diff options
| author | Evandro Menezes <e.menezes@samsung.com> | 2016-09-15 19:55:23 +0000 |
|---|---|---|
| committer | Evandro Menezes <e.menezes@samsung.com> | 2016-09-15 19:55:23 +0000 |
| commit | 19b2aed3080eb88f982dfe97a356afa7e1467d9b (patch) | |
| tree | b8336c4bdc2a0d1d99b6e7d8c4edb05b36ba315a /llvm | |
| parent | 252f9bf7d387b8108adc92231ad7dd4632e6020d (diff) | |
| download | bcm5719-llvm-19b2aed3080eb88f982dfe97a356afa7e1467d9b.tar.gz bcm5719-llvm-19b2aed3080eb88f982dfe97a356afa7e1467d9b.zip | |
[AArch64] Support for FP FMA when -ffp-contract=fast
Currently, the machine combiner can proceed matching when -ffast-math is on.
It should also match when only -ffp-contract=fast is specified as was the
case before when DAGCombiner was doing the job.
Patch by: Abderrazek Zaafrani <a.zaafrani@samsung.com>.
Differential Revision: https://reviews.llvm.org/D24366
llvm-svn: 281649
Diffstat (limited to 'llvm')
| -rw-r--r-- | llvm/lib/Target/AArch64/AArch64InstrInfo.cpp | 8 | ||||
| -rw-r--r-- | llvm/test/CodeGen/AArch64/arm64-fma-combine-with-fpfusion.ll | 12 |
2 files changed, 17 insertions, 3 deletions
diff --git a/llvm/lib/Target/AArch64/AArch64InstrInfo.cpp b/llvm/lib/Target/AArch64/AArch64InstrInfo.cpp index 6907e061332..859f7828901 100644 --- a/llvm/lib/Target/AArch64/AArch64InstrInfo.cpp +++ b/llvm/lib/Target/AArch64/AArch64InstrInfo.cpp @@ -2901,6 +2901,8 @@ static bool isCombineInstrCandidate64(unsigned Opc) { // FP Opcodes that can be combined with a FMUL static bool isCombineInstrCandidateFP(const MachineInstr &Inst) { switch (Inst.getOpcode()) { + default: + break; case AArch64::FADDSrr: case AArch64::FADDDrr: case AArch64::FADDv2f32: @@ -2911,9 +2913,9 @@ static bool isCombineInstrCandidateFP(const MachineInstr &Inst) { case AArch64::FSUBv2f32: case AArch64::FSUBv2f64: case AArch64::FSUBv4f32: - return Inst.getParent()->getParent()->getTarget().Options.UnsafeFPMath; - default: - break; + TargetOptions Options = Inst.getParent()->getParent()->getTarget().Options; + return (Options.UnsafeFPMath || + Options.AllowFPOpFusion == FPOpFusion::Fast); } return false; } diff --git a/llvm/test/CodeGen/AArch64/arm64-fma-combine-with-fpfusion.ll b/llvm/test/CodeGen/AArch64/arm64-fma-combine-with-fpfusion.ll new file mode 100644 index 00000000000..095a0b0edd2 --- /dev/null +++ b/llvm/test/CodeGen/AArch64/arm64-fma-combine-with-fpfusion.ll @@ -0,0 +1,12 @@ +; RUN: llc < %s -mtriple=aarch64-linux-gnu -fp-contract=fast | FileCheck %s +define float @mul_add(float %a, float %b, float %c) local_unnamed_addr #0 { +; CHECK-LABEL: %entry +; CHECK: fmadd {{s[0-9]+}}, {{s[0-9]+}}, {{s[0-9]+}} + entry: + %mul = fmul float %a, %b + %add = fadd float %mul, %c + ret float %add +} + +attributes #0 = { norecurse nounwind readnone "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="generic" "target-features"="+neon" "unsafe-fp-math"="false" "use-soft-float"="false" } + |
