Skip to content

[X86] combineCONCAT_VECTORS - fold concat(extract_subvector(X,0),extract_subvector(Y,0)) --> shuffle(X,Y) #135985

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

Closed
wants to merge 1 commit into from
Closed

[X86] combineCONCAT_VECTORS - fold concat(extract_subvector(X,0),extract_subvector(Y,0)) --> shuffle(X,Y) #135985

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
22 changes: 22 additions & 0 deletions llvm/lib/Target/X86/X86ISelLowering.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -58911,6 +58911,28 @@ static SDValue combineCONCAT_VECTORS(SDNode *N, SelectionDAG &DAG,
return R;
}

// Fold concat(extract_subvector(X,0),extract_subvector(Y,0))
// --> shuffle(X,Y)
// This is a more limited version of combineConcatVectorOfExtracts for use
// after legalization.
if (Ops.size() == 2 && TLI.isTypeLegal(VT)) {
SDValue Lo = Ops[0], Hi = Ops[1];
if (Lo.getOpcode() == ISD::EXTRACT_SUBVECTOR &&
Hi.getOpcode() == ISD::EXTRACT_SUBVECTOR &&
Lo.getOperand(0).getValueSizeInBits() == VT.getSizeInBits() &&
Hi.getOperand(0).getValueSizeInBits() == VT.getSizeInBits() &&
isNullConstant(Lo.getOperand(1)) && isNullConstant(Hi.getOperand(1))) {
unsigned NumElts = VT.getVectorNumElements();
unsigned HalfElts = NumElts / 2;
SmallVector<int, 8> ConcatMask(NumElts);
std::iota(ConcatMask.begin(), ConcatMask.begin() + HalfElts, 0);
std::iota(ConcatMask.begin() + HalfElts, ConcatMask.end(), NumElts);
return DAG.getVectorShuffle(
VT, SDLoc(N), DAG.getBitcast(VT, Lo.getOperand(0)),
DAG.getBitcast(VT, Hi.getOperand(0)), ConcatMask);
}
}

return SDValue();
}

Expand Down
14 changes: 6 additions & 8 deletions llvm/test/CodeGen/X86/combine-pmuldq.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -396,9 +396,8 @@ define <8 x i32> @PR49658_zext(ptr %ptr, i32 %mul) {
; AVX2-NEXT: vpmovzxdq {{.*#+}} ymm3 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
; AVX2-NEXT: vpmuludq %ymm3, %ymm1, %ymm3
; AVX2-NEXT: vpmuludq %ymm2, %ymm1, %ymm2
; AVX2-NEXT: vperm2i128 {{.*#+}} ymm4 = ymm3[2,3],ymm2[2,3]
; AVX2-NEXT: vinserti128 $1, %xmm2, %ymm3, %ymm2
; AVX2-NEXT: vshufps {{.*#+}} ymm2 = ymm2[1,3],ymm4[1,3],ymm2[5,7],ymm4[5,7]
; AVX2-NEXT: vshufps {{.*#+}} ymm2 = ymm2[1,3],ymm3[1,3],ymm2[5,7],ymm3[5,7]
; AVX2-NEXT: vpermpd {{.*#+}} ymm2 = ymm2[0,2,1,3]
; AVX2-NEXT: vpaddd %ymm0, %ymm2, %ymm0
; AVX2-NEXT: subq $-128, %rax
; AVX2-NEXT: jne .LBB7_1
Expand Down Expand Up @@ -568,13 +567,12 @@ define <8 x i32> @PR49658_sext(ptr %ptr, i32 %mul) {
; AVX2-NEXT: .p2align 4
; AVX2-NEXT: .LBB8_1: # %loop
; AVX2-NEXT: # =>This Inner Loop Header: Depth=1
