Skip to content

[X86] combineEXTRACT_SUBVECTOR - extract from a larger subvector insertion #132950

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Mar 26, 2025
Merged

[X86] combineEXTRACT_SUBVECTOR - extract from a larger subvector insertion #132950

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
30 changes: 16 additions & 14 deletions llvm/lib/Target/X86/X86ISelLowering.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -59085,20 +59085,22 @@ static SDValue combineEXTRACT_SUBVECTOR(SDNode *N, SelectionDAG &DAG,
return extractSubVector(InVec.getOperand(0), NewIdx, DAG, DL, SizeInBits);
}

// If we are extracting from an insert into a larger vector, replace with a
// smaller insert if we don't access less than the original subvector. Don't
// do this for i1 vectors.
// TODO: Relax the matching indices requirement?
if (VT.getVectorElementType() != MVT::i1 &&
InVec.getOpcode() == ISD::INSERT_SUBVECTOR && InVec.hasOneUse() &&
IdxVal == InVec.getConstantOperandVal(2) &&
InVec.getOperand(1).getValueSizeInBits() <= SizeInBits) {
SDValue NewExt = DAG.getNode(ISD::EXTRACT_SUBVECTOR, DL, VT,
InVec.getOperand(0), N->getOperand(1));
unsigned NewIdxVal = InVec.getConstantOperandVal(2) - IdxVal;
return DAG.getNode(ISD::INSERT_SUBVECTOR, DL, VT, NewExt,
InVec.getOperand(1),
DAG.getVectorIdxConstant(NewIdxVal, DL));
// EXTRACT_SUBVECTOR(INSERT_SUBVECTOR(SRC,SUB,C1),C2)
// --> INSERT_SUBVECTOR(EXTRACT_SUBVECTOR(SRC,C2),SUB,C1-C2)
// iff SUB is entirely contained in the extraction.
if (VT.getVectorElementType() != MVT::i1 && TLI.isTypeLegal(VT) &&
InVec.getOpcode() == ISD::INSERT_SUBVECTOR && InVec.hasOneUse()) {
SDValue Src = InVec.getOperand(0);
SDValue Sub = InVec.getOperand(1);
EVT SubVT = Sub.getValueType();
uint64_t InsIdx = InVec.getConstantOperandVal(2);
if (IdxVal <= InsIdx &&
(IdxVal + NumSubElts) >= (InsIdx + SubVT.getVectorNumElements())) {
SDValue NewSrc = DAG.getNode(ISD::EXTRACT_SUBVECTOR, DL, VT, Src,
DAG.getVectorIdxConstant(IdxVal, DL));
return DAG.getNode(ISD::INSERT_SUBVECTOR, DL, VT, NewSrc, Sub,
DAG.getVectorIdxConstant(InsIdx - IdxVal, DL));
}
}

// If we're extracting an upper subvector from a broadcast we should just
