Index: llvm/trunk/lib/Target/AArch64/AArch64InstrInfo.cpp =================================================================== --- llvm/trunk/lib/Target/AArch64/AArch64InstrInfo.cpp +++ llvm/trunk/lib/Target/AArch64/AArch64InstrInfo.cpp @@ -2901,6 +2901,8 @@ // 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 @@ 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; } Index: llvm/trunk/test/CodeGen/AArch64/arm64-fma-combine-with-fpfusion.ll =================================================================== --- llvm/trunk/test/CodeGen/AArch64/arm64-fma-combine-with-fpfusion.ll +++ llvm/trunk/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" } +