[llvm] r255387 - Revert r248483, r242546, r242545, and r242409 - absdiff intrinsics
Hal Finkel via llvm-commits
llvm-commits at lists.llvm.org
Fri Dec 11 15:11:53 PST 2015
Author: hfinkel
Date: Fri Dec 11 17:11:52 2015
New Revision: 255387
URL: http://llvm.org/viewvc/llvm-project?rev=255387&view=rev
Log:
Revert r248483, r242546, r242545, and r242409 - absdiff intrinsics
After much discussion, ending here:
http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20151123/315620.html
it has been decided that, instead of having the vectorizer directly generate
special absdiff and horizontal-add intrinsics, we'll recognize the relevant
reduction patterns during CodeGen. Accordingly, these intrinsics are not needed
(the operations they represent can be pattern matched, as is already done in
some backends). Thus, we're backing these out in favor of the current
development work.
r248483 - Codegen: Fix llvm.*absdiff semantic.
r242546 - [ARM] Use [SU]ABSDIFF nodes instead of intrinsics for VABD/VABA
r242545 - [AArch64] Use [SU]ABSDIFF nodes instead of intrinsics for ABD/ABA
r242409 - [Codegen] Add intrinsics 'absdiff' and corresponding SDNodes for absolute difference operation
Removed:
llvm/trunk/test/CodeGen/X86/absdiff_128.ll
llvm/trunk/test/CodeGen/X86/absdiff_256.ll
Modified:
llvm/trunk/docs/LangRef.rst
llvm/trunk/include/llvm/CodeGen/ISDOpcodes.h
llvm/trunk/include/llvm/IR/Intrinsics.td
llvm/trunk/include/llvm/Target/TargetSelectionDAG.td
llvm/trunk/lib/CodeGen/SelectionDAG/LegalizeIntegerTypes.cpp
llvm/trunk/lib/CodeGen/SelectionDAG/LegalizeVectorOps.cpp
llvm/trunk/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp
llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAGDumper.cpp
llvm/trunk/lib/CodeGen/TargetLoweringBase.cpp
llvm/trunk/lib/Target/AArch64/AArch64ISelLowering.cpp
llvm/trunk/lib/Target/AArch64/AArch64InstrInfo.td
llvm/trunk/lib/Target/ARM/ARMISelLowering.cpp
llvm/trunk/lib/Target/ARM/ARMInstrNEON.td
Modified: llvm/trunk/docs/LangRef.rst
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/docs/LangRef.rst?rev=255387&r1=255386&r2=255387&view=diff
==============================================================================
--- llvm/trunk/docs/LangRef.rst (original)
+++ llvm/trunk/docs/LangRef.rst Fri Dec 11 17:11:52 2015
@@ -11217,68 +11217,6 @@ Examples:
%r2 = call float @llvm.fmuladd.f32(float %a, float %b, float %c) ; yields float:r2 = (a * b) + c
-
-'``llvm.uabsdiff.*``' and '``llvm.sabsdiff.*``' Intrinsics
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-
-Syntax:
-"""""""
-This is an overloaded intrinsic. The loaded data is a vector of any integer bit width.
-
-.. code-block:: llvm
-
- declare <4 x integer> @llvm.uabsdiff.v4i32(<4 x integer> %a, <4 x integer> %b)
-
-
-Overview:
-"""""""""
-
-The ``llvm.uabsdiff`` intrinsic returns a vector result of the absolute difference
-of the two operands, treating them both as unsigned integers. The intermediate
-calculations are computed using infinitely precise unsigned arithmetic. The final
-result will be truncated to the given type.
-
-The ``llvm.sabsdiff`` intrinsic returns a vector result of the absolute difference of
-the two operands, treating them both as signed integers. If the result overflows, the
-behavior is undefined.
-
-.. note::
-
- These intrinsics are primarily used during the code generation stage of compilation.
- They are generated by compiler passes such as the Loop and SLP vectorizers. It is not
- recommended for users to create them manually.
-
-Arguments:
-""""""""""
-
-Both intrinsics take two integer of the same bitwidth.
-
-Semantics:
-""""""""""
-
-The expression::
-
- call <4 x i32> @llvm.uabsdiff.v4i32(<4 x i32> %a, <4 x i32> %b)
-
-is equivalent to::
-
- %1 = zext <4 x i32> %a to <4 x i64>
- %2 = zext <4 x i32> %b to <4 x i64>
- %sub = sub <4 x i64> %1, %2
- %trunc = trunc <4 x i64> to <4 x i32>
-
-and the expression::
-
- call <4 x i32> @llvm.sabsdiff.v4i32(<4 x i32> %a, <4 x i32> %b)
-
-is equivalent to::
-
- %sub = sub nsw <4 x i32> %a, %b
- %ispos = icmp sge <4 x i32> %sub, zeroinitializer
- %neg = sub nsw <4 x i32> zeroinitializer, %sub
- %1 = select <4 x i1> %ispos, <4 x i32> %sub, <4 x i32> %neg
-
-
Half Precision Floating Point Intrinsics
----------------------------------------
Modified: llvm/trunk/include/llvm/CodeGen/ISDOpcodes.h
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/include/llvm/CodeGen/ISDOpcodes.h?rev=255387&r1=255386&r2=255387&view=diff
==============================================================================
--- llvm/trunk/include/llvm/CodeGen/ISDOpcodes.h (original)
+++ llvm/trunk/include/llvm/CodeGen/ISDOpcodes.h Fri Dec 11 17:11:52 2015
@@ -338,10 +338,6 @@ namespace ISD {
/// Byte Swap and Counting operators.
