BF16 matmul from KernelBench working#145
Open
rengolin wants to merge 4 commits into
Open
Conversation
Performance is twice as F32, which is around 85% of peak, so good first step.
…mark from arguments
Member
Author
|
@adam-smnk some of the "automation" for schedules we discussed today. |
adam-smnk
approved these changes
May 13, 2026
Member
adam-smnk
left a comment
adam-smnk
left a comment
There was a problem hiding this comment.
Overall looks good 👍
Makes do with what we have today.
As we generalize and improve different schedules, we should see complexity shift from pipelines back into transforms and IR.
Member
There was a problem hiding this comment.
High-level question, how will this scale further to bf16 avx512 vs amx etc.?
adam-smnk
reviewed
May 13, 2026
| return kb_default_pipeline | ||
|
|
||
| # Level 1 matmuls should use the same pipelines | ||
| if kernel_name.startswith("level1") and "matrix_multiplication" in kernel_name: |
Member
There was a problem hiding this comment.
Some level1 kernels also just use _Matmul_ in their names. Not sure if you tested with these too.
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Performance is twice as F32, which is around 85% of peak, so good first step.