diff options
| author | Daniil Fukalov <daniil.fukalov@amd.com> | 2018-01-17 14:05:05 +0000 |
|---|---|---|
| committer | Daniil Fukalov <daniil.fukalov@amd.com> | 2018-01-17 14:05:05 +0000 |
| commit | d5fca554e2384fe99d4cc89829955fa0222d0b5f (patch) | |
| tree | c90ba3b14de30ab717bb1bfef889707e19bab6a2 /llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp | |
| parent | 6b65f7c3805ea1e49ee3354802ec6ecc9ca0de21 (diff) | |
| download | bcm5719-llvm-d5fca554e2384fe99d4cc89829955fa0222d0b5f.tar.gz bcm5719-llvm-d5fca554e2384fe99d4cc89829955fa0222d0b5f.zip | |
[AMDGPU] add LDS f32 intrinsics
added llvm.amdgcn.atomic.{add|min|max}.f32 intrinsics
to allow generate ds_{add|min|max}[_rtn]_f32 instructions
needed for OpenCL float atomics in LDS
Reviewed by: arsenm
Differential Revision: https://reviews.llvm.org/D37985
llvm-svn: 322656
Diffstat (limited to 'llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp')
| -rw-r--r-- | llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp | 3 |
1 files changed, 3 insertions, 0 deletions
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp b/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp index 77c2d4b956c..21088d3e48e 100644 --- a/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp +++ b/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp @@ -475,6 +475,9 @@ static bool isIntrinsicSourceOfDivergence(const IntrinsicInst *I) { case Intrinsic::r600_read_tidig_z: case Intrinsic::amdgcn_atomic_inc: case Intrinsic::amdgcn_atomic_dec: + case Intrinsic::amdgcn_atomic_fadd: + case Intrinsic::amdgcn_atomic_fmin: + case Intrinsic::amdgcn_atomic_fmax: case Intrinsic::amdgcn_image_atomic_swap: case Intrinsic::amdgcn_image_atomic_add: case Intrinsic::amdgcn_image_atomic_sub: |