BSWAP, CTTZ, CTLZ, CTPOP, BITREVERSE,
- /// [SU]ABSDIFF - Signed/Unsigned absolute difference of two input integer
- /// vector. These nodes are generated from llvm.*absdiff* intrinsics.
- SABSDIFF, UABSDIFF,
-
/// Bit counting operators with an undefined result for zero inputs.
CTTZ_ZERO_UNDEF, CTLZ_ZERO_UNDEF,
Modified: llvm/trunk/include/llvm/IR/Intrinsics.td
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/include/llvm/IR/Intrinsics.td?rev=255387&r1=255386&r2=255387&view=diff
==============================================================================
--- llvm/trunk/include/llvm/IR/Intrinsics.td (original)
+++ llvm/trunk/include/llvm/IR/Intrinsics.td Fri Dec 11 17:11:52 2015
@@ -631,12 +631,6 @@ def int_convertuu : Intrinsic<[llvm_any
def int_clear_cache : Intrinsic<[], [llvm_ptr_ty, llvm_ptr_ty],
[], "llvm.clear_cache">;
-// Calculate the Absolute Differences of the two input vectors.
-def int_sabsdiff : Intrinsic<[llvm_anyvector_ty],
- [ LLVMMatchType<0>, LLVMMatchType<0> ], [IntrNoMem]>;
-def int_uabsdiff : Intrinsic<[llvm_anyvector_ty],
- [ LLVMMatchType<0>, LLVMMatchType<0> ], [IntrNoMem]>;
-
//===-------------------------- Masked Intrinsics -------------------------===//
//
def int_masked_store : Intrinsic<[], [llvm_anyvector_ty, LLVMPointerTo<0>,
Modified: llvm/trunk/include/llvm/Target/TargetSelectionDAG.td
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/include/llvm/Target/TargetSelectionDAG.td?rev=255387&r1=255386&r2=255387&view=diff
==============================================================================
--- llvm/trunk/include/llvm/Target/TargetSelectionDAG.td (original)
+++ llvm/trunk/include/llvm/Target/TargetSelectionDAG.td Fri Dec 11 17:11:52 2015
@@ -396,8 +396,6 @@ def smax : SDNode<"ISD::SMAX"
def umin : SDNode<"ISD::UMIN" , SDTIntBinOp>;
def umax : SDNode<"ISD::UMAX" , SDTIntBinOp>;
-def sabsdiff : SDNode<"ISD::SABSDIFF" , SDTIntBinOp>;
-def uabsdiff : SDNode<"ISD::UABSDIFF" , SDTIntBinOp>;
def sext_inreg : SDNode<"ISD::SIGN_EXTEND_INREG", SDTExtInreg>;
def bitreverse : SDNode<"ISD::BITREVERSE" , SDTIntUnaryOp>;
def bswap : SDNode<"ISD::BSWAP" , SDTIntUnaryOp>;
Modified: llvm/trunk/lib/CodeGen/SelectionDAG/LegalizeIntegerTypes.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/CodeGen/SelectionDAG/LegalizeIntegerTypes.cpp?rev=255387&r1=255386&r2=255387&view=diff
==============================================================================
--- llvm/trunk/lib/CodeGen/SelectionDAG/LegalizeIntegerTypes.cpp (original)
+++ llvm/trunk/lib/CodeGen/SelectionDAG/LegalizeIntegerTypes.cpp Fri Dec 11 17:11:52 2015
@@ -147,10 +147,6 @@ void DAGTypeLegalizer::PromoteIntegerRes
case ISD::ATOMIC_CMP_SWAP_WITH_SUCCESS:
Res = PromoteIntRes_AtomicCmpSwap(cast<AtomicSDNode>(N), ResNo);
break;
- case ISD::UABSDIFF:
- case ISD::SABSDIFF:
- Res = PromoteIntRes_SimpleIntBinOp(N);
- break;
}
// If the result is null then the sub-method took care of registering it.
Modified: llvm/trunk/lib/CodeGen/SelectionDAG/LegalizeVectorOps.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/CodeGen/SelectionDAG/LegalizeVectorOps.cpp?rev=255387&r1=255386&r2=255387&view=diff
==============================================================================
--- llvm/trunk/lib/CodeGen/SelectionDAG/LegalizeVectorOps.cpp (original)
+++ llvm/trunk/lib/CodeGen/SelectionDAG/LegalizeVectorOps.cpp Fri Dec 11 17:11:52 2015
@@ -105,7 +105,6 @@ class VectorLegalizer {
SDValue ExpandLoad(SDValue Op);
SDValue ExpandStore(SDValue Op);
SDValue ExpandFNEG(SDValue Op);
- SDValue ExpandABSDIFF(SDValue Op);
/// \brief Implements vector promotion.
///
@@ -330,8 +329,6 @@ SDValue VectorLegalizer::LegalizeOp(SDVa
case ISD::SMAX:
case ISD::UMIN:
case ISD::UMAX:
- case ISD::UABSDIFF:
- case ISD::SABSDIFF:
QueryType = Node->getValueType(0);
break;
case ISD::FP_ROUND_INREG:
@@ -718,42 +715,11 @@ SDValue VectorLegalizer::Expand(SDValue
return ExpandFNEG(Op);
case ISD::SETCC:
return UnrollVSETCC(Op);
- case ISD::UABSDIFF:
- case ISD::SABSDIFF:
- return ExpandABSDIFF(Op);
default:
return DAG.UnrollVectorOp(Op.getNode());
}
}
-SDValue VectorLegalizer::ExpandABSDIFF(SDValue Op) {
- SDLoc dl(Op);
- SDValue Op0 = Op.getOperand(0);
- SDValue Op1 = Op.getOperand(1);
- EVT VT = Op.getValueType();
-
- // For unsigned intrinsic, promote the type to handle unsigned overflow.
- bool isUabsdiff = (Op->getOpcode() == ISD::UABSDIFF);
- if (isUabsdiff) {
- VT = VT.widenIntegerVectorElementType(*DAG.getContext());
- Op0 = DAG.getNode(ISD::ZERO_EXTEND, dl, VT, Op0);
- Op1 = DAG.getNode(ISD::ZERO_EXTEND, dl, VT, Op1);
- }
-
- SDNodeFlags Flags;
- Flags.setNoSignedWrap(!isUabsdiff);
- SDValue Sub = DAG.getNode(ISD::SUB, dl, VT, Op0, Op1, &Flags);
- if (isUabsdiff)
- return DAG.getNode(ISD::TRUNCATE, dl, Op.getValueType(), Sub);
-
- SDValue Cmp =
- DAG.getNode(ISD::SETCC, dl, TLI.getSetCCResultType(DAG.getDataLayout(),
- *DAG.getContext(), VT),
- Sub, DAG.getConstant(0, dl, VT), DAG.getCondCode(ISD::SETGE));
- SDValue Neg = DAG.getNode(ISD::SUB, dl, VT, DAG.getConstant(0, dl, VT), Sub, &Flags);
- return DAG.getNode(ISD::VSELECT, dl, VT, Cmp, Sub, Neg);
-}
-
SDValue VectorLegalizer::ExpandSELECT(SDValue Op) {
// Lower a select instruction where the condition is a scalar and the
// operands are vectors. Lower this select to VSELECT and implement it
Modified: llvm/trunk/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp?rev=255387&r1=255386&r2=255387&view=diff
==============================================================================
--- llvm/trunk/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp (original)
+++ llvm/trunk/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp Fri Dec 11 17:11:52 2015
@@ -684,8 +684,6 @@ void DAGTypeLegalizer::SplitVectorResult
case ISD::SMAX:
case ISD::UMIN:
case ISD::UMAX:
- case ISD::UABSDIFF:
- case ISD::SABSDIFF:
SplitVecRes_BinOp(N, Lo, Hi);
break;
case ISD::FMA:
Modified: llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp?rev=255387&r1=255386&r2=255387&view=diff
==============================================================================
--- llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp (original)
+++ llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp Fri Dec 11 17:11:52 2015
@@ -4880,18 +4880,6 @@ SelectionDAGBuilder::visitIntrinsicCall(
getValue(I.getArgOperand(0)).getValueType(),
getValue(I.getArgOperand(0))));
return nullptr;
- case Intrinsic::uabsdiff:
- setValue(&I, DAG.getNode(ISD::UABSDIFF, sdl,
- getValue(I.getArgOperand(0)).getValueType(),
- getValue(I.getArgOperand(0)),
- getValue(I.getArgOperand(1))));
- return nullptr;
- case Intrinsic::sabsdiff:
- setValue(&I, DAG.getNode(ISD::SABSDIFF, sdl,
- getValue(I.getArgOperand(0)).getValueType(),
- getValue(I.getArgOperand(0)),
- getValue(I.getArgOperand(1))));
- return nullptr;
case Intrinsic::cttz: {
SDValue Arg = getValue(I.getArgOperand(0));
ConstantInt *CI = cast<ConstantInt>(I.getArgOperand(1));
Modified: llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAGDumper.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAGDumper.cpp?rev=255387&r1=255386&r2=255387&view=diff
==============================================================================
--- llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAGDumper.cpp (original)
+++ llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAGDumper.cpp Fri Dec 11 17:11:52 2015
@@ -235,8 +235,6 @@ std::string SDNode::getOperationName(con
case ISD::SHL_PARTS: return "shl_parts";
case ISD::SRA_PARTS: return "sra_parts";
case ISD::SRL_PARTS: return "srl_parts";
- case ISD::UABSDIFF: return "uabsdiff";
- case ISD::SABSDIFF: return "sabsdiff";
// Conversion operators.
case ISD::SIGN_EXTEND: return "sign_extend";
Modified: llvm/trunk/lib/CodeGen/TargetLoweringBase.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/CodeGen/TargetLoweringBase.cpp?rev=255387&r1=255386&r2=255387&view=diff
==============================================================================
--- llvm/trunk/lib/CodeGen/TargetLoweringBase.cpp (original)
+++ llvm/trunk/lib/CodeGen/TargetLoweringBase.cpp Fri Dec 11 17:11:52 2015
@@ -826,8 +826,7 @@ void TargetLoweringBase::initActions() {
setOperationAction(ISD::USUBO, VT, Expand);
setOperationAction(ISD::SMULO, VT, Expand);
setOperationAction(ISD::UMULO, VT, Expand);
- setOperationAction(ISD::UABSDIFF, VT, Expand);
- setOperationAction(ISD::SABSDIFF, VT, Expand);
+
setOperationAction(ISD::BITREVERSE, VT, Expand);
// These library functions default to expand.
Modified: llvm/trunk/lib/Target/AArch64/AArch64ISelLowering.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/AArch64/AArch64ISelLowering.cpp?rev=255387&r1=255386&r2=255387&view=diff
==============================================================================
--- llvm/trunk/lib/Target/AArch64/AArch64ISelLowering.cpp (original)
+++ llvm/trunk/lib/Target/AArch64/AArch64ISelLowering.cpp Fri Dec 11 17:11:52 2015
@@ -691,12 +691,10 @@ void AArch64TargetLowering::addTypeForNE
setOperationAction(ISD::FP_TO_SINT, VT.getSimpleVT(), Custom);
setOperationAction(ISD::FP_TO_UINT, VT.getSimpleVT(), Custom);
- // [SU][MIN|MAX] and [SU]ABSDIFF are available for all NEON types apart from
- // i64.
