Skip to content

[X86] combineEXTRACT_SUBVECTOR - fold extract_subvector(subv_broadcast_load(ptr),0) -> load(ptr) #126523

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 2 commits into from
Feb 12, 2025
Merged

[X86] combineEXTRACT_SUBVECTOR - fold extract_subvector(subv_broadcast_load(ptr),0) -> load(ptr) #126523

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
75f7ac7
[X86] combineEXTRACT_SUBVECTOR - fold extract_subvector(subv_broadcas…
RKSimon Feb 10, 2025
c3916b6
Merge branch 'upstream' into x86-extract-broadcast128
RKSimon Feb 12, 2025
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
24 changes: 20 additions & 4 deletions llvm/lib/Target/X86/X86ISelLowering.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -58485,10 +58485,26 @@ static SDValue combineEXTRACT_SUBVECTOR(SDNode *N, SelectionDAG &DAG,
DAG.isSplatValue(InVec, /*AllowUndefs*/ false)))
return extractSubVector(InVec, 0, DAG, DL, SizeInBits);

// If we're extracting a broadcasted subvector, just use the lowest subvector.
if (IdxVal != 0 && InVec.getOpcode() == X86ISD::SUBV_BROADCAST_LOAD &&
cast<MemIntrinsicSDNode>(InVec)->getMemoryVT() == VT)
return extractSubVector(InVec, 0, DAG, DL, SizeInBits);
// Check if we're extracting a whole broadcasted subvector.
if (InVec.getOpcode() == X86ISD::SUBV_BROADCAST_LOAD) {
auto *MemIntr = cast<MemIntrinsicSDNode>(InVec);
EVT MemVT = MemIntr->getMemoryVT();
if (MemVT == VT) {
// Just use the lowest subvector.
if (IdxVal != 0)
return extractSubVector(InVec, 0, DAG, DL, SizeInBits);
// If this is the only use, we can replace with a regular load (this may
// have been missed by SimplifyDemandedVectorElts due to extra uses of the
// memory chain).
if (InVec.hasOneUse()) {
SDValue Ld =
DAG.getLoad(MemVT, DL, MemIntr->getChain(), MemIntr->getBasePtr(),
MemIntr->getMemOperand());
DAG.makeEquivalentMemoryOrdering(SDValue(MemIntr, 1), Ld.getValue(1));
return Ld;
}
}
}

// Attempt to extract from the source of a shuffle vector.
if ((InSizeInBits % SizeInBits) == 0 && (IdxVal % NumSubElts) == 0) {
Expand Down
18 changes: 8 additions & 10 deletions llvm/test/CodeGen/X86/any_extend_vector_inreg_of_broadcast_from_memory.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3634,19 +3634,18 @@ define void @vec384_i32_widen_to_i128_factor4_broadcast_to_v3i128_factor3(ptr %i
;
; AVX-LABEL: vec384_i32_widen_to_i128_factor4_broadcast_to_v3i128_factor3:
; AVX: # %bb.0:
; AVX-NEXT: vbroadcastf128 {{.*#+}} ymm0 = mem[0,1,0,1]
; AVX-NEXT: vblendps {{.*#+}} xmm1 = xmm0[0],mem[1,2,3]
; AVX-NEXT: vmovdqa (%rdi), %xmm0
; AVX-NEXT: vpblendw {{.*#+}} xmm1 = xmm0[0,1],mem[2,3,4,5,6,7]
; AVX-NEXT: vpaddb (%rsi), %xmm1, %xmm1
; AVX-NEXT: vmovdqa (%rdi), %xmm2
; AVX-NEXT: vmovdqa 16(%rdi), %xmm3
; AVX-NEXT: vpaddb 48(%rsi), %xmm3, %xmm3
; AVX-NEXT: vpaddb 16(%rsi), %xmm0, %xmm0
; AVX-NEXT: vpaddb 32(%rsi), %xmm2, %xmm2
; AVX-NEXT: vmovdqa %xmm2, 32(%rdx)
; AVX-NEXT: vpaddb 16(%rsi), %xmm0, %xmm0
; AVX-NEXT: vmovdqa %xmm0, 16(%rdx)
; AVX-NEXT: vmovdqa %xmm2, 32(%rdx)
; AVX-NEXT: vmovdqa %xmm3, 48(%rdx)
; AVX-NEXT: vmovdqa %xmm1, (%rdx)
; AVX-NEXT: vzeroupper
; AVX-NEXT: retq
;
; AVX2-LABEL: vec384_i32_widen_to_i128_factor4_broadcast_to_v3i128_factor3:
Expand Down Expand Up @@ -3820,19 +3819,18 @@ define void @vec384_i64_widen_to_i128_factor2_broadcast_to_v3i128_factor3(ptr %i
;
; AVX-LABEL: vec384_i64_widen_to_i128_factor2_broadcast_to_v3i128_factor3:
; AVX: # %bb.0:
; AVX-NEXT: vbroadcastf128 {{.*#+}} ymm0 = mem[0,1,0,1]
; AVX-NEXT: vblendps {{.*#+}} xmm1 = xmm0[0,1],mem[2,3]
; AVX-NEXT: vmovdqa (%rdi), %xmm0
; AVX-NEXT: vpblendw {{.*#+}} xmm1 = xmm0[0,1,2,3],mem[4,5,6,7]
; AVX-NEXT: vpaddb (%rsi), %xmm1, %xmm1
; AVX-NEXT: vmovdqa (%rdi), %xmm2
; AVX-NEXT: vmovdqa 16(%rdi), %xmm3
; AVX-NEXT: vpaddb 48(%rsi), %xmm3, %xmm3
; AVX-NEXT: vpaddb 16(%rsi), %xmm0, %xmm0
; AVX-NEXT: vpaddb 32(%rsi), %xmm2, %xmm2
; AVX-NEXT: vmovdqa %xmm2, 32(%rdx)
; AVX-NEXT: vpaddb 16(%rsi), %xmm0, %xmm0
; AVX-NEXT: vmovdqa %xmm0, 16(%rdx)
; AVX-NEXT: vmovdqa %xmm2, 32(%rdx)
; AVX-NEXT: vmovdqa %xmm3, 48(%rdx)
; AVX-NEXT: vmovdqa %xmm1, (%rdx)
; AVX-NEXT: vzeroupper
; AVX-NEXT: retq
;
; AVX2-LABEL: vec384_i64_widen_to_i128_factor2_broadcast_to_v3i128_factor3:
Expand Down
22 changes: 10 additions & 12 deletions llvm/test/CodeGen/X86/zero_extend_vector_inreg_of_broadcast_from_memory.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4044,18 +4044,17 @@ define void @vec384_i32_widen_to_i128_factor4_broadcast_to_v3i128_factor3(ptr %i
;
; AVX-LABEL: vec384_i32_widen_to_i128_factor4_broadcast_to_v3i128_factor3:
; AVX: # %bb.0:
; AVX-NEXT: vbroadcastf128 {{.*#+}} ymm0 = mem[0,1,0,1]
; AVX-NEXT: vblendps {{.*#+}} xmm1 = xmm0[0],mem[1,2,3]
; AVX-NEXT: vmovdqa (%rdi), %xmm0
; AVX-NEXT: vpblendw {{.*#+}} xmm1 = xmm0[0,1],mem[2,3,4,5,6,7]
; AVX-NEXT: vmovd {{.*#+}} xmm2 = mem[0],zero,zero,zero
; AVX-NEXT: vxorps %xmm3, %xmm3, %xmm3
; AVX-NEXT: vblendps {{.*#+}} xmm0 = xmm0[0],xmm3[1,2,3]
; AVX-NEXT: vpaddb 16(%rsi), %xmm0, %xmm0
; AVX-NEXT: vpaddb (%rsi), %xmm1, %xmm1
; AVX-NEXT: vpxor %xmm3, %xmm3, %xmm3
; AVX-NEXT: vpblendw {{.*#+}} xmm0 = xmm0[0,1],xmm3[2,3,4,5,6,7]
; AVX-NEXT: vpaddb 16(%rsi), %xmm0, %xmm0
; AVX-NEXT: vpaddb 32(%rsi), %xmm2, %xmm2
; AVX-NEXT: vmovdqa %xmm2, 32(%rdx)
; AVX-NEXT: vmovdqa %xmm1, (%rdx)
; AVX-NEXT: vmovdqa %xmm0, 16(%rdx)
; AVX-NEXT: vzeroupper
; AVX-NEXT: vmovdqa %xmm1, (%rdx)
; AVX-NEXT: retq
;
; AVX2-LABEL: vec384_i32_widen_to_i128_factor4_broadcast_to_v3i128_factor3:
Expand Down Expand Up @@ -4263,17 +4262,16 @@ define void @vec384_i64_widen_to_i128_factor2_broadcast_to_v3i128_factor3(ptr %i
;
; AVX-LABEL: vec384_i64_widen_to_i128_factor2_broadcast_to_v3i128_factor3:
; AVX: # %bb.0:
; AVX-NEXT: vbroadcastf128 {{.*#+}} ymm0 = mem[0,1,0,1]
; AVX-NEXT: vblendps {{.*#+}} xmm1 = xmm0[0,1],mem[2,3]
; AVX-NEXT: vmovdqa (%rdi), %xmm0
; AVX-NEXT: vpblendw {{.*#+}} xmm1 = xmm0[0,1,2,3],mem[4,5,6,7]
; AVX-NEXT: vmovq {{.*#+}} xmm2 = mem[0],zero
; AVX-NEXT: vpaddb (%rsi), %xmm1, %xmm1
; AVX-NEXT: vmovq {{.*#+}} xmm0 = xmm0[0],zero
; AVX-NEXT: vpaddb 16(%rsi), %xmm0, %xmm0
; AVX-NEXT: vpaddb (%rsi), %xmm1, %xmm1
; AVX-NEXT: vpaddb 32(%rsi), %xmm2, %xmm2
; AVX-NEXT: vmovdqa %xmm2, 32(%rdx)
; AVX-NEXT: vmovdqa %xmm1, (%rdx)
; AVX-NEXT: vmovdqa %xmm0, 16(%rdx)
; AVX-NEXT: vzeroupper
; AVX-NEXT: vmovdqa %xmm1, (%rdx)
; AVX-NEXT: retq
;
; AVX2-LABEL: vec384_i64_widen_to_i128_factor2_broadcast_to_v3i128_factor3:
Expand Down