Skip to content
This repository was archived by the owner on Mar 28, 2023. It is now read-only.

Set the row major store on B test to xfail on the GPU #1392

Merged
merged 2 commits into from
Dec 5, 2022

Conversation

dkhaldi
Copy link

@dkhaldi dkhaldi commented Nov 17, 2022

This test store the matrix B that is VNNIed (packed) in a row major fashion. This is expected to fail on the GPU because the implementation does not support automatic transformation YET, in this case: VNNI to row major in the store.

@dkhaldi dkhaldi requested a review from a team as a code owner November 17, 2022 15:31
@sergey-semenov
Copy link

@dkhaldi Could you please add a comment explaining the reason this is expected to fail?

@dkhaldi
Copy link
Author

dkhaldi commented Nov 18, 2022

@duanhanbing, can you please approve?

@dkhaldi
Copy link
Author

dkhaldi commented Nov 21, 2022

unrelated test SYCL :: KernelAndProgram/kernel-bundle-merge-options-env.cpp is failing on Windows.

@intel/llvm-reviewers-runtime, can you help review/merge this minor change?

@duanhanbing
Copy link

Hi, @dkhaldi , could you help answer @sergey-semenov 's question?

@sergey-semenov
Copy link

To clarify, I see the updated commit description, but I would prefer this to be reflected in a comment next to XFAIL as well.

@dkhaldi
Copy link
Author

dkhaldi commented Nov 22, 2022

To clarify, I see the updated commit description, but I would prefer this to be reflected in a comment next to XFAIL as well.

I see, let me add that. Thanks

@dkhaldi
Copy link
Author

dkhaldi commented Dec 3, 2022

@sergey-semenov can you please help merge? these are unrelated failures to this xfail addition.

@sergey-semenov sergey-semenov merged commit 909dc76 into intel:intel Dec 5, 2022
myler added a commit to myler/llvm-test-suite that referenced this pull request Mar 22, 2023
Auto pulldown and update tc files for xmain branch on 20221115
myler pushed a commit to myler/llvm-test-suite that referenced this pull request Mar 22, 2023
This test store the matrix B that is VNNIed (packed) in a row major fashion. This is expected to fail on the GPU because the implementation does not support automatic transformation YET, in this case: VNNI to row major in the store.
aelovikov-intel pushed a commit to aelovikov-intel/llvm that referenced this pull request Mar 27, 2023
…t-suite#1392)

This test store the matrix B that is VNNIed (packed) in a row major fashion. This is expected to fail on the GPU because the implementation does not support automatic transformation YET, in this case: VNNI to row major in the store.
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants