NEXT: vsetvli zero, zero, e16, m2, ta, ma
+; CHECK-NEXT: vsetivli zero, 1, e16, m1, ta, ma
; CHECK-NEXT: vmv.s.x v0, a0
-; CHECK-NEXT: vsetvli zero, zero, e8, m1, ta, mu
-; CHECK-NEXT: vrgather.vv v8, v9, v10, v0.t
+; CHECK-NEXT: vsetivli zero, 16, e8, m1, ta, mu
+; CHECK-NEXT: vslideup.vi v8, v9, 1, v0.t
; CHECK-NEXT: ret
%tmp0 = shufflevector <16 x i8> %v0, <16 x i8> %v1, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
ret <16 x i8> %tmp0
@@ -58,9 +52,8 @@ define <16 x i8> @trn2.v16i8(<16 x i8> %v0, <16 x i8> %v1) {
; CHECK-NEXT: addi a0, a0, -1366
; CHECK-NEXT: vsetvli zero, zero, e16, m2, ta, ma
; CHECK-NEXT: vmv.s.x v0, a0
-; CHECK-NEXT: vsetvli zero, zero, e8, m1, ta, mu
-; CHECK-NEXT: vid.v v10
-; CHECK-NEXT: vrgather.vv v8, v9, v10, v0.t
+; CHECK-NEXT: vsetvli zero, zero, e8, m1, ta, ma
+; CHECK-NEXT: vmerge.vvm v8, v8, v9, v0
; CHECK-NEXT: ret
%tmp0 = shufflevector <16 x i8> %v0, <16 x i8> %v1, <16 x i32> <i32 1, i32 17, i32 3, i32 19, i32 5, i32 21, i32 7, i32 23, i32 9, i32 25, i32 11, i32 27, i32 13, i32 29, i32 15, i32 31>
ret <16 x i8> %tmp0
@@ -69,11 +62,10 @@ define <16 x i8> @trn2.v16i8(<16 x i8> %v0, <16 x i8> %v1) {
define <4 x i16> @trn1.v4i16(<4 x i16> %v0, <4 x i16> %v1) {
; CHECK-LABEL: trn1.v4i16:
; CHECK: # %bb.0:
-; CHECK-NEXT: vsetivli zero, 4, e16, mf2, ta, mu
-; CHECK-NEXT: vid.v v10
+; CHECK-NEXT: vsetivli zero, 1, e8, mf8, ta, ma
; CHECK-NEXT: vmv.v.i v0, 10
-; CHECK-NEXT: vadd.vi v10, v10, -1
-; CHECK-NEXT: vrgather.vv v8, v9, v10, v0.t
+; CHECK-NEXT: vsetivli zero, 4, e16, mf2, ta, mu
+; CHECK-NEXT: vslideup.vi v8, v9, 1, v0.t
; CHECK-NEXT: ret
%tmp0 = shufflevector <4 x i16> %v0, <4 x i16> %v1, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
ret <4 x i16> %tmp0
@@ -82,11 +74,10 @@ define <4 x i16> @trn1.v4i16(<4 x i16> %v0, <4 x i16> %v1) {
define <4 x i16> @trn2.v4i16(<4 x i16> %v0, <4 x i16> %v1) {
; CHECK-LABEL: trn2.v4i16:
; CHECK: # %bb.0:
-; CHECK-NEXT: vsetivli zero, 4, e16, mf2, ta, mu
-; CHECK-NEXT: vslidedown.vi v8, v8, 1
+; CHECK-NEXT: vsetivli zero, 4, e16, mf2, ta, ma
; CHECK-NEXT: vmv.v.i v0, 10
-; CHECK-NEXT: vid.v v10
-; CHECK-NEXT: vrgather.vv v8, v9, v10, v0.t
+; CHECK-NEXT: vslidedown.vi v8, v8, 1
+; CHECK-NEXT: vmerge.vvm v8, v8, v9, v0
; CHECK-NEXT: ret
%tmp0 = shufflevector <4 x i16> %v0, <4 x i16> %v1, <4 x i32> <i32 1, i32 5, i32 3, i32 7>
ret <4 x i16> %tmp0
@@ -95,12 +86,10 @@ define <4 x i16> @trn2.v4i16(<4 x i16> %v0, <4 x i16> %v1) {
define <8 x i16> @trn1.v8i16(<8 x i16> %v0, <8 x i16> %v1) {
; CHECK-LABEL: trn1.v8i16:
; CHECK: # %bb.0:
-; CHECK-NEXT: vsetivli zero, 8, e16, m1, ta, mu
