Optimized sgemv_t for small N based on AVX512#3260
Merged
martin-frbg merged 1 commit intoOpenMathLib:developfrom Jun 10, 2021
Merged
Optimized sgemv_t for small N based on AVX512#3260martin-frbg merged 1 commit intoOpenMathLib:developfrom
martin-frbg merged 1 commit intoOpenMathLib:developfrom
Conversation
Collaborator
|
Unfortunately there appears to be a problem with the sgemv_t microkernel for SkylakeX that you introduced with this PR, causing about 1060 failures in the LAPACK testsuite. Apologies for not catching this earlier, and I wonder if you could recheck your contribution ? Running |
Collaborator
|
Now fixed by guowangy's #3348 |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 patch is to optimized sgemv_t for N=1-8, as original algorithm would divied M and N no matter how big M and N is. This patch is to customize kernel for individual N size to get much better performance with vectorization .
The performance improvement is up to 8.16x per the verification on Cascade server