Announcement

Collapse
No announcement yet.

Radeon HD 5000 Series Gallium3D Performance vs. Catalyst

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

  • Radeon HD 5000 Series Gallium3D Performance vs. Catalyst

    Phoronix: Radeon HD 5000 Series Gallium3D Performance vs. Catalyst

    Earlier this week I delivered results showing the AMD Radeon HD 6000 open-source driver becoming more competitive against the proprietary AMD Catalyst driver. The Gallium3D driver is still far from reigning supreme in most aspects that concern desktop Linux users, but much progress has been made in recent months. For those HD 5000 series graphics card owners, here are similar open-source driver vs. AMD Catalyst OpenGL Linux performance tests.

    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
    Enabling the shader optimization probably could've pushed R600 to be just as fast as Catalyst for the close tests and prob 75% of the way to catalyst for the the bigger gaps
    All opinions are my own not those of my employer if you know who they are.

    Comment


    • #3
      That is: with no 3D bugs and with the chance to use kwin_gles instead of kwin, boosting enormously CPU idle times. Can you make a battery life comparison? I think Catalyst may have an edge still, but not a significant one.

      Comment


      • #4
        I think the important thing to note is that every one of these tests showed very playable frame-rates. That is an accomplishment in of itself for R600g.

        Comment


        • #5
          Comercial Games?

          It's nice to see how close the performance is betwixt the Open Source Drivers and the Close Source drivers with Open Source games, but it would be also nice to see more Comercially available games being compared like L4D2, or Metro Last Light (when it comes out for linux). now understandably most of us using older video cards maybe dont play that much anymore or we play older games, like Doom 3 that would also be a nice addition to the Bench table.

          I know that the mentality is that we all should be able to reproduce the results on our machines using Phoronix Benchmark hence why there might not be comercial games support for it, but I trust in your results, and from time to time it would be nice to see these games being benched

          Comment


          • #6
            On my system (AMD E-450, Fedora 19 with updates, r600g stock, kernel 3.11rc6 with DPM and SB shaders), Bastion and Half Life 1 run beautifully, and also Superbrothers Sword & Sorcery. DotA hangs, but was unplayable in Windows anyway, so, it doesn't matter.

            Comment


            • #7
              The rest of the platform was left stock, including not forcing the R600 SB back-end, but separate Phoronix articles will deliver the shader optimization back-end benchmarks especially now that it looks like it could soon be enabled by default.
              Yes!

              Even without them the results are pretty impressive, although it's be super nice if we could get more shader intensive benchmarks in the coming articles

              Comment


              • #8
                Taraaam!

                Originally posted by Ericg View Post
                Enabling the shader optimization probably could've pushed R600 to be just as fast as Catalyst for the close tests and prob 75% of the way to catalyst for the the bigger gaps
                Shader optimizations?

                Comment


                • #9
                  Originally posted by kwahoo View Post
                  Wow! nice job

                  Comment


                  • #10
                    To be fair the Unigine benchmarks don't really work well on OSS drivers due to their OpenGL issues.

                    Comment

                    Working...
                    X