maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[X86][AVX] combineExtractSubvector - 'little to big' extract_subvector(bitcast()) support 

Ideally this needs to be a generic combine in DAGCombiner::visitEXTRACT_SUBVECTOR but there's some nasty regressions in aarch64 due to neon shuffles not handling bitcasts at all.....

llvm-svn: 364407
This commit is contained in:
Simon Pilgrim 2019-06-26 11:21:09 +00:00
parent e821e79fce
commit c0711af7f9
9 changed files with 109 additions and 91 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
llvm/lib/Target/X86/X86ISelLowering.cpp
View File

@ -43630,6 +43630,34 @@ static SDValue combineExtractSubvector(SDNode *N, SelectionDAG &DAG,
VT, SDLoc(N), VT, SDLoc(N),
InVec.getNode()->ops().slice(IdxVal, VT.getVectorNumElements())); InVec.getNode()->ops().slice(IdxVal, VT.getVectorNumElements()));
// Try to move vector bitcast after extract_subv by scaling extraction index:
// extract_subv (bitcast X), Index --> bitcast (extract_subv X, Index')
// TODO: Move this to DAGCombiner::visitEXTRACT_SUBVECTOR
if (InVec.getOpcode() == ISD::BITCAST &&
InVec.getOperand(0).getValueType().isVector()) {
SDValue SrcOp = InVec.getOperand(0);
EVT SrcVT = SrcOp.getValueType();
unsigned SrcNumElts = SrcVT.getVectorNumElements();
unsigned DestNumElts = InVec.getValueType().getVectorNumElements();
if ((DestNumElts % SrcNumElts) == 0) {
unsigned DestSrcRatio = DestNumElts / SrcNumElts;
if ((VT.getVectorNumElements() % DestSrcRatio) == 0) {
unsigned NewExtNumElts = VT.getVectorNumElements() / DestSrcRatio;
EVT NewExtVT = EVT::getVectorVT(*DAG.getContext(),
SrcVT.getScalarType(), NewExtNumElts);
if ((N->getConstantOperandVal(1) % DestSrcRatio) == 0 &&
TLI.isOperationLegalOrCustom(ISD::EXTRACT_SUBVECTOR, NewExtVT)) {
unsigned IndexValScaled = N->getConstantOperandVal(1) / DestSrcRatio;
SDLoc DL(N);
SDValue NewIndex = DAG.getIntPtrConstant(IndexValScaled, DL);
SDValue NewExtract = DAG.getNode(ISD::EXTRACT_SUBVECTOR, DL, NewExtVT,
SrcOp, NewIndex);
return DAG.getBitcast(VT, NewExtract);
}
}
}
}
// If we're extracting from a broadcast then we're better off just // If we're extracting from a broadcast then we're better off just
// broadcasting to the smaller type directly, assuming this is the only use. // broadcasting to the smaller type directly, assuming this is the only use.
// As its a broadcast we don't care about the extraction index. // As its a broadcast we don't care about the extraction index.