; AVX2-NEXT: vpmovsxdq 2097168(%rdi,%rax), %ymm2
; AVX2-NEXT: vpmovsxdq 2097152(%rdi,%rax), %ymm3
; AVX2-NEXT: vpmovsxdq 2097152(%rdi,%rax), %ymm2
; AVX2-NEXT: vpmovsxdq 2097168(%rdi,%rax), %ymm3
; AVX2-NEXT: vpmuldq %ymm3, %ymm1, %ymm3
; AVX2-NEXT: vpmuldq %ymm2, %ymm1, %ymm2
; AVX2-NEXT: vperm2i128 {{.*#+}} ymm4 = ymm3[2,3],ymm2[2,3]
; AVX2-NEXT: vinserti128 $1, %xmm2, %ymm3, %ymm2
; AVX2-NEXT: vshufps {{.*#+}} ymm2 = ymm2[1,3],ymm4[1,3],ymm2[5,7],ymm4[5,7]
; AVX2-NEXT: vshufps {{.*#+}} ymm2 = ymm2[1,3],ymm3[1,3],ymm2[5,7],ymm3[5,7]
; AVX2-NEXT: vpermpd {{.*#+}} ymm2 = ymm2[0,2,1,3]
; AVX2-NEXT: vpaddd %ymm0, %ymm2, %ymm0
; AVX2-NEXT: subq $-128, %rax
; AVX2-NEXT: jne .LBB8_1
Expand Down
5 changes: 2 additions & 3 deletions llvm/test/CodeGen/X86/masked_store_trunc.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -172,9 +172,8 @@ define void @truncstore_v8i64_v8i32(<8 x i64> %x, ptr %p, <8 x i32> %mask) {
; AVX2-NEXT: vpcmpeqd %ymm3, %ymm2, %ymm2
; AVX2-NEXT: vpcmpeqd %ymm3, %ymm3, %ymm3
; AVX2-NEXT: vpxor %ymm3, %ymm2, %ymm2
; AVX2-NEXT: vperm2f128 {{.*#+}} ymm3 = ymm0[2,3],ymm1[2,3]
; AVX2-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX2-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm3[0,2],ymm0[4,6],ymm3[4,6]
; AVX2-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm1[0,2],ymm0[4,6],ymm1[4,6]
; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,2,1,3]
; AVX2-NEXT: vpmaskmovd %ymm0, %ymm2, (%rdi)
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
Expand Down
5 changes: 2 additions & 3 deletions llvm/test/CodeGen/X86/masked_store_trunc_ssat.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -334,9 +334,8 @@ define void @truncstore_v8i64_v8i32(<8 x i64> %x, ptr %p, <8 x i32> %mask) {
; AVX2-NEXT: vblendvpd %ymm4, %ymm1, %ymm3, %ymm1
; AVX2-NEXT: vpcmpgtq %ymm3, %ymm0, %ymm4
; AVX2-NEXT: vblendvpd %ymm4, %ymm0, %ymm3, %ymm0
; AVX2-NEXT: vperm2f128 {{.*#+}} ymm3 = ymm0[2,3],ymm1[2,3]
; AVX2-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX2-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm3[0,2],ymm0[4,6],ymm3[4,6]
; AVX2-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm1[0,2],ymm0[4,6],ymm1[4,6]
; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,2,1,3]
; AVX2-NEXT: vpmaskmovd %ymm0, %ymm2, (%rdi)
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
Expand Down
5 changes: 2 additions & 3 deletions llvm/test/CodeGen/X86/masked_store_trunc_usat.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -266,9 +266,8 @@ define void @truncstore_v8i64_v8i32(<8 x i64> %x, ptr %p, <8 x i32> %mask) {
