Announcement

Collapse
No announcement yet.

4K AMD/NVIDIA High-End GPU Comparison On SteamOS Linux

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

  • #11
    So what was the CPU and GPU usage figures then Michael?. I guess you measure both whilst benching

    Could be interesting to see the difference with the Cat driver and NV in various games not just TF2

    Comment


    • #12
      Since when is a GTX 950 a high-end card?

      Comment


      • #13
        Originally posted by darkbasic View Post
        Are you serious when claiming that Haswell-E 1000$ CPU is the bottleneck? In that fucking single test amd cards are faster, period.
        Are you serious? Do you honestly think TF2 uses 16 threads? I never checked myself but I don't think that game would use beyond 4. If any thread to the game 100% maxes out a CPU core, then yes, the CPU is the bottleneck.

        Comment


        • #14
          Could we please get the same test for the RadeonSI drivers, perhaps with comparison to the fglrx numbers that was collected in this test?

          Comment


          • #15
            Originally posted by Daktyl198 View Post
            As an AMD user, I'm just waiting for the Vulkan results. I wish I could use DirectX 12 right now to see what my hardware can do, but the only game I play that has support for it (Ark: Survival Evolved) isn't releasing it because NVidia won't let them. Nvidia has to update GameWorks to cripple AMD's DX12 performance first :P

            Actually, Ashes of Singularity entered Early Access a couple of days back. But at this point it is still very, very badly optimized.

            Comment


            • #16
              Most of the games require high single-core performance so there is a chance that the dual core Pentium G3258 overclocked to something like 4.3-4.5GHz performs better then this Haswell-E.

              Comment


              • #17
                Originally posted by Azpegath View Post
                Could we please get the same test for the RadeonSI drivers, perhaps with comparison to the fglrx numbers that was collected in this test?
                I agree. RadeonSI should have been benched first and then to satisfy curiosity Catalyst could have been benched next. AMD has already said that gamers should using the OSS drivers, therefore it should be the first choice for benching. If you want to compare against Catalyst then that's perfectly fine, but Catalyst should never ever be the baseline.

                It just seems to me like doing comparisons in this way takes the worst aspects and purposefully emphasizes them. Especially since it's known that Catalyst isn't intended for gamers.

                Comment


                • #18
                  Originally posted by Azpegath View Post
                  Could we please get the same test for the RadeonSI drivers, perhaps with comparison to the fglrx numbers that was collected in this test?
                  Did you read the article? End of article or end of first page?
                  Michael Larabel
                  https://www.michaellarabel.com/

                  Comment


                  • #19
                    Originally posted by mao_dze_dun View Post


                    Actually, Ashes of Singularity entered Early Access a couple of days back. But at this point it is still very, very badly optimized.
                    But it shows the DX12 strength - with my R7 260X it drops from 20fps in small batches to 11fps in heavy batches with DX11, while with DX12 it is 21fps and 17fps respectively.

                    Comment


                    • #20
                      Originally posted by schmidtbag View Post
                      Are you serious? Do you honestly think TF2 uses 16 threads? I never checked myself but I don't think that game would use beyond 4. If any thread to the game 100% maxes out a CPU core, then yes, the CPU is the bottleneck.
                      No it doesn't use 16 threads, but the frequency of that CPU is high enough to not be the bottleneck. Also CPU usage is one of qualities of a driver, so even if there is a bottleneck AMD driver's handles it better in this specific test.
                      ## VGA ##
                      AMD: X1950XTX, HD3870, HD5870
                      Intel: GMA45, HD3000 (Core i5 2500K)

                      Comment

                      Working...
                      X