4
llvm/test/CodeGen/X86/avg.ll
View File

@ -382,7 +382,7 @@ define void @avg_v48i8(<48 x i8>* %a, <48 x i8>* %b) nounwind {
; AVX2-NEXT: vpshufd {{.*#+}} xmm2 = xmm0[2,3,0,1] ; AVX2-NEXT: vpshufd {{.*#+}} xmm2 = xmm0[2,3,0,1]
; AVX2-NEXT: vpmovzxbd {{.*#+}} ymm2 = xmm2[0],zero,zero,zero,xmm2[1],zero,zero,zero,xmm2[2],zero,zero,zero,xmm2[3],zero,zero,zero,xmm2[4],zero,zero,zero,xmm2[5],zero,zero,zero,xmm2[6],zero,zero,zero,xmm2[7],zero,zero,zero ; AVX2-NEXT: vpmovzxbd {{.*#+}} ymm2 = xmm2[0],zero,zero,zero,xmm2[1],zero,zero,zero,xmm2[2],zero,zero,zero,xmm2[3],zero,zero,zero,xmm2[4],zero,zero,zero,xmm2[5],zero,zero,zero,xmm2[6],zero,zero,zero,xmm2[7],zero,zero,zero
; AVX2-NEXT: vpmovzxbd {{.*#+}} ymm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero,xmm0[4],zero,zero,zero,xmm0[5],zero,zero,zero,xmm0[6],zero,zero,zero,xmm0[7],zero,zero,zero ; AVX2-NEXT: vpmovzxbd {{.*#+}} ymm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero,xmm0[4],zero,zero,zero,xmm0[5],zero,zero,zero,xmm0[6],zero,zero,zero,xmm0[7],zero,zero,zero
; AVX2-NEXT: vpbroadcastq 24(%rdi), %ymm3 ; AVX2-NEXT: vpbroadcastq 24(%rdi), %xmm3
; AVX2-NEXT: vpmovzxbd {{.*#+}} ymm3 = xmm3[0],zero,zero,zero,xmm3[1],zero,zero,zero,xmm3[2],zero,zero,zero,xmm3[3],zero,zero,zero,xmm3[4],zero,zero,zero,xmm3[5],zero,zero,zero,xmm3[6],zero,zero,zero,xmm3[7],zero,zero,zero ; AVX2-NEXT: vpmovzxbd {{.*#+}} ymm3 = xmm3[0],zero,zero,zero,xmm3[1],zero,zero,zero,xmm3[2],zero,zero,zero,xmm3[3],zero,zero,zero,xmm3[4],zero,zero,zero,xmm3[5],zero,zero,zero,xmm3[6],zero,zero,zero,xmm3[7],zero,zero,zero
; AVX2-NEXT: vpmovzxbd {{.*#+}} ymm4 = mem[0],zero,zero,zero,mem[1],zero,zero,zero,mem[2],zero,zero,zero,mem[3],zero,zero,zero,mem[4],zero,zero,zero,mem[5],zero,zero,zero,mem[6],zero,zero,zero,mem[7],zero,zero,zero ; AVX2-NEXT: vpmovzxbd {{.*#+}} ymm4 = mem[0],zero,zero,zero,mem[1],zero,zero,zero,mem[2],zero,zero,zero,mem[3],zero,zero,zero,mem[4],zero,zero,zero,mem[5],zero,zero,zero,mem[6],zero,zero,zero,mem[7],zero,zero,zero
; AVX2-NEXT: vpshufd {{.*#+}} xmm5 = xmm1[2,3,0,1] ; AVX2-NEXT: vpshufd {{.*#+}} xmm5 = xmm1[2,3,0,1]
@ -395,7 +395,7 @@ define void @avg_v48i8(<48 x i8>* %a, <48 x i8>* %b) nounwind {
; AVX2-NEXT: vpaddd %ymm1, %ymm2, %ymm1 ; AVX2-NEXT: vpaddd %ymm1, %ymm2, %ymm1
; AVX2-NEXT: vpmovzxbd {{.*#+}} ymm2 = xmm6[0],zero,zero,zero,xmm6[1],zero,zero,zero,xmm6[2],zero,zero,zero,xmm6[3],zero,zero,zero,xmm6[4],zero,zero,zero,xmm6[5],zero,zero,zero,xmm6[6],zero,zero,zero,xmm6[7],zero,zero,zero ; AVX2-NEXT: vpmovzxbd {{.*#+}} ymm2 = xmm6[0],zero,zero,zero,xmm6[1],zero,zero,zero,xmm6[2],zero,zero,zero,xmm6[3],zero,zero,zero,xmm6[4],zero,zero,zero,xmm6[5],zero,zero,zero,xmm6[6],zero,zero,zero,xmm6[7],zero,zero,zero
; AVX2-NEXT: vpaddd %ymm2, %ymm0, %ymm0 ; AVX2-NEXT: vpaddd %ymm2, %ymm0, %ymm0
; AVX2-NEXT: vpbroadcastq 24(%rsi), %ymm2 ; AVX2-NEXT: vpbroadcastq 24(%rsi), %xmm2
; AVX2-NEXT: vpmovzxbd {{.*#+}} ymm2 = xmm2[0],zero,zero,zero,xmm2[1],zero,zero,zero,xmm2[2],zero,zero,zero,xmm2[3],zero,zero,zero,xmm2[4],zero,zero,zero,xmm2[5],zero,zero,zero,xmm2[6],zero,zero,zero,xmm2[7],zero,zero,zero ; AVX2-NEXT: vpmovzxbd {{.*#+}} ymm2 = xmm2[0],zero,zero,zero,xmm2[1],zero,zero,zero,xmm2[2],zero,zero,zero,xmm2[3],zero,zero,zero,xmm2[4],zero,zero,zero,xmm2[5],zero,zero,zero,xmm2[6],zero,zero,zero,xmm2[7],zero,zero,zero
; AVX2-NEXT: vpaddd %ymm2, %ymm3, %ymm2 ; AVX2-NEXT: vpaddd %ymm2, %ymm3, %ymm2
; AVX2-NEXT: vpmovzxbd {{.*#+}} ymm3 = mem[0],zero,zero,zero,mem[1],zero,zero,zero,mem[2],zero,zero,zero,mem[3],zero,zero,zero,mem[4],zero,zero,zero,mem[5],zero,zero,zero,mem[6],zero,zero,zero,mem[7],zero,zero,zero ; AVX2-NEXT: vpmovzxbd {{.*#+}} ymm3 = mem[0],zero,zero,zero,mem[1],zero,zero,zero,mem[2],zero,zero,zero,mem[3],zero,zero,zero,mem[4],zero,zero,zero,mem[5],zero,zero,zero,mem[6],zero,zero,zero,mem[7],zero,zero,zero

4
llvm/test/CodeGen/X86/horizontal-reduce-smax.ll
View File

@ -472,7 +472,7 @@ define i64 @test_reduce_v4i64(<4 x i64> %a0) {
; X86-AVX2-NEXT: vblendvpd %ymm2, %ymm0, %ymm1, %ymm0 ; X86-AVX2-NEXT: vblendvpd %ymm2, %ymm0, %ymm1, %ymm0
; X86-AVX2-NEXT: vpermilps {{.*#+}} xmm1 = xmm0[2,3,0,1] ; X86-AVX2-NEXT: vpermilps {{.*#+}} xmm1 = xmm0[2,3,0,1]
; X86-AVX2-NEXT: vpcmpgtq %ymm1, %ymm0, %ymm2 ; X86-AVX2-NEXT: vpcmpgtq %ymm1, %ymm0, %ymm2
; X86-AVX2-NEXT: vblendvpd %ymm2, %ymm0, %ymm1, %ymm0 ; X86-AVX2-NEXT: vblendvpd %xmm2, %xmm0, %xmm1, %xmm0
; X86-AVX2-NEXT: vmovd %xmm0, %eax ; X86-AVX2-NEXT: vmovd %xmm0, %eax
; X86-AVX2-NEXT: vpextrd $1, %xmm0, %edx ; X86-AVX2-NEXT: vpextrd $1, %xmm0, %edx
; X86-AVX2-NEXT: vzeroupper ; X86-AVX2-NEXT: vzeroupper
@ -1139,7 +1139,7 @@ define i64 @test_reduce_v8i64(<8 x i64> %a0) {
; X86-AVX2-NEXT: vblendvpd %ymm2, %ymm0, %ymm1, %ymm0 ; X86-AVX2-NEXT: vblendvpd %ymm2, %ymm0, %ymm1, %ymm0
; X86-AVX2-NEXT: vpermilps {{.*#+}} xmm1 = xmm0[2,3,0,1] ; X86-AVX2-NEXT: vpermilps {{.*#+}} xmm1 = xmm0[2,3,0,1]
; X86-AVX2-NEXT: vpcmpgtq %ymm1, %ymm0, %ymm2 ; X86-AVX2-NEXT: vpcmpgtq %ymm1, %ymm0, %ymm2
; X86-AVX2-NEXT: vblendvpd %ymm2, %ymm0, %ymm1, %ymm0 ; X86-AVX2-NEXT: vblendvpd %xmm2, %xmm0, %xmm1, %xmm0
; X86-AVX2-NEXT: vmovd %xmm0, %eax ; X86-AVX2-NEXT: vmovd %xmm0, %eax
; X86-AVX2-NEXT: vpextrd $1, %xmm0, %edx ; X86-AVX2-NEXT: vpextrd $1, %xmm0, %edx
; X86-AVX2-NEXT: vzeroupper ; X86-AVX2-NEXT: vzeroupper

4
llvm/test/CodeGen/X86/horizontal-reduce-smin.ll
View File

@ -475,7 +475,7 @@ define i64 @test_reduce_v4i64(<4 x i64> %a0) {
; X86-AVX2-NEXT: vblendvpd %ymm2, %ymm0, %ymm1, %ymm0 ; X86-AVX2-NEXT: vblendvpd %ymm2, %ymm0, %ymm1, %ymm0
; X86-AVX2-NEXT: vpermilps {{.*#+}} xmm1 = xmm0[2,3,0,1] ; X86-AVX2-NEXT: vpermilps {{.*#+}} xmm1 = xmm0[2,3,0,1]
; X86-AVX2-NEXT: vpcmpgtq %ymm0, %ymm1, %ymm2 ; X86-AVX2-NEXT: vpcmpgtq %ymm0, %ymm1, %ymm2
; X86-AVX2-NEXT: vblendvpd %ymm2, %ymm0, %ymm1, %ymm0 ; X86-AVX2-NEXT: vblendvpd %xmm2, %xmm0, %xmm1, %xmm0
; X86-AVX2-NEXT: vmovd %xmm0, %eax ; X86-AVX2-NEXT: vmovd %xmm0, %eax
; X86-AVX2-NEXT: vpextrd $1, %xmm0, %edx ; X86-AVX2-NEXT: vpextrd $1, %xmm0, %edx
; X86-AVX2-NEXT: vzeroupper ; X86-AVX2-NEXT: vzeroupper
@ -1143,7 +1143,7 @@ define i64 @test_reduce_v8i64(<8 x i64> %a0) {
; X86-AVX2-NEXT: vblendvpd %ymm2, %ymm0, %ymm1, %ymm0 ; X86-AVX2-NEXT: vblendvpd %ymm2, %ymm0, %ymm1, %ymm0
; X86-AVX2-NEXT: vpermilps {{.*#+}} xmm1 = xmm0[2,3,0,1] ; X86-AVX2-NEXT: vpermilps {{.*#+}} xmm1 = xmm0[2,3,0,1]
; X86-AVX2-NEXT: vpcmpgtq %ymm0, %ymm1, %ymm2 ; X86-AVX2-NEXT: vpcmpgtq %ymm0, %ymm1, %ymm2
; X86-AVX2-NEXT: vblendvpd %ymm2, %ymm0, %ymm1, %ymm0 ; X86-AVX2-NEXT: vblendvpd %xmm2, %xmm0, %xmm1, %xmm0
; X86-AVX2-NEXT: vmovd %xmm0, %eax ; X86-AVX2-NEXT: vmovd %xmm0, %eax
; X86-AVX2-NEXT: vpextrd $1, %xmm0, %edx ; X86-AVX2-NEXT: vpextrd $1, %xmm0, %edx
; X86-AVX2-NEXT: vzeroupper ; X86-AVX2-NEXT: vzeroupper

