Results 1 to 2 of 2

Thread: Feature request: transfer bandwidth specification / priority

  1. #1
    Junior Member
    Join Date
    Apr 2012
    Posts
    2

    Feature request: transfer bandwidth specification / priority

    Hi,

    Let us assume that NVidia finally implements a working out-of-order queue, then the next step could be data transfer bandwidth specification.

    Why would you need this? Say you have an iterative process, which consist for a large part of first uploading the data to GPU (only transfer), and then processing it (99% computation, 1% transfer). If you have an out of order command queue, you could start transfer for the next iteration at some point during the computationally intensive part. However, if small chunks of data transfer need to occur during this time, you need either to have reserved bandwidth, or a priority-based data transfer system.

    That's pretty much my situation now. Still waiting on NVidia to do out-of-order right though...

  2. #2
    Junior Member
    Join Date
    Dec 2009
    Posts
    17

    Re: Feature request: transfer bandwidth specification / prio

    You probably want to put this is the "Suggestions for next release" forum.

Similar Threads

  1. New feature request : kernel parameters as 'static' !
    By polar01 in forum Suggestions for next release
    Replies: 1
    Last Post: 09-13-2011, 04:10 PM
  2. bandwidth test
    By matrem in forum OpenCL
    Replies: 5
    Last Post: 01-04-2010, 01:03 AM

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts
  •