Expand Down
8 changes: 4 additions & 4 deletions llvm/test/CodeGen/X86/vector-interleaved-store-i16-stride-6.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -993,13 +993,13 @@ define void @store_i16_stride6_vf8(ptr %in.vecptr0, ptr %in.vecptr1, ptr %in.vec
; AVX512-NEXT: vmovdqa (%r8), %xmm2
; AVX512-NEXT: vinserti128 $1, (%rsi), %ymm0, %ymm0
; AVX512-NEXT: vinserti128 $1, (%rcx), %ymm1, %ymm1
; AVX512-NEXT: vinserti32x4 $1, (%r9), %zmm2, %zmm2
; AVX512-NEXT: vpermq {{.*#+}} ymm3 = ymm1[0,2,1,3]
; AVX512-NEXT: vmovdqa {{.*#+}} ymm4 = [0,1,8,9,6,7,14,15,6,7,14,15,2,3,10,11,16,17,24,25,16,17,24,25,24,25,26,27,18,19,26,27]
; AVX512-NEXT: vpshufb %ymm4, %ymm3, %ymm3
; AVX512-NEXT: vpermq {{.*#+}} ymm5 = ymm0[0,2,1,3]
; AVX512-NEXT: vpshufb %ymm4, %ymm5, %ymm4
; AVX512-NEXT: vpblendd {{.*#+}} ymm3 = ymm4[0,1],ymm3[2],ymm4[3,4],ymm3[5],ymm4[6,7]
; AVX512-NEXT: vinserti128 $1, (%r9), %ymm2, %ymm2
; AVX512-NEXT: vpermq {{.*#+}} ymm4 = ymm2[0,2,1,3]
; AVX512-NEXT: vpshufb {{.*#+}} ymm4 = ymm4[4,5,12,13,u,u,u,u,u,u,u,u,6,7,14,15,u,u,u,u,u,u,u,u,16,17,24,25,u,u,u,u]
; AVX512-NEXT: vpblendd {{.*#+}} ymm3 = ymm4[0],ymm3[1,2],ymm4[3],ymm3[4,5],ymm4[6],ymm3[7]
Expand Down Expand Up @@ -1035,7 +1035,6 @@ define void @store_i16_stride6_vf8(ptr %in.vecptr0, ptr %in.vecptr1, ptr %in.vec
; AVX512-FCP-NEXT: vmovdqa (%r8), %xmm2
; AVX512-FCP-NEXT: vinserti128 $1, (%rsi), %ymm0, %ymm0
; AVX512-FCP-NEXT: vinserti128 $1, (%rcx), %ymm1, %ymm1
; AVX512-FCP-NEXT: vinserti32x4 $1, (%r9), %zmm2, %zmm2
; AVX512-FCP-NEXT: vbroadcasti128 {{.*#+}} ymm3 = [2,6,1,5,2,6,1,5]
; AVX512-FCP-NEXT: # ymm3 = mem[0,1,0,1]
; AVX512-FCP-NEXT: vpermd %ymm1, %ymm3, %ymm3
Expand All @@ -1044,6 +1043,7 @@ define void @store_i16_stride6_vf8(ptr %in.vecptr0, ptr %in.vecptr1, ptr %in.vec
; AVX512-FCP-NEXT: vpermq {{.*#+}} ymm5 = ymm0[0,2,1,3]
; AVX512-FCP-NEXT: vpshufb %ymm4, %ymm5, %ymm4
; AVX512-FCP-NEXT: vpblendd {{.*#+}} ymm3 = ymm4[0,1],ymm3[2],ymm4[3,4],ymm3[5],ymm4[6,7]
; AVX512-FCP-NEXT: vinserti128 $1, (%r9), %ymm2, %ymm2
; AVX512-FCP-NEXT: vpermq {{.*#+}} ymm4 = ymm2[0,2,1,3]
; AVX512-FCP-NEXT: vpshufb {{.*#+}} ymm4 = ymm4[4,5,12,13,u,u,u,u,u,u,u,u,6,7,14,15,u,u,u,u,u,u,u,u,16,17,24,25,u,u,u,u]
; AVX512-FCP-NEXT: vpblendd {{.*#+}} ymm3 = ymm4[0],ymm3[1,2],ymm4[3],ymm3[4,5],ymm4[6],ymm3[7]
Expand Down Expand Up @@ -1085,13 +1085,13 @@ define void @store_i16_stride6_vf8(ptr %in.vecptr0, ptr %in.vecptr1, ptr %in.vec
; AVX512DQ-NEXT: vmovdqa (%r8), %xmm2
; AVX512DQ-NEXT: vinserti128 $1, (%rsi), %ymm0, %ymm0
; AVX512DQ-NEXT: vinserti128 $1, (%rcx), %ymm1, %ymm1
; AVX512DQ-NEXT: vinserti32x4 $1, (%r9), %zmm2, %zmm2
; AVX512DQ-NEXT: vpermq {{.*#+}} ymm3 = ymm1[0,2,1,3]
; AVX512DQ-NEXT: vmovdqa {{.*#+}} ymm4 = [0,1,8,9,6,7,14,15,6,7,14,15,2,3,10,11,16,17,24,25,16,17,24,25,24,25,26,27,18,19,26,27]
; AVX512DQ-NEXT: vpshufb %ymm4, %ymm3, %ymm3
; AVX512DQ-NEXT: vpermq {{.*#+}} ymm5 = ymm0[0,2,1,3]
; AVX512DQ-NEXT: vpshufb %ymm4, %ymm5, %ymm4
; AVX512DQ-NEXT: vpblendd {{.*#+}} ymm3 = ymm4[0,1],ymm3[2],ymm4[3,4],ymm3[5],ymm4[6,7]
; AVX512DQ-NEXT: vinserti128 $1, (%r9), %ymm2, %ymm2
; AVX512DQ-NEXT: vpermq {{.*#+}} ymm4 = ymm2[0,2,1,3]
; AVX512DQ-NEXT: vpshufb {{.*#+}} ymm4 = ymm4[4,5,12,13,u,u,u,u,u,u,u,u,6,7,14,15,u,u,u,u,u,u,u,u,16,17,24,25,u,u,u,u]
; AVX512DQ-NEXT: vpblendd {{.*#+}} ymm3 = ymm4[0],ymm3[1,2],ymm4[3],ymm3[4,5],ymm4[6],ymm3[7]
Expand Down Expand Up @@ -1127,7 +1127,6 @@ define void @store_i16_stride6_vf8(ptr %in.vecptr0, ptr %in.vecptr1, ptr %in.vec
; AVX512DQ-FCP-NEXT: vmovdqa (%r8), %xmm2
; AVX512DQ-FCP-NEXT: vinserti128 $1, (%rsi), %ymm0, %ymm0
; AVX512DQ-FCP-NEXT: vinserti128 $1, (%rcx), %ymm1, %ymm1
; AVX512DQ-FCP-NEXT: vinserti32x4 $1, (%r9), %zmm2, %zmm2
; AVX512DQ-FCP-NEXT: vbroadcasti128 {{.*#+}} ymm3 = [2,6,1,5,2,6,1,5]
; AVX512DQ-FCP-NEXT: # ymm3 = mem[0,1,0,1]
; AVX512DQ-FCP-NEXT: vpermd %ymm1, %ymm3, %ymm3
Expand All @@ -1136,6 +1135,7 @@ define void @store_i16_stride6_vf8(ptr %in.vecptr0, ptr %in.vecptr1, ptr %in.vec
; AVX512DQ-FCP-NEXT: vpermq {{.*#+}} ymm5 = ymm0[0,2,1,3]
; AVX512DQ-FCP-NEXT: vpshufb %ymm4, %ymm5, %ymm4
; AVX512DQ-FCP-NEXT: vpblendd {{.*#+}} ymm3 = ymm4[0,1],ymm3[2],ymm4[3,4],ymm3[5],ymm4[6,7]
; AVX512DQ-FCP-NEXT: vinserti128 $1, (%r9), %ymm2, %ymm2
; AVX512DQ-FCP-NEXT: vpermq {{.*#+}} ymm4 = ymm2[0,2,1,3]