4
llvm/test/CodeGen/X86/horizontal-reduce-umax.ll
View File

@ -565,7 +565,7 @@ define i64 @test_reduce_v4i64(<4 x i64> %a0) {
; X86-AVX2-NEXT: vxorpd %ymm2, %ymm0, %ymm3 ; X86-AVX2-NEXT: vxorpd %ymm2, %ymm0, %ymm3
; X86-AVX2-NEXT: vxorpd %ymm2, %ymm1, %ymm2 ; X86-AVX2-NEXT: vxorpd %ymm2, %ymm1, %ymm2
; X86-AVX2-NEXT: vpcmpgtq %ymm2, %ymm3, %ymm2 ; X86-AVX2-NEXT: vpcmpgtq %ymm2, %ymm3, %ymm2
; X86-AVX2-NEXT: vblendvpd %ymm2, %ymm0, %ymm1, %ymm0 ; X86-AVX2-NEXT: vblendvpd %xmm2, %xmm0, %xmm1, %xmm0
; X86-AVX2-NEXT: vmovd %xmm0, %eax ; X86-AVX2-NEXT: vmovd %xmm0, %eax
; X86-AVX2-NEXT: vpextrd $1, %xmm0, %edx ; X86-AVX2-NEXT: vpextrd $1, %xmm0, %edx
; X86-AVX2-NEXT: vzeroupper ; X86-AVX2-NEXT: vzeroupper
@ -1290,7 +1290,7 @@ define i64 @test_reduce_v8i64(<8 x i64> %a0) {
; X86-AVX2-NEXT: vxorpd %ymm2, %ymm0, %ymm3 ; X86-AVX2-NEXT: vxorpd %ymm2, %ymm0, %ymm3
; X86-AVX2-NEXT: vxorpd %ymm2, %ymm1, %ymm2 ; X86-AVX2-NEXT: vxorpd %ymm2, %ymm1, %ymm2
; X86-AVX2-NEXT: vpcmpgtq %ymm2, %ymm3, %ymm2 ; X86-AVX2-NEXT: vpcmpgtq %ymm2, %ymm3, %ymm2
; X86-AVX2-NEXT: vblendvpd %ymm2, %ymm0, %ymm1, %ymm0 ; X86-AVX2-NEXT: vblendvpd %xmm2, %xmm0, %xmm1, %xmm0
; X86-AVX2-NEXT: vmovd %xmm0, %eax ; X86-AVX2-NEXT: vmovd %xmm0, %eax
; X86-AVX2-NEXT: vpextrd $1, %xmm0, %edx ; X86-AVX2-NEXT: vpextrd $1, %xmm0, %edx
; X86-AVX2-NEXT: vzeroupper ; X86-AVX2-NEXT: vzeroupper

4
llvm/test/CodeGen/X86/horizontal-reduce-umin.ll
View File

@ -503,7 +503,7 @@ define i64 @test_reduce_v4i64(<4 x i64> %a0) {
; X86-AVX2-NEXT: vxorpd %ymm2, %ymm0, %ymm3 ; X86-AVX2-NEXT: vxorpd %ymm2, %ymm0, %ymm3
; X86-AVX2-NEXT: vxorpd %ymm2, %ymm1, %ymm2 ; X86-AVX2-NEXT: vxorpd %ymm2, %ymm1, %ymm2
; X86-AVX2-NEXT: vpcmpgtq %ymm3, %ymm2, %ymm2 ; X86-AVX2-NEXT: vpcmpgtq %ymm3, %ymm2, %ymm2
; X86-AVX2-NEXT: vblendvpd %ymm2, %ymm0, %ymm1, %ymm0 ; X86-AVX2-NEXT: vblendvpd %xmm2, %xmm0, %xmm1, %xmm0
; X86-AVX2-NEXT: vmovd %xmm0, %eax ; X86-AVX2-NEXT: vmovd %xmm0, %eax
; X86-AVX2-NEXT: vpextrd $1, %xmm0, %edx ; X86-AVX2-NEXT: vpextrd $1, %xmm0, %edx
; X86-AVX2-NEXT: vzeroupper ; X86-AVX2-NEXT: vzeroupper
@ -1192,7 +1192,7 @@ define i64 @test_reduce_v8i64(<8 x i64> %a0) {
; X86-AVX2-NEXT: vxorpd %ymm2, %ymm0, %ymm3 ; X86-AVX2-NEXT: vxorpd %ymm2, %ymm0, %ymm3
; X86-AVX2-NEXT: vxorpd %ymm2, %ymm1, %ymm2 ; X86-AVX2-NEXT: vxorpd %ymm2, %ymm1, %ymm2
; X86-AVX2-NEXT: vpcmpgtq %ymm3, %ymm2, %ymm2 ; X86-AVX2-NEXT: vpcmpgtq %ymm3, %ymm2, %ymm2
; X86-AVX2-NEXT: vblendvpd %ymm2, %ymm0, %ymm1, %ymm0 ; X86-AVX2-NEXT: vblendvpd %xmm2, %xmm0, %xmm1, %xmm0
; X86-AVX2-NEXT: vmovd %xmm0, %eax ; X86-AVX2-NEXT: vmovd %xmm0, %eax
; X86-AVX2-NEXT: vpextrd $1, %xmm0, %edx ; X86-AVX2-NEXT: vpextrd $1, %xmm0, %edx
; X86-AVX2-NEXT: vzeroupper ; X86-AVX2-NEXT: vzeroupper

