Change matmul / kernel_bench tests to reuse CPU pipeline#140
Merged
Conversation
This PR moves all remaining schedules from CPU test `matmul.py` into their own schedules in Lighthouse, so they can be reused by the kernel_bench test for similar tests (L1, K1 & K2). The performance of `matmul.py` remains the same, while the perf for the Kernel Bench kernels has improved dramatically. This is only working for FP32 for now, so the BF16 tests in KB are still using the old (lower-to-loops) strategy. A follow up PR will fix the perf for BF16 and update the kernel bench testing to start tracking performance, just like `matmul.py`. assisted-by: GitHub Copilot
Member
Author
|
PS: Added some benchmarking facilities on a separate branch and getting 70~80% of the performance for |
adam-smnk
reviewed
May 12, 2026
adam-smnk
reviewed
May 12, 2026
Member
adam-smnk
left a comment
adam-smnk
left a comment
There was a problem hiding this comment.
Overall direction is good.
+1 for converging on schedules instead of transforms/both
-1 for finer details
This was referenced May 12, 2026
adam-smnk
reviewed
May 12, 2026
adam-smnk
approved these changes
May 12, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR moves all remaining schedules from CPU test
matmul.pyinto their own schedules in Lighthouse, so they can be reused by the kernel_bench test for similar tests (L1, K1 & K2).The performance of
matmul.pyremains the same, while the perf for the Kernel Bench kernels has improved dramatically.This is only working for FP32 for now, so the BF16 tests in KB are still using the old (lower-to-loops) strategy. A follow up PR will fix the perf for BF16 and update the kernel bench testing to start tracking performance, just like
matmul.py.Fixes #123
assisted-by: GitHub Copilot