Announcement

Collapse
No announcement yet.

AMD GPU-PRO vs. NVIDIA Linux OpenCL Compute Performance

Collapse
X
 
  • Filter
  • Time
  • Show
Clear All
new posts

  • #31
    The good news is that (with a bit of luck) it should just take a tweak in the PTS file that wraps the test. Michael mentioned that he hadn't gone near the SHOC test for a while, so it was probably set up correctly at a time when GPUs were smaller and slower.

    The only catch is that there is maybe a 50:1 range between the fastest and slowest GPUs in use today so if the test is set up to give accurate results for the kind of GPUs that get tested regularly the runtime might be too long if Michael decides to write an epic "GPU compute performance over the last 10 years" article. I'm hoping that something like -s 4 -n 3 will be a good compromise.
    Last edited by bridgman; 03-25-2016, 07:19 PM.

    Comment


    • #32
      Originally posted by bridgman View Post
      The good news is that (with a bit of luck) it should just take a tweak in the PTS file that wraps the test. Michael mentioned that he hadn't gone near the SHOC test for a while, so it was probably set up correctly at a time when GPUs were smaller and slower.

      The only catch is that there is maybe a 50:1 range between the fastest and slowest GPUs in use today so if the test is set up to give accurate results for the kind of GPUs that get tested regularly the runtime might be too long if Michael decides to write an epic "GPU compute performance over the last 10 years" article. I'm hoping that something like -s 4 -n 3 will be a good compromise.
      It's just awesome how much effort you dedicate to communicating with the community.

      Definitely a big reason why I buy AMD .

      Comment


      • #33
        Thanks !

        Comment

        Working...
        X