64
llvm/test/CodeGen/X86/vector-reduce-mul-widen.ll
View File

@ -144,14 +144,14 @@ define i64 @test_v4i64(<4 x i64> %a0) {
; AVX2-LABEL: test_v4i64: ; AVX2-LABEL: test_v4i64:
; AVX2: # %bb.0: ; AVX2: # %bb.0:
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1 ; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vpsrlq $32, %ymm0, %ymm2 ; AVX2-NEXT: vpsrlq $32, %xmm0, %xmm2
; AVX2-NEXT: vpmuludq %ymm1, %ymm2, %ymm2 ; AVX2-NEXT: vpmuludq %xmm1, %xmm2, %xmm2
; AVX2-NEXT: vpsrlq $32, %ymm1, %ymm3 ; AVX2-NEXT: vpsrlq $32, %xmm1, %xmm3
; AVX2-NEXT: vpmuludq %ymm3, %ymm0, %ymm3 ; AVX2-NEXT: vpmuludq %xmm3, %xmm0, %xmm3
; AVX2-NEXT: vpaddq %ymm2, %ymm3, %ymm2 ; AVX2-NEXT: vpaddq %xmm2, %xmm3, %xmm2
; AVX2-NEXT: vpsllq $32, %ymm2, %ymm2 ; AVX2-NEXT: vpsllq $32, %xmm2, %xmm2
; AVX2-NEXT: vpmuludq %ymm1, %ymm0, %ymm0 ; AVX2-NEXT: vpmuludq %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vpaddq %ymm2, %ymm0, %ymm0 ; AVX2-NEXT: vpaddq %xmm2, %xmm0, %xmm0
; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1] ; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
; AVX2-NEXT: vpsrlq $32, %xmm0, %xmm2 ; AVX2-NEXT: vpsrlq $32, %xmm0, %xmm2
; AVX2-NEXT: vpmuludq %xmm1, %xmm2, %xmm2 ; AVX2-NEXT: vpmuludq %xmm1, %xmm2, %xmm2
@ -168,14 +168,14 @@ define i64 @test_v4i64(<4 x i64> %a0) {
; AVX512BW-LABEL: test_v4i64: ; AVX512BW-LABEL: test_v4i64:
; AVX512BW: # %bb.0: ; AVX512BW: # %bb.0:
; AVX512BW-NEXT: vextracti128 $1, %ymm0, %xmm1 ; AVX512BW-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512BW-NEXT: vpsrlq $32, %ymm0, %ymm2 ; AVX512BW-NEXT: vpsrlq $32, %xmm0, %xmm2
; AVX512BW-NEXT: vpmuludq %ymm1, %ymm2, %ymm2 ; AVX512BW-NEXT: vpmuludq %xmm1, %xmm2, %xmm2
; AVX512BW-NEXT: vpsrlq $32, %ymm1, %ymm3 ; AVX512BW-NEXT: vpsrlq $32, %xmm1, %xmm3
; AVX512BW-NEXT: vpmuludq %ymm3, %ymm0, %ymm3 ; AVX512BW-NEXT: vpmuludq %xmm3, %xmm0, %xmm3
; AVX512BW-NEXT: vpaddq %ymm2, %ymm3, %ymm2 ; AVX512BW-NEXT: vpaddq %xmm2, %xmm3, %xmm2
; AVX512BW-NEXT: vpsllq $32, %ymm2, %ymm2 ; AVX512BW-NEXT: vpsllq $32, %xmm2, %xmm2
; AVX512BW-NEXT: vpmuludq %ymm1, %ymm0, %ymm0 ; AVX512BW-NEXT: vpmuludq %xmm1, %xmm0, %xmm0
; AVX512BW-NEXT: vpaddq %ymm2, %ymm0, %ymm0 ; AVX512BW-NEXT: vpaddq %xmm2, %xmm0, %xmm0
; AVX512BW-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1] ; AVX512BW-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
; AVX512BW-NEXT: vpsrlq $32, %xmm0, %xmm2 ; AVX512BW-NEXT: vpsrlq $32, %xmm0, %xmm2
; AVX512BW-NEXT: vpmuludq %xmm1, %xmm2, %xmm2 ; AVX512BW-NEXT: vpmuludq %xmm1, %xmm2, %xmm2
