This repository has been archived by the owner on Aug 11, 2020. It is now read-only.
Improve batch gemm performance using MKL #342
Merged
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
|
@piiswrong @sxjscience please help take a review :) thanks in advance. |
sxjscience
reviewed
Jun 22, 2018
mshadow/dot_engine-inl.h
Outdated
| @@ -291,11 +292,48 @@ struct BLASEngine<cpu, float> { | |||
| const float *A, int lda, const float *B, int ldb, | |||
| float beta, float *C, int ldc, int batch_count, | |||
| float **workspace) { | |||
| #if MSHADOW_USE_MKL | |||
There was a problem hiding this comment.
Is cblas_sgemm_batch and cblas_dgemm_batch generally supported in MKL? Do we need to check the version?
There was a problem hiding this comment.
According to this page, Intel MKL 11.3 Beta (part of Intel® Parallel Studio XE 2016 Beta) includes a new flavor of GEMM feature called "Batch GEMM".
sxjscience
approved these changes
Jun 23, 2018
6 tasks
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.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 is to improve the performance of small size matrix batch gemm around 5-10x by using MKL. This optimization will be useful for attention layer in sockeye.
Performance comparison:
1000 loops
@pengzhao-intel