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][E2E][Matrix] Restrict XFAIL in some tests to DG2 #17639

Merged
merged 5 commits into from
Mar 27, 2025

Conversation

sarnex
Copy link
Contributor

@sarnex sarnex commented Mar 25, 2025

XPASSing in nightly but failing in pre/postcommit, make them XFAIL only where they actually fail.

@sarnex sarnex temporarily deployed to WindowsCILock March 25, 2025 16:34 — with GitHub Actions Inactive
@sarnex sarnex temporarily deployed to WindowsCILock March 25, 2025 16:58 — with GitHub Actions Inactive
@sarnex sarnex temporarily deployed to WindowsCILock March 25, 2025 16:58 — with GitHub Actions Inactive
@sarnex sarnex marked this pull request as ready for review March 26, 2025 14:17
@sarnex sarnex requested a review from a team as a code owner March 26, 2025 14:17
@sarnex sarnex requested a review from YuriPlyakhin March 26, 2025 14:37
Copy link
Contributor

@YuriPlyakhin YuriPlyakhin left a comment

Choose a reason for hiding this comment

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

@sarnex , are they indeed failing in pre/post-commit? Or are they actually skipped because there is an XFAIL and multiple backends?
What if you just remove XFAIL. Probably, it will just pass in pre/post-commit.
Could you please try that?

Also, are we using different gpu driver versions in nightly and pre/post-commit?

Signed-off-by: Sarnie, Nick <[email protected]>
@sarnex
Copy link
Contributor Author

sarnex commented Mar 26, 2025

Driver should be the same, testing that now

@sarnex sarnex temporarily deployed to WindowsCILock March 26, 2025 16:07 — with GitHub Actions Inactive
Copy link
Contributor

@dkhaldi dkhaldi left a comment

Choose a reason for hiding this comment

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

LGTM

@YuriPlyakhin
Copy link
Contributor

Driver should be the same, testing that now

ok, based on testing results - passed on PVC, failed on DG2. Hence, xfail needs to be there for 2 tests, but only for DG2 architecture, which makes sense to me (feature is implemented only for PVC/BMG for now).

Failed Tests (2):
  SYCL :: Matrix/SG32/joint_matrix_int8_colmajorA_colmajorB.cpp
  SYCL :: Matrix/joint_matrix_int8_colmajorA_colmajorB.cpp

Signed-off-by: Sarnie, Nick <[email protected]>
@sarnex
Copy link
Contributor Author

sarnex commented Mar 26, 2025

done

@sarnex sarnex temporarily deployed to WindowsCILock March 26, 2025 18:10 — with GitHub Actions Inactive
@YuriPlyakhin
Copy link
Contributor

@sarnex , you may want to update title/description, before merging. Thanks for taking care of it!

@sarnex sarnex changed the title [SYCL][E2E][Matrix] Move XPASSing tests in nightly to unsupported [SYCL][E2E][Matrix] Restrict XFAIL in some tests to DG2 Mar 26, 2025
@sarnex
Copy link
Contributor Author

sarnex commented Mar 26, 2025

Done, thx

@sarnex
Copy link
Contributor Author

sarnex commented Mar 26, 2025

@YuriPlyakhin They're failing on BMG

@YuriPlyakhin
Copy link
Contributor

@YuriPlyakhin They're failing on BMG

Then, pls, add || bmg to xfail for now. I guess we will need to investigate...

Signed-off-by: Sarnie, Nick <[email protected]>
@@ -18,7 +18,7 @@
// This tests support of col major layout for matrix B which does transpose and
// then VNNI transform. This is currently only available on AMX

// XFAIL: gpu
// XFAIL: gpu-intel-dg2 || arch-intel_gpu_bmg_g21
// XFAIL-TRACKER: GSD-5768
Copy link
Contributor

Choose a reason for hiding this comment

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

The BMG part is fine.
But for dg2, we need add:
"
// SG size = 32 is not currently supported for SYCL Joint Matrix by IGC on DG2
// UNSUPPORTED: gpu-intel-dg2
"

Copy link
Contributor Author

Choose a reason for hiding this comment

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

just pushed a new commit that should address this, thanks!

Signed-off-by: Sarnie, Nick <[email protected]>
@sarnex sarnex temporarily deployed to WindowsCILock March 27, 2025 15:52 — with GitHub Actions Inactive
@sarnex sarnex temporarily deployed to WindowsCILock March 27, 2025 16:05 — with GitHub Actions Inactive
@sarnex sarnex temporarily deployed to WindowsCILock March 27, 2025 16:05 — with GitHub Actions Inactive
@sarnex sarnex requested a review from dkhaldi March 27, 2025 16:35
@sarnex
Copy link
Contributor Author

sarnex commented Mar 27, 2025

Merging since nightly is broken, happy to address anything post-commit.

@sarnex sarnex merged commit 8fec832 into intel:sycl Mar 27, 2025
26 of 47 checks passed
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