FBGEMM redesign parallelism for small B

redesign parallelism for small B

Open brad-mengchi opened this issue 1 year ago • 5 comments

Summary: As titled, redesign for small B (1< B < 64) and small T (T<=320) case, since current implementation only benefits large B * T.

Differential Revision: D54270887

Feb 28 '24 07:02 brad-mengchi

This pull request was exported from Phabricator. Differential Revision: D54270887

Feb 28 '24 07:02 facebook-github-bot

Name	Link
Latest commit	3dc6a4be86cdcf949d916f2d1affaa3bcc1f4b7b
Latest deploy log	https://app.netlify.com/sites/pytorch-fbgemm-docs/deploys/65df6b5aa40ccb0007ab68e6
Deploy Preview	https://deploy-preview-2365--pytorch-fbgemm-docs.netlify.app
Preview on mobile	Toggle QR Code... Use your smartphone camera to open QR code link.

To edit notification comments on pull requests, go to your Netlify site configuration.

Feb 28 '24 07:02 netlify[bot]

This pull request was exported from Phabricator. Differential Revision: D54270887

Feb 28 '24 17:02 facebook-github-bot

This pull request was exported from Phabricator. Differential Revision: D54270887

Feb 28 '24 17:02 facebook-github-bot

This pull request was exported from Phabricator. Differential Revision: D54270887

Feb 28 '24 17:02 facebook-github-bot