; AVX2-NEXT: vpxor %ymm4, %ymm0, %ymm4
; AVX2-NEXT: vpcmpgtq %ymm4, %ymm6, %ymm4
; AVX2-NEXT: vblendvpd %ymm4, %ymm0, %ymm3, %ymm0
; AVX2-NEXT: vperm2f128 {{.*#+}} ymm3 = ymm0[2,3],ymm1[2,3]
; AVX2-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX2-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm3[0,2],ymm0[4,6],ymm3[4,6]
; AVX2-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm1[0,2],ymm0[4,6],ymm1[4,6]
; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,2,1,3]
; AVX2-NEXT: vpmaskmovd %ymm0, %ymm2, (%rdi)
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
Expand Down
5 changes: 2 additions & 3 deletions llvm/test/CodeGen/X86/pr40891.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,9 +8,8 @@ define <8 x i32> @foo(<8 x i64> %x, <4 x i64> %y) {
; CHECK: # %bb.0:
; CHECK-NEXT: vandps %ymm2, %ymm0, %ymm0
; CHECK-NEXT: vandps {{\.?LCPI[0-9]+_[0-9]+}}, %ymm1, %ymm1
; CHECK-NEXT: vperm2f128 {{.*#+}} ymm2 = ymm0[2,3],ymm1[2,3]
; CHECK-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; CHECK-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm2[0,2],ymm0[4,6],ymm2[4,6]
; CHECK-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm1[0,2],ymm0[4,6],ymm1[4,6]
; CHECK-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,2,1,3]
; CHECK-NEXT: retl
%a = shufflevector <4 x i64> %y, <4 x i64> <i64 12345, i64 67890, i64 13579, i64 24680>, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
%b = and <8 x i64> %x, %a
Expand Down
154 changes: 37 additions & 117 deletions llvm/test/CodeGen/X86/psubus.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,9 +3,9 @@
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+ssse3 | FileCheck %s --check-prefixes=SSE,SSE2OR3,SSSE3
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse4.1 | FileCheck %s --check-prefixes=SSE,SSE41
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefixes=AVX,AVX1
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefixes=AVX,AVX2,AVX2-SLOW
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2,+fast-variable-crosslane-shuffle,+fast-variable-perlane-shuffle | FileCheck %s --check-prefixes=AVX,AVX2,AVX2-FAST-ALL
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2,+fast-variable-perlane-shuffle | FileCheck %s --check-prefixes=AVX,AVX2,AVX2-FAST-PERLANE
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefixes=AVX,AVX2
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2,+fast-variable-crosslane-shuffle,+fast-variable-perlane-shuffle | FileCheck %s --check-prefixes=AVX,AVX2
