Announcement

Collapse
No announcement yet.

The "Dirndl" On AMD Opterons Are Impressive

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

  • The "Dirndl" On AMD Opterons Are Impressive

    Phoronix: The "Dirndl" On AMD Opterons Are Impressive

    In regards to the impressive open-source launch I alluded to yesterday, I am told by a company representative that "the ball is rolling" and it's being pushed to go out today. Though based upon the time now, and that the press release is going out via PRNewsWire, I would guess it may not hit the wire until midnight (EST). Regardless, the Phoronix information exposing this project we've codenamed "Dirndl" is ready...

    http://www.phoronix.com/vr.php?view=OTU1MQ

  • #2
    Any chance of this having an impact on the performance of Mesa?

    Comment


    • #3
      Originally posted by allquixotic View Post
      Any chance of this having an impact on the performance of Mesa?
      Chances are it'll only affect CPU bound operations

      Comment


      • #4
        Originally posted by FireBurn View Post
        Chances are it'll only affect CPU bound operations
        Unless it's the GPGPU "CUDA-killer" compiler and not EKOPath.

        But enough of this. Speculating is a waste of time and effort. Wake me up when there's actually some news.

        Comment


        • #5
          Originally posted by allquixotic View Post
          Any chance of this having an impact on the performance of Mesa?
          That's what i'm hoping too. Btw. what compiler AMD and NVIDIA use to compile the blobs? GCC?

          Comment


          • #6
            Nice. Wondering if this can also speed up multimedia encoding and decoding, mplayer/ffmpeg/x264, etc.

            Comment


            • #7
              Originally posted by ahlaht View Post
              That's what i'm hoping too. Btw. what compiler AMD and NVIDIA use to compile the blobs? GCC?
              AFAIK Catalyst is compiled with gcc, not sure about nvidia, but probably also gcc.

              Comment


              • #8
                Ffmpeg

                I'm really curious as to how this would affect two things:

                1) FFMpeg
                2) MLT (used by Kdenlive to composite video effects)

                I recently started video editing on a similar rig (2x 2352's, same mobo that I bought after the phoronix review of the initial barcelona release), and while I'm fine editing SD video (10 effects on three layers, smooth as butter. scales to 8 cores real well), I would love some performance increase for when I do projects in HD.

                I suppose the implied wish here is for an MLT benchmark in the PTS, preferably with the frei0r plugins.

                Anyways, the improvement in floating point is mighty impressive, I'm excited.

                Comment


                • #9
                  I would like to see a comparison between that, gcc and Visual Studio's compiler for the same code.

                  Comment


                  • #10
                    Why don't you feel the need to tell your readers what's this all about? Why do you take it for granted everyone knows what you're talking about?

                    I have no idea what Dirndl is or what it is all about. If you have explained it before, put a link to that earlier article. If you haven't, put a link to an external source that explains it.

                    This is web journalism 101 and you miss it all the time.

                    Comment

                    Working...
                    X