Lxx/dev/gfx950 fwd v3 hd192x128 adjust dispatch #1718
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Contributor
There was a problem hiding this comment.
Pull request overview
This PR updates the dispatch logic for the GFX950 FMHA v3 forward kernel to handle the 192x128 head dimension configuration differently. The changes rename kernel identifiers from "hd192_hd128" to "hd192x128" and introduce special-case dispatch logic for this configuration.
- Renames kernel name strings from "hd192_hd128" to "hd192x128" for consistency
- Adds conditional dispatch logic to handle 192-dimension heads with different grid dimensions
- Forces tune_opt to 0 for the 192x128 configuration in both wrapper functions
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Comment on lines
+191
to
+194
| if (a.hdim_q == 192 && a.hdim_v == 128) | ||
| { | ||
| tune_opt = 0; | ||
| } |
There was a problem hiding this comment.
This logic is duplicated at lines 191-194 and 258-261. Consider extracting this into a helper function or consolidating the logic to avoid duplication.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Motivation
Technical Details
Test Plan
Test Result
Submission Checklist