[libspirv] Use generic atomic implementation for amdgcn-amd-amdhsa #21065
+11
−378
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
Previously implementation uses builtins (e.g. __builtin_amdgcn_flat_atomic_fmax_f64) which is only available in specific ISA, making amdgcn-amd-amdhsa libspirv dependent on overly strict target-cpu/target-features. Switching to generic implementation is portable and doesn't degrade quality. This PR also add some missing atomic builtins for amdgcn-amd-amdhsa, e.g. _Z18__spirv_AtomicLoadPU3AS1dii. This PR is a prep step for removing `-mcpu=gfx942` hack for amdgcn.
wenju-he
had a problem deploying
to
WindowsCILock
GitHub Actions
Error
wenju-he
temporarily deployed
to
WindowsCILock
GitHub Actions
Inactive
wenju-he
temporarily deployed
to
WindowsCILock
GitHub Actions
Inactive
wenju-he
temporarily deployed
to
WindowsCILock
GitHub Actions
Inactive
wenju-he
temporarily deployed
to
WindowsCILock
GitHub Actions
Inactive
wenju-he
temporarily deployed
to
WindowsCILock
GitHub Actions
Inactive
wenju-he
temporarily deployed
to
WindowsCILock
GitHub Actions
Inactive
wenju-he
temporarily deployed
to
WindowsCILock
GitHub Actions
Inactive
wenju-he
temporarily deployed
to
WindowsCILock
GitHub Actions
Inactive
wenju-he
temporarily deployed
to
WindowsCILock
GitHub Actions
Inactive
wenju-he
temporarily deployed
to
WindowsCILock
GitHub Actions
Inactive
wenju-he
temporarily deployed
to
WindowsCILock
GitHub Actions
Inactive
wenju-he
had a problem deploying
to
WindowsCILock
GitHub Actions
Failure
wenju-he
temporarily deployed
to
WindowsCILock
GitHub Actions
Inactive
bratpiorka
approved these changes
Jan 16, 2026
Contributor
Author
|
@intel/llvm-gatekeepers please merge, thanks |
wenju-he
temporarily deployed
to
WindowsCILock
GitHub Actions
Inactive
wenju-he
temporarily deployed
to
WindowsCILock
GitHub Actions
Inactive
wenju-he
temporarily deployed
to
WindowsCILock
GitHub Actions
Inactive
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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.
Previously implementation uses builtins (e.g. __builtin_amdgcn_flat_atomic_fmax_f64) which is only available in specific ISA, making amdgcn-amd-amdhsa libspirv dependent on overly strict target-cpu/target-features. Switching to generic implementation is portable and doesn't degrade quality.
fpAtomicFunc test in amdgpu_unsafe_atomics.cpp no longer mixes safe and unsafe atomics, so remove it.
This PR also add some missing atomic builtins for amdgcn-amd-amdhsa, e.g. _Z18__spirv_AtomicLoadPU3AS1dii.
This PR is a prep step for removing
-mcpu=gfx942hack for amdgcn.