+ // [SU][MIN|MAX] are available for all NEON types apart from i64.
if (!VT.isFloatingPoint() &&
VT.getSimpleVT() != MVT::v2i64 && VT.getSimpleVT() != MVT::v1i64)
- for (unsigned Opcode : {ISD::SMIN, ISD::SMAX, ISD::UMIN, ISD::UMAX,
- ISD::SABSDIFF, ISD::UABSDIFF})
+ for (unsigned Opcode : {ISD::SMIN, ISD::SMAX, ISD::UMIN, ISD::UMAX})
setOperationAction(Opcode, VT.getSimpleVT(), Legal);
// F[MIN|MAX][NUM|NAN] are available for all FP NEON types (not f16 though!).
@@ -8251,15 +8249,14 @@ static SDValue performAddSubLongCombine(
// (aarch64_neon_umull (extract_high (v2i64 vec)))
// (extract_high (v2i64 (dup128 scalar)))))
//
-static SDValue tryCombineLongOpWithDup(SDNode *N,
+static SDValue tryCombineLongOpWithDup(unsigned IID, SDNode *N,
TargetLowering::DAGCombinerInfo &DCI,
SelectionDAG &DAG) {
if (DCI.isBeforeLegalizeOps())
return SDValue();
- bool IsIntrinsic = N->getOpcode() == ISD::INTRINSIC_WO_CHAIN;
- SDValue LHS = N->getOperand(IsIntrinsic ? 1 : 0);
- SDValue RHS = N->getOperand(IsIntrinsic ? 2 : 1);
+ SDValue LHS = N->getOperand(1);
+ SDValue RHS = N->getOperand(2);
assert(LHS.getValueType().is64BitVector() &&
RHS.getValueType().is64BitVector() &&
"unexpected shape for long operation");
@@ -8277,13 +8274,8 @@ static SDValue tryCombineLongOpWithDup(S
return SDValue();
}
- // N could either be an intrinsic or a sabsdiff/uabsdiff node.
- if (IsIntrinsic)
- return DAG.getNode(ISD::INTRINSIC_WO_CHAIN, SDLoc(N), N->getValueType(0),
- N->getOperand(0), LHS, RHS);
- else
- return DAG.getNode(N->getOpcode(), SDLoc(N), N->getValueType(0),
- LHS, RHS);
+ return DAG.getNode(ISD::INTRINSIC_WO_CHAIN, SDLoc(N), N->getValueType(0),
+ N->getOperand(0), LHS, RHS);
}
static SDValue tryCombineShiftImm(unsigned IID, SDNode *N, SelectionDAG &DAG) {
@@ -8401,12 +8393,6 @@ static SDValue performIntrinsicCombine(S
case Intrinsic::aarch64_neon_fmin:
return DAG.getNode(ISD::FMINNAN, SDLoc(N), N->getValueType(0),
N->getOperand(1), N->getOperand(2));
- case Intrinsic::aarch64_neon_sabd:
- return DAG.getNode(ISD::SABSDIFF, SDLoc(N), N->getValueType(0),
- N->getOperand(1), N->getOperand(2));
- case Intrinsic::aarch64_neon_uabd:
- return DAG.getNode(ISD::UABSDIFF, SDLoc(N), N->getValueType(0),
- N->getOperand(1), N->getOperand(2));
case Intrinsic::aarch64_neon_fmaxnm:
return DAG.getNode(ISD::FMAXNUM, SDLoc(N), N->getValueType(0),
N->getOperand(1), N->getOperand(2));
@@ -8417,7 +8403,7 @@ static SDValue performIntrinsicCombine(S
case Intrinsic::aarch64_neon_umull:
case Intrinsic::aarch64_neon_pmull:
case Intrinsic::aarch64_neon_sqdmull:
- return tryCombineLongOpWithDup(N, DCI, DAG);
+ return tryCombineLongOpWithDup(IID, N, DCI, DAG);
case Intrinsic::aarch64_neon_sqshl:
case Intrinsic::aarch64_neon_uqshl:
case Intrinsic::aarch64_neon_sqshlu:
@@ -8442,15 +8428,18 @@ static SDValue performExtendCombine(SDNo
// helps the backend to decide that an sabdl2 would be useful, saving a real
// extract_high operation.
if (!DCI.isBeforeLegalizeOps() && N->getOpcode() == ISD::ZERO_EXTEND &&
- (N->getOperand(0).getOpcode() == ISD::SABSDIFF ||
- N->getOperand(0).getOpcode() == ISD::UABSDIFF)) {
+ N->getOperand(0).getOpcode() == ISD::INTRINSIC_WO_CHAIN) {
SDNode *ABDNode = N->getOperand(0).getNode();
- SDValue NewABD = tryCombineLongOpWithDup(ABDNode, DCI, DAG);
- if (!NewABD.getNode())
- return SDValue();
+ unsigned IID = getIntrinsicID(ABDNode);
+ if (IID == Intrinsic::aarch64_neon_sabd ||
+ IID == Intrinsic::aarch64_neon_uabd) {
+ SDValue NewABD = tryCombineLongOpWithDup(IID, ABDNode, DCI, DAG);
+ if (!NewABD.getNode())
+ return SDValue();
- return DAG.getNode(ISD::ZERO_EXTEND, SDLoc(N), N->getValueType(0),
- NewABD);
+ return DAG.getNode(ISD::ZERO_EXTEND, SDLoc(N), N->getValueType(0),
+ NewABD);
+ }
}
// This is effectively a custom type legalization for AArch64.
