Announcement

Collapse
No announcement yet.

RV670 Benchmark: KMS vs UMS vs KMS w/o vsync

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

  • RV670 Benchmark: KMS vs UMS vs KMS w/o vsync
















    Download in .ods format


    world of padman
    KMS http://global.phoronix-test-suite.co...13-27365-20812
    UMS http://global.phoronix-test-suite.co...859-22133-6469
    KMS (w/o vsync) http://global.phoronix-test-suite.co...68-31208-13312

    nexuiz
    KMS http://global.phoronix-test-suite.co...6129-21156-461
    UMS too slow to bench
    KMS (w/o vsync) http://global.phoronix-test-suite.co...92-15535-15307

    ut2004
    KMS http://global.phoronix-test-suite.co...068-4177-23194
    UMS http://global.phoronix-test-suite.co...35-22734-26276
    KMS (w/o vsync) http://global.phoronix-test-suite.co...954-29578-5306

    Benchmarks with Obscene_CNN performance patches will follow
    ## VGA ##
    AMD: X1950XTX, HD3870, HD5870
    Intel: GMA45, HD3000 (Core i5 2500K)

  • #2
    I precise that disabling vline waiting for buffer swaps in the dri2 paths I saw no tearing but only icreased performance.

    By the way, here is the patch (KMS w/o vsync):
    Code:
    diff --git a/src/radeon_dri2.c b/src/radeon_dri2.c
    index 103972f..7ddcda0 100644
    --- a/src/radeon_dri2.c
    +++ b/src/radeon_dri2.c
    @@ -313,7 +313,7 @@ radeon_dri2_copy_region(DrawablePtr drawable,
         }
     
         vsync = info->accel_state->vsync;
    -    info->accel_state->vsync = TRUE;
    +    //info->accel_state->vsync = TRUE;
     
         (*gc->ops->CopyArea)(&src_pixmap->drawable, &dst_pixmap->drawable, gc,
                              0, 0, drawable->width, drawable->height, 0, 0);
    ## VGA ##
    AMD: X1950XTX, HD3870, HD5870
    Intel: GMA45, HD3000 (Core i5 2500K)

    Comment


    • #3
      Very nice, thanks for posting this.

      You never mentioned what hardware you were running this on, though.
      RV670, is that a 3850 or greater?

      Curious to see KMS outperforming UMS across the board, it's the opposite of what I've seen earlier...

      Could you post comparisons of gtkperf or some other 2d rendering benchmark too?

      Comment


      • #4
        Originally posted by Sadako View Post
        You never mentioned what hardware you were running this on, though.
        RV670, is that a 3850 or greater?
        Because you can see the hardware details in the global.phoronix-test-suite.com links
        RV670 is high-end R600, so 3850 or 3870. Mine is HD3870.

        Originally posted by Sadako View Post
        Curious to see KMS outperforming UMS across the board, it's the opposite of what I've seen earlier...
        UMS has a much higher max framerate, but also terrible slowdowns, so the average framerate is slower. Unfortunately PTS-2.4.1 prints only the average framerate
        Also, UMS has never performed well with my card. Particularly nexuiz which seems to use software rendering! I already filed bugs but no one ever answered...

        Originally posted by Sadako View Post
        Could you post comparisons of gtkperf or some other 2d rendering benchmark too?
        I already planned 2D benchmarks, but I'dd like to test Obscene_CNN performance patches before.
        I'm waiting for him to send me latest kernel patches against drm-radeon-testing and to fix the problems with the other patches.
        ## VGA ##
        AMD: X1950XTX, HD3870, HD5870
        Intel: GMA45, HD3000 (Core i5 2500K)

        Comment


        • #5
          F*CKING edit time :@

          Originally posted by Sadako View Post
          Curious to see KMS outperforming UMS across the board, it's the opposite of what I've seen earlier...
          Furthermore, phoronix benchmarks had always used a highly outdated graphic stack and in the meanwhile KMS paths improved.
          ## VGA ##
          AMD: X1950XTX, HD3870, HD5870
          Intel: GMA45, HD3000 (Core i5 2500K)

          Comment


          • #6
            Originally posted by darkbasic View Post
            F*CKING edit time :@


            Furthermore, phoronix benchmarks had always used a highly outdated graphic stack and in the meanwhile KMS paths improved.
            Dude, there's a difference between "highly outdated" and "current, non experimental". That "highly outdated" you refer to is what people use today.

            Comment


            • #7
              That's the problem with periods of rapid progress. Code from a few weeks ago *is* totally outdated

              Comment


              • #8
                Don't get me started again about the "Linux Driver Model"

                *The non-existent one.

                Comment


                • #9
                  Well, since they merged gpu recovery it doesn't matter for me: damn, I love it!
                  ## VGA ##
                  AMD: X1950XTX, HD3870, HD5870
                  Intel: GMA45, HD3000 (Core i5 2500K)

                  Comment


                  • #10
                    P.S.
                    I was starting to think about switching back to nvidia before gpu recovery was implemented
                    ## VGA ##
                    AMD: X1950XTX, HD3870, HD5870
                    Intel: GMA45, HD3000 (Core i5 2500K)

                    Comment


                    • #11
                      IMO for desktop compositing and video, Vsync is desired because we certainly wouldn't mind compiz or your favortie movie to be capped at 60 FPS would providing smooth animation. However when running intensive rendering programs we would like to leave the option of whether to enable or disable Vsync to the program or to the user.

                      So hope KMS guys can get rid of this hard coded Vsync and use some sort of flag to control its effectiveness, that would be blissful

                      Comment


                      • #12
                        Originally posted by FunkyRider View Post
                        So hope KMS guys can get rid of this hard coded Vsync and use some sort of flag to control its effectiveness
                        I agree.

                        [fucking character limit]
                        ## VGA ##
                        AMD: X1950XTX, HD3870, HD5870
                        Intel: GMA45, HD3000 (Core i5 2500K)

                        Comment


                        • #13
                          After 2 weeks:



                          From 31,78 fps to 25,73 fps.
                          The only explanation I can image is that some more effects work now.
                          ## VGA ##
                          AMD: X1950XTX, HD3870, HD5870
                          Intel: GMA45, HD3000 (Core i5 2500K)

                          Comment


                          • #14
                            Originally posted by darkbasic View Post
                            After 2 weeks:



                            From 31,78 fps to 25,73 fps.
                            The only explanation I can image is that some more effects work now.
                            Maybe you should update again. There was a big performance bug, that was fixed today: http://bugs.freedesktop.org/show_bug.cgi?id=27284

                            Comment


                            • #15
                              I already had this fix (I synced at 23:00), but I synced and benched again today: 25,67 FPS.
                              ## VGA ##
                              AMD: X1950XTX, HD3870, HD5870
                              Intel: GMA45, HD3000 (Core i5 2500K)

                              Comment

                              Working...
                              X