aboutsummaryrefslogtreecommitdiff
path: root/clang/lib/Frontend/TestModuleFileExtension.cpp
diff options
context:
space:
mode:
authorJoseph Huber <huberjn@outlook.com>2025-02-05 12:38:48 -0600
committerGitHub <noreply@github.com>2025-02-05 12:38:48 -0600
commit2d8106cb5a505326d1da0f4461708ed44a0ac761 (patch)
tree851690635e45b47ae81bea4ddfd8bb3a83ac57d5 /clang/lib/Frontend/TestModuleFileExtension.cpp
parent96d46c694da6b040ea89d2004289ebfb6092892b (diff)
downloadllvm-2d8106cb5a505326d1da0f4461708ed44a0ac761.zip
llvm-2d8106cb5a505326d1da0f4461708ed44a0ac761.tar.gz
llvm-2d8106cb5a505326d1da0f4461708ed44a0ac761.tar.bz2
[Clang] Add width handling for <gpuintrin.h> shuffle helper (#125896)
Summary: The CUDA impelementation has long supported the `width` argument on its shuffle instrucitons, which makes it more difficult to replace those uses with this helper. This patch just correctly implements that for AMDGPU and NVPTX so it's equivalent to `__shfl_sync` in CUDA. This will ease porting. Fortunately these get optimized out correctly when passing in known widths.
Diffstat (limited to 'clang/lib/Frontend/TestModuleFileExtension.cpp')
0 files changed, 0 insertions, 0 deletions