Skip to content

[libspirv] refactor generic atomic builtin to use CLC functions #21017

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Merged
uditagarwal97 merged 3 commits into from
Jan 15, 2026
Merged

[libspirv] refactor generic atomic builtin to use CLC functions #21017

uditagarwal97 merged 3 commits into from
Jan 15, 2026

Conversation

@wenju-he
Copy link
Contributor

@wenju-he wenju-he commented Jan 8, 2026 •
edited
Loading

Previous implementation uses outdated function e.g. __sync_val_compare_and_swap.
This automatically addd more variants of __spirv_AtomicIDecrement/AtomicIIncrement to libspirv-amdgcn--amdhsa.bc.

Test WorkGroupMemory/reduction_lambda.cpp now passes on native-cpu device.

@wenju-he
[libspirv] refactor generic atomic builtin to use CLC functions
f354f1f 
Previous implementation uses outdated function e.g. __sync_val_compare_and_swap.
@wenju-he wenju-he requested a review from a team as a code owner January 8, 2026 06:07
@wenju-he wenju-he requested a review from kfelskow January 8, 2026 06:07
@wenju-he wenju-he requested a review from a team as a code owner January 8, 2026 08:12
@wenju-he wenju-he requested a review from againull January 8, 2026 08:12
againull
againull approved these changes Jan 13, 2026
View reviewed changes
Copy link
Contributor

@againull againull left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

sycl/test-e2e/WorkGroupMemory/reduction_lambda.cpp change lgtm.

bader
bader requested changes Jan 15, 2026
View reviewed changes
Copy link
Contributor

@bader bader left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Add new __spirv_AtomicFlagClear and __spirv_AtomicFlagTestAndSet builtins. Add more variants of __spirv_AtomicIDecrement/AtomicIIncrement to libspirv-amdgcn--amdhsa.bc.

Test WorkGroupMemory/reduction_lambda.cpp now passes on native-cpu device.

This part seems to be unrelated to the refactoring. Let's open a separate PR with this change.

@wenju-he
Copy link
Contributor Author

wenju-he commented Jan 15, 2026

Add new __spirv_AtomicFlagClear and __spirv_AtomicFlagTestAndSet builtins. Add more variants of __spirv_AtomicIDecrement/AtomicIIncrement to libspirv-amdgcn--amdhsa.bc.
Test WorkGroupMemory/reduction_lambda.cpp now passes on native-cpu device.

This part seems to be unrelated to the refactoring. Let's open a separate PR with this change.

Removed Add new __spirv_AtomicFlagClear and __spirv_AtomicFlagTestAndSet builtins in 9e0d9ae

“Adding more variants of __spirv_AtomicIDecrement/AtomicIIncrement to libspirv-amdgcn--amdhsa.bc is an automatic outcome of the refactor, so separating it into its own PR isn’t practical.

The test WorkGroupMemory/reduction_lambda.cpp now unexpectedly passes with this PR, causing a CI failure. I'd like to keep the change so CI is green.

@wenju-he wenju-he requested a review from bader January 15, 2026 22:44
@wenju-he
Copy link
Contributor Author

wenju-he commented Jan 15, 2026

@intel/llvm-gatekeepers please merge, thanks

@uditagarwal97 uditagarwal97 merged commit 164f520 into intel:sycl Jan 15, 2026
28 checks passed
@uditagarwal97 uditagarwal97 mentioned this pull request Jan 15, 2026
Open
@wenju-he wenju-he deleted the libspirv-atomic-generic-refactor branch January 15, 2026 23:35
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@bader bader bader approved these changes

@bratpiorka bratpiorka bratpiorka approved these changes

@againull againull againull approved these changes

@kfelskow kfelskow Awaiting requested review from kfelskow kfelskow is a code owner automatically assigned from intel/llvm-reviewers-cuda

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

5 participants

@wenju-he @bader @bratpiorka @againull @uditagarwal97