Announcement

Collapse
No announcement yet.

Using NVIDIA's VDPAU On Mobile Platforms

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

  • #16
    Originally posted by deanjo View Post
    Well once some android phones start coming out with Tegra it shouldn't be a problem.
    The hardware can handle this NOW. The problem is that the decoding is being done on the _wrong_ chip (or portion of it, if it's on one die).

    Comment


    • #17
      Just give me a portable android device running tegra using vdpau and a port of xbmc for the device and I would be in heaven, true 1080p output on the go with a awesome UI (which just cries for a touch interface). One thing I really like about XBMC right now is that you can use it for HD youtube playback utilizing vdpau.

      Comment


      • #18
        All these benchmark articles need to state what test data (ie, what video file) they're using. And none of the graphs are labeled on the x-axis. I assume it's time in the video, but who can be sure if it's not stated?

        Comment


        • #19
          Originally posted by ethana2 View Post
          Maybe it should say "Sorry, it appears you've mistaken this mobile for an N900. Dream on!."
          There, FTFY.

          Comment


          • #20
            Sorry, but these benchmarks are crap, for several reasons.

            First (*), using CPU-based decoding, the file does not play in realtime. No word about that in the article; it almost looks like the author failed to notice or understand it.
            The Atom 330 (not N330, which does not exist, by the way) is a dual-core w/ SMT and appears as 4 logical cores. This means 25% CPU load in the graph represent full load on one core. The other cores are not used at all - MPlayer is single-threaded.

            Second, hardware accelerated colorspace conversion should be activated when gl2 is used for best results. The suboption "yuv=2" does that.

            Third, knowing (*) it doesn't make sense to compare power consumption.

            Fourth, the sample is very low on bitrate. Please use a somewhat more demanding sample. Try this, for example: http://www.stfcc.org/misc/SAMPLE-Clo...264-CtrlHD.mkv

            Comment


            • #21
              Originally posted by brent View Post
              Sorry, but these benchmarks are crap, for several reasons.

              First (*), using CPU-based decoding, the file does not play in realtime. No word about that in the article; it almost looks like the author failed to notice or understand it.
              The Atom 330 (not N330, which does not exist, by the way) is a dual-core w/ SMT and appears as 4 logical cores. This means 25% CPU load in the graph represent full load on one core. The other cores are not used at all - MPlayer is single-threaded.

              Second, hardware accelerated colorspace conversion should be activated when gl2 is used for best results. The suboption "yuv=2" does that.

              Third, knowing (*) it doesn't make sense to compare power consumption.

              Fourth, the sample is very low on bitrate. Please use a somewhat more demanding sample. Try this, for example: http://www.stfcc.org/misc/SAMPLE-Clo...264-CtrlHD.mkv
              There is a multithreaded mplayer .. your sample is not playable at all on a 2.66ghz core 2 duo but works fine on the same machine with mplayer-mt. (And I agree that the benchmark is a joke).

              Comment


              • #22
                Originally posted by brent View Post
                Fourth, the sample is very low on bitrate. Please use a somewhat more demanding sample. Try this, for example: http://www.stfcc.org/misc/SAMPLE-Clo...264-CtrlHD.mkv
                The cloverfield sample is technically illegal in the US (and other countries) and can't be legally redistributed without consent of the studio. Even use of the clip can be illegal as well. It's a great clip to test but falls well outside "safe and legal" sources.

                Comment


                • #23
                  Originally posted by Dragoran View Post
                  There is a multithreaded mplayer
                  Yes... but it's not usable in mainline MPlayer svn, only git, and obviously wasn't used in this benchmark.

                  Comment


                  • #24
                    It is really easy to get mplayer-mt, i have got one script for this to demonstrate how to do that.

                    Comment


                    • #25
                      Originally posted by Kano View Post
                      It is really easy to get mplayer-mt, i have got one script for this to demonstrate how to do that.
                      Kano, your tagline should be changed to "Scriptmaster". Don't deny your dentistry! No matter what the issue is, you always have a script ready to use.

                      Comment


                      • #26
                        Originally posted by BlackStar View Post
                        Kano, your tagline should be changed to "Scriptmaster". Don't deny your dentistry! No matter what the issue is, you always have a script ready to use.
                        I think you mean "destiny" not "dentistry." :-)

                        By the way, that video is very resource-intensive. It slows down when playing with VDPAU on my 8600mGT. (The CPU usage is only 5-6%, though.)

                        Comment


                        • #27
                          Originally posted by thefirstm
                          I think you mean "destiny" not "dentistry." :-)
                          Nope, that was on purpose.

                          Comment

                          Working...
                          X