@ -336,14 +336,14 @@ define i64 @test_v8i64(<8 x i64> %a0) {
; AVX2-NEXT: vpmuludq %ymm1, %ymm0, %ymm0 ; AVX2-NEXT: vpmuludq %ymm1, %ymm0, %ymm0
; AVX2-NEXT: vpaddq %ymm2, %ymm0, %ymm0 ; AVX2-NEXT: vpaddq %ymm2, %ymm0, %ymm0
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1 ; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vpsrlq $32, %ymm0, %ymm2 ; AVX2-NEXT: vpsrlq $32, %xmm0, %xmm2
; AVX2-NEXT: vpmuludq %ymm1, %ymm2, %ymm2 ; AVX2-NEXT: vpmuludq %xmm1, %xmm2, %xmm2
; AVX2-NEXT: vpsrlq $32, %ymm1, %ymm3 ; AVX2-NEXT: vpsrlq $32, %xmm1, %xmm3
; AVX2-NEXT: vpmuludq %ymm3, %ymm0, %ymm3 ; AVX2-NEXT: vpmuludq %xmm3, %xmm0, %xmm3
; AVX2-NEXT: vpaddq %ymm2, %ymm3, %ymm2 ; AVX2-NEXT: vpaddq %xmm2, %xmm3, %xmm2
; AVX2-NEXT: vpsllq $32, %ymm2, %ymm2 ; AVX2-NEXT: vpsllq $32, %xmm2, %xmm2
; AVX2-NEXT: vpmuludq %ymm1, %ymm0, %ymm0 ; AVX2-NEXT: vpmuludq %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vpaddq %ymm2, %ymm0, %ymm0 ; AVX2-NEXT: vpaddq %xmm2, %xmm0, %xmm0
; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1] ; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
; AVX2-NEXT: vpsrlq $32, %xmm0, %xmm2 ; AVX2-NEXT: vpsrlq $32, %xmm0, %xmm2
; AVX2-NEXT: vpmuludq %xmm1, %xmm2, %xmm2 ; AVX2-NEXT: vpmuludq %xmm1, %xmm2, %xmm2
@ -639,14 +639,14 @@ define i64 @test_v16i64(<16 x i64> %a0) {
; AVX2-NEXT: vpmuludq %ymm1, %ymm0, %ymm0 ; AVX2-NEXT: vpmuludq %ymm1, %ymm0, %ymm0
; AVX2-NEXT: vpaddq %ymm2, %ymm0, %ymm0 ; AVX2-NEXT: vpaddq %ymm2, %ymm0, %ymm0
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1 ; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vpsrlq $32, %ymm0, %ymm2 ; AVX2-NEXT: vpsrlq $32, %xmm0, %xmm2
; AVX2-NEXT: vpmuludq %ymm1, %ymm2, %ymm2 ; AVX2-NEXT: vpmuludq %xmm1, %xmm2, %xmm2
; AVX2-NEXT: vpsrlq $32, %ymm1, %ymm3 ; AVX2-NEXT: vpsrlq $32, %xmm1, %xmm3
; AVX2-NEXT: vpmuludq %ymm3, %ymm0, %ymm3 ; AVX2-NEXT: vpmuludq %xmm3, %xmm0, %xmm3
; AVX2-NEXT: vpaddq %ymm2, %ymm3, %ymm2 ; AVX2-NEXT: vpaddq %xmm2, %xmm3, %xmm2
; AVX2-NEXT: vpsllq $32, %ymm2, %ymm2 ; AVX2-NEXT: vpsllq $32, %xmm2, %xmm2
; AVX2-NEXT: vpmuludq %ymm1, %ymm0, %ymm0 ; AVX2-NEXT: vpmuludq %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vpaddq %ymm2, %ymm0, %ymm0 ; AVX2-NEXT: vpaddq %xmm2, %xmm0, %xmm0
; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1] ; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
; AVX2-NEXT: vpsrlq $32, %xmm0, %xmm2 ; AVX2-NEXT: vpsrlq $32, %xmm0, %xmm2
; AVX2-NEXT: vpmuludq %xmm1, %xmm2, %xmm2 ; AVX2-NEXT: vpmuludq %xmm1, %xmm2, %xmm2

64
llvm/test/CodeGen/X86/vector-reduce-mul.ll
View File

@ -144,14 +144,14 @@ define i64 @test_v4i64(<4 x i64> %a0) {
; AVX2-LABEL: test_v4i64: ; AVX2-LABEL: test_v4i64:
; AVX2: # %bb.0: ; AVX2: # %bb.0:
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1 ; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vpsrlq $32, %ymm0, %ymm2 ; AVX2-NEXT: vpsrlq $32, %xmm0, %xmm2
; AVX2-NEXT: vpmuludq %ymm1, %ymm2, %ymm2 ; AVX2-NEXT: vpmuludq %xmm1, %xmm2, %xmm2
; AVX2-NEXT: vpsrlq $32, %ymm1, %ymm3 ; AVX2-NEXT: vpsrlq $32, %xmm1, %xmm3
; AVX2-NEXT: vpmuludq %ymm3, %ymm0, %ymm3 ; AVX2-NEXT: vpmuludq %xmm3, %xmm0, %xmm3
; AVX2-NEXT: vpaddq %ymm2, %ymm3, %ymm2 ; AVX2-NEXT: vpaddq %xmm2, %xmm3, %xmm2
; AVX2-NEXT: vpsllq $32, %ymm2, %ymm2 ; AVX2-NEXT: vpsllq $32, %xmm2, %xmm2
; AVX2-NEXT: vpmuludq %ymm1, %ymm0, %ymm0 ; AVX2-NEXT: vpmuludq %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vpaddq %ymm2, %ymm0, %ymm0 ; AVX2-NEXT: vpaddq %xmm2, %xmm0, %xmm0
; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1] ; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
; AVX2-NEXT: vpsrlq $32, %xmm0, %xmm2 ; AVX2-NEXT: vpsrlq $32, %xmm0, %xmm2
; AVX2-NEXT: vpmuludq %xmm1, %xmm2, %xmm2 ; AVX2-NEXT: vpmuludq %xmm1, %xmm2, %xmm2
@ -168,14 +168,14 @@ define i64 @test_v4i64(<4 x i64> %a0) {
; AVX512BW-LABEL: test_v4i64: ; AVX512BW-LABEL: test_v4i64:
; AVX512BW: # %bb.0: ; AVX512BW: # %bb.0:
; AVX512BW-NEXT: vextracti128 $1, %ymm0, %xmm1 ; AVX512BW-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512BW-NEXT: vpsrlq $32, %ymm0, %ymm2 ; AVX512BW-NEXT: vpsrlq $32, %xmm0, %xmm2
; AVX512BW-NEXT: vpmuludq %ymm1, %ymm2, %ymm2 ; AVX512BW-NEXT: vpmuludq %xmm1, %xmm2, %xmm2
; AVX512BW-NEXT: vpsrlq $32, %ymm1, %ymm3 ; AVX512BW-NEXT: vpsrlq $32, %xmm1, %xmm3
; AVX512BW-NEXT: vpmuludq %ymm3, %ymm0, %ymm3 ; AVX512BW-NEXT: vpmuludq %xmm3, %xmm0, %xmm3
; AVX512BW-NEXT: vpaddq %ymm2, %ymm3, %ymm2 ; AVX512BW-NEXT: vpaddq %xmm2, %xmm3, %xmm2
; AVX512BW-NEXT: vpsllq $32, %ymm2, %ymm2 ; AVX512BW-NEXT: vpsllq $32, %xmm2, %xmm2
; AVX512BW-NEXT: vpmuludq %ymm1, %ymm0, %ymm0 ; AVX512BW-NEXT: vpmuludq %xmm1, %xmm0, %xmm0
; AVX512BW-NEXT: vpaddq %ymm2, %ymm0, %ymm0 ; AVX512BW-NEXT: vpaddq %xmm2, %xmm0, %xmm0
; AVX512BW-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1] ; AVX512BW-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
; AVX512BW-NEXT: vpsrlq $32, %xmm0, %xmm2 ; AVX512BW-NEXT: vpsrlq $32, %xmm0, %xmm2
; AVX512BW-NEXT: vpmuludq %xmm1, %xmm2, %xmm2 ; AVX512BW-NEXT: vpmuludq %xmm1, %xmm2, %xmm2
@ -336,14 +336,14 @@ define i64 @test_v8i64(<8 x i64> %a0) {
; AVX2-NEXT: vpmuludq %ymm1, %ymm0, %ymm0 ; AVX2-NEXT: vpmuludq %ymm1, %ymm0, %ymm0
; AVX2-NEXT: vpaddq %ymm2, %ymm0, %ymm0 ; AVX2-NEXT: vpaddq %ymm2, %ymm0, %ymm0
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1 ; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vpsrlq $32, %ymm0, %ymm2 ; AVX2-NEXT: vpsrlq $32, %xmm0, %xmm2
; AVX2-NEXT: vpmuludq %ymm1, %ymm2, %ymm2 ; AVX2-NEXT: vpmuludq %xmm1, %xmm2, %xmm2
; AVX2-NEXT: vpsrlq $32, %ymm1, %ymm3 ; AVX2-NEXT: vpsrlq $32, %xmm1, %xmm3
; AVX2-NEXT: vpmuludq %ymm3, %ymm0, %ymm3 ; AVX2-NEXT: vpmuludq %xmm3, %xmm0, %xmm3
; AVX2-NEXT: vpaddq %ymm2, %ymm3, %ymm2 ; AVX2-NEXT: vpaddq %xmm2, %xmm3, %xmm2
; AVX2-NEXT: vpsllq $32, %ymm2, %ymm2 ; AVX2-NEXT: vpsllq $32, %xmm2, %xmm2
; AVX2-NEXT: vpmuludq %ymm1, %ymm0, %ymm0 ; AVX2-NEXT: vpmuludq %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vpaddq %ymm2, %ymm0, %ymm0 ; AVX2-NEXT: vpaddq %xmm2, %xmm0, %xmm0
; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1] ; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
; AVX2-NEXT: vpsrlq $32, %xmm0, %xmm2 ; AVX2-NEXT: vpsrlq $32, %xmm0, %xmm2
; AVX2-NEXT: vpmuludq %xmm1, %xmm2, %xmm2 ; AVX2-NEXT: vpmuludq %xmm1, %xmm2, %xmm2
@ -639,14 +639,14 @@ define i64 @test_v16i64(<16 x i64> %a0) {
; AVX2-NEXT: vpmuludq %ymm1, %ymm0, %ymm0 ; AVX2-NEXT: vpmuludq %ymm1, %ymm0, %ymm0
; AVX2-NEXT: vpaddq %ymm2, %ymm0, %ymm0 ; AVX2-NEXT: vpaddq %ymm2, %ymm0, %ymm0
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1 ; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vpsrlq $32, %ymm0, %ymm2 ; AVX2-NEXT: vpsrlq $32, %xmm0, %xmm2
; AVX2-NEXT: vpmuludq %ymm1, %ymm2, %ymm2 ; AVX2-NEXT: vpmuludq %xmm1, %xmm2, %xmm2
; AVX2-NEXT: vpsrlq $32, %ymm1, %ymm3 ; AVX2-NEXT: vpsrlq $32, %xmm1, %xmm3
; AVX2-NEXT: vpmuludq %ymm3, %ymm0, %ymm3 ; AVX2-NEXT: vpmuludq %xmm3, %xmm0, %xmm3
; AVX2-NEXT: vpaddq %ymm2, %ymm3, %ymm2 ; AVX2-NEXT: vpaddq %xmm2, %xmm3, %xmm2
; AVX2-NEXT: vpsllq $32, %ymm2, %ymm2 ; AVX2-NEXT: vpsllq $32, %xmm2, %xmm2
; AVX2-NEXT: vpmuludq %ymm1, %ymm0, %ymm0 ; AVX2-NEXT: vpmuludq %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vpaddq %ymm2, %ymm0, %ymm0 ; AVX2-NEXT: vpaddq %xmm2, %xmm0, %xmm0
; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1] ; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
; AVX2-NEXT: vpsrlq $32, %xmm0, %xmm2 ; AVX2-NEXT: vpsrlq $32, %xmm0, %xmm2
; AVX2-NEXT: vpmuludq %xmm1, %xmm2, %xmm2 ; AVX2-NEXT: vpmuludq %xmm1, %xmm2, %xmm2

