Announcement

Collapse
No announcement yet.

Where An Open ATI Driver Beats The Catalyst Driver

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

  • Where An Open ATI Driver Beats The Catalyst Driver

    Phoronix: Where An Open ATI Driver Beats The Catalyst Driver

    A number of weeks back a set of benchmarks were published showing even the latest open-source ATI 3D driver is still no match to an old Catalyst driver and that even Gallium3D lags behind the Catalyst driver for those interested in OpenGL gaming. However, in other areas the open-source ATI driver stack is beginning to win by measurable amounts.

    http://www.phoronix.com/vr.php?view=15031

  • #2
    I believe it

    The high-definition playback of the open-source drivers has been fantastic for me using Ubuntu Lucid. It seems like it has improved a little every few months. I don't experience any of the tears and slowdowns I did before.

    Comment


    • #3
      I also like how the open source Radeon driver also has a higher resolution for the text modes. FGLRX looks like it uses 40x40 text cols. I feel like I'm starting a BBC Acorn Computer, not a modern linux system.

      Comment


      • #4
        When using the XvBA + VA-API combination for the proprietary Catalyst driver, the CPU usage had only fallen to 95%. Looking at the MPlayer output had shown that libva/VA-API was being used, but whether it's a bug in Catalyst 10.6
        I confirm this, on my ati hd4350 using fglrx 10.5 i experienced a considerable CPU reduction on 720p and 1080p h264 videos. Now with 10.6 it seems that video acceleration is not working correctly and I observe the same behaviour (no cpu usage reduction).

        Comment


        • #5
          Maybe you should have asked gb or me before doing that test or take a look at the description at the end of my script:

          http://kanotix.com/files/fix/mplayer-vaapi-latest.txt

          Please delete your test results and retest. You do NOT need to disable vdpau when you compile the vaapi patched mplayer, i never do that and it can be used easyly for comparision.

          Instead of -vc overrides (even for vdpau due to the used mplayer-vdpau.patch) you need to use

          VAAPI: -va vaapi -vo vaapi
          VDPAU: -va vdpau -vo vdpau
          XV: -vo xv

          When you do it correctly you might see wrong decoded h264 l5.1 files, but up to l4.1 it should work. You can test VC1 too, that has got no glitches.

          Comment


          • #6
            So the CPU spike while the GPU is busy too? My CPU usage gets no worse than 40% with a HD5770 framebuffer (no vid decode) with a downloaded matroska 720p vid on KDE4. It is a two year old AMD Phenom 9950 x4 non-OC.

            What the fsck... so how is GPU playback drawing less power?

            However someday I think the FLOSS ATI drivers will beat fglrx at anything except top speed.

            Comment


            • #7
              You should better look into the pts mplayer profile, then you know that only software decoding was benched.

              Comment


              • #8
                Originally posted by Kano View Post
                You should better look into the pts mplayer profile, then you know that only software decoding was benched.
                Ah, OK. I found it was a little strange

                Comment


                • #9
                  Originally posted by Kano View Post
                  Maybe you should have asked gb or me before doing that test or take a look at the description at the end of my script:
                  Kano, I suspect it is not a compilation problem, the mplayer I have compiled was working fine on fglrx 10.5 but not on 10.6. It is possible I screw up something, I normally use mplayer-mt and not the vaapi version. Let's see if more plp can share their experiences.

                  Comment


                  • #10
                    Originally posted by Jimbo View Post
                    Kano, I suspect it is not a compilation problem, the mplayer I have compiled was working fine on fglrx 10.5 but not on 10.6. It is possible I screw up something, I normally use mplayer-mt and not the vaapi version. Let's see if more plp can share their experiences.
                    It shouldn't be a compilation problem, but the main point of this article anyways as expressed is about the X-Video performance, which is clear.
                    Michael Larabel
                    http://www.michaellarabel.com/

                    Comment

                    Working...
                    X