-; CHECK-NEXT: vid.v v10
; CHECK-NEXT: li a0, 170
+; CHECK-NEXT: vsetivli zero, 8, e16, m1, ta, mu
; CHECK-NEXT: vmv.s.x v0, a0
-; CHECK-NEXT: vadd.vi v10, v10, -1
-; CHECK-NEXT: vrgather.vv v8, v9, v10, v0.t
+; CHECK-NEXT: vslideup.vi v8, v9, 1, v0.t
; CHECK-NEXT: ret
%tmp0 = shufflevector <8 x i16> %v0, <8 x i16> %v1, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
ret <8 x i16> %tmp0
@@ -109,12 +98,11 @@ define <8 x i16> @trn1.v8i16(<8 x i16> %v0, <8 x i16> %v1) {
define <8 x i16> @trn2.v8i16(<8 x i16> %v0, <8 x i16> %v1) {
; CHECK-LABEL: trn2.v8i16:
; CHECK: # %bb.0:
-; CHECK-NEXT: vsetivli zero, 8, e16, m1, ta, mu
-; CHECK-NEXT: vslidedown.vi v8, v8, 1
+; CHECK-NEXT: vsetivli zero, 8, e16, m1, ta, ma
; CHECK-NEXT: li a0, 170
; CHECK-NEXT: vmv.s.x v0, a0
-; CHECK-NEXT: vid.v v10
-; CHECK-NEXT: vrgather.vv v8, v9, v10, v0.t
+; CHECK-NEXT: vslidedown.vi v8, v8, 1
+; CHECK-NEXT: vmerge.vvm v8, v8, v9, v0
; CHECK-NEXT: ret
%tmp0 = shufflevector <8 x i16> %v0, <8 x i16> %v1, <8 x i32> <i32 1, i32 9, i32 3, i32 11, i32 5, i32 13, i32 7, i32 15>
ret <8 x i16> %tmp0
@@ -133,11 +121,10 @@ define <2 x i32> @trn1.v2i32(<2 x i32> %v0, <2 x i32> %v1) {
define <2 x i32> @trn2.v2i32(<2 x i32> %v0, <2 x i32> %v1) {
; CHECK-LABEL: trn2.v2i32:
; CHECK: # %bb.0:
-; CHECK-NEXT: vsetivli zero, 2, e32, mf2, ta, mu
+; CHECK-NEXT: vsetivli zero, 2, e32, mf2, ta, ma
; CHECK-NEXT: vmv.v.i v0, 2
; CHECK-NEXT: vrgather.vi v10, v8, 1
-; CHECK-NEXT: vrgather.vi v10, v9, 1, v0.t
-; CHECK-NEXT: vmv1r.v v8, v10
+; CHECK-NEXT: vmerge.vvm v8, v10, v9, v0
; CHECK-NEXT: ret
%tmp0 = shufflevector <2 x i32> %v0, <2 x i32> %v1, <2 x i32> <i32 1, i32 3>
ret <2 x i32> %tmp0
@@ -146,11 +133,10 @@ define <2 x i32> @trn2.v2i32(<2 x i32> %v0, <2 x i32> %v1) {
define <4 x i32> @trn1.v4i32(<4 x i32> %v0, <4 x i32> %v1) {
; CHECK-LABEL: trn1.v4i32:
; CHECK: # %bb.0:
-; CHECK-NEXT: vsetivli zero, 4, e32, m1, ta, mu
-; CHECK-NEXT: vid.v v10
+; CHECK-NEXT: vsetivli zero, 1, e8, mf8, ta, ma
; CHECK-NEXT: vmv.v.i v0, 10
-; CHECK-NEXT: vadd.vi v10, v10, -1
-; CHECK-NEXT: vrgather.vv v8, v9, v10, v0.t
+; CHECK-NEXT: vsetivli zero, 4, e32, m1, ta, mu
+; CHECK-NEXT: vslideup.vi v8, v9, 1, v0.t
; CHECK-NEXT: ret
%tmp0 = shufflevector <4 x i32> %v0, <4 x i32> %v1, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
ret <4 x i32> %tmp0
@@ -159,11 +145,10 @@ define <4 x i32> @trn1.v4i32(<4 x i32> %v0, <4 x i32> %v1) {
define <4 x i32> @trn2.v4i32(<4 x i32> %v0, <4 x i32> %v1) {
; CHECK-LABEL: trn2.v4i32:
; CHECK: # %bb.0:
-; CHECK-NEXT: vsetivli zero, 4, e32, m1, ta, mu
-; CHECK-NEXT: vslidedown.vi v8, v8, 1
+; CHECK-NEXT: vsetivli zero, 4, e32, m1, ta, ma
; CHECK-NEXT: vmv.v.i v0, 10
-; CHECK-NEXT: vid.v v10
-; CHECK-NEXT: vrgather.vv v8, v9, v10, v0.t
+; CHECK-NEXT: vslidedown.vi v8, v8, 1
+; CHECK-NEXT: vmerge.vvm v8, v8, v9, v0
; CHECK-NEXT: ret
%tmp0 = shufflevector <4 x i32> %v0, <4 x i32> %v1, <4 x i32> <i32 1, i32 5, i32 3, i32 7>
ret <4 x i32> %tmp0
@@ -182,11 +167,10 @@ define <2 x i64> @trn1.v2i64(<2 x i64> %v0, <2 x i64> %v1) {
define <2 x i64> @trn2.v2i64(<2 x i64> %v0, <2 x i64> %v1) {
; CHECK-LABEL: trn2.v2i64:
; CHECK: # %bb.0:
-; CHECK-NEXT: vsetivli zero, 2, e64, m1, ta, mu
+; CHECK-NEXT: vsetivli zero, 2, e64, m1, ta, ma
; CHECK-NEXT: vmv.v.i v0, 2
; CHECK-NEXT: vrgather.vi v10, v8, 1
-; CHECK-NEXT: vrgather.vi v10, v9, 1, v0.t
-; CHECK-NEXT: vmv.v.v v8, v10
+; CHECK-NEXT: vmerge.vvm v8, v10, v9, v0
; CHECK-NEXT: ret
%tmp0 = shufflevector <2 x i64> %v0, <2 x i64> %v1, <2 x i32> <i32 1, i32 3>
ret <2 x i64> %tmp0
@@ -205,11 +189,10 @@ define <2 x float> @trn1.v2f32(<2 x float> %v0, <2 x float> %v1) {
define <2 x float> @trn2.v2f32(<2 x float> %v0, <2 x float> %v1) {
; CHECK-LABEL: trn2.v2f32:
; CHECK: # %bb.0:
-; CHECK-NEXT: vsetivli zero, 2, e32, mf2, ta, mu
+; CHECK-NEXT: vsetivli zero, 2, e32, mf2, ta, ma
; CHECK-NEXT: vmv.v.i v0, 2
; CHECK-NEXT: vrgather.vi v10, v8, 1
-; CHECK-NEXT: vrgather.vi v10, v9, 1, v0.t
-; CHECK-NEXT: vmv1r.v v8, v10
+; CHECK-NEXT: vmerge.vvm v8, v10, v9, v0
; CHECK-NEXT: ret
%tmp0 = shufflevector <2 x float> %v0, <2 x float> %v1, <2 x i32> <i32 1, i32 3>
ret <2 x float> %tmp0
@@ -218,11 +201,10 @@ define <2 x float> @trn2.v2f32(<2 x float> %v0, <2 x float> %v1) {
define <4 x float> @trn1.v4f32(<4 x float> %v0, <4 x float> %v1) {
; CHECK-LABEL: trn1.v4f32:
; CHECK: # %bb.0:
-; CHECK-NEXT: vsetivli zero, 4, e32, m1, ta, mu
-; CHECK-NEXT: vid.v v10
+; CHECK-NEXT: vsetivli zero, 1, e8, mf8, ta, ma
; CHECK-NEXT: vmv.v.i v0, 10
-; CHECK-NEXT: vadd.vi v10, v10, -1
-; CHECK-NEXT: vrgather.vv v8, v9, v10, v0.t
+; CHECK-NEXT: vsetivli zero, 4, e32, m1, ta, mu
+; CHECK-NEXT: vslideup.vi v8, v9, 1, v0.t
; CHECK-NEXT: ret
%tmp0 = shufflevector <4 x float> %v0, <4 x float> %v1, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
ret <4 x float> %tmp0
@@ -231,11 +213,10 @@ define <4 x float> @trn1.v4f32(<4 x float> %v0, <4 x float> %v1) {
define <4 x float> @trn2.v4f32(<4 x float> %v0, <4 x float> %v1) {
; CHECK-LABEL: trn2.v4f32:
; CHECK: # %bb.0:
-; CHECK-NEXT: vsetivli zero, 4, e32, m1, ta, mu
-; CHECK-NEXT: vslidedown.vi v8, v8, 1
+; CHECK-NEXT: vsetivli zero, 4, e32, m1, ta, ma
; CHECK-NEXT: vmv.v.i v0, 10
-; CHECK-NEXT: vid.v v10
