Change multi-threading logic for SBGEMV to be the same as SGEMV. #4933
Conversation
This file contains 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
|
The failures don't seem to be related to my change since they are not BF16. |
right. that is fallout from yesrerday's pr merge that made the ctests raise sigabrt on failure. this uncovered a latent failure that makes little sense except as a compiler error (given that it affects the pure C mips64_generic target, and only the cblas version of the test) |
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Outdated suggestions cannot be applied.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.
The logic for threading SBGEMV was only using the size of the vector when determining whether or not to thread it.
This makes the logic the same as SGEMV (F32).
With 32 threads, I'm seeing a 4.9X improvement for SBGEMV.