Announcement

Collapse
No announcement yet.

AMDGPU-PRO vs. Open-Source Gallium3D OpenGL Performance On Polaris Is A Very Tight Race

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

  • #41
    Originally posted by pal666 View Post
    that day will never come because mesa is not going to get compat profile support
    But why?

    Comment


    • #42
      Originally posted by Azpegath View Post

      You should post a bug on this issue, with all the relevant information you've gathered. I think there are quite a few performance issues that never get reported.
      I wouldn't worry about that since it's haagch i don't think there's many users (if any) that tests everything and files more bug reports the he does.
      What he does is great and now he seems to have an RX480 as well which is great but i still hope he will try things out on the old hardware as well since i liked to see how playable thing where on that hardware.

      Comment


      • #43
        Originally posted by pal666 View Post
        that day will never come because mesa is not going to get compat profile support
        It's a matter of interpretation.
        Catalyst is more or less dead but i can see that amdgpu-pro can still be called catalyst since it's less confusing.
        AMD is already letting mesa do there bidding and is the driver for most users the pro driver is for pro consumers the ones that needs compat profile support.
        A few can argue that there's no OpenCL2 or fully functional vulkan support with the mesa driver yet but the ones that needs it should be rather few and more of an special case until there's support for it with the non-pro driver.
        I still think that what i said is true.

        Comment


        • #44
          I want edit to come back.
          I think that the transition from catalyst to amdgpu is more then a new blob driver since i think it shows a new path for AMD with amdgpu for users and -pro for pro-consumers (not enthusiasts).

          Comment


          • #45
            Originally posted by faph View Post
            But why?
            Because no one should use compatibility profile with recent versions of OpenGL. It causes incompatibilities with drivers and there is no good reason to use it. It is not needed to play games either.
            Some extra information: https://www.opengl.org/wiki/Core_And...ty_in_Contexts

            Originally posted by Nille_kungen View Post
            I want edit to come back.
            Phoronix Premium users can edit their messages.
            Last edited by Tomin; 21 August 2016, 08:17 AM. Reason: Added an link

            Comment


            • #46
              Originally posted by Herem View Post
              Something else I noticed in the previous test results; the old Mesa graph shows the min / max to the left of each bar and the number to the right of each bar is clearly an average, whereas the New Mesa results only showed min. Is it possible the New Mesa results were displaying the maximum fps rather than the average fps? This would make the previous results more consistent with this article; however, it would also mean the New Mesa results from the previous article were only a small improvement, rather than the 40% performance improvement reported.
              No, it's all fully-automated from result collection to graphing... No manual intervention. (Nor any code changes in that area lately, so no regression possible either.)
              Michael Larabel
              https://www.michaellarabel.com/

              Comment


              • #47
                Originally posted by Nille_kungen View Post
                I wouldn't worry about that since it's haagch i don't think there's many users (if any) that tests everything and files more bug reports the he does.
                That's a depressing thought, because I really don't file that many. I just hope there are more dedicated people out there...

                Comment


                • #48
                  Impressive! Makes me wonder whether the investment on the closed-source AMDGPU part wouldn't have been better spent on the open-source Gallium-3D driver instead.

                  Or considering AMD's proprietary OpenGL driver isn't known for its high implementation quality, replacing it with the Gallium3D version across all supported platforums

                  Comment


                  • #49
                    Originally posted by Michael View Post

                    No, it's all fully-automated from result collection to graphing... No manual intervention. (Nor any code changes in that area lately, so no regression possible either.)
                    If there haven't been any code changes, do the latest set of Mesa results include the recent Bioshock performance patch? The latest results seem to have dropped from the previous article back to around the pre-patch values and in the case of the RX460 the results are significantly worse than either of the previous two sets of results?

                    Benchmark Average Frame Rate
                    RX460 Old Mesa 62.82
                    RX460 New Mesa 82.80
                    RX460 Latest Results 32.47

                    Would it be possible to observe the AMDGPU-PRO Bioshock benchmarks running on the R9 Fury to determine if the frame rate really is rock solid at close to the maximum value or if there's a problem with the way the results are being collected? A difference of only 0.32% between the maximum (82.38 fps) and the average (82.11 fps) results sounds much to low unless the frame rate has been capped.

                    Comment


                    • #50
                      Originally posted by Herem View Post

                      If there haven't been any code changes, do the latest set of Mesa results include the recent Bioshock performance patch? The latest results seem to have dropped from the previous article back to around the pre-patch values and in the case of the RX460 the results are significantly worse than either of the previous two sets of results?

                      Benchmark Average Frame Rate
                      RX460 Old Mesa 62.82
                      RX460 New Mesa 82.80
                      RX460 Latest Results 32.47

                      Would it be possible to observe the AMDGPU-PRO Bioshock benchmarks running on the R9 Fury to determine if the frame rate really is rock solid at close to the maximum value or if there's a problem with the way the results are being collected? A difference of only 0.32% between the maximum (82.38 fps) and the average (82.11 fps) results sounds much to low unless the frame rate has been capped.
                      This was with the latest Mesa Git as of like two days ago. There may be some regression on Linux 4.8 / Mesa Git, ran into another odd situation this morning with a R7 260X and will likely have an article out shortly about that.
                      Michael Larabel
                      https://www.michaellarabel.com/

                      Comment

                      Working...
                      X