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

Port and run runtime tests #227

Merged
merged 1 commit into from
Jan 15, 2024
Merged

Conversation

whitneywhtsang
Copy link
Contributor

No description provided.

@whitneywhtsang whitneywhtsang self-assigned this Jan 10, 2024
@whitneywhtsang whitneywhtsang linked an issue Jan 10, 2024 that may be closed by this pull request
@pbchekin
Copy link
Contributor

@pbchekin https://github.com/intel/intel-xpu-backend-for-triton/actions/runs/7479468952/job/20356718182 didn't catch the yapf failure caught by https://github.com/intel/intel-xpu-backend-for-triton/actions/runs/7479468953.

I don't see anything reported by yapf in https://github.com/intel/intel-xpu-backend-for-triton/actions/runs/7479468953. Looks like yapf has crashed rather than worked normally and reported any changed files. A potential root cause for the yapf crash is race condition, see https://github.com/intel/intel-xpu-backend-for-triton/blob/llvm-target/.github/workflows/build_and_test_2.yaml#L51.

@whitneywhtsang
Copy link
Contributor Author

I don't see anything reported by yapf in https://github.com/intel/intel-xpu-backend-for-triton/actions/runs/7479468953. Looks like yapf has crashed rather than worked normally and reported any changed files. A potential root cause for the yapf crash is race condition, see https://github.com/intel/intel-xpu-backend-for-triton/blob/llvm-target/.github/workflows/build_and_test_2.yaml#L51.

yapf.....................................................................Failed
- hook id: yapf
- duration: 5.92s
- files were modified by this hook

And this is the file modification:

--- a/python/test/unit/runtime/test_autotuner.py
+++ b/python/test/unit/runtime/test_autotuner.py
@@ -7,6 +7,7 @@ import pytest
 # FIXME remove this once Triton L0 queue and IPEX SYCL queue can be synchronized through events
 torch.xpu.enable_sync_mode()
 
+
 def test_kwargs():
     N = 1024
     src = torch.empty(N, device='xpu')

@pbchekin
Copy link
Contributor

And this is the file modification:

Strange, but I do not see this modification in https://github.com/intel/intel-xpu-backend-for-triton/actions/runs/7479468953/job/20356717890. Anyway, good catch, should be fixed in #230.

@whitneywhtsang whitneywhtsang force-pushed the whitneywhtsang/runtime branch 3 times, most recently from 070a09d to 0869ef7 Compare January 12, 2024 15:06
@whitneywhtsang whitneywhtsang force-pushed the whitneywhtsang/runtime branch 3 times, most recently from 48a5ccf to 4c3a0d1 Compare January 12, 2024 16:07
Signed-off-by: Tsang, Whitney <[email protected]>
@whitneywhtsang whitneywhtsang merged commit fb7c841 into llvm-target Jan 15, 2024
2 of 3 checks passed
@whitneywhtsang whitneywhtsang deleted the whitneywhtsang/runtime branch January 15, 2024 02:45
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.

Port and run runtime tests
4 participants