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

Posted to dev@horn.apache.org by "Edward J. Yoon (JIRA)" <ji...@apache.org> on 2016/08/10 01:58:22 UTC

[jira] [Commented] (HORN-29) Support GPUs

    [ https://issues.apache.org/jira/browse/HORN-29?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15414592#comment-15414592 ] 

Edward J. Yoon commented on HORN-29:
------------------------------------

On my NVIDIA gpu machine, aparapi works greatly. I think this can be used for model averaging, batch normalization, and neuron computations.

$ ./print-devices 
platform 0: vendor 'NVIDIA Corporation'
  device 0: 'Tesla K80'
  device 1: 'Tesla K80'
  device 2: 'Tesla K80'
  device 3: 'Tesla K80'
  device 4: 'Tesla K80'
  device 5: 'Tesla K80'
  device 6: 'Tesla K80'
  device 7: 'Tesla K80'
  device 8: 'Tesla K80'
  device 9: 'Tesla K80'
  device 10: 'Tesla K80'
  device 11: 'Tesla K80'
  device 12: 'Tesla K80'
  device 13: 'Tesla K80'
  device 14: 'Tesla K80'
  device 15: 'Tesla K80'
$ bin/horn jar target/horn-0.1.0-SNAPSHOT.jar org.apache.horn.examples.GPUTest
Time taken for kenel execution in GPU mode is :15643
Time taken for kenel execution in Sequential CPU mode is :1476831


> Support GPUs 
> -------------
>
>                 Key: HORN-29
>                 URL: https://issues.apache.org/jira/browse/HORN-29
>             Project: Apache Horn
>          Issue Type: New Feature
>            Reporter: Edward J. Yoon
>            Assignee: Edward J. Yoon
>
> I'm testing GPUs using aparapi.



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)