-; CHECK-NEXT: vrgather.vv v8, v9, v10, v0.t
+; CHECK-NEXT: vslidedown.vi v8, v8, 1
+; CHECK-NEXT: vmerge.vvm v8, v8, v9, v0
; CHECK-NEXT: ret
%tmp0 = shufflevector <4 x float> %v0, <4 x float> %v1, <4 x i32> <i32 1, i32 5, i32 3, i32 7>
ret <4 x float> %tmp0
@@ -254,11 +235,10 @@ define <2 x double> @trn1.v2f64(<2 x double> %v0, <2 x double> %v1) {
define <2 x double> @trn2.v2f64(<2 x double> %v0, <2 x double> %v1) {
; CHECK-LABEL: trn2.v2f64:
; CHECK: # %bb.0:
-; CHECK-NEXT: vsetivli zero, 2, e64, m1, ta, mu
+; CHECK-NEXT: vsetivli zero, 2, e64, m1, ta, ma
; CHECK-NEXT: vmv.v.i v0, 2
; CHECK-NEXT: vrgather.vi v10, v8, 1
-; CHECK-NEXT: vrgather.vi v10, v9, 1, v0.t
-; CHECK-NEXT: vmv.v.v v8, v10
+; CHECK-NEXT: vmerge.vvm v8, v10, v9, v0
; CHECK-NEXT: ret
%tmp0 = shufflevector <2 x double> %v0, <2 x double> %v1, <2 x i32> <i32 1, i32 3>
ret <2 x double> %tmp0
@@ -267,11 +247,10 @@ define <2 x double> @trn2.v2f64(<2 x double> %v0, <2 x double> %v1) {
define <4 x half> @trn1.v4f16(<4 x half> %v0, <4 x half> %v1) {
; CHECK-LABEL: trn1.v4f16:
; CHECK: # %bb.0:
-; CHECK-NEXT: vsetivli zero, 4, e16, mf2, ta, mu
-; CHECK-NEXT: vid.v v10
+; CHECK-NEXT: vsetivli zero, 1, e8, mf8, ta, ma
; CHECK-NEXT: vmv.v.i v0, 10
-; CHECK-NEXT: vadd.vi v10, v10, -1
-; CHECK-NEXT: vrgather.vv v8, v9, v10, v0.t
+; CHECK-NEXT: vsetivli zero, 4, e16, mf2, ta, mu
+; CHECK-NEXT: vslideup.vi v8, v9, 1, v0.t
; CHECK-NEXT: ret
%tmp0 = shufflevector <4 x half> %v0, <4 x half> %v1, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
ret <4 x half> %tmp0
@@ -280,11 +259,10 @@ define <4 x half> @trn1.v4f16(<4 x half> %v0, <4 x half> %v1) {
define <4 x half> @trn2.v4f16(<4 x half> %v0, <4 x half> %v1) {
; CHECK-LABEL: trn2.v4f16:
; CHECK: # %bb.0:
-; CHECK-NEXT: vsetivli zero, 4, e16, mf2, ta, mu
-; CHECK-NEXT: vslidedown.vi v8, v8, 1
+; CHECK-NEXT: vsetivli zero, 4, e16, mf2, ta, ma
; CHECK-NEXT: vmv.v.i v0, 10
-; CHECK-NEXT: vid.v v10
-; CHECK-NEXT: vrgather.vv v8, v9, v10, v0.t
+; CHECK-NEXT: vslidedown.vi v8, v8, 1
+; CHECK-NEXT: vmerge.vvm v8, v8, v9, v0
; CHECK-NEXT: ret
%tmp0 = shufflevector <4 x half> %v0, <4 x half> %v1, <4 x i32> <i32 1, i32 5, i32 3, i32 7>
ret <4 x half> %tmp0
@@ -293,12 +271,10 @@ define <4 x half> @trn2.v4f16(<4 x half> %v0, <4 x half> %v1) {
define <8 x half> @trn1.v8f16(<8 x half> %v0, <8 x half> %v1) {
; CHECK-LABEL: trn1.v8f16:
; CHECK: # %bb.0:
-; CHECK-NEXT: vsetivli zero, 8, e16, m1, ta, mu
-; CHECK-NEXT: vid.v v10
; CHECK-NEXT: li a0, 170
+; CHECK-NEXT: vsetivli zero, 8, e16, m1, ta, mu
; CHECK-NEXT: vmv.s.x v0, a0
-; CHECK-NEXT: vadd.vi v10, v10, -1
-; CHECK-NEXT: vrgather.vv v8, v9, v10, v0.t
