Skip to content

[SYCL][NFC] Fix check-work-group-attributes-match.cpp for AMDGPU#22446

Merged
wenju-he merged 2 commits into
intel:sycl-webfrom
wenju-he:fix-CodeGenSYCL-check-work-group-attributes-match.cpp
Jun 26, 2026
Merged

[SYCL][NFC] Fix check-work-group-attributes-match.cpp for AMDGPU#22446
wenju-he merged 2 commits into
intel:sycl-webfrom
wenju-he:fix-CodeGenSYCL-check-work-group-attributes-match.cpp

Conversation

@wenju-he

Copy link
Copy Markdown
Contributor

b3ca5fb introduced amdgpu-flat-work-group-size attributes with per-kernel values, causing each kernel to get a distinct attribute group (#0, #2, #4) on amdgcn targets. Relax the attribute group checks from the hardcoded #0 to #{{[0-9]+}}.

Fixes CodeGenSYCL/check-work-group-attributes-match.cpp CMPLRLLVM-76303

b3ca5fb introduced amdgpu-flat-work-group-size attributes with
per-kernel values, causing each kernel to get a distinct attribute group
(#0, intel#2, intel#4) on amdgcn targets. Relax the attribute group checks from
the hardcoded #0 to #{{[0-9]+}}.

Fixes CodeGenSYCL/check-work-group-attributes-match.cpp
CMPLRLLVM-76303

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
@wenju-he wenju-he requested a review from a team as a code owner June 25, 2026 23:57
@wenju-he wenju-he merged commit c53885f into intel:sycl-web Jun 26, 2026
@wenju-he wenju-he deleted the fix-CodeGenSYCL-check-work-group-attributes-match.cpp branch June 26, 2026 03:18
wenju-he added a commit that referenced this pull request Jun 26, 2026
)

b3ca5fb introduced amdgpu-flat-work-group-size attributes with
per-kernel values, causing each kernel to get a distinct attribute group.

Fixes CodeGenSYCL/check-work-group-attributes-match.cpp
CMPLRLLVM-76303

---------

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
@bader

bader commented Jun 26, 2026

Copy link
Copy Markdown
Contributor

@wenju-he, SYCL doesn't support AMDGPU anymore. Do we need to maintain both b3ca5fb and c53885f changes in this repository?
It makes sense either to submit both to llvm-project or revert both and remove the test to simplify the maintanance.

@intel/dpcpp-cfe-reviewers, @tahonermann, what do you think?

@tahonermann

Copy link
Copy Markdown
Contributor

Since intel/llvm/dpclang is now being productized and beginning to be included in Linux distributions, I think caution is warranted with regard to discarding support for other vendor hardware. We might begin to see contributions outside of Intel as the SYCL ecosystem grows; which could be a considerable benefit to Intel. For that reason, I think it is worth putting minimal effort towards keeping what currently works working as a gesture of good will to the SYCL community. I don't think doing so conflicts with Intel's goals to prioritize support for its own products.

@wenju-he

Copy link
Copy Markdown
Contributor Author

will try to upstream #22452
Other fixes are lit tests that fail in pulldown. Removing amdgpu RUN lines should be done separately if needed, so it is the task from pulldown coordinator.

@wenju-he

Copy link
Copy Markdown
Contributor Author

so it is the task from pulldown coordinator.

sorry, I mean it is not the task from pulldown coordinator.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants