Results 1 to 3 of 3

Thread: Open CL speedup obtained is above 7000

  1. #1
    Newbie kuba15's Avatar
    Join Date
    Nov 2017
    Location
    Berlin, Germany
    Posts
    2

    Open CL speedup obtained is above 7000

    I have an OpenCL sequential program and a parallel program which consists of the same algorithm. I have got the execution time results as 133000 milliseconds for sequential and 17 milliseconds as the kernel time for parallel. So when I calculate the speed up that is 133000/17 i get 7823 as the speedup. Whether this much of speed up possible?

  2. #2
    Senior Member
    Join Date
    Apr 2015
    Posts
    292
    It is possible that your sequential program is poorly written and does not utlilize your CPU's resources. Or your kernel is simply wrong. But dependiing on the task, I don't see why not.
    Last edited by Salabar; 11-14-2017 at 03:27 AM.

  3. #3
    Junior Member
    Join Date
    Aug 2015
    Posts
    21
    it is not preferred to compare two independent implementations.

    however, comparing run-times between devices (CPU vs GPU) using the same OpenCL code, in most cases, is valid.

    in any case, such high speed up ratio is not common, before you get too excited, make sure the results are both correct, and the computation performed by both codes are comparable. otherwise, you are comparing apples with oranges.

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts
  •  
Proudly hosted by Digital Ocean