Announcement

Collapse
No announcement yet.

Nouveau With Boost Patches Are Now Competitive To Radeon/AMDGPU With RadeonSI

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

  • Nouveau With Boost Patches Are Now Competitive To Radeon/AMDGPU With RadeonSI

    Phoronix: Nouveau With Boost Patches Are Now Competitive To Radeon/AMDGPU With RadeonSI

    Last week I published benchmarks showing Nouveau's "boost" patches offering much performance potential compared to the current state of the open-source NVIDIA Linux graphics driver but generally still not enough performance to compete with NVIDIA's proprietary Linux graphics driver. I've since carried out some fresh open-source AMD Linux results for reference to see how the NVIDIA vs. AMD GPU open-source speeds are comparing.

    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
    That's actually pretty decent, seems like gaming on open source drivers is becoming perfectly viable, with more and more games supporting it as well. People who aren't running the heaviest games out there might be pretty content with open source drivers more often than not by now. If they have decent hardware.

    Comment


    • #3
      Originally posted by rabcor View Post
      That's actually pretty decent, seems like gaming on open source drivers is becoming perfectly viable, with more and more games supporting it as well. People who aren't running the heaviest games out there might be pretty content with open source drivers more often than not by now. If they have decent hardware.
      Agreed. Don't forget that the nouveau drivers are actually doing a pretty good job keeping up with mesa specs too. With a little more tweaking, I'd say the nouveau drivers might actually be a viable replacement to the closed source drivers (for some people). As of right now, the drivers are really only good enough for offices or generic home use.

      But until nouveau is fully up-to-spec (which doesn't actually seem that far away), it seems the closed source drivers are the better choice for gamers and workstations.

      Comment


      • #4
        s/nouveau/few card models with nouveau/

        Comment


        • #5
          At these insanely high resolutions, the games will be mainly limited by pixel fillrate, actually overshadowing the real driver performance differences. That's why the guys from Valve only showed benchmarks for very low resolutions; since the work to be done by the GPU was trivial, it really made the differences in driver overhead of OpenGL vs Vulkan shine.

          Comment


          • #6
            Originally posted by Ancurio View Post
            At these insanely high resolutions, the games will be mainly limited by pixel fillrate, actually overshadowing the real driver performance differences. That's why the guys from Valve only showed benchmarks for very low resolutions; since the work to be done by the GPU was trivial, it really made the differences in driver overhead of OpenGL vs Vulkan shine.

            ohh 3840x2160, 2560x1440 and 1920x1080 are "insanely high" for you? Then By that logic, "very low" is... 1680x1050?

            Comment


            • #7
              Originally posted by karolherbst View Post


              ohh 3840x2160, 2560x1440 and 1920x1080 are "insanely high" for you? Then By that logic, "very low" is... 1680x1050?
              I think Ancurio meant 4K as high and 1366x768 as very low. Since that's the spectrum I've observed for 99% of PC screens lately, I don't think it's that unreasonable.
              (If 4K is “insanely” high instead of just high is still a question, though …)

              Comment


              • #8
                Originally posted by CrystalGamma View Post

                I think Ancurio meant 4K as high and 1366x768 as very low. Since that's the spectrum I've observed for 99% of PC screens lately, I don't think it's that unreasonable.
                (If 4K is “insanely” high instead of just high is still a question, though …)
                Yeah right, but to stay a benchmark is garbage (and that's what he tries to pull), just because high resolutions were used, which are actually used, then he clearly just wants to try to find _any_ reasons why this benchmark is stupid and doesn't fit in his view of the world (most likely)
                Last edited by karolherbst; 20 April 2016, 01:49 PM.

                Comment


                • #9
                  Originally posted by karolherbst View Post
                  Yeah right, but to stay a benchmark is garbage (and that's what he tries to pull), just because high resolutions were used, which are actually used, then he clearly just wants to try to find _any_ reasons why this benchmark is stupid and doesn't fit in his view of the world (most likely)
                  I'm glad you're basing your argument purely on the exact words that Ancurio used instead of just making stuff up.

                  Comment


                  • #10
                    Originally posted by devius View Post

                    I'm glad you're basing your argument purely on the exact words that Ancurio used instead of just making stuff up.

                    I'm sorry :/ I know I overreact a bit, but this is just the feeling I get after reading his comment, because he totally misses the point. And is also wrong due some of those benchmarks don't even need a high fill rate and pixmark_piano is soley limited by shader processing speed.

                    Comment

                    Working...
                    X