; AVX512DQ-FCP-NEXT: vpshufb {{.*#+}} ymm4 = ymm4[4,5,12,13,u,u,u,u,u,u,u,u,6,7,14,15,u,u,u,u,u,u,u,u,16,17,24,25,u,u,u,u]
; AVX512DQ-FCP-NEXT: vpblendd {{.*#+}} ymm3 = ymm4[0],ymm3[1,2],ymm4[3],ymm3[4,5],ymm4[6],ymm3[7]
Expand Down
64 changes: 32 additions & 32 deletions llvm/test/CodeGen/X86/vector-interleaved-store-i8-stride-3.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -740,14 +740,14 @@ define void @store_i8_stride3_vf16(ptr %in.vecptr0, ptr %in.vecptr1, ptr %in.vec
; AVX512-NEXT: vpalignr {{.*#+}} xmm0 = xmm3[5,6,7,8,9,10,11,12,13,14,15],xmm0[0,1,2,3,4]
; AVX512-NEXT: vpalignr {{.*#+}} xmm2 = xmm2[5,6,7,8,9,10,11,12,13,14,15],xmm3[0,1,2,3,4]
; AVX512-NEXT: vpalignr {{.*#+}} xmm1 = xmm4[5,6,7,8,9,10,11,12,13,14,15],xmm1[0,1,2,3,4]
; AVX512-NEXT: vmovdqa {{.*#+}} xmm3 = [0,11,6,1,12,7,2,13,8,3,14,9,4,15,10,5]
; AVX512-NEXT: vpshufb %xmm3, %xmm1, %xmm1
; AVX512-NEXT: vpalignr {{.*#+}} xmm0 = xmm0[5,6,7,8,9,10,11,12,13,14,15],xmm2[0,1,2,3,4]
; AVX512-NEXT: vpshufb %xmm3, %xmm0, %xmm0
; AVX512-NEXT: vpalignr {{.*#+}} xmm2 = xmm2[5,6,7,8,9,10,11,12,13,14,15],xmm4[0,1,2,3,4]
; AVX512-NEXT: vbroadcasti128 {{.*#+}} ymm3 = [0,11,6,1,12,7,2,13,8,3,14,9,4,15,10,5,0,11,6,1,12,7,2,13,8,3,14,9,4,15,10,5]
; AVX512-NEXT: # ymm3 = mem[0,1,0,1]
; AVX512-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512-NEXT: vinserti32x4 $1, %xmm0, %zmm1, %zmm0
; AVX512-NEXT: vmovdqa %xmm2, 32(%rcx)
; AVX512-NEXT: vinserti128 $1, %xmm0, %ymm1, %ymm0
; AVX512-NEXT: vpshufb %ymm3, %ymm0, %ymm0
; AVX512-NEXT: vmovdqa %ymm0, (%rcx)
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
Expand All @@ -763,14 +763,14 @@ define void @store_i8_stride3_vf16(ptr %in.vecptr0, ptr %in.vecptr1, ptr %in.vec
; AVX512-FCP-NEXT: vpalignr {{.*#+}} xmm0 = xmm3[5,6,7,8,9,10,11,12,13,14,15],xmm0[0,1,2,3,4]
; AVX512-FCP-NEXT: vpalignr {{.*#+}} xmm2 = xmm2[5,6,7,8,9,10,11,12,13,14,15],xmm3[0,1,2,3,4]
; AVX512-FCP-NEXT: vpalignr {{.*#+}} xmm1 = xmm4[5,6,7,8,9,10,11,12,13,14,15],xmm1[0,1,2,3,4]
; AVX512-FCP-NEXT: vmovdqa {{.*#+}} xmm3 = [0,11,6,1,12,7,2,13,8,3,14,9,4,15,10,5]
; AVX512-FCP-NEXT: vpshufb %xmm3, %xmm1, %xmm1
