diff options
| author | Yaxun (Sam) Liu <yaxun.liu@amd.com> | 2023-09-11 17:04:55 -0400 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-09-11 17:04:55 -0400 |
| commit | f2a1331a01ff8ad19fed6bd407501791467ad061 (patch) | |
| tree | 9c2311c45021bfc0e51c5b956bee13377da49838 /llvm/lib/Transforms/Utils/LoopUnrollRuntime.cpp | |
| parent | a2a9918a8524f3f7675297b75daa2a80bc0790ff (diff) | |
| download | llvm-f2a1331a01ff8ad19fed6bd407501791467ad061.zip llvm-f2a1331a01ff8ad19fed6bd407501791467ad061.tar.gz llvm-f2a1331a01ff8ad19fed6bd407501791467ad061.tar.bz2 | |
[CUDA][HIP] Do not mark extern shared var (#65990)
Fixes: https://github.com/llvm/llvm-project/issues/65806
Currently clang put extern shared var ODR-used by host device functions
in global var __clang_gpu_used_external. This behavior was due to
https://reviews.llvm.org/D123441. However, clang should not do that for
extern shared vars since their addresses are per warp, therefore cannot
be accessed by host code.
Diffstat (limited to 'llvm/lib/Transforms/Utils/LoopUnrollRuntime.cpp')
0 files changed, 0 insertions, 0 deletions