Announcement

Collapse
No announcement yet.

There's Not Yet A Catalyst 15.4 Beta For Linux

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

  • There's Not Yet A Catalyst 15.4 Beta For Linux

    Phoronix: There's Not Yet A Catalyst 15.4 Beta For Linux

    Windows users this week saw the release of an AMD Catalyst 15.4 Beta driver, but if you're looking out for the equivalent Linux build, sadly it has yet to surface...

    Phoronix, Linux Hardware Reviews, Linux hardware benchmarks, Linux server benchmarks, Linux benchmarking, Desktop Linux, Linux performance, Open Source graphics, Linux How To, Ubuntu benchmarks, Ubuntu hardware, Phoronix Test Suite

  • #2
    oh, please... The main choice for AMD hardware since ~ kernel 3.13 is Radeon, the only reasons to use catalyst instead are if you really need that little extra performance, openGL 4.x support, or you have a GCN 1.2 card, and the latter two will be solved soon enough.

    Comment


    • #3
      Catalyst 15.3 Beta and the new 15.4 Beta for Windows are *still* only 14.12 Omega with a handful of bugfixes backported. So not much too see there anyway.

      Comment


      • #4
        The only real reason 15.4 beta was released for Windows was because GTA V came out. Big release...

        Comment


        • #5
          Originally posted by phoronix
          The only downside of the new stack is that it basically tosses all current AMD Linux Catalyst users under the bus since this new AMDGPU open and closed-source driver stack is only for the Radeon R9 285 and future Rx 300 series graphics processors, but not the existing GPUs. For there, with an infrequently updated Catalyst Linux driver, the main choice is becoming the open-source R600/RadeonSI stack, which is still evolving for providing faster performance, suitable compute/OpenCL/HSA options, and slowly but surely gaining OpenGL 4.x functionality.
          Note that AMD has been clear from the start that the R9 285 and upcoming Rx 300 generation will continue to be using the old fglrx stack.

          The plan is for them to do behind the scenes testing on that generation to get the AMDGPU kernel working, but users will still be using the old fglrx driver only. The switch for users will occur with the Rx 400 series (assuming it works out well).

          Comment


          • #6
            soon?

            Originally posted by Luke_Wolf View Post
            oh, please... The main choice for AMD hardware since ~ kernel 3.13 is Radeon, the only reasons to use catalyst instead are if you really need that little extra performance, openGL 4.x support, or you have a GCN 1.2 card, and the latter two will be solved soon enough.
            soon? years and years waiting for some good driver

            Comment


            • #7
              Originally posted by Luke_Wolf View Post
              oh, please... The main choice for AMD hardware since ~ kernel 3.13 is Radeon, the only reasons to use catalyst instead are if you really need that little extra performance, openGL 4.x support, or you have a GCN 1.2 card, and the latter two will be solved soon enough.
              You also need Catalyst for gpu folding on Linux, as far as I know Radeon isn't able to run FAH.
              Those who would give up Essential Liberty to purchase a little Temporary Safety,deserve neither Liberty nor Safety.
              Ben Franklin 1755

              Comment


              • #8
                Key point here IMO is that we are still adding support for new GPUs to Catalyst and plan to keep doing that until amdgpu+HSA can functionally replace the current Catalyst stack. It's a pain and I hate diverting resources from the new stack but I think we have to do it.
                Test signature

                Comment


                • #9
                  Originally posted by bridgman View Post
                  It's a pain and I hate diverting resources from the new stack but I think we have to do it.
                  At least you can give us hope there won't be two different Vulkan drivers.

                  Situation when Catalyst getting own implementation of thing like hardware video encode (won't say decode as there likely DRM crap) when it's already working and superior encode in FOSS driver just looks weird.
                  Last edited by SXX⁣; 15 April 2015, 11:43 PM.

                  Comment


                  • #10
                    Originally posted by SXX⁣ View Post
                    Situation when Catalyst getting own implementation of thing like hardware video encode (won't say decode as there likely DRM crap) when it's already working and superior encode in FOSS driver just looks weird.
                    Yeah, we're fixing that. And a few other things...
                    Test signature

                    Comment

                    Working...
                    X