; AVX512-FCP-NEXT: vpalignr {{.*#+}} xmm0 = xmm0[5,6,7,8,9,10,11,12,13,14,15],xmm2[0,1,2,3,4]
; AVX512-FCP-NEXT: vpshufb %xmm3, %xmm0, %xmm0
; AVX512-FCP-NEXT: vpalignr {{.*#+}} xmm2 = xmm2[5,6,7,8,9,10,11,12,13,14,15],xmm4[0,1,2,3,4]
; AVX512-FCP-NEXT: vbroadcasti128 {{.*#+}} ymm3 = [0,11,6,1,12,7,2,13,8,3,14,9,4,15,10,5,0,11,6,1,12,7,2,13,8,3,14,9,4,15,10,5]
; AVX512-FCP-NEXT: # ymm3 = mem[0,1,0,1]
; AVX512-FCP-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512-FCP-NEXT: vinserti32x4 $1, %xmm0, %zmm1, %zmm0
; AVX512-FCP-NEXT: vmovdqa %xmm2, 32(%rcx)
; AVX512-FCP-NEXT: vinserti128 $1, %xmm0, %ymm1, %ymm0
; AVX512-FCP-NEXT: vpshufb %ymm3, %ymm0, %ymm0
; AVX512-FCP-NEXT: vmovdqa %ymm0, (%rcx)
; AVX512-FCP-NEXT: vzeroupper
; AVX512-FCP-NEXT: retq
Expand All @@ -786,14 +786,14 @@ define void @store_i8_stride3_vf16(ptr %in.vecptr0, ptr %in.vecptr1, ptr %in.vec
; AVX512DQ-NEXT: vpalignr {{.*#+}} xmm0 = xmm3[5,6,7,8,9,10,11,12,13,14,15],xmm0[0,1,2,3,4]
; AVX512DQ-NEXT: vpalignr {{.*#+}} xmm2 = xmm2[5,6,7,8,9,10,11,12,13,14,15],xmm3[0,1,2,3,4]
; AVX512DQ-NEXT: vpalignr {{.*#+}} xmm1 = xmm4[5,6,7,8,9,10,11,12,13,14,15],xmm1[0,1,2,3,4]
; AVX512DQ-NEXT: vmovdqa {{.*#+}} xmm3 = [0,11,6,1,12,7,2,13,8,3,14,9,4,15,10,5]
; AVX512DQ-NEXT: vpshufb %xmm3, %xmm1, %xmm1
; AVX512DQ-NEXT: vpalignr {{.*#+}} xmm0 = xmm0[5,6,7,8,9,10,11,12,13,14,15],xmm2[0,1,2,3,4]
; AVX512DQ-NEXT: vpshufb %xmm3, %xmm0, %xmm0
; AVX512DQ-NEXT: vpalignr {{.*#+}} xmm2 = xmm2[5,6,7,8,9,10,11,12,13,14,15],xmm4[0,1,2,3,4]
; AVX512DQ-NEXT: vbroadcasti128 {{.*#+}} ymm3 = [0,11,6,1,12,7,2,13,8,3,14,9,4,15,10,5,0,11,6,1,12,7,2,13,8,3,14,9,4,15,10,5]
; AVX512DQ-NEXT: # ymm3 = mem[0,1,0,1]
; AVX512DQ-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512DQ-NEXT: vinserti32x4 $1, %xmm0, %zmm1, %zmm0
; AVX512DQ-NEXT: vmovdqa %xmm2, 32(%rcx)
; AVX512DQ-NEXT: vinserti128 $1, %xmm0, %ymm1, %ymm0
; AVX512DQ-NEXT: vpshufb %ymm3, %ymm0, %ymm0
; AVX512DQ-NEXT: vmovdqa %ymm0, (%rcx)
; AVX512DQ-NEXT: vzeroupper
; AVX512DQ-NEXT: retq
Expand All @@ -809,14 +809,14 @@ define void @store_i8_stride3_vf16(ptr %in.vecptr0, ptr %in.vecptr1, ptr %in.vec
; AVX512DQ-FCP-NEXT: vpalignr {{.*#+}} xmm0 = xmm3[5,6,7,8,9,10,11,12,13,14,15],xmm0[0,1,2,3,4]
; AVX512DQ-FCP-NEXT: vpalignr {{.*#+}} xmm2 = xmm2[5,6,7,8,9,10,11,12,13,14,15],xmm3[0,1,2,3,4]
; AVX512DQ-FCP-NEXT: vpalignr {{.*#+}} xmm1 = xmm4[5,6,7,8,9,10,11,12,13,14,15],xmm1[0,1,2,3,4]
; AVX512DQ-FCP-NEXT: vmovdqa {{.*#+}} xmm3 = [0,11,6,1,12,7,2,13,8,3,14,9,4,15,10,5]
; AVX512DQ-FCP-NEXT: vpshufb %xmm3, %xmm1, %xmm1
; AVX512DQ-FCP-NEXT: vpalignr {{.*#+}} xmm0 = xmm0[5,6,7,8,9,10,11,12,13,14,15],xmm2[0,1,2,3,4]
; AVX512DQ-FCP-NEXT: vpshufb %xmm3, %xmm0, %xmm0
; AVX512DQ-FCP-NEXT: vpalignr {{.*#+}} xmm2 = xmm2[5,6,7,8,9,10,11,12,13,14,15],xmm4[0,1,2,3,4]
; AVX512DQ-FCP-NEXT: vbroadcasti128 {{.*#+}} ymm3 = [0,11,6,1,12,7,2,13,8,3,14,9,4,15,10,5,0,11,6,1,12,7,2,13,8,3,14,9,4,15,10,5]
; AVX512DQ-FCP-NEXT: # ymm3 = mem[0,1,0,1]
; AVX512DQ-FCP-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512DQ-FCP-NEXT: vinserti32x4 $1, %xmm0, %zmm1, %zmm0
; AVX512DQ-FCP-NEXT: vmovdqa %xmm2, 32(%rcx)
; AVX512DQ-FCP-NEXT: vinserti128 $1, %xmm0, %ymm1, %ymm0
; AVX512DQ-FCP-NEXT: vpshufb %ymm3, %ymm0, %ymm0
; AVX512DQ-FCP-NEXT: vmovdqa %ymm0, (%rcx)
; AVX512DQ-FCP-NEXT: vzeroupper
; AVX512DQ-FCP-NEXT: retq
Expand All @@ -832,14 +832,14 @@ define void @store_i8_stride3_vf16(ptr %in.vecptr0, ptr %in.vecptr1, ptr %in.vec
; AVX512BW-NEXT: vpalignr {{.*#+}} xmm0 = xmm3[5,6,7,8,9,10,11,12,13,14,15],xmm0[0,1,2,3,4]
; AVX512BW-NEXT: vpalignr {{.*#+}} xmm2 = xmm2[5,6,7,8,9,10,11,12,13,14,15],xmm3[0,1,2,3,4]
; AVX512BW-NEXT: vpalignr {{.*#+}} xmm1 = xmm4[5,6,7,8,9,10,11,12,13,14,15],xmm1[0,1,2,3,4]
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm3 = [0,11,6,1,12,7,2,13,8,3,14,9,4,15,10,5]
; AVX512BW-NEXT: vpshufb %xmm3, %xmm1, %xmm1
; AVX512BW-NEXT: vpalignr {{.*#+}} xmm0 = xmm0[5,6,7,8,9,10,11,12,13,14,15],xmm2[0,1,2,3,4]
; AVX512BW-NEXT: vpshufb %xmm3, %xmm0, %xmm0
; AVX512BW-NEXT: vpalignr {{.*#+}} xmm2 = xmm2[5,6,7,8,9,10,11,12,13,14,15],xmm4[0,1,2,3,4]
; AVX512BW-NEXT: vbroadcasti128 {{.*#+}} ymm3 = [0,11,6,1,12,7,2,13,8,3,14,9,4,15,10,5,0,11,6,1,12,7,2,13,8,3,14,9,4,15,10,5]
; AVX512BW-NEXT: # ymm3 = mem[0,1,0,1]
; AVX512BW-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512BW-NEXT: vinserti32x4 $1, %xmm0, %zmm1, %zmm0
