Announcement

Collapse
No announcement yet.

AMD R600 Gallium3D Optimizing Back-End Merged

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

  • #16
    I've done some ad-hoc comparisons with WebGL demos from the "chrome experiments" site, and R600_DEBUG=sb gives me a solid 50-60% FPS boost with demos that use heavy-weight shaders (blur, raytracing, etc.). Very nice. The Unity dash blur also seems to be noticeably faster.

    Looking at the statistics (R600_DEBUG=sb,sbstat) this does not surprise - r600-sb optimizations in many cases brutally reduce the length of the shader program, the number of GPRs used and the number of ALU operations. I haven't noticed any bugs yet.
    Last edited by brent; 05-01-2013, 10:24 AM.

    Comment


    • #17
      Originally posted by pingufunkybeat View Post
      This is the patchset which brings Unigine Heaven to Windows 7 performance.

      Things just keep getting better and better!

      And to think that OpenCL is making progress and that the PM code has already been written and is awaiting release.... W00t w00t!
      THIS. IS. AMAZING!

      Congrats AMD and every developer involved!

      The PM is really one big cons of the FOSS driver atm, let's hope it turns out as good as fglrx so I and many people can say a final goodbye to closed drivers.
      Last edited by Azultra; 05-01-2013, 12:20 PM.

      Comment


      • #18
        Looks more likely I'll switch back to the OSS drivers for my 4670 card. Waiting for the benchmarks from Michael to make my decision.

        Now we just need better opengl compliance and power managements and then the OSS drivers will be able to replace fglrx for the majority of users.

        Comment


        • #19
          Hit a few snags trying to build it, so no test results from me today.

          @gururise

          The difference for your 4670 is 3.1 vs 3.3, or mainly geometry shaders - hardly an often used feature.

          Comment


          • #20
            Wow, Vadim replied in less than an hour, fast customer service that

            It built now, but the results are pretty bad on my RV710 (HD 4350).

            glxgears has wrong output:

            Also some of my private apps regressed badly, 28 -> 7 fps, visual errors, and a pegged cpu core.

            Comment


            • #21
              Originally posted by curaga View Post
              Wow, Vadim replied in less than an hour, fast customer service that

              It built now, but the results are pretty bad on my RV710 (HD 4350).

              glxgears has wrong output:

              Also some of my private apps regressed badly, 28 -> 7 fps, visual errors, and a pegged cpu core.
              Good catch, Lauri...

              Comment


              • #22
                Originally posted by Drago View Post
                Good catch, Lauri...
                Looks like it's been fixed now - newer GCC was zeroing out certain structs on creation, but that wasn't guaranteed behavior and apparently it wasn't happening on whatever old gcc version he tried it with.

                Comment


                • #23
                  The SB fixes aren't yet merged. The one I sent, for the shader key, is an unrelated fix.

                  Comment


                  • #24
                    Did you do any tests on optimizer? I am eager to know how close r600g is to catalyst.

                    Comment


                    • #25
                      Yes, but only against r600g, I don't run catalyst. The mentioned app went to 32 fps, from 28. Haven't tested other things.

                      Comment


                      • #26
                        Originally posted by curaga View Post
                        The SB fixes aren't yet merged. The one I sent, for the shader key, is an unrelated fix.
                        I was referring to this commit, which I thought was the fix, not your shader key commit.

                        http://cgit.freedesktop.org/mesa/mes...af805909712d88

                        Comment


                        • #27
                          Where new tests by Michael?

                          Comment


                          • #28
                            It might be a bit early for benchmarks. The code has just been merged and there have been quite a few bugs in the initial code drop. The most serious ones are fixed already, though.

                            Comment


                            • #29
                              Originally posted by brent View Post
                              It might be a bit early for benchmarks. The code has just been merged and there have been quite a few bugs in the initial code drop. The most serious ones are fixed already, though.
                              They will be test only speed.

                              Comment

                              Working...
                              X