Draft
Conversation
Collaborator
saleelk
reviewed
Mar 17, 2026
| uint g = __builtin_amdgcn_workgroup_id_x(); | ||
| ulong id = (g * 256 + l); | ||
|
|
||
| // Handle head, body and tail - each store in a separate warp to reduce divergence |
There was a problem hiding this comment.
Future HW could have 32 wavefront size, how does that affect the kernel perf?
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Currently we use three separate kernels to implement an unaligned memset operation. This kernel allows us to handle aligned and unaligned cases with one kernel and achieve better performance for the unaligned case, while maintaining aligned perf.
This has been tested inside HIP and will be wired into CLR in a seperate PR.
Unaligned results: