diff options
| author | Anshil Gandhi <Anshil.Gandhi@amd.com> | 2023-03-28 15:58:02 -0600 |
|---|---|---|
| committer | Anshil Gandhi <Anshil.Gandhi@amd.com> | 2023-03-28 15:58:30 -0600 |
| commit | a955a31896370b67c6490251eca0095295d55f1f (patch) | |
| tree | 6c848152af9fd71a3662bc18c2cdd0742a3bf8aa /clang/lib/CodeGen/CodeGenModule.cpp | |
| parent | afeec474ea6263055be9a9dc9ece65d8d73c3465 (diff) | |
| download | llvm-a955a31896370b67c6490251eca0095295d55f1f.zip llvm-a955a31896370b67c6490251eca0095295d55f1f.tar.gz llvm-a955a31896370b67c6490251eca0095295d55f1f.tar.bz2 | |
[AMDGPU] Replace target feature for global fadd32
Change target feature of __builtin_amdgcn_global_atomic_fadd_f32
to atomic-fadd-rtn-insts. Enable atomic-fadd-rtn-insts for gfx90a,
gfx940 and gfx1100 as they all support the return variant of
`global_atomic_add_f32`.
Fixes https://github.com/llvm/llvm-project/issues/61331.
Reviewed By: rampitec
Differential Revision: https://reviews.llvm.org/D146840
Diffstat (limited to 'clang/lib/CodeGen/CodeGenModule.cpp')
0 files changed, 0 insertions, 0 deletions