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2,+fast-variable-perlane-shuffle | FileCheck %s --check-prefixes=AVX,AVX2
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw,+avx512vl,+fast-variable-crosslane-shuffle,+fast-variable-perlane-shuffle | FileCheck %s --check-prefixes=AVX,AVX512
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw,+avx512vl,+fast-variable-perlane-shuffle | FileCheck %s --check-prefixes=AVX,AVX512

Expand Down Expand Up @@ -2846,60 +2846,22 @@ define <8 x i32> @test33(<8 x i32> %a0, <8 x i64> %a1) {
; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0
; AVX1-NEXT: retq
;
; AVX2-SLOW-LABEL: test33:
; AVX2-SLOW: # %bb.0:
; AVX2-SLOW-NEXT: vpbroadcastq {{.*#+}} ymm3 = [9223372036854775808,9223372036854775808,9223372036854775808,9223372036854775808]
; AVX2-SLOW-NEXT: vpxor %ymm3, %ymm2, %ymm4
; AVX2-SLOW-NEXT: vpbroadcastq {{.*#+}} ymm5 = [9223372041149743103,9223372041149743103,9223372041149743103,9223372041149743103]
; AVX2-SLOW-NEXT: vpcmpgtq %ymm4, %ymm5, %ymm4
; AVX2-SLOW-NEXT: vbroadcastsd {{.*#+}} ymm6 = [4294967295,4294967295,4294967295,4294967295]
; AVX2-SLOW-NEXT: vblendvpd %ymm4, %ymm2, %ymm6, %ymm2
; AVX2-SLOW-NEXT: vpxor %ymm3, %ymm1, %ymm3
; AVX2-SLOW-NEXT: vpcmpgtq %ymm3, %ymm5, %ymm3
; AVX2-SLOW-NEXT: vblendvpd %ymm3, %ymm1, %ymm6, %ymm1
; AVX2-SLOW-NEXT: vperm2f128 {{.*#+}} ymm3 = ymm1[2,3],ymm2[2,3]
; AVX2-SLOW-NEXT: vinsertf128 $1, %xmm2, %ymm1, %ymm1
; AVX2-SLOW-NEXT: vshufps {{.*#+}} ymm1 = ymm1[0,2],ymm3[0,2],ymm1[4,6],ymm3[4,6]
; AVX2-SLOW-NEXT: vpmaxud %ymm1, %ymm0, %ymm0
; AVX2-SLOW-NEXT: vpsubd %ymm1, %ymm0, %ymm0
; AVX2-SLOW-NEXT: retq
;
; AVX2-FAST-ALL-LABEL: test33:
; AVX2-FAST-ALL: # %bb.0:
; AVX2-FAST-ALL-NEXT: vpbroadcastq {{.*#+}} ymm3 = [9223372036854775808,9223372036854775808,9223372036854775808,9223372036854775808]
; AVX2-FAST-ALL-NEXT: vpxor %ymm3, %ymm1, %ymm4
; AVX2-FAST-ALL-NEXT: vpbroadcastq {{.*#+}} ymm5 = [9223372041149743103,9223372041149743103,9223372041149743103,9223372041149743103]
; AVX2-FAST-ALL-NEXT: vpcmpgtq %ymm4, %ymm5, %ymm4
; AVX2-FAST-ALL-NEXT: vbroadcastsd {{.*#+}} ymm6 = [4294967295,4294967295,4294967295,4294967295]
; AVX2-FAST-ALL-NEXT: vblendvpd %ymm4, %ymm1, %ymm6, %ymm1
; AVX2-FAST-ALL-NEXT: vmovapd {{.*#+}} ymm4 = [0,2,4,6,4,6,6,7]
; AVX2-FAST-ALL-NEXT: vpermps %ymm1, %ymm4, %ymm1
; AVX2-FAST-ALL-NEXT: vpxor %ymm3, %ymm2, %ymm3
; AVX2-FAST-ALL-NEXT: vpcmpgtq %ymm3, %ymm5, %ymm3
; AVX2-FAST-ALL-NEXT: vblendvpd %ymm3, %ymm2, %ymm6, %ymm2
; AVX2-FAST-ALL-NEXT: vpermps %ymm2, %ymm4, %ymm2
; AVX2-FAST-ALL-NEXT: vinsertf128 $1, %xmm2, %ymm1, %ymm1
; AVX2-FAST-ALL-NEXT: vpmaxud %ymm1, %ymm0, %ymm0
; AVX2-FAST-ALL-NEXT: vpsubd %ymm1, %ymm0, %ymm0
; AVX2-FAST-ALL-NEXT: retq
;
; AVX2-FAST-PERLANE-LABEL: test33:
; AVX2-FAST-PERLANE: # %bb.0:
; AVX2-FAST-PERLANE-NEXT: vpbroadcastq {{.*#+}} ymm3 = [9223372036854775808,9223372036854775808,9223372036854775808,9223372036854775808]
; AVX2-FAST-PERLANE-NEXT: vpxor %ymm3, %ymm2, %ymm4
; AVX2-FAST-PERLANE-NEXT: vpbroadcastq {{.*#+}} ymm5 = [9223372041149743103,9223372041149743103,9223372041149743103,9223372041149743103]
; AVX2-FAST-PERLANE-NEXT: vpcmpgtq %ymm4, %ymm5, %ymm4
; AVX2-FAST-PERLANE-NEXT: vbroadcastsd {{.*#+}} ymm6 = [4294967295,4294967295,4294967295,4294967295]
; AVX2-FAST-PERLANE-NEXT: vblendvpd %ymm4, %ymm2, %ymm6, %ymm2
; AVX2-FAST-PERLANE-NEXT: vpxor %ymm3, %ymm1, %ymm3
; AVX2-FAST-PERLANE-NEXT: vpcmpgtq %ymm3, %ymm5, %ymm3
; AVX2-FAST-PERLANE-NEXT: vblendvpd %ymm3, %ymm1, %ymm6, %ymm1
; AVX2-FAST-PERLANE-NEXT: vperm2f128 {{.*#+}} ymm3 = ymm1[2,3],ymm2[2,3]
; AVX2-FAST-PERLANE-NEXT: vinsertf128 $1, %xmm2, %ymm1, %ymm1
; AVX2-FAST-PERLANE-NEXT: vshufps {{.*#+}} ymm1 = ymm1[0,2],ymm3[0,2],ymm1[4,6],ymm3[4,6]
; AVX2-FAST-PERLANE-NEXT: vpmaxud %ymm1, %ymm0, %ymm0
; AVX2-FAST-PERLANE-NEXT: vpsubd %ymm1, %ymm0, %ymm0
; AVX2-FAST-PERLANE-NEXT: retq
; AVX2-LABEL: test33:
; AVX2: # %bb.0:
; AVX2-NEXT: vpbroadcastq {{.*#+}} ymm3 = [9223372036854775808,9223372036854775808,9223372036854775808,9223372036854775808]
; AVX2-NEXT: vpxor %ymm3, %ymm2, %ymm4
; AVX2-NEXT: vpbroadcastq {{.*#+}} ymm5 = [9223372041149743103,9223372041149743103,9223372041149743103,9223372041149743103]
; AVX2-NEXT: vpcmpgtq %ymm4, %ymm5, %ymm4
; AVX2-NEXT: vbroadcastsd {{.*#+}} ymm6 = [4294967295,4294967295,4294967295,4294967295]
; AVX2-NEXT: vblendvpd %ymm4, %ymm2, %ymm6, %ymm2
; AVX2-NEXT: vpxor %ymm3, %ymm1, %ymm3
; AVX2-NEXT: vpcmpgtq %ymm3, %ymm5, %ymm3
; AVX2-NEXT: vblendvpd %ymm3, %ymm1, %ymm6, %ymm1
; AVX2-NEXT: vshufps {{.*#+}} ymm1 = ymm1[0,2],ymm2[0,2],ymm1[4,6],ymm2[4,6]
; AVX2-NEXT: vpermpd {{.*#+}} ymm1 = ymm1[0,2,1,3]
; AVX2-NEXT: vpmaxud %ymm1, %ymm0, %ymm0
; AVX2-NEXT: vpsubd %ymm1, %ymm0, %ymm0
; AVX2-NEXT: retq
;
; AVX512-LABEL: test33:
; AVX512: # %bb.0:
Expand Down Expand Up @@ -3070,66 +3032,24 @@ define <8 x i32> @test34(<8 x i32> %a0, <8 x i64> %a1) {
; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0
; AVX1-NEXT: retq
;
; AVX2-SLOW-LABEL: test34:
; AVX2-SLOW: # %bb.0:
; AVX2-SLOW-NEXT: vpbroadcastd {{.*#+}} ymm3 = [1,1,1,1,1,1,1,1]
; AVX2-SLOW-NEXT: vpand %ymm3, %ymm0, %ymm0
