Author Topic: OpenCL - when to use it? (help and benchmark oppose each other!)  (Read 50748 times)

ektorbarajas

  • Jr. Member
  • **
  • Posts: 45
    • View Profile
    • DJ ektorbarajas
Re: OpenCL - when to use it? (help and benchmark oppose each other!)
« Reply #330 on: October 31, 2013, 21:40:50 »
Hi. It has being a long time  :)

Just wanted to know if this minor issue has being corrected in the beta 1.9.0?

Regards

Admin

  • Administrator
  • Hero Member
  • *****
  • Posts: 664
    • View Profile
    • https://www.smilarityapp.com
Re: OpenCL - when to use it? (help and benchmark oppose each other!)
« Reply #331 on: November 04, 2013, 08:11:23 »
Thanks for reminder, we fixed help text:
Don’t turn on OpenCL acceleration if the results of OpenCL benchmark are longer in ms. than processor’s benchmark, because this will increase overhead costs due to increased expenses for data transfer to the OpenCL device.

ektorbarajas

  • Jr. Member
  • **
  • Posts: 45
    • View Profile
    • DJ ektorbarajas
Re: OpenCL - when to use it? (help and benchmark oppose each other!)
« Reply #332 on: November 04, 2013, 14:41:00 »
Great!!!

Kind regards

soylentgreen

  • Jr. Member
  • **
  • Posts: 4
    • View Profile
Re: OpenCL - when to use it? (help and benchmark oppose each other!)
« Reply #333 on: April 22, 2014, 14:42:23 »
Which would be better in this situation:

Work size= 64
CPU= 600ms
GPU= 74ms

Work size= 512
CPU= 700ms
GPU= 150ms

The 512 GPU is still much faster than CPU. So would 512 be faster than 64 in this case?

Admin

  • Administrator
  • Hero Member
  • *****
  • Posts: 664
    • View Profile
    • https://www.smilarityapp.com
Re: OpenCL - when to use it? (help and benchmark oppose each other!)
« Reply #334 on: April 22, 2014, 18:16:00 »
lower values is better.
use work size 64, work size is how much separate "threads/processes" run simultaneously, it doesn't directly related to performance, different devices have different optimum value. 512 doesn't mean better 64.