Skip to content
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.

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

[SYCL] Implement device arch comparison according to sycl_ext_oneapi_device_architecture spec update #12752

Merged
merged 11 commits into from
Mar 6, 2024

Conversation

dm-vodopyanov
Copy link
Contributor

This patch implements device AOT and host APIs for device architecture comparison in accordance to spec update

…device_architecture spec update

This patch implements device AOT and host APIs for device architecture
comparison in accordance to [spec update](intel#12259)
@dm-vodopyanov
Copy link
Contributor Author

Adding @gmlueck as optional reviewer

@dm-vodopyanov
Copy link
Contributor Author

Failed Tests (1):
  SYCL :: Graph/RecordReplay/host_task_multiple_roots.cpp

Sporadic issue unrelated to this patch, #12759

Copy link
Contributor

@gmlueck gmlueck left a comment

Choose a reason for hiding this comment

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

Thanks for doing this!

I did not look at the implementation in depth, but I have a few questions below.

@dm-vodopyanov
Copy link
Contributor Author

@aelovikov-intel, @intel/llvm-reviewers-runtime: friendly ping

@dm-vodopyanov
Copy link
Contributor Author

@intel/llvm-reviewers-runtime, Andrei is on vacation, can someone review please?

Copy link
Contributor

@cperkinsintel cperkinsintel left a comment

Choose a reason for hiding this comment

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

nice to see the GMDID in the architecture enumeration! Awesome.

@dm-vodopyanov dm-vodopyanov merged commit 6844546 into intel:sycl Mar 6, 2024
12 checks passed
Comment on lines +674 to +679
#if __SYCL_TARGET_AMD_GPU_GFX90a__
return ext::oneapi::experimental::architecture::amd_gpu_gfx90a;
#endif
#if __SYCL_TARGET_AMD_GPU_GFX90c__
return ext::oneapi::experimental::architecture::amd_gpu_gfx90c;
#endif
Copy link
Contributor

Choose a reason for hiding this comment

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

@dm-vodopyanov shouldn't these have been __SYCL_TARGET_AMD_GPU_GFX90A__ and __SYCL_TARGET_AMD_GPU_GFX90C__ (note the uppercase A and C) to match the definitions above ?

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.

5 participants