; AVX512BW-NEXT: vmovdqa %xmm2, 32(%rcx)
; AVX512BW-NEXT: vinserti128 $1, %xmm0, %ymm1, %ymm0
; AVX512BW-NEXT: vpshufb %ymm3, %ymm0, %ymm0
; AVX512BW-NEXT: vmovdqa %ymm0, (%rcx)
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
Expand All @@ -855,14 +855,14 @@ define void @store_i8_stride3_vf16(ptr %in.vecptr0, ptr %in.vecptr1, ptr %in.vec
; AVX512BW-FCP-NEXT: vpalignr {{.*#+}} xmm0 = xmm3[5,6,7,8,9,10,11,12,13,14,15],xmm0[0,1,2,3,4]
; AVX512BW-FCP-NEXT: vpalignr {{.*#+}} xmm2 = xmm2[5,6,7,8,9,10,11,12,13,14,15],xmm3[0,1,2,3,4]
; AVX512BW-FCP-NEXT: vpalignr {{.*#+}} xmm1 = xmm4[5,6,7,8,9,10,11,12,13,14,15],xmm1[0,1,2,3,4]
; AVX512BW-FCP-NEXT: vmovdqa {{.*#+}} xmm3 = [0,11,6,1,12,7,2,13,8,3,14,9,4,15,10,5]
; AVX512BW-FCP-NEXT: vpshufb %xmm3, %xmm1, %xmm1
; AVX512BW-FCP-NEXT: vpalignr {{.*#+}} xmm0 = xmm0[5,6,7,8,9,10,11,12,13,14,15],xmm2[0,1,2,3,4]
; AVX512BW-FCP-NEXT: vpshufb %xmm3, %xmm0, %xmm0
; AVX512BW-FCP-NEXT: vpalignr {{.*#+}} xmm2 = xmm2[5,6,7,8,9,10,11,12,13,14,15],xmm4[0,1,2,3,4]
; AVX512BW-FCP-NEXT: vbroadcasti128 {{.*#+}} ymm3 = [0,11,6,1,12,7,2,13,8,3,14,9,4,15,10,5,0,11,6,1,12,7,2,13,8,3,14,9,4,15,10,5]
; AVX512BW-FCP-NEXT: # ymm3 = mem[0,1,0,1]
; AVX512BW-FCP-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512BW-FCP-NEXT: vinserti32x4 $1, %xmm0, %zmm1, %zmm0
; AVX512BW-FCP-NEXT: vmovdqa %xmm2, 32(%rcx)
; AVX512BW-FCP-NEXT: vinserti128 $1, %xmm0, %ymm1, %ymm0
; AVX512BW-FCP-NEXT: vpshufb %ymm3, %ymm0, %ymm0
; AVX512BW-FCP-NEXT: vmovdqa %ymm0, (%rcx)
; AVX512BW-FCP-NEXT: vzeroupper
; AVX512BW-FCP-NEXT: retq
Expand All @@ -878,14 +878,14 @@ define void @store_i8_stride3_vf16(ptr %in.vecptr0, ptr %in.vecptr1, ptr %in.vec
; AVX512DQ-BW-NEXT: vpalignr {{.*#+}} xmm0 = xmm3[5,6,7,8,9,10,11,12,13,14,15],xmm0[0,1,2,3,4]
; AVX512DQ-BW-NEXT: vpalignr {{.*#+}} xmm2 = xmm2[5,6,7,8,9,10,11,12,13,14,15],xmm3[0,1,2,3,4]
; AVX512DQ-BW-NEXT: vpalignr {{.*#+}} xmm1 = xmm4[5,6,7,8,9,10,11,12,13,14,15],xmm1[0,1,2,3,4]
; AVX512DQ-BW-NEXT: vmovdqa {{.*#+}} xmm3 = [0,11,6,1,12,7,2,13,8,3,14,9,4,15,10,5]
; AVX512DQ-BW-NEXT: vpshufb %xmm3, %xmm1, %xmm1
