You are viewing a plain text version of this content. The canonical link for it is here.

Posted to commits@mxnet.apache.org by GitBox <gi...@apache.org> on 2019/08/25 17:26:41 UTC

[GitHub] [incubator-mxnet] mahmoodn opened a new issue #16001: Low kernel performance

mahmoodn opened a new issue #16001: Low kernel performance
URL: https://github.com/apache/incubator-mxnet/issues/16001
 
 
   I have profiled the latest git version on 1080ti and see that there is kernel named "mshadow::cuda::AddTakeGradKernel` which is really slow. The achieved occupancy is 0.031 and the executed IPC is 0.064.
   I haven't seen this kernel to be in the top used kernel list before (I mean the version I used 6 months ago). I also see this [issue](https://github.com/apache/incubator-mxnet/issues/2612) which is dated on 2016.
   
   Any idea? What is the purpose of that kernel? I tested cnn text classification example.

----------------------------------------------------------------
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:
users@infra.apache.org


With regards,
Apache Git Services