Modified: llvm/trunk/lib/Target/AArch64/AArch64InstrInfo.td
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/AArch64/AArch64InstrInfo.td?rev=255387&r1=255386&r2=255387&view=diff
==============================================================================
--- llvm/trunk/lib/Target/AArch64/AArch64InstrInfo.td (original)
+++ llvm/trunk/lib/Target/AArch64/AArch64InstrInfo.td Fri Dec 11 17:11:52 2015
@@ -2633,7 +2633,7 @@ defm FMOV : FPMoveImmediate<"fmov">;
//===----------------------------------------------------------------------===//
defm UABDL : SIMDLongThreeVectorBHSabdl<1, 0b0111, "uabdl",
- uabsdiff>;
+ int_aarch64_neon_uabd>;
// Match UABDL in log2-shuffle patterns.
def : Pat<(xor (v8i16 (AArch64vashr v8i16:$src, (i32 15))),
(v8i16 (add (sub (zext (v8i8 V64:$opA)),
@@ -2905,8 +2905,8 @@ defm MLS : SIMDThreeSameVectorBHSTi
defm MUL : SIMDThreeSameVectorBHS<0, 0b10011, "mul", mul>;
defm PMUL : SIMDThreeSameVectorB<1, 0b10011, "pmul", int_aarch64_neon_pmul>;
defm SABA : SIMDThreeSameVectorBHSTied<0, 0b01111, "saba",
- TriOpFrag<(add node:$LHS, (sabsdiff node:$MHS, node:$RHS))> >;
-defm SABD : SIMDThreeSameVectorBHS<0,0b01110,"sabd", sabsdiff>;
+ TriOpFrag<(add node:$LHS, (int_aarch64_neon_sabd node:$MHS, node:$RHS))> >;
+defm SABD : SIMDThreeSameVectorBHS<0,0b01110,"sabd", int_aarch64_neon_sabd>;
defm SHADD : SIMDThreeSameVectorBHS<0,0b00000,"shadd", int_aarch64_neon_shadd>;
defm SHSUB : SIMDThreeSameVectorBHS<0,0b00100,"shsub", int_aarch64_neon_shsub>;
defm SMAXP : SIMDThreeSameVectorBHS<0,0b10100,"smaxp", int_aarch64_neon_smaxp>;
@@ -2924,8 +2924,8 @@ defm SRSHL : SIMDThreeSameVector<0,0b
defm SSHL : SIMDThreeSameVector<0,0b01000,"sshl", int_aarch64_neon_sshl>;
defm SUB : SIMDThreeSameVector<1,0b10000,"sub", sub>;
defm UABA : SIMDThreeSameVectorBHSTied<1, 0b01111, "uaba",
- TriOpFrag<(add node:$LHS, (uabsdiff node:$MHS, node:$RHS))> >;
-defm UABD : SIMDThreeSameVectorBHS<1,0b01110,"uabd", uabsdiff>;
+ TriOpFrag<(add node:$LHS, (int_aarch64_neon_uabd node:$MHS, node:$RHS))> >;
+defm UABD : SIMDThreeSameVectorBHS<1,0b01110,"uabd", int_aarch64_neon_uabd>;
defm UHADD : SIMDThreeSameVectorBHS<1,0b00000,"uhadd", int_aarch64_neon_uhadd>;
defm UHSUB : SIMDThreeSameVectorBHS<1,0b00100,"uhsub", int_aarch64_neon_uhsub>;
defm UMAXP : SIMDThreeSameVectorBHS<1,0b10100,"umaxp", int_aarch64_neon_umaxp>;
@@ -3427,9 +3427,9 @@ defm RADDHN : SIMDNarrowThreeVectorBHS<1
defm RSUBHN : SIMDNarrowThreeVectorBHS<1,0b0110,"rsubhn",int_aarch64_neon_rsubhn>;
defm PMULL : SIMDDifferentThreeVectorBD<0,0b1110,"pmull",int_aarch64_neon_pmull>;
defm SABAL : SIMDLongThreeVectorTiedBHSabal<0,0b0101,"sabal",
- sabsdiff>;
+ int_aarch64_neon_sabd>;
defm SABDL : SIMDLongThreeVectorBHSabdl<0, 0b0111, "sabdl",
- sabsdiff>;
+ int_aarch64_neon_sabd>;
defm SADDL : SIMDLongThreeVectorBHS< 0, 0b0000, "saddl",
BinOpFrag<(add (sext node:$LHS), (sext node:$RHS))>>;
defm SADDW : SIMDWideThreeVectorBHS< 0, 0b0001, "saddw",
@@ -3450,7 +3450,7 @@ defm SSUBL : SIMDLongThreeVectorBHS<0,
defm SSUBW : SIMDWideThreeVectorBHS<0, 0b0011, "ssubw",
BinOpFrag<(sub node:$LHS, (sext node:$RHS))>>;
defm UABAL : SIMDLongThreeVectorTiedBHSabal<1, 0b0101, "uabal",
- uabsdiff>;
+ int_aarch64_neon_uabd>;
defm UADDL : SIMDLongThreeVectorBHS<1, 0b0000, "uaddl",
BinOpFrag<(add (zext node:$LHS), (zext node:$RHS))>>;
defm UADDW : SIMDWideThreeVectorBHS<1, 0b0001, "uaddw",
Modified: llvm/trunk/lib/Target/ARM/ARMISelLowering.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/ARM/ARMISelLowering.cpp?rev=255387&r1=255386&r2=255387&view=diff
==============================================================================
--- llvm/trunk/lib/Target/ARM/ARMISelLowering.cpp (original)
+++ llvm/trunk/lib/Target/ARM/ARMISelLowering.cpp Fri Dec 11 17:11:52 2015
@@ -143,15 +143,10 @@ void ARMTargetLowering::addTypeForNEON(M
setOperationAction(ISD::UREM, VT, Expand);
setOperationAction(ISD::FREM, VT, Expand);
- if (VT.isInteger()) {
- setOperationAction(ISD::SABSDIFF, VT, Legal);
- setOperationAction(ISD::UABSDIFF, VT, Legal);
- }
if (!VT.isFloatingPoint() &&
VT != MVT::v2i64 && VT != MVT::v1i64)
for (unsigned Opcode : {ISD::SMIN, ISD::SMAX, ISD::UMIN, ISD::UMAX})
setOperationAction(Opcode, VT, Legal);
-
}
void ARMTargetLowering::addDRTypeForNEON(MVT VT) {
@@ -10148,15 +10143,6 @@ static SDValue PerformIntrinsicCombine(S
// Don't do anything for most intrinsics.
break;
- case Intrinsic::arm_neon_vabds:
- if (!N->getValueType(0).isInteger())
- return SDValue();
- return DAG.getNode(ISD::SABSDIFF, SDLoc(N), N->getValueType(0),
- N->getOperand(1), N->getOperand(2));
- case Intrinsic::arm_neon_vabdu:
- return DAG.getNode(ISD::UABSDIFF, SDLoc(N), N->getValueType(0),
- N->getOperand(1), N->getOperand(2));
-
// Vector shifts: check for immediate versions and lower them.
// Note: This is done during DAG combining instead of DAG legalizing because
// the build_vectors for 64-bit vector element shift counts are generally
Modified: llvm/trunk/lib/Target/ARM/ARMInstrNEON.td
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/ARM/ARMInstrNEON.td?rev=255387&r1=255386&r2=255387&view=diff
==============================================================================
--- llvm/trunk/lib/Target/ARM/ARMInstrNEON.td (original)
+++ llvm/trunk/lib/Target/ARM/ARMInstrNEON.td Fri Dec 11 17:11:52 2015
@@ -4994,10 +4994,10 @@ def VBITq : N3VX<1, 0, 0b10, 0b0001,
// VABD : Vector Absolute Difference
defm VABDs : N3VInt_QHS<0, 0, 0b0111, 0, N3RegFrm,
IIC_VSUBi4D, IIC_VSUBi4D, IIC_VSUBi4Q, IIC_VSUBi4Q,
- "vabd", "s", sabsdiff, 1>;
+ "vabd", "s", int_arm_neon_vabds, 1>;
defm VABDu : N3VInt_QHS<1, 0, 0b0111, 0, N3RegFrm,
IIC_VSUBi4D, IIC_VSUBi4D, IIC_VSUBi4Q, IIC_VSUBi4Q,
- "vabd", "u", uabsdiff, 1>;
+ "vabd", "u", int_arm_neon_vabdu, 1>;
def VABDfd : N3VDInt<1, 0, 0b10, 0b1101, 0, N3RegFrm, IIC_VBIND,
"vabd", "f32", v2f32, v2f32, int_arm_neon_vabds, 1>;
def VABDfq : N3VQInt<1, 0, 0b10, 0b1101, 0, N3RegFrm, IIC_VBINQ,
@@ -5005,9 +5005,9 @@ def VABDfq : N3VQInt<1, 0, 0b10, 0b11
// VABDL : Vector Absolute Difference Long (Q = | D - D |)
defm VABDLs : N3VLIntExt_QHS<0,1,0b0111,0, IIC_VSUBi4Q,
- "vabdl", "s", sabsdiff, zext, 1>;
+ "vabdl", "s", int_arm_neon_vabds, zext, 1>;
defm VABDLu : N3VLIntExt_QHS<1,1,0b0111,0, IIC_VSUBi4Q,
- "vabdl", "u", uabsdiff, zext, 1>;
+ "vabdl", "u", int_arm_neon_vabdu, zext, 1>;
def abd_shr :
PatFrag<(ops node:$in1, node:$in2, node:$shift),
@@ -5034,15 +5034,15 @@ def : Pat<(xor (v4i32 (bitconvert (v2i64
// VABA : Vector Absolute Difference and Accumulate
defm VABAs : N3VIntOp_QHS<0,0,0b0111,1, IIC_VABAD, IIC_VABAQ,
- "vaba", "s", sabsdiff, add>;
+ "vaba", "s", int_arm_neon_vabds, add>;
defm VABAu : N3VIntOp_QHS<1,0,0b0111,1, IIC_VABAD, IIC_VABAQ,
- "vaba", "u", uabsdiff, add>;
+ "vaba", "u", int_arm_neon_vabdu, add>;
// VABAL : Vector Absolute Difference and Accumulate Long (Q += | D - D |)
defm VABALs : N3VLIntExtOp_QHS<0,1,0b0101,0, IIC_VABAD,
- "vabal", "s", sabsdiff, zext, add>;
+ "vabal", "s", int_arm_neon_vabds, zext, add>;
defm VABALu : N3VLIntExtOp_QHS<1,1,0b0101,0, IIC_VABAD,
- "vabal", "u", uabsdiff, zext, add>;
+ "vabal", "u", int_arm_neon_vabdu, zext, add>;
// Vector Maximum and Minimum.