+; CHECK-NEXT: vslideup.vi v8, v9, 1, v0.t
; CHECK-NEXT: ret
%tmp0 = shufflevector <8 x half> %v0, <8 x half> %v1, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
ret <8 x half> %tmp0
@@ -307,12 +283,11 @@ define <8 x half> @trn1.v8f16(<8 x half> %v0, <8 x half> %v1) {
define <8 x half> @trn2.v8f16(<8 x half> %v0, <8 x half> %v1) {
; CHECK-LABEL: trn2.v8f16:
; CHECK: # %bb.0:
-; CHECK-NEXT: vsetivli zero, 8, e16, m1, ta, mu
-; CHECK-NEXT: vslidedown.vi v8, v8, 1
+; CHECK-NEXT: vsetivli zero, 8, e16, m1, ta, ma
; CHECK-NEXT: li a0, 170
; CHECK-NEXT: vmv.s.x v0, a0
-; CHECK-NEXT: vid.v v10
-; CHECK-NEXT: vrgather.vv v8, v9, v10, v0.t
+; CHECK-NEXT: vslidedown.vi v8, v8, 1
+; CHECK-NEXT: vmerge.vvm v8, v8, v9, v0
; CHECK-NEXT: ret
%tmp0 = shufflevector <8 x half> %v0, <8 x half> %v1, <8 x i32> <i32 1, i32 9, i32 3, i32 11, i32 5, i32 13, i32 7, i32 15>
ret <8 x half> %tmp0
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-shufflevector-vnsrl.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-shufflevector-vnsrl.ll
index ff6a9dc38999c2..25af5ba2f079f1 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-shufflevector-vnsrl.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-shufflevector-vnsrl.ll
@@ -179,12 +179,11 @@ define void @vnsrl_32_i32(ptr %in, ptr %out) {
; ZVE32F: # %bb.0: # %entry
; ZVE32F-NEXT: vsetivli zero, 4, e32, m1, ta, ma
; ZVE32F-NEXT: vle32.v v8, (a0)
-; ZVE32F-NEXT: vsetivli zero, 2, e32, m1, ta, mu
-; ZVE32F-NEXT: vslidedown.vi v9, v8, 2
; ZVE32F-NEXT: vmv.v.i v0, 2
-; ZVE32F-NEXT: vrgather.vi v10, v8, 1
-; ZVE32F-NEXT: vrgather.vi v10, v9, 1, v0.t
-; ZVE32F-NEXT: vse32.v v10, (a1)
+; ZVE32F-NEXT: vsetivli zero, 2, e32, m1, ta, mu
+; ZVE32F-NEXT: vrgather.vi v9, v8, 1
+; ZVE32F-NEXT: vslidedown.vi v9, v8, 2, v0.t
+; ZVE32F-NEXT: vse32.v v9, (a1)
; ZVE32F-NEXT: ret
entry:
%0 = load <4 x i32>, ptr %in, align 4
@@ -234,12 +233,11 @@ define void @vnsrl_32_float(ptr %in, ptr %out) {
; ZVE32F: # %bb.0: # %entry
; ZVE32F-NEXT: vsetivli zero, 4, e32, m1, ta, ma
; ZVE32F-NEXT: vle32.v v8, (a0)
-; ZVE32F-NEXT: vsetivli zero, 2, e32, m1, ta, mu
-; ZVE32F-NEXT: vslidedown.vi v9, v8, 2
; ZVE32F-NEXT: vmv.v.i v0, 2
-; ZVE32F-NEXT: vrgather.vi v10, v8, 1
-; ZVE32F-NEXT: vrgather.vi v10, v9, 1, v0.t
-; ZVE32F-NEXT: vse32.v v10, (a1)
+; ZVE32F-NEXT: vsetivli zero, 2, e32, m1, ta, mu
+; ZVE32F-NEXT: vrgather.vi v9, v8, 1
+; ZVE32F-NEXT: vslidedown.vi v9, v8, 2, v0.t
+; ZVE32F-NEXT: vse32.v v9, (a1)
; ZVE32F-NEXT: ret
entry:
%0 = load <4 x float>, ptr %in, align 4
@@ -278,12 +276,11 @@ define void @vnsrl_64_i64(ptr %in, ptr %out) {
