Announcement

Collapse
No announcement yet.

NVIDIA 375.10 vs. Linux 4.8 + Mesa 13.1-dev AMD GPU Benchmarks

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

  • #71
    I just want to point out (again) 0 people will play a game at 336fps, so therefore 0 people will find information in these benchmarks that they can actually use to there benefit. The bottlenecks experienced at 336 fps -will not- represent the bottlenecks experienced at framerates people actually play at. I understand that this forum is full of retards that think higher is better, but I promise you, you aren't seeing actual performance here.

    Comment


    • #72
      Originally posted by marek View Post

      I'm not. Well, I probably need more sleep.
      Yeah, sure, go to sleep. Cause that X thing will right itself in the meantime.
      Slacker...




      /s

      Comment


      • #73
        I can't believe a Radeon R9 Fury still can't beat a GeForce GTX 950 in games like Bioshock Infinite which has been out for years...

        Comment


        • #74
          Originally posted by duby229 View Post
          I just want to point out (again) 0 people will play a game at 336fps.
          I guess some will play it at 336 fps if there is some CPU bottleneck in particular area that is 10 times slower

          What actually matters there is lowest amount of fps you have to match target, so you can fire up FRTC at that... you see how i easy forgot that we don't have those features And really there are a lot enhancement non spec features for better user experience

          Or FreeSync, or even that shader cache or threaded GL... you name it, problem is as once you feel what smoothness is you start to consider that feature as essential

          That is how things works for average Joe... if he can't force AA modes, he consider driver as totaly unusable Just do not underestemate power of average Joe, he is not retard just because he can't bisect anything

          Comment


          • #75
            Originally posted by Xen0sys View Post
            I can't believe a Radeon R9 Fury still can't beat a GeForce GTX 950 in games like Bioshock Infinite which has been out for years...
            Micheals benchmarks of that card generally run slower than you will actually get. Additionally, he doesn't bother tweaking game or driver settings to get close to refresh rate, so the bottlenecks experienced by him will not be the same bottlenecks experienced by you.

            Comment


            • #76
              Originally posted by bug77 View Post
              Michael doesn't test it, but is everything in the video department supported in the open source stack as well (i.e. does it offer proper encoding/decoding acceleration, multi-monitor support)?
              We use the open source multimedia stack in the pro driver as well.

              Originally posted by Xen0sys View Post
              I can't believe a Radeon R9 Fury still can't beat a GeForce GTX 950 in games like Bioshock Infinite which has been out for years...
              Saying "950 is faster than Fury" is arguably over-dramatizing things when the game is obviously CPU-limited and all of the cards are faster than display refresh rate. Performance work so far has focused on getting the slowest games to run faster, not on winning 150 FPS vs 100 FPS benchmarks with specific games.
              Last edited by bridgman; 25 October 2016, 11:13 AM.
              Test signature

              Comment


              • #77
                Originally posted by duby229 View Post

                Micheals benchmarks of that card generally run slower than you will actually get. Additionally, he doesn't bother tweaking game or driver settings to get close to refresh rate, so the bottlenecks experienced by him will not be the same bottlenecks experienced by you.
                Close to refresh rate or not - playability is one thing and optimization is another. It's depressing that a powerful Fury has to go full swing on a game that a 950 can handle with little effort. Says a lot about driver efficiency.

                Comment


                • #78
                  Originally posted by bridgman View Post
                  Saying "950 is faster than Fury" is arguably over-dramatizing things when the game is obviously CPU-limited and all of the cards are faster than display refresh rate. Performance work so far has focused on getting the slowest games to run faster, not on winning 150 FPS vs 100 FPS benchmarks with specific games.
                  If it was CPU limited, all cards would be hit proportionately. Starting at the low end and bringing that up is great. I still wait for the day when the ceiling gets raised to where it should be.

                  I'm not over-dramatizing things. The results speak for themselves. An enthusiast level card gets shown up but an entry level card.

                  I hate NVIDIA and won't ever buy their cards - definitely an AMD fanboy - but the results are hit or miss depressing still. Makes it hard.
                  Last edited by Xen0sys; 25 October 2016, 11:17 AM.

                  Comment


                  • #79
                    Originally posted by bridgman View Post
                    We use the open source multimedia stack in the pro driver as well.
                    Which means multimedia/HTPC needs are covered by the open source driver. Good to know.

                    Comment


                    • #80
                      Originally posted by Xen0sys View Post
                      I can't believe a Radeon R9 Fury still can't beat a GeForce GTX 950 in games like Bioshock Infinite which has been out for years...
                      I think that main reason for difference there is that VP's eON pretty much depends on non-default nvidia driver variable

                      So without breaking news on Phoronix that threaded GL works on Gallium, do not expect something to change

                      Comment

                      Working...
                      X