; AVX2-SLOW-NEXT: vpbroadcastq {{.*#+}} ymm3 = [9223372036854775808,9223372036854775808,9223372036854775808,9223372036854775808]
; AVX2-SLOW-NEXT: vpxor %ymm3, %ymm2, %ymm4
; AVX2-SLOW-NEXT: vpbroadcastq {{.*#+}} ymm5 = [9223372041149743103,9223372041149743103,9223372041149743103,9223372041149743103]
; AVX2-SLOW-NEXT: vpcmpgtq %ymm4, %ymm5, %ymm4
; AVX2-SLOW-NEXT: vbroadcastsd {{.*#+}} ymm6 = [4294967295,4294967295,4294967295,4294967295]
; AVX2-SLOW-NEXT: vblendvpd %ymm4, %ymm2, %ymm6, %ymm2
; AVX2-SLOW-NEXT: vpxor %ymm3, %ymm1, %ymm3
; AVX2-SLOW-NEXT: vpcmpgtq %ymm3, %ymm5, %ymm3
; AVX2-SLOW-NEXT: vblendvpd %ymm3, %ymm1, %ymm6, %ymm1
; AVX2-SLOW-NEXT: vperm2f128 {{.*#+}} ymm3 = ymm1[2,3],ymm2[2,3]
; AVX2-SLOW-NEXT: vinsertf128 $1, %xmm2, %ymm1, %ymm1
; AVX2-SLOW-NEXT: vshufps {{.*#+}} ymm1 = ymm1[0,2],ymm3[0,2],ymm1[4,6],ymm3[4,6]
; AVX2-SLOW-NEXT: vpmaxud %ymm1, %ymm0, %ymm0
; AVX2-SLOW-NEXT: vpsubd %ymm1, %ymm0, %ymm0
; AVX2-SLOW-NEXT: retq
;
; AVX2-FAST-ALL-LABEL: test34:
; AVX2-FAST-ALL: # %bb.0:
; AVX2-FAST-ALL-NEXT: vpbroadcastd {{.*#+}} ymm3 = [1,1,1,1,1,1,1,1]
; AVX2-FAST-ALL-NEXT: vpand %ymm3, %ymm0, %ymm0
; AVX2-FAST-ALL-NEXT: vpbroadcastq {{.*#+}} ymm3 = [9223372036854775808,9223372036854775808,9223372036854775808,9223372036854775808]
; AVX2-FAST-ALL-NEXT: vpxor %ymm3, %ymm1, %ymm4
; AVX2-FAST-ALL-NEXT: vpbroadcastq {{.*#+}} ymm5 = [9223372041149743103,9223372041149743103,9223372041149743103,9223372041149743103]
; AVX2-FAST-ALL-NEXT: vpcmpgtq %ymm4, %ymm5, %ymm4
; AVX2-FAST-ALL-NEXT: vbroadcastsd {{.*#+}} ymm6 = [4294967295,4294967295,4294967295,4294967295]
; AVX2-FAST-ALL-NEXT: vblendvpd %ymm4, %ymm1, %ymm6, %ymm1
; AVX2-FAST-ALL-NEXT: vmovapd {{.*#+}} ymm4 = [0,2,4,6,4,6,6,7]
; AVX2-FAST-ALL-NEXT: vpermps %ymm1, %ymm4, %ymm1
; AVX2-FAST-ALL-NEXT: vpxor %ymm3, %ymm2, %ymm3
; AVX2-FAST-ALL-NEXT: vpcmpgtq %ymm3, %ymm5, %ymm3
; AVX2-FAST-ALL-NEXT: vblendvpd %ymm3, %ymm2, %ymm6, %ymm2
; AVX2-FAST-ALL-NEXT: vpermps %ymm2, %ymm4, %ymm2
; AVX2-FAST-ALL-NEXT: vinsertf128 $1, %xmm2, %ymm1, %ymm1
; AVX2-FAST-ALL-NEXT: vpmaxud %ymm1, %ymm0, %ymm0
; AVX2-FAST-ALL-NEXT: vpsubd %ymm1, %ymm0, %ymm0
; AVX2-FAST-ALL-NEXT: retq
;
; AVX2-FAST-PERLANE-LABEL: test34:
; AVX2-FAST-PERLANE: # %bb.0:
; AVX2-FAST-PERLANE-NEXT: vpbroadcastd {{.*#+}} ymm3 = [1,1,1,1,1,1,1,1]
; AVX2-FAST-PERLANE-NEXT: vpand %ymm3, %ymm0, %ymm0
; AVX2-FAST-PERLANE-NEXT: vpbroadcastq {{.*#+}} ymm3 = [9223372036854775808,9223372036854775808,9223372036854775808,9223372036854775808]
; AVX2-FAST-PERLANE-NEXT: vpxor %ymm3, %ymm2, %ymm4
; AVX2-FAST-PERLANE-NEXT: vpbroadcastq {{.*#+}} ymm5 = [9223372041149743103,9223372041149743103,9223372041149743103,9223372041149743103]
; AVX2-FAST-PERLANE-NEXT: vpcmpgtq %ymm4, %ymm5, %ymm4
; AVX2-FAST-PERLANE-NEXT: vbroadcastsd {{.*#+}} ymm6 = [4294967295,4294967295,4294967295,4294967295]
; AVX2-FAST-PERLANE-NEXT: vblendvpd %ymm4, %ymm2, %ymm6, %ymm2
; AVX2-FAST-PERLANE-NEXT: vpxor %ymm3, %ymm1, %ymm3
; AVX2-FAST-PERLANE-NEXT: vpcmpgtq %ymm3, %ymm5, %ymm3
; AVX2-FAST-PERLANE-NEXT: vblendvpd %ymm3, %ymm1, %ymm6, %ymm1
; AVX2-FAST-PERLANE-NEXT: vperm2f128 {{.*#+}} ymm3 = ymm1[2,3],ymm2[2,3]
; AVX2-FAST-PERLANE-NEXT: vinsertf128 $1, %xmm2, %ymm1, %ymm1
; AVX2-FAST-PERLANE-NEXT: vshufps {{.*#+}} ymm1 = ymm1[0,2],ymm3[0,2],ymm1[4,6],ymm3[4,6]
; AVX2-FAST-PERLANE-NEXT: vpmaxud %ymm1, %ymm0, %ymm0
; AVX2-FAST-PERLANE-NEXT: vpsubd %ymm1, %ymm0, %ymm0
; AVX2-FAST-PERLANE-NEXT: retq
; AVX2-LABEL: test34:
; AVX2: # %bb.0:
; AVX2-NEXT: vpbroadcastd {{.*#+}} ymm3 = [1,1,1,1,1,1,1,1]
; AVX2-NEXT: vpand %ymm3, %ymm0, %ymm0
; AVX2-NEXT: vpbroadcastq {{.*#+}} ymm3 = [9223372036854775808,9223372036854775808,9223372036854775808,9223372036854775808]
; AVX2-NEXT: vpxor %ymm3, %ymm2, %ymm4
; AVX2-NEXT: vpbroadcastq {{.*#+}} ymm5 = [9223372041149743103,9223372041149743103,9223372041149743103,9223372041149743103]
; AVX2-NEXT: vpcmpgtq %ymm4, %ymm5, %ymm4
; AVX2-NEXT: vbroadcastsd {{.*#+}} ymm6 = [4294967295,4294967295,4294967295,4294967295]
; AVX2-NEXT: vblendvpd %ymm4, %ymm2, %ymm6, %ymm2
; AVX2-NEXT: vpxor %ymm3, %ymm1, %ymm3
; AVX2-NEXT: vpcmpgtq %ymm3, %ymm5, %ymm3
; AVX2-NEXT: vblendvpd %ymm3, %ymm1, %ymm6, %ymm1
; AVX2-NEXT: vshufps {{.*#+}} ymm1 = ymm1[0,2],ymm2[0,2],ymm1[4,6],ymm2[4,6]
; AVX2-NEXT: vpermpd {{.*#+}} ymm1 = ymm1[0,2,1,3]
; AVX2-NEXT: vpmaxud %ymm1, %ymm0, %ymm0
; AVX2-NEXT: vpsubd %ymm1, %ymm0, %ymm0
; AVX2-NEXT: retq
;
; AVX512-LABEL: test34:
; AVX512: # %bb.0:
Expand Down
5 changes: 2 additions & 3 deletions llvm/test/CodeGen/X86/vector-reduce-xor-bool.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -585,9 +585,8 @@ define i1 @trunc_v8i64_v8i1(<8 x i64>) nounwind {
;
; AVX2-LABEL: trunc_v8i64_v8i1:
; AVX2: # %bb.0:
; AVX2-NEXT: vperm2f128 {{.*#+}} ymm2 = ymm0[2,3],ymm1[2,3]
; AVX2-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX2-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm2[0,2],ymm0[4,6],ymm2[4,6]
; AVX2-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm1[0,2],ymm0[4,6],ymm1[4,6]
; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,2,1,3]
; AVX2-NEXT: vpslld $31, %ymm0, %ymm0
; AVX2-NEXT: vmovmskps %ymm0, %eax
; AVX2-NEXT: testb %al, %al
Expand Down
Loading
Loading