Announcement

Collapse
No announcement yet.

VA-API Gets New H.264/MPEG-2 Encoding API Support

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

  • VA-API Gets New H.264/MPEG-2 Encoding API Support

    Phoronix: VA-API Gets New H.264/MPEG-2 Encoding API Support

    NVIDIA's proprietary driver and the open-source Gallium3D Linux graphics drivers -- namely now the open-source Radeon UVD support -- are using VDPAU as their accelerated video playback API. Meanwhile, Intel still continues to invest heavily in VA-API as their preferred video acceleration API for Linux. An exciting set of 42 patches to improve VA-API was published on Monday...

    http://www.phoronix.com/vr.php?view=MTM3MTU

  • #2
    Question:

    Will VA-API work be usefull for Android? Or is it for other userlands?

    Comment


    • #3
      Great

      How about H.265/HEVC, and VP9?

      Comment


      • #4
        I was under impression that one whom had Ivy,Sandy or newer Intel machine already had support for encoding though vaapi. I guess it must have not been previously merged or maybe to lesser extend or something.

        Anyway is there hi10p (10bit) hardware decoding on the horizon any time soon for any hardware out there?

        Comment


        • #5
          but now video encoding support is being spiced up by Intel to benefit their latest generations of Intel hardware running Linux.
          Is that related to Quick Sync support on Linux?

          Comment


          • #6
            Originally posted by YAFU View Post
            Is that related to Quick Sync support on Linux?
            Yea, that was my fist thought as well. Sounds quite likely. I wonder if FFmpeg will be able to make use of that. That would be pretty awesome.

            Comment


            • #7
              Originally posted by YAFU View Post
              Is that related to Quick Sync support on Linux?
              Yes, it IS QuickSync, but there is a lot of work to be done to allow software to use it.

              Comment


              • #8
                Originally posted by ryszardzonk View Post
                Anyway is there hi10p (10bit) hardware decoding on the horizon any time soon for any hardware out there?
                Nope .

                Comment


                • #9
                  Originally posted by TheLexMachine View Post
                  Yes, it IS QuickSync, but there is a lot of work to be done to allow software to use it.
                  And I guess there's even more work to be done until we have a Lucid-Virtu-like solution to engage Intel graphics or discrete cards on a per-application basis, which is what makes QuickSync really useful for professional work.

                  Anyway, I've been waiting for QuickSync to come to Linux for a long time, so this is great news.

                  Comment


                  • #10
                    Originally posted by Aleve Sicofante View Post
                    And I guess there's even more work to be done until we have a Lucid-Virtu-like solution to engage Intel graphics or discrete cards on a per-application basis, which is what makes QuickSync really useful for professional work.
                    I've always wanted to know why Bumblebee technology (or nvidia Optimus) is only available for Notebooks. Perhaps it could be adapted to Desktop machines and work as Lucid on Windows.

                    Comment


                    • #11
                      Originally posted by YAFU View Post
                      I've always wanted to know why Bumblebee technology (or nvidia Optimus) is only available for Notebooks. Perhaps it could be adapted to Desktop machines and work as Lucid on Windows.
                      You can already do it with desktop cards with provider stuff the latest X server. The question is why would you want it? If you have a faster card, just use it directly rather than having it render and copy the results to the slower card for display.

                      Comment


                      • #12
                        Originally posted by agd5f View Post
                        The question is why would you want it? If you have a faster card, just use it directly rather than having it render and copy the results to the slower card for display.
                        For the same reason that people find useful to use LucidVirtu on Windows. You could have the best of both GPU's at the same time, or when needed.

                        Comment


                        • #13
                          Originally posted by YAFU View Post
                          I've always wanted to know why Bumblebee technology (or nvidia Optimus) is only available for Notebooks. Perhaps it could be adapted to Desktop machines and work as Lucid on Windows.
                          Don't quote me for this, but I don't think they serve the same purpose. Is it Bumblebee/Optimus engaging on or the other graphics on a PER APPLICATION BASIS. My understanding was it selects the app automatically based on load.

                          Comment


                          • #14
                            Originally posted by agd5f View Post
                            You can already do it with desktop cards with provider stuff the latest X server. The question is why would you want it? If you have a faster card, just use it directly rather than having it render and copy the results to the slower card for display.
                            QuickSync is both faster and of higher quality when it comes to video encoding. It's a weird thing, I know, but even CUDA and OpenCL on discrete cards do a much worse job at that. So when you're going to encode video, you should use the integrated graphics, not the discrete ones.

                            How do you use one or the other graphics ON A PER APPLICATION BASIS "with provider stuff the latest X server"?

                            Comment


                            • #15
                              Originally posted by YAFU View Post
                              For the same reason that people find useful to use LucidVirtu on Windows. You could have the best of both GPU's at the same time, or when needed.
                              Nah, it's always beena bad idea, it only makes a little sense on laptops since pretty much all of Intel's mobile CPUs that are actually being used in mass production hardware have an IGP, thus they can switch off the dedicated GPU. having to pass off the render from the fast GPU to the IGP incurs increased power consumption and increased latency.

                              On a desktop however, you shouldn't be buying an IGP system if you need a fast GPU anyways. The fast GPUs have made huge strides in idle power consumption every generation, at least for AMD's GPUs. Nvidia's not so much...

                              Comment

                              Working...
                              X