Skip to content

Conversation

@evedovelli
Copy link
Contributor

Proposed changes

Enables hipTensor to access the WMMA HW functionalities for datatype FP16 + compute type FP16 and datatype BF16 + compute type BF16 on gfx11 and gfx12.

The low level implementation already existed, and this PR adds the interface to the WMMA functions to API used by hipTensor.

Checklist

  • I have added tests relevant to the introduced functionality, and the unit tests are passing locally
  • I have added the test to REGRESSION_TESTS list defined at the top of CMakeLists.txt in tests/CMakeLists.txt, IF the test takes more than 30 seconds to run.
  • I have added inline documentation which enables the maintainers with understanding the motivation
  • I have removed the stale documentation which is no longer relevant after this pull request
  • (If this change is user-facing) I have added release notes which provide the end users with a brief summary of the improvement from this pull request
  • I have run clang-format on all changed files
  • Any dependent changes have been merged

Enables hipTensor to access the WMMA HW functionalities
for these combinations of datatype on gfx11 and gfx12.
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.

2 participants