diff options
| author | Farhana Aleen <farhana.aleen@gmail.com> | 2018-05-09 21:18:34 +0000 |
|---|---|---|
| committer | Farhana Aleen <farhana.aleen@gmail.com> | 2018-05-09 21:18:34 +0000 |
| commit | e24f3ff8dea7bfc7b65d0ababbe0c180c88ff7af (patch) | |
| tree | 83993a6087cca7fb701ba3594efbc7dc536d9ff4 /llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.h | |
| parent | eac81b244843423a58ed6301c5fb8ca25ffa2308 (diff) | |
| download | bcm5719-llvm-e24f3ff8dea7bfc7b65d0ababbe0c180c88ff7af.tar.gz bcm5719-llvm-e24f3ff8dea7bfc7b65d0ababbe0c180c88ff7af.zip | |
[AMDGPU] Support horizontal vectorization of min/max.
Author: FarhanaAleen
Reviewed By: rampitec
Subscribers: AMDGPU
Differential Revision: https://reviews.llvm.org/D46604
llvm-svn: 331920
Diffstat (limited to 'llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.h')
| -rw-r--r-- | llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.h | 3 |
1 files changed, 3 insertions, 0 deletions
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.h b/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.h index 744093d038f..4a0b46d28db 100644 --- a/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.h +++ b/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.h @@ -176,6 +176,9 @@ public: int getArithmeticReductionCost(unsigned Opcode, Type *Ty, bool IsPairwise); + int getMinMaxReductionCost(Type *Ty, Type *CondTy, + bool IsPairwiseForm, + bool IsUnsigned); }; } // end namespace llvm |
