Announcement

Collapse
No announcement yet.

GeForce GTX 1080 Ti: Core i7 7700K vs. Ryzen 7 1800X Linux Gaming Performance

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

  • #31
    Originally posted by NihilMomentum View Post
    Why does it perform so bad on Vulkan (Dota 2)? Is that a source 2 thing or is it across the board like that?

    Does the 4.10 and 4.11 kernels give better performance?
    Dota 2's Vulkan implementation does not seem to be representative of Vulkan performance in general, but in this specific test context there may be additional problems.

    Comment


    • #32
      There's something wrong with the Tomb Raider Benchmark.
      No way the 1080 Ti is pushing 160fps in 4k Ultra.
      And no way the fps stays exactly the same between 4k normal and 4k ultra.

      Other than that, performance difference between the 1800x and 7700k seems consistent with what I've seen elsewhere.
      In gaming, Ryzen is hamstrung by its memory controller and has an IPC ~ 85% of Sandy Bridge which means ~ 70% of SkyLake/KabyLake
      Given that the 7700k runs at 4.2Ghz (all core) vs 3.7 Ghz (all core) for the 1800x, that gives a theoretical advantage of ~ 65% to Skylake for gaming workload that don't benefit from more than 4 cores / 8 threads.
      And that's pretty much what we see with Deus Ex MD (in 1080p), Dota 2, Civ 6 and Unigine Valley.
      The gap is smaller with Unigine Heaven probably because it's taxing the GPU more.
      It's also smaller for Metro Last Light because this game can benefit from more than 4 cores as show in a previous phoronix article.

      Comment


      • #33
        Originally posted by gurv View Post
        There's something wrong with the Tomb Raider Benchmark.
        No way the 1080 Ti is pushing 160fps in 4k Ultra.
        And no way the fps stays exactly the same between 4k normal and 4k ultra.

        Other than that, performance difference between the 1800x and 7700k seems consistent with what I've seen elsewhere.
        In gaming, Ryzen is hamstrung by its memory controller and has an IPC ~ 85% of Sandy Bridge which means ~ 70% of SkyLake/KabyLake
        Given that the 7700k runs at 4.2Ghz (all core) vs 3.7 Ghz (all core) for the 1800x, that gives a theoretical advantage of ~ 65% to Skylake for gaming workload that don't benefit from more than 4 cores / 8 threads.
        And that's pretty much what we see with Deus Ex MD (in 1080p), Dota 2, Civ 6 and Unigine Valley.
        The gap is smaller with Unigine Heaven probably because it's taxing the GPU more.
        It's also smaller for Metro Last Light because this game can benefit from more than 4 cores as show in a previous phoronix article.
        It's the old TR, not the "denuvo edition". It runs on 10-year-old low-end potatoes at infinite speed. A 1080Ti being CPU limited is quite possible here.

        Comment


        • #34
          Originally posted by pal666 View Post
          1800x's competitor is 6900k, why compare with unrelated overclocked 4 core?
          x2, its a bizarre comparison, makes no sense. Even more so when we know up front these games are optimized for 4-core processors. Why knowingly benchmark an inappropriate workload?

          This makes about as much sense as running a 16-thread synthetic benchmark on these two. Ryzen would destroy the 7700k in that scenario.
          Last edited by torsionbar28; 13 March 2017, 12:22 AM.

          Comment


          • #35
            Originally posted by gurv View Post
            There's something wrong with the Tomb Raider Benchmark.
            No way the 1080 Ti is pushing 160fps in 4k Ultra.
            And no way the fps stays exactly the same between 4k normal and 4k ultra.

            Other than that, performance difference between the 1800x and 7700k seems consistent with what I've seen elsewhere.
            In gaming, Ryzen is hamstrung by its memory controller and has an IPC ~ 85% of Sandy Bridge which means ~ 70% of SkyLake/KabyLake
            Given that the 7700k runs at 4.2Ghz (all core) vs 3.7 Ghz (all core) for the 1800x, that gives a theoretical advantage of ~ 65% to Skylake for gaming workload that don't benefit from more than 4 cores / 8 threads.
            You seem to be theoretizing too much, I'd say, actual measurements are different, in my experience.

            Originally posted by gurv View Post
            And that's pretty much what we see with Deus Ex MD (in 1080p), Dota 2, Civ 6 and Unigine Valley.
            ...
            65%? Where? That number is an outlier in what I've seen so far. Here is a Deus Ex test in 1080p, "very high" quality (as opposed to "high quality" here). This is with NVidia Titan Pascal, which is very similar in performance to the 1080 Ti, on Windows:
            http://www.techspot.com/review/1348-...nce/page2.html

            There [for Deus Ex], 1800X with SMT on gets 72%, and with SMT off, 85%.
            Here, it is 59%. (SMT off not tested).

            In many games there, the 1800X, even with SMT on, gets around 80% or more. And SMT on, at least with the current Windows scheduler, is a handicap since the Windows scheduler (and probably the games) don't recognize the SMT cores as virtual (not physical).

            Most of the tests in this article are at the GPU-intensive 4K resolution, where the gaps should be smaller than in most reviews, even with the "Ti" version of the 1080.

            EDIT:
            The 16 game average for the 1080p resolution, in the above Windows test, is 83% with SMT on, 1800X vs 7700K on NVidia Titan Pascal.

            For the 1440p resolution, which is closer to 4K, it is 90%. For 4K, it should be even higher.
            Last edited by indepe; 13 March 2017, 01:07 AM.

            Comment


            • #36
              Originally posted by eydee View Post

              It's the old TR, not the "denuvo edition". It runs on 10-year-old low-end potatoes at infinite speed. A 1080Ti being CPU limited is quite possible here.
              Assuming 159 fps in 4K Ultra is possible with the old Tomb Raider, there is no explanation how Rhyzen could be 2.3x faster than the 7700K by plain performance advantage.

              Comment


              • #37
                What is the RAM running at?

                As previously stated. Why are you using kernel 4.9?

                Comment


                • #38
                  Seeing this article I did some of my own benchmarks regarding the thread affinity in games.

                  Comment


                  • #39
                    Originally posted by schmidtbag View Post

                    mlau
                    I'm not so sure about that. From what I recall, other benchmarks showing the 1800X vs the 7700K at stock speeds (with boosts enabled) don't show results contrasting this much.
                    Right. 20% perf difference could be explained by the clock difference (i.e. 7700k max turbo is >20% higher than 1800x's), but the rest seems like result of nvidia driver differences between this and Michaels last Zen tests. Obviously there's a lot of optimizations to be had with the nvidia driver.

                    @Michael: but you didn't disable the turbo on both systems?

                    Comment


                    • #40
                      Originally posted by pal666 View Post
                      1800x's competitor is 6900k, why compare with unrelated overclocked 4 core?
                      Price-wise, the 1800x is comparible to the 7700k. IT is an entirely appropriate article if you are looking to build a Linux gaming machine and aren't sure whether to splash the cash on intel or AMD

                      Comment

                      Working...
                      X