[all-commits] [llvm/llvm-project] d8a9c5: [CUDA] refactor in-header implementation of __ld*/...
Artem Belevich via All-commits
all-commits at lists.llvm.org
Wed Apr 8 10:38:30 PDT 2026
Branch: refs/heads/main
Home: https://github.com/llvm/llvm-project
Commit: d8a9c560ed04369f12eb44f12bcbcfc7ddb5f78a
https://github.com/llvm/llvm-project/commit/d8a9c560ed04369f12eb44f12bcbcfc7ddb5f78a
Author: Artem Belevich <tra at google.com>
Date: 2026-04-08 (Wed, 08 Apr 2026)
Changed paths:
M clang/lib/Headers/__clang_cuda_intrinsics.h
A clang/test/Headers/cuda_intrinsics.cu
Log Message:
-----------
[CUDA] refactor in-header implementation of __ld*/__st* with different cache modes. (#190021)
* Generalized creation of the variant sets.
* Added implementations for the missing operation modes. Now we match
what's available in CUDA headers.
* Cleaned up discrepancies in `__asm__ __volatile__` use (needed for
some ops that warm up the cache, but should not be discarded if the load
result is unused)
Manually verified that clang's versions of these functions generate
exactly the same instructions nvcc generates from CUDA headers.
To unsubscribe from these emails, change your notification settings at https://github.com/llvm/llvm-project/settings/notifications
More information about the All-commits
mailing list