Announcement

Collapse
No announcement yet.

Linux Gaming Performance Doesn't Appear Affected By The x86 PTI Work

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

  • Linux Gaming Performance Doesn't Appear Affected By The x86 PTI Work

    Phoronix: Linux Gaming Performance Doesn't Appear Affected By The x86 PTI Work

    With the recently published Initial Benchmarks Of The Performance Impact Resulting From Linux's x86 Security Changes, one of the common questions that came up is whether gaming performance is adversely affected by the x86 Page Table Isolation changes recently merged to the Linux kernel...

    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
    Cool, at least it seems not very total catastrophe Maybe try all Intel further - i mean how their iGPUs now behave.
    Last edited by dungeon; 02 January 2018, 10:24 PM.

    Comment


    • #3
      Frame rates are not affected. What about loading times?

      Comment


      • #4
        I was promised an APOCALYPSE! I want my money back!

        Comment


        • #5
          Originally posted by chuckula View Post
          I was promised an APOCALYPSE! I want my money back!
          LOL, that is funny...

          Comment


          • #6
            Originally posted by eydee View Post
            Frame rates are not affected. What about loading times?
            This, since it seems to affect I/O performance. Michael, please test this!

            Comment


            • #7
              Wouldn't an NVIDIA card inclusion be more interesting since they rely on software scheduling?

              Comment


              • #8
                Did you test frame pacing stability? Because if the context switches aren't frequent enough to affect FPS, but still enough to affect frame pacing, then it would be a big issue.

                Comment


                • #9
                  Also, were the tests CPU or GPU-bound? It would be normal that there's no perf difference if the GPU is the bottleneck instead of the CPU.

                  Comment


                  • #10
                    A check for older CPUs might also be interesting.

                    Comment

                    Working...
                    X