; AVX512DQ-BW-NEXT: vpalignr {{.*#+}} xmm0 = xmm0[5,6,7,8,9,10,11,12,13,14,15],xmm2[0,1,2,3,4]
; AVX512DQ-BW-NEXT: vpshufb %xmm3, %xmm0, %xmm0
; AVX512DQ-BW-NEXT: vpalignr {{.*#+}} xmm2 = xmm2[5,6,7,8,9,10,11,12,13,14,15],xmm4[0,1,2,3,4]
; AVX512DQ-BW-NEXT: vbroadcasti128 {{.*#+}} ymm3 = [0,11,6,1,12,7,2,13,8,3,14,9,4,15,10,5,0,11,6,1,12,7,2,13,8,3,14,9,4,15,10,5]
; AVX512DQ-BW-NEXT: # ymm3 = mem[0,1,0,1]
; AVX512DQ-BW-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512DQ-BW-NEXT: vinserti32x4 $1, %xmm0, %zmm1, %zmm0
; AVX512DQ-BW-NEXT: vmovdqa %xmm2, 32(%rcx)
; AVX512DQ-BW-NEXT: vinserti128 $1, %xmm0, %ymm1, %ymm0
; AVX512DQ-BW-NEXT: vpshufb %ymm3, %ymm0, %ymm0
; AVX512DQ-BW-NEXT: vmovdqa %ymm0, (%rcx)
; AVX512DQ-BW-NEXT: vzeroupper
; AVX512DQ-BW-NEXT: retq
Expand All @@ -901,14 +901,14 @@ define void @store_i8_stride3_vf16(ptr %in.vecptr0, ptr %in.vecptr1, ptr %in.vec
; AVX512DQ-BW-FCP-NEXT: vpalignr {{.*#+}} xmm0 = xmm3[5,6,7,8,9,10,11,12,13,14,15],xmm0[0,1,2,3,4]
; AVX512DQ-BW-FCP-NEXT: vpalignr {{.*#+}} xmm2 = xmm2[5,6,7,8,9,10,11,12,13,14,15],xmm3[0,1,2,3,4]
; AVX512DQ-BW-FCP-NEXT: vpalignr {{.*#+}} xmm1 = xmm4[5,6,7,8,9,10,11,12,13,14,15],xmm1[0,1,2,3,4]
; AVX512DQ-BW-FCP-NEXT: vmovdqa {{.*#+}} xmm3 = [0,11,6,1,12,7,2,13,8,3,14,9,4,15,10,5]
; AVX512DQ-BW-FCP-NEXT: vpshufb %xmm3, %xmm1, %xmm1
; AVX512DQ-BW-FCP-NEXT: vpalignr {{.*#+}} xmm0 = xmm0[5,6,7,8,9,10,11,12,13,14,15],xmm2[0,1,2,3,4]
; AVX512DQ-BW-FCP-NEXT: vpshufb %xmm3, %xmm0, %xmm0
; AVX512DQ-BW-FCP-NEXT: vpalignr {{.*#+}} xmm2 = xmm2[5,6,7,8,9,10,11,12,13,14,15],xmm4[0,1,2,3,4]
; AVX512DQ-BW-FCP-NEXT: vbroadcasti128 {{.*#+}} ymm3 = [0,11,6,1,12,7,2,13,8,3,14,9,4,15,10,5,0,11,6,1,12,7,2,13,8,3,14,9,4,15,10,5]
; AVX512DQ-BW-FCP-NEXT: # ymm3 = mem[0,1,0,1]
; AVX512DQ-BW-FCP-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512DQ-BW-FCP-NEXT: vinserti32x4 $1, %xmm0, %zmm1, %zmm0
; AVX512DQ-BW-FCP-NEXT: vmovdqa %xmm2, 32(%rcx)
; AVX512DQ-BW-FCP-NEXT: vinserti128 $1, %xmm0, %ymm1, %ymm0
; AVX512DQ-BW-FCP-NEXT: vpshufb %ymm3, %ymm0, %ymm0
; AVX512DQ-BW-FCP-NEXT: vmovdqa %ymm0, (%rcx)
; AVX512DQ-BW-FCP-NEXT: vzeroupper
; AVX512DQ-BW-FCP-NEXT: retq
Expand Down
Loading