[HIP][libclc] Fix race in cmpxchg and change xor to use CAS instead of atomic builtin #11876
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode characters
hdelan had a problem deploying to WindowsCILock 
GitHub Actions Failure hdelan had a problem deploying to WindowsCILock GitHub Actions Failure 
Contributor Author
| @intel/llvm-gatekeepers we would like to merge this soon if that's OK |
Contributor
| Windows CI build only failed in post-testing cleanup. Merging. |
Contributor Author
| Thanks @steffenlarsen ! |
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit. This suggestion is invalid because no changes were made to the code. Suggestions cannot be applied while the pull request is closed. Suggestions cannot be applied while viewing a subset of changes. Only one suggestion per line can be applied in a batch. Add this suggestion to a batch that can be applied as a single commit. Applying suggestions on deleted lines is not supported. You must change the existing code in this line in order to create a valid suggestion. Outdated suggestions cannot be applied. This suggestion has been applied or marked resolved. Suggestions cannot be applied from pending reviews. Suggestions cannot be applied on multi-line comments. Suggestions cannot be applied while the pull request is queued to merge. Suggestion cannot be applied right now. Please check back later.
atomic_xorto use a CAS loop instead of atomic builtin. This is needed to merge this in UR [HIP] Revert add prefetch for USM hip allocations a6b8fa66b537753415d24076f… oneapi-src/unified-runtime#936 so that perf regression can be fixed. The long term fix is to use a compiler flag to choose between builtin and safe CAS implementation, but talks upstream may take some time to figure out the details. See [AMDGPU] Add an option to disable unsafe uses of atomic xor llvm/llvm-project#69229