Announcement

Collapse
No announcement yet.

Radeon Gallium3D Is Running Increasingly Well Against AMD's Catalyst Driver

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

  • #31
    Originally posted by verde View Post
    In real life is performing about 30% of the Catalyst performance and 10% of Catalyst rendering quality. There are missing textures, flickering etc in the most Steam games.
    Xonotic is a dream now? I'm sure I've played it in real life.

    The game developer is often to blame, writing their software for NVIDIA too often.

    Comment


    • #32
      What ever happened to HyperZ? Are there plans to get it fixed so it can be re-enabled by default? I know it's a bit undermanned and priorities must unfortunately be made, but the speed up would be amazing.

      Comment


      • #33
        Originally posted by verde View Post
        In real life is performing about 30% of the Catalyst performance and 10% of Catalyst rendering quality. There are missing textures, flickering etc in the most Steam games.
        I found the opposite. Oh sure, my fps was higher, but it was all jittery.

        Comment


        • #34
          Originally posted by curaga View Post
          Uhm, the vliw difference only really affects the shaders. Which OA 0.8.5 doesn't use. Look at Xonotic and Nexuiz.
          Then that means Vadim optimized SB backend for 6870 and other VLIW5 hardware, but not for 6950, etc... So it is in similar situation like GCNs which some months ago all perform slower then 6870, but not today.

          That also may mean VLIW4 might work better with llvm then , but i don't really know - don't have a hardware .

          Mabye VM implementation for VLIW4, like for GCNs in kernel 3.16 can make it fly .
          Last edited by dungeon; 07 August 2014, 03:42 AM.

          Comment


          • #35
            Originally posted by sireangelus View Post
            Michael, with all my kindness, you added frame time, you changed the graph but you are still unable to present it in a way that makes sense.
            Frame time measurement is taken to look for "spikes" that might make you lag during gaming. As in, the variance between the average frame time and a frame that took a very long time to render, and how much does this happen during the test.
            ? The box plot has this information. It may not be as intuitive, but you can learn to read it pretty fast.

            Comment


            • #36
              Originally posted by curaga View Post
              ? The box plot has this information. It may not be as intuitive, but you can learn to read it pretty fast.
              yeah, good explanation here: http://en.wikipedia.org/wiki/Boxplot

              Comment

              Working...
              X