24
llvm/test/CodeGen/X86/vselect.ll
View File

@ -671,23 +671,13 @@ define i64 @vselect_any_extend_vector_inreg_crash(<8 x i8>* %x) {
; SSE41-NEXT: movq %xmm2, %rax ; SSE41-NEXT: movq %xmm2, %rax
; SSE41-NEXT: retq ; SSE41-NEXT: retq
; ;
; AVX1-LABEL: vselect_any_extend_vector_inreg_crash: ; AVX-LABEL: vselect_any_extend_vector_inreg_crash:
; AVX1: # %bb.0: ; AVX: # %bb.0:
; AVX1-NEXT: vpmovzxbw {{.*#+}} xmm0 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero ; AVX-NEXT: vpmovzxbw {{.*#+}} xmm0 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero
; AVX1-NEXT: vpcmpeqw {{.*}}(%rip), %xmm0, %xmm0 ; AVX-NEXT: vpcmpeqw {{.*}}(%rip), %xmm0, %xmm0
; AVX1-NEXT: vmovq %xmm0, %rax ; AVX-NEXT: vmovq %xmm0, %rax
; AVX1-NEXT: andl $32768, %eax # imm = 0x8000 ; AVX-NEXT: andl $32768, %eax # imm = 0x8000
; AVX1-NEXT: retq ; AVX-NEXT: retq
;
; AVX2-LABEL: vselect_any_extend_vector_inreg_crash:
; AVX2: # %bb.0:
; AVX2-NEXT: vpmovzxbw {{.*#+}} xmm0 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero
; AVX2-NEXT: vpcmpeqw {{.*}}(%rip), %xmm0, %xmm0
; AVX2-NEXT: vpmovzxwq {{.*#+}} ymm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero
; AVX2-NEXT: vmovq %xmm0, %rax
; AVX2-NEXT: andl $32768, %eax # imm = 0x8000
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
0: 0:
%1 = load <8 x i8>, <8 x i8>* %x %1 = load <8 x i8>, <8 x i8>* %x
%2 = icmp eq <8 x i8> %1, <i8 49, i8 49, i8 49, i8 49, i8 49, i8 49, i8 49, i8 49> %2 = icmp eq <8 x i8> %1, <i8 49, i8 49, i8 49, i8 49, i8 49, i8 49, i8 49, i8 49>