Removed: llvm/trunk/test/CodeGen/X86/absdiff_128.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/absdiff_128.ll?rev=255386&view=auto
==============================================================================
--- llvm/trunk/test/CodeGen/X86/absdiff_128.ll (original)
+++ llvm/trunk/test/CodeGen/X86/absdiff_128.ll (removed)
@@ -1,181 +0,0 @@
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown | FileCheck %s
-
-declare <4 x i8> @llvm.uabsdiff.v4i8(<4 x i8>, <4 x i8>)
-
-define <4 x i8> @test_uabsdiff_v4i8_expand(<4 x i8> %a1, <4 x i8> %a2) {
-; CHECK-LABEL: test_uabsdiff_v4i8_expand
-; CHECK: pshufd
-; CHECK: movd
-; CHECK: subl
-; CHECK: punpckldq
-; CHECK-DAG: movd %xmm1, [[SRC:%.*]]
-; CHECK-DAG: movd %xmm0, [[DST:%.*]]
-; CHECK: subl [[SRC]], [[DST]]
-; CHECK: movd
-; CHECK: pshufd
-; CHECK: movd
-; CHECK: punpckldq
-; CHECK: movdqa
-; CHECK: retq
-
- %1 = call <4 x i8> @llvm.uabsdiff.v4i8(<4 x i8> %a1, <4 x i8> %a2)
- ret <4 x i8> %1
-}
-
-declare <4 x i8> @llvm.sabsdiff.v4i8(<4 x i8>, <4 x i8>)
-
-define <4 x i8> @test_sabsdiff_v4i8_expand(<4 x i8> %a1, <4 x i8> %a2) {
-; CHECK-LABEL: test_sabsdiff_v4i8_expand
-; CHECK: psubd
-; CHECK: pcmpgtd
-; CHECK: pcmpeqd
-; CHECK: pxor
-; CHECK-DAG: psubd {{%xmm[0-9]+}}, [[SRC1:%xmm[0-9]+]]
-; CHECK-DAG: pandn {{%xmm[0-9]+}}, [[SRC2:%xmm[0-9]+]]
-; CHECK-DAG: pandn [[SRC1]], [[DST:%xmm[0-9]+]]
-; CHECK: por [[SRC2]], [[DST]]
-; CHECK: retq
-
- %1 = call <4 x i8> @llvm.sabsdiff.v4i8(<4 x i8> %a1, <4 x i8> %a2)
- ret <4 x i8> %1
-}
-
-declare <8 x i8> @llvm.sabsdiff.v8i8(<8 x i8>, <8 x i8>)
-
-define <8 x i8> @test_sabsdiff_v8i8_expand(<8 x i8> %a1, <8 x i8> %a2) {
-; CHECK-LABEL: test_sabsdiff_v8i8_expand
-; CHECK: psubw
-; CHECK: pcmpgtw
-; CHECK: pcmpeqd
-; CHECK: pxor
-; CHECK-DAG: psubw {{%xmm[0-9]+}}, [[SRC1:%xmm[0-9]+]]
-; CHECK-DAG: pandn {{%xmm[0-9]+}}, [[SRC2:%xmm[0-9]+]]
-; CHECK-DAG: pandn [[SRC1]], [[DST:%xmm[0-9]+]]
-; CHECK: por [[SRC2]], [[DST]]
-; CHECK: retq
-
- %1 = call <8 x i8> @llvm.sabsdiff.v8i8(<8 x i8> %a1, <8 x i8> %a2)
- ret <8 x i8> %1
-}
-
-declare <16 x i8> @llvm.uabsdiff.v16i8(<16 x i8>, <16 x i8>)
-
-define <16 x i8> @test_uabsdiff_v16i8_expand(<16 x i8> %a1, <16 x i8> %a2) {
-; CHECK-LABEL: test_uabsdiff_v16i8_expand
-; CHECK: movd
-; CHECK: movzbl
-; CHECK: movzbl
-; CHECK: subl
-; CHECK: punpcklbw
-; CHECK: retq
-
- %1 = call <16 x i8> @llvm.uabsdiff.v16i8(<16 x i8> %a1, <16 x i8> %a2)
- ret <16 x i8> %1
-}
-
-declare <8 x i16> @llvm.uabsdiff.v8i16(<8 x i16>, <8 x i16>)
-
-define <8 x i16> @test_uabsdiff_v8i16_expand(<8 x i16> %a1, <8 x i16> %a2) {
-; CHECK-LABEL: test_uabsdiff_v8i16_expand
-; CHECK: pextrw
-; CHECK: pextrw
-; CHECK: subl
-; CHECK: punpcklwd
-; CHECK: retq
-
- %1 = call <8 x i16> @llvm.uabsdiff.v8i16(<8 x i16> %a1, <8 x i16> %a2)
- ret <8 x i16> %1
-}
-
-declare <8 x i16> @llvm.sabsdiff.v8i16(<8 x i16>, <8 x i16>)
-
-define <8 x i16> @test_sabsdiff_v8i16_expand(<8 x i16> %a1, <8 x i16> %a2) {
-; CHECK-LABEL: test_sabsdiff_v8i16_expand
-; CHECK: psubw
-; CHECK: pcmpgtw
-; CHECK: pcmpeqd
-; CHECK: pxor
-; CHECK-DAG: psubw {{%xmm[0-9]+}}, [[SRC1:%xmm[0-9]+]]
-; CHECK-DAG: pandn {{%xmm[0-9]+}}, [[SRC2:%xmm[0-9]+]]
-; CHECK-DAG: pandn [[SRC1]], [[DST:%xmm[0-9]+]]
-; CHECK: por [[SRC2]], [[DST]]
-; CHECK: retq
-
- %1 = call <8 x i16> @llvm.sabsdiff.v8i16(<8 x i16> %a1, <8 x i16> %a2)
- ret <8 x i16> %1
-}
-
-declare <4 x i32> @llvm.sabsdiff.v4i32(<4 x i32>, <4 x i32>)
-
-define <4 x i32> @test_sabsdiff_v4i32_expand(<4 x i32> %a1, <4 x i32> %a2) {
-; CHECK-LABEL: test_sabsdiff_v4i32_expand
-; CHECK: psubd
-; CHECK: pcmpgtd
-; CHECK: pcmpeqd
-; CHECK: pxor
-; CHECK-DAG: psubd {{%xmm[0-9]+}}, [[SRC1:%xmm[0-9]+]]
-; CHECK-DAG: pandn {{%xmm[0-9]+}}, [[SRC2:%xmm[0-9]+]]
-; CHECK-DAG: pandn [[SRC1]], [[DST:%xmm[0-9]+]]
-; CHECK: por [[SRC2]], [[DST]]
-; CHECK: retq
- %1 = call <4 x i32> @llvm.sabsdiff.v4i32(<4 x i32> %a1, <4 x i32> %a2)
- ret <4 x i32> %1
-}
-
-declare <4 x i32> @llvm.uabsdiff.v4i32(<4 x i32>, <4 x i32>)
-
-define <4 x i32> @test_uabsdiff_v4i32_expand(<4 x i32> %a1, <4 x i32> %a2) {
-; CHECK-LABEL: test_uabsdiff_v4i32_expand
-; CHECK: pshufd
-; CHECK: movd
-; CHECK: subl
-; CHECK: punpckldq
-; CHECK-DAG: movd %xmm1, [[SRC:%.*]]
-; CHECK-DAG: movd %xmm0, [[DST:%.*]]
-; CHECK: subl [[SRC]], [[DST]]
-; CHECK: movd
-; CHECK: pshufd
-; CHECK: movd
-; CHECK: punpckldq
-; CHECK: movdqa
-; CHECK: retq
-
- %1 = call <4 x i32> @llvm.uabsdiff.v4i32(<4 x i32> %a1, <4 x i32> %a2)
- ret <4 x i32> %1
-}
-
-declare <2 x i32> @llvm.sabsdiff.v2i32(<2 x i32>, <2 x i32>)
-
-define <2 x i32> @test_sabsdiff_v2i32_expand(<2 x i32> %a1, <2 x i32> %a2) {
-; CHECK-LABEL: test_sabsdiff_v2i32_expand
-; CHECK: psubq
-; CHECK: pcmpgtd
-; CHECK: pcmpeqd
-; CHECK: pxor
-; CHECK-DAG: psubq {{%xmm[0-9]+}}, [[SRC1:%xmm[0-9]+]]
-; CHECK-DAG: pandn {{%xmm[0-9]+}}, [[SRC2:%xmm[0-9]+]]
-; CHECK-DAG: pandn [[SRC1]], [[DST:%xmm[0-9]+]]
-; CHECK: por [[SRC2]], [[DST]]
-; CHECK: retq
-
- %1 = call <2 x i32> @llvm.sabsdiff.v2i32(<2 x i32> %a1, <2 x i32> %a2)
- ret <2 x i32> %1
-}
-
-declare <2 x i64> @llvm.sabsdiff.v2i64(<2 x i64>, <2 x i64>)
-
-define <2 x i64> @test_sabsdiff_v2i64_expand(<2 x i64> %a1, <2 x i64> %a2) {
-; CHECK-LABEL: test_sabsdiff_v2i64_expand
-; CHECK: psubq
-; CHECK: pcmpgtd
-; CHECK: pcmpeqd
-; CHECK: pxor
-; CHECK-DAG: psubq {{%xmm[0-9]+}}, [[SRC1:%xmm[0-9]+]]
-; CHECK-DAG: pandn {{%xmm[0-9]+}}, [[SRC2:%xmm[0-9]+]]
-; CHECK-DAG: pandn [[SRC1]], [[DST:%xmm[0-9]+]]
-; CHECK: por [[SRC2]], [[DST]]
-; CHECK: retq
-
- %1 = call <2 x i64> @llvm.sabsdiff.v2i64(<2 x i64> %a1, <2 x i64> %a2)
- ret <2 x i64> %1
-}
Removed: llvm/trunk/test/CodeGen/X86/absdiff_256.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/absdiff_256.ll?rev=255386&view=auto
==============================================================================
--- llvm/trunk/test/CodeGen/X86/absdiff_256.ll (original)
+++ llvm/trunk/test/CodeGen/X86/absdiff_256.ll (removed)
@@ -1,29 +0,0 @@
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown | FileCheck %s
-
-declare <16 x i16> @llvm.sabsdiff.v16i16(<16 x i16>, <16 x i16>)
-
-define <16 x i16> @test_sabsdiff_v16i16_expand(<16 x i16> %a1, <16 x i16> %a2) {
-; CHECK-LABEL: test_sabsdiff_v16i16_expand:
-; CHECK: # BB#0:
-; CHECK: psubw
-; CHECK: pxor
-; CHECK: pcmpgtw
-; CHECK: movdqa
-; CHECK: pandn
-; CHECK: pxor
-; CHECK: psubw
-; CHECK: pcmpeqd
-; CHECK: pxor
-; CHECK: pandn
-; CHECK: por
-; CHECK: pcmpgtw
-; CHECK-DAG: psubw {{%xmm[0-9]+}}, [[SRC:%xmm[0-9]+]]
-; CHECK-DAG: pxor {{%xmm[0-9]+}}, [[DST:%xmm[0-9]+]]
-; CHECK: pandn [[SRC]], [[DST]]
-; CHECK: por
-; CHECK: movdqa
-; CHECK: retq
- %1 = call <16 x i16> @llvm.sabsdiff.v16i16(<16 x i16> %a1, <16 x i16> %a2)
- ret <16 x i16> %1
-}
-
More information about the llvm-commits
mailing list