; V: # %bb.0: # %entry
; V-NEXT: vsetivli zero, 4, e64, m1, ta, ma
; V-NEXT: vle64.v v8, (a0)
-; V-NEXT: vsetivli zero, 2, e64, m1, ta, mu
-; V-NEXT: vslidedown.vi v9, v8, 2
; V-NEXT: vmv.v.i v0, 2
-; V-NEXT: vrgather.vi v10, v8, 1
-; V-NEXT: vrgather.vi v10, v9, 1, v0.t
-; V-NEXT: vse64.v v10, (a1)
+; V-NEXT: vsetivli zero, 2, e64, m1, ta, mu
+; V-NEXT: vrgather.vi v9, v8, 1
+; V-NEXT: vslidedown.vi v9, v8, 2, v0.t
+; V-NEXT: vse64.v v9, (a1)
; V-NEXT: ret
;
; ZVE32F-LABEL: vnsrl_64_i64:
@@ -330,12 +327,11 @@ define void @vnsrl_64_double(ptr %in, ptr %out) {
; V: # %bb.0: # %entry
; V-NEXT: vsetivli zero, 4, e64, m1, ta, ma
; V-NEXT: vle64.v v8, (a0)
-; V-NEXT: vsetivli zero, 2, e64, m1, ta, mu
-; V-NEXT: vslidedown.vi v9, v8, 2
; V-NEXT: vmv.v.i v0, 2
-; V-NEXT: vrgather.vi v10, v8, 1
-; V-NEXT: vrgather.vi v10, v9, 1, v0.t
-; V-NEXT: vse64.v v10, (a1)
+; V-NEXT: vsetivli zero, 2, e64, m1, ta, mu
+; V-NEXT: vrgather.vi v9, v8, 1
+; V-NEXT: vslidedown.vi v9, v8, 2, v0.t
+; V-NEXT: vse64.v v9, (a1)
; V-NEXT: ret
;
; ZVE32F-LABEL: vnsrl_64_double:
diff --git a/llvm/test/CodeGen/RISCV/rvv/vector-deinterleave-fixed.ll b/llvm/test/CodeGen/RISCV/rvv/vector-deinterleave-fixed.ll
index 84e9e2801ff6db..f3c70ed78c747f 100644
--- a/llvm/test/CodeGen/RISCV/rvv/vector-deinterleave-fixed.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/vector-deinterleave-fixed.ll
@@ -82,9 +82,9 @@ define {<2 x i64>, <2 x i64>} @vector_deinterleave_v2i64_v4i64(<4 x i64> %vec) {
; CHECK-NEXT: vslidedown.vi v10, v8, 2
; CHECK-NEXT: vsetivli zero, 1, e8, mf8, ta, ma
; CHECK-NEXT: vmv.v.i v0, 2
-; CHECK-NEXT: vsetivli zero, 2, e64, m1, ta, mu
+; CHECK-NEXT: vsetivli zero, 2, e64, m1, ta, ma
; CHECK-NEXT: vrgather.vi v9, v8, 1
-; CHECK-NEXT: vrgather.vi v9, v10, 1, v0.t
+; CHECK-NEXT: vmerge.vvm v9, v9, v10, v0
; CHECK-NEXT: vslideup.vi v8, v10, 1
; CHECK-NEXT: ret
%retval = call {<2 x i64>, <2 x i64>} @llvm.experimental.vector.deinterleave2.v4i64(<4 x i64> %vec)
@@ -169,9 +169,9 @@ define {<2 x double>, <2 x double>} @vector_deinterleave_v2f64_v4f64(<4 x double
; CHECK-NEXT: vslidedown.vi v10, v8, 2
; CHECK-NEXT: vsetivli zero, 1, e8, mf8, ta, ma
; CHECK-NEXT: vmv.v.i v0, 2
-; CHECK-NEXT: vsetivli zero, 2, e64, m1, ta, mu
+; CHECK-NEXT: vsetivli zero, 2, e64, m1, ta, ma
; CHECK-NEXT: vrgather.vi v9, v8, 1
-; CHECK-NEXT: vrgather.vi v9, v10, 1, v0.t
+; CHECK-NEXT: vmerge.vvm v9, v9, v10, v0
; CHECK-NEXT: vslideup.vi v8, v10, 1
; CHECK-NEXT: ret
%retval = call {<2 x double>, <2 x double>} @llvm.experimental.vector.deinterleave2.v4f64(<4 x double> %vec)
More information about the llvm-commits
mailing list