JAX FA Benchmarking Script

[Micky774]

Description

Please include a brief summary of the changes, relevant motivation and context.

Fixes # (issue)

Type of change

• Documentation change (change only to the documentation, either a fix or a new content)
• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• Infra/Build change
• Code refactoring

Changes

Please list the changes introduced in this PR:

• Change A
• Change B

Checklist:

• I have read and followed the contributing guidelines
• The functionality is complete
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• My changes generate no new warnings
• I have added tests that prove my fix is effective or that my feature works
• New and existing unit tests pass locally with my changes

[ipanfilo]

Why ck_fused_attn_bwd needs modification if the PR is for fwd-pass only?

[Micky774]

Note that I have added the BWD pass implementation as well to this PR.

[Micky774]

Pinging @wangye805 @wenchenvincent in case either of you are interested in reviewing this PR as well, thanks!

[wenchenvincent]

Have you compared the kernel time measured from CK FA API vs from rocprof?

[wenchenvincent]

Have you compared the kernel time measured from CK FA API vs from rocprof?

@Micky774 Could you follow up? Let's try to close this PR soon.

[Micky774]

@wenchenvincent just confirmed the timings reported match those recorded via rocprofv3. Anything else you'd like to see, or are we good to merge?