Announcement

Collapse
No announcement yet.

AMD's Radeon Gallium3D Starts Posing A Threat To Catalyst

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

  • #11
    It would be nice to see where the APU performance is at. I have a laptop with an E-350 and abandoning Catalyst seems to be a more interesting proposition every day -- especially if/when the VDPAU Hi10P support gets merged.

    Comment


    • #12
      Originally posted by [Knuckles] View Post
      It would be nice to see where the APU performance is at. I have a laptop with an E-350 and abandoning Catalyst seems to be a more interesting proposition every day -- especially if/when the VDPAU Hi10P support gets merged.
      I get max 30% of the performance with radeon drivers and A10-5800k. Tried it several times - it's just unusable. I have no clue what i am doing wrong!

      Comment


      • #13
        Originally posted by brosis View Post
        Thats what Greg Kroah-Hartman thinks about it: http://youtu.be/L2SED6sewRw?t=34m10s

        AMD is doing the right thing with opensource driver and its going to get them more customers and save more costs.
        Holy $%!7, did anyone catch gkh's comments about window's driver development (it's around 39:35 in the above video)? They apparently don't have a stable internal api either. There goes the annoying criticism of linux that if only it would keep its internal api stable like windows

        Comment


        • #14
          Originally posted by jrch2k8 View Post
          well maybe you are blaming AMD for a crappy motherboard bios, as far i tested every 4000 - 7000 series card i have UVD works peachy including the 4350 and 4250
          I can confirm that RS780/880 UVD support does not work (I own both) and is also not supported according to [1].
          Would be very happy to see some work in that direction again, although I know very well that better 3D performance of the newer chips is probably higher priority. At least an update of the status of UVD on RS780/880 would be nice.

          [1] http://xorg.freedesktop.org/wiki/RadeonFeature/#4

          Comment


          • #15
            Originally posted by Vim_User View Post
            As long as things like UVD on RS780/880 don't work the FOSS driver will at least on part of my machines never be a threat to the blob.
            I agree. I have a RS880 based laptop and still no UVD unfortunately, it really kills the whole experience.

            Originally posted by jrch2k8
            well maybe you are blaming AMD for a crappy motherboard bios, as far i tested every 4000 - 7000 series card i have UVD works peachy including the 4350 and 4250
            How exactly do you have UVD on those chips using the open source r600g drivers? As far as I know the support is not yet included or even implemented.

            Comment


            • #16
              Originally posted by Kemosabe View Post
              I get max 30% of the performance with radeon drivers and A10-5800k. Tried it several times - it's just unusable. I have no clue what i am doing wrong!
              You need a 3.11 or WIP 3.12 kernel and a boot option (radeon.dpm=1 IIRC) to enable DPM. If you have both of those and still not seeing decent performance then please post back.

              Originally posted by kmare View Post
              I agree. I have a RS880 based laptop and still no UVD unfortunately, it really kills the whole experience.
              How exactly do you have UVD on those chips using the open source r600g drivers? As far as I know the support is not yet included or even implemented.
              UVD is supported in the open drivers for more recent chips -- IIRC everything after rv10/730 is supported but rv770 and earlier (including all the IGPs) are not. The older UVD internals were sufficiently different in the areas which affect our ability to release open source support that we pretty much have to go through the whole review exercise a second time.
              Test signature

              Comment


              • #17
                Originally posted by BO$$
                Probably the final 5% will take 10 years since they will have to re-architecture everything. No way the amateur beginner programmers will be a match to the big corporation pros, unless of course the pros from the said corporations start helping them, like is the case for AMD. By themselves the FOSS community would have never gotten here.
                You must be really stupid. FLOSS driver has much less development power and was started much later compared to Catalyst, but it's nearly as fast as blob in those benchmarks. Furthermore, Big Corporations (tm) are part of FLOSS idiot.

                Comment


                • #18
                  I have the 6870. Using the 3.12 rc kernel. I would also like to add something that benchmarks don't show you, is how the catalyst driver also makes it much better to alt/tab and switch virtual desktop while playing games. Wine games now don't crash when I switch desktop. Dota2/l4d2/tf2 don't freeze while switching virtual desktop.
                  Tf2 doesn't have map rendering corruption on the open source drivers.
                  I'm getting constant 60fps on the valve games.

                  The open source drivers just give a much better experience.
                  The is no way in hell I'm going back to the closed source ones.

                  Good job AMD and the guys coding the open source driver.

                  Comment


                  • #19
                    good job

                    good job, finally some good drivers to amd/ati users, fglrx sucks.

                    they need improve radeonsi like this one, in my opinion is a lot more importante improve radeonsi than r600g, new apu will use radeonsi. maybe in summer we have radeon si with opengl 3.3 and good perfomance

                    Comment


                    • #20
                      Originally posted by Kemosabe View Post
                      I get max 30% of the performance with radeon drivers and A10-5800k. Tried it several times - it's just unusable. I have no clue what i am doing wrong!
                      You have APU.
                      We already had this case here.
                      I recommend you to read all the thread, even if its old.

                      So, DPM got enabled in 3.11 and should work good in 3.12-next. This means, 3.12 solve your APU thermal room problem NOW.
                      The rest - shader optimisations got enabled in MESA 9.13 by default. Current stable MESA is already 10.0.
                      And finally, you need to get 3.12-next to get the cpufreq ondemand governor fixed, or you need to manually find out and set its values.
                      Just read through this subforum and learn about it. As for me, I have AII630 on one of the machines - its here. My optimal values are 35% with 6 delay. Or just upgrade to 3.12.

                      Anyway, the best upgrading guides are: radeonhowto; and archlinux and gentoo linux corresponding radeon pages.
                      May the google be with you.
                      Last edited by brosis; 30 October 2013, 06:17 PM.

                      Comment

                      Working...
                      X