Skip to content

[X86][ISel][FMA] Get a handle on operand nodes when negating FMA #130176

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 17, 2025
Merged

[X86][ISel][FMA] Get a handle on operand nodes when negating FMA #130176

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
5 changes: 5 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 @@ -55673,7 +55673,12 @@ static SDValue combineFMA(SDNode *N, SelectionDAG &DAG,
// Do not convert the passthru input of scalar intrinsics.
// FIXME: We could allow negations of the lower element only.
bool NegA = invertIfNegative(A);
// Create a dummy use for A so that in the process of negating B or C
// recursively, it is not deleted.
HandleSDNode NegAHandle(A);
bool NegB = invertIfNegative(B);
// Similar to A, get a handle on B.
HandleSDNode NegBHandle(B);
bool NegC = invertIfNegative(C);

if (!NegA && !NegB && !NegC)
Expand Down
25 changes: 25 additions & 0 deletions llvm/test/CodeGen/X86/combine-fma-negate.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,25 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc < %s -mtriple=x86_64-unknown-linux-gnu -mattr=+avx512f -mattr=+fma | FileCheck %s

define void @fma_neg(<8 x i1> %r280, ptr %pp1, ptr %pp2) {
; CHECK-LABEL: fma_neg:
; CHECK: # %bb.0:
; CHECK-NEXT: vpmovsxwq %xmm0, %zmm0
; CHECK-NEXT: vpsllq $63, %zmm0, %zmm0
; CHECK-NEXT: vptestmq %zmm0, %zmm0, %k1
; CHECK-NEXT: vmovdqu64 (%rdi), %zmm0
; CHECK-NEXT: vpxorq {{\.?LCPI[0-9]+_[0-9]+}}(%rip){1to8}, %zmm0, %zmm1 {%k1} {z}
; CHECK-NEXT: vxorpd %xmm2, %xmm2, %xmm2
; CHECK-NEXT: vfnmadd213pd {{.*#+}} zmm2 = -(zmm0 * zmm2) + zmm1
; CHECK-NEXT: vmovupd %zmm2, (%rsi)
; CHECK-NEXT: vzeroupper
; CHECK-NEXT: retq
%r290 = load <8 x double>, ptr %pp1, align 8
%r307 = fneg <8 x double> %r290
%r309 = select <8 x i1> %r280, <8 x double> %r307, <8 x double> zeroinitializer
%r311 = tail call <8 x double> @llvm.x86.avx512.vfmadd.pd.512(<8 x double> %r307, <8 x double> zeroinitializer, <8 x double> %r309, i32 4)
store <8 x double> %r311, ptr %pp2, align 8
ret void
}

declare <8 x double> @llvm.x86.avx512.vfmadd.pd.512(<8 x double>, <8 x double>, <8 x double>, i32 immarg)