OpenMathLib / OpenMathLib/OpenBLAS

SGEMM performance opportunity on POWER8 VSX

Open
#950 1 comment 0 reactions 1 assignee View on GitHub

@xianyi is already working on this.

Since Sep 15, 2016.

Dominant language
C
Stars
7.6k
Forks
1.7k
Avg merge
1d 3h
Merged PRs (30d)
42

Description

SGEMM performance on POWER8 VSX has some opportunities for improvement.

For cblas_sgemm_googlenet,

M = 192, N = 3136, K = 576 shows the slowest performance
and
M = 320, N = 196, K = 1440 seems to have the greatest opportunity for improvement

cblas_sgemm_googlenet.cpp.txt

For cblas_sgemm_vggnet,

M = 256, N = 3136, K = 2304 shows the slowest performance
and
M = 512, N = 196, K = 4680 seems to have the greatest opportunity for improvement

cblas_sgemm_vggnet.cpp.txt

relative to alternate optimized BLAS implementations.

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.