diff options
Diffstat (limited to 'lib/Target/AMDGPU/AMDGPUCodeGenPrepare.cpp')
-rw-r--r-- | lib/Target/AMDGPU/AMDGPUCodeGenPrepare.cpp | 4 |
1 files changed, 3 insertions, 1 deletions
diff --git a/lib/Target/AMDGPU/AMDGPUCodeGenPrepare.cpp b/lib/Target/AMDGPU/AMDGPUCodeGenPrepare.cpp index b312dbc8d14d..31ee9206ae27 100644 --- a/lib/Target/AMDGPU/AMDGPUCodeGenPrepare.cpp +++ b/lib/Target/AMDGPU/AMDGPUCodeGenPrepare.cpp @@ -380,7 +380,9 @@ bool AMDGPUCodeGenPrepare::visitFDiv(BinaryOperator &FDiv) { FastMathFlags FMF = FPOp->getFastMathFlags(); bool UnsafeDiv = HasUnsafeFPMath || FMF.unsafeAlgebra() || FMF.allowReciprocal(); - if (ST->hasFP32Denormals() && !UnsafeDiv) + + // With UnsafeDiv node will be optimized to just rcp and mul. + if (ST->hasFP32Denormals() || UnsafeDiv) return false; IRBuilder<> Builder(FDiv.getParent(), std::next(FDiv.getIterator()), FPMath); |