Skip to content

release/20.x: [SLP] Check for PHI nodes (potentially cycles!) when checking dependencies #127267

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
Feb 14, 2025
Merged

release/20.x: [SLP] Check for PHI nodes (potentially cycles!) when checking dependencies #127267

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
10 changes: 9 additions & 1 deletion llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13181,8 +13181,16 @@ BoUpSLP::isGatherShuffledSingleRegisterEntry(
continue;
// If the user instruction is used for some reason in different
// vectorized nodes - make it depend on index.
// If any vector node is PHI node, this dependency might not work
// because of cycle dependencies, so disable it.
if (TEUseEI.UserTE != UseEI.UserTE &&
TEUseEI.UserTE->Idx < UseEI.UserTE->Idx)
(TEUseEI.UserTE->Idx < UseEI.UserTE->Idx ||
any_of(
VectorizableTree,
[](const std::unique_ptr<TreeEntry> &TE) {
return TE->State == TreeEntry::Vectorize &&
TE->getOpcode() == Instruction::PHI;
})))
continue;
}

Expand Down
2 changes: 1 addition & 1 deletion llvm/test/Transforms/SLPVectorizer/X86/delayed-gather-emission.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,7 +31,7 @@ define void @test() {
; CHECK-NEXT: [[TOBOOL:%.*]] = fcmp une float [[I2]], 0.000000e+00
; CHECK-NEXT: [[TMP8:%.*]] = shufflevector <2 x float> [[TMP5]], <2 x float> poison, <2 x i32> <i32 poison, i32 0>
; CHECK-NEXT: [[TMP9]] = insertelement <2 x float> [[TMP8]], float [[I2]], i32 0
; CHECK-NEXT: [[TMP10]] = shufflevector <2 x float> [[TMP9]], <2 x float> [[TMP2]], <2 x i32> <i32 0, i32 3>
; CHECK-NEXT: [[TMP10]] = insertelement <2 x float> [[TMP2]], float [[I2]], i32 0
; CHECK-NEXT: br i1 [[TOBOOL]], label [[BB1]], label [[BB2]]
;
entry:
Expand Down
2 changes: 1 addition & 1 deletion llvm/test/Transforms/SLPVectorizer/X86/matching-gather-nodes-phi-users.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@
; YAML: Function: test
; YAML: Args:
; YAML: - String: 'Stores SLP vectorized with cost '
; YAML: - Cost: '-6'
; YAML: - Cost: '-3'
; YAML: - String: ' and with tree size '
; YAML: - TreeSize: '14'
; YAML: ...
Expand Down
59 changes: 59 additions & 0 deletions llvm/test/Transforms/SLPVectorizer/X86/phi-node-with-cycle.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,59 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
; RUN: opt -S --passes=slp-vectorizer -mtriple=x86_64-unknown-linux-gnu -mcpu=haswell < %s | FileCheck %s

define void @test(float %0) {
; CHECK-LABEL: define void @test(
; CHECK-SAME: float [[TMP0:%.*]]) #[[ATTR0:[0-9]+]] {
; CHECK-NEXT: [[TMP2:%.*]] = insertelement <2 x float> <float 0.000000e+00, float poison>, float [[TMP0]], i32 1
; CHECK-NEXT: [[TMP3:%.*]] = fdiv <2 x float> [[TMP2]], zeroinitializer
; CHECK-NEXT: [[TMP4:%.*]] = insertelement <2 x float> <float poison, float 0.000000e+00>, float [[TMP0]], i32 0
; CHECK-NEXT: [[TMP5:%.*]] = fdiv <2 x float> [[TMP4]], zeroinitializer
; CHECK-NEXT: br label %[[BB6:.*]]
; CHECK: [[BB6]]:
; CHECK-NEXT: [[TMP7:%.*]] = fmul <2 x float> [[TMP5]], zeroinitializer
; CHECK-NEXT: [[TMP8:%.*]] = fsub <2 x float> zeroinitializer, [[TMP7]]
; CHECK-NEXT: br label %[[BB10:.*]]
; CHECK: [[BB9:.*]]:
; CHECK-NEXT: br label %[[BB10]]
; CHECK: [[BB10]]:
; CHECK-NEXT: [[TMP11:%.*]] = phi <2 x float> [ [[TMP8]], %[[BB6]] ], [ poison, %[[BB9]] ]
; CHECK-NEXT: br label %[[BB12:.*]]
; CHECK: [[BB12]]:
; CHECK-NEXT: [[TMP13:%.*]] = fmul <2 x float> [[TMP3]], zeroinitializer
; CHECK-NEXT: [[TMP14:%.*]] = fsub <2 x float> [[TMP11]], [[TMP13]]
; CHECK-NEXT: [[TMP15:%.*]] = extractelement <2 x float> [[TMP14]], i32 0
; CHECK-NEXT: [[TMP16:%.*]] = extractelement <2 x float> [[TMP14]], i32 1
; CHECK-NEXT: [[TMP17:%.*]] = fadd float [[TMP15]], [[TMP16]]
; CHECK-NEXT: [[TMP18:%.*]] = call float @llvm.fabs.f32(float [[TMP17]])
; CHECK-NEXT: ret void
;
%2 = fdiv float 0.000000e+00, 0.000000e+00
%3 = fdiv float 0.000000e+00, 0.000000e+00
%4 = fdiv float %0, 0.000000e+00
br label %5

5:
%6 = fmul float %4, 0.000000e+00
%7 = fsub float 0.000000e+00, %6
%8 = fmul float %3, 0.000000e+00
%9 = fsub float 0.000000e+00, %8
br label %11

10:
br label %11

11:
%12 = phi float [ %7, %5 ], [ 0.000000e+00, %10 ]
%13 = phi float [ %9, %5 ], [ 0.000000e+00, %10 ]
br label %14

14:
%15 = fmul float %2, 0.000000e+00
%16 = fsub float %12, %15
%17 = fmul float %4, 0.000000e+00
%18 = fsub float %13, %17
%19 = fadd float %16, %18
%20 = call float @llvm.fabs.f32(float %19)
ret void
}

Loading