mahmoodn commented on issue #16001: Low kernel performance URL: https://github.com/apache/incubator-mxnet/issues/16001#issuecomment-526315273 Unfortunately, no... When I profile with no metric, I see the following kernel rankings where `AddTakeGradLargeBatchKernel` is on the top. https://pasteboard.co/IuYuGmA.png When I profile with `--metrics ipc`, I see that kernel goes to the second place. Also, the IPC is low on 1080ti. https://pasteboard.co/IuYudIO.png
---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services
