Announcement

Collapse
No announcement yet.

AMD Catalyst vs. Linux 3.7 + Mesa 9.1-devel Gallium3D Performance

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

  • AMD Catalyst vs. Linux 3.7 + Mesa 9.1-devel Gallium3D Performance

    Phoronix: AMD Catalyst vs. Linux 3.7 + Mesa 9.1-devel Gallium3D Performance

    In this article is a large OpenGL performance comparison looking at the frame-rates in different Linux games for different AMD Radeon Linux graphics cards when running the stock Ubuntu 12.10 operating system (Mesa 9.0 + Linux 3.5), the Catalyst Linux driver (fglrx 9.0.2) as found in the Ubuntu Quantal archive, and then when running the very latest Radeon Git code: The Linux 3.7 kernel, Mesa 9.1-devel, and xf86-video-ati 7.0.99 Git.

    http://www.phoronix.com/vr.php?view=18184

  • #2
    Huge improvements all around, although still far from fglrx.

    Comment


    • #3
      Awesome! It's great to see xf86-video-ati make significant improvements in most tests. It's ~half as good as Catalyst in ~half the tests, which is great news indeed. Nice work, AMD devs. I'm eagerly awaiting the day the OSS drivers come within 80-90% performance of Catalyst on most cases and I can switch away from Catalyst 12.6 legacy.

      Comment


      • #4
        4+ years later, the open source driver still isn't mature.

        Comment


        • #5
          The worst benchmark results (Reaction Quake and Xonotic) are caused by inefficiency in TTM. 90% of all time is spent in TTM, which moves buffers between VRAM and RAM all the time like crazy, and 10% of time is spent on the rendering. At least we know where the problem is.

          Comment


          • #6
            Originally posted by marek View Post
            The worst benchmark results (Reaction Quake and Xonotic) are caused by inefficiency in TTM. 90% of all time is spent in TTM, which moves buffers between VRAM and RAM all the time like crazy, and 10% of time is spent on the rendering. At least we know where the problem is.
            So you have some defined test suite for performance? Can you recommend some PTS test ? Are such perf benchmarks beneficial for you? If not those what else can be tested?

            Comment


            • #7
              Originally posted by mark45 View Post
              4+ years later, the open source driver still isn't mature.
              Maturity can not be simplified only to performance.

              And other features *WOULD* be there if only *legal* department of AMD gave green light. AMD devs had (have?) all necessary patches.

              And 4y is too little to get serious performance (on pair with production that was tweaked and developed x0 of years).

              Comment


              • #8
                Originally posted by przemoli View Post
                So you have some defined test suite for performance? Can you recommend some PTS test ? Are such perf benchmarks beneficial for you? If not those what else can be tested?

                I'd imagine he's tracing.

                Comment


                • #9
                  Originally posted by przemoli View Post
                  Maturity can not be simplified only to performance.

                  And other features *WOULD* be there if only *legal* department of AMD gave green light. AMD devs had (have?) all necessary patches.

                  And 4y is too little to get serious performance (on pair with production that was tweaked and developed x0 of years).
                  bla-bla-bla. legal bla bla...

                  Marek said it's TTM.

                  Comment


                  • #10
                    Originally posted by F i L View Post
                    Awesome! It's great to see xf86-video-ati make significant improvements in most tests. It's ~half as good as Catalyst in ~half the tests, which is great news indeed. Nice work, AMD devs. I'm eagerly awaiting the day the OSS drivers come within 80-90% performance of Catalyst on most cases and I can switch away from Catalyst 12.6 legacy.
                    How sad.

                    AMD WAKE UP, OR YOU'LL DIE IN THE NEXT 2 YEARS CRUSHED BY NVIDIA AND INTEL. YOU KNOW WAY BETTER THAN ME HOW MUCH TRUTH THERE IS IN WHAT I JUST SAID.

                    Comment


                    • #11
                      Please test unigine heaven
                      ## VGA ##
                      AMD: X1950XTX, HD3870, HD5870
                      Intel: GMA45, HD3000 (Core i5 2500K)

                      Comment


                      • #12
                        Originally posted by przemoli View Post
                        So you have some defined test suite for performance? Can you recommend some PTS test ? Are such perf benchmarks beneficial for you? If not those what else can be tested?
                        I assess the performance based on Phoronix articles and some games I like to use for testing, I also sometimes run some well-known AAA games under Wine.

                        Comment


                        • #13
                          Progress is progress. My heartiest appreciation goes out to the devs.

                          Comment


                          • #14
                            Run the same tests on the same kernel. I'm betting the proprietary driver stomps heavier. You could run it on Linux 3.6.6 against the 3.7 trunk and see how less impressive the open source driver is but you know that already.

                            Comment


                            • #15
                              Marc Driftmeyer the kernel actually has nothing (much) to do with the AMD proprietary drivers.

                              The later kernel is used in testing the OS driver because of the later kernel drivers.

                              Looking at the figures most of those games are more than playable on the OS driver.

                              Comment

                              Working...
                              X