Announcement

Collapse
No announcement yet.

Running Benchmarks On Newer, Popular AAA Linux Games***

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

  • #11
    Originally posted by Michael View Post
    No update on the upstream issue being fixed.... Did alert my Valve contacts who relayed my issue to the A4 folks, but no fix yet. But today did do a workaround after working with Lauri to get libframetime working for the games. So as of this morning on OpenBenchmarking.org are metroll-redux and metro2033-redux test profiles.... Will share more details tomorrow.
    Thanks

    Comment


    • #12
      Originally posted by Adriannho View Post
      well, Witcher 2 might be a good start. Borderlands, the upcoming Two Worlds 2, Bioshock Infinite after lunch....everything that is AAA and available on linux basically.
      Terrible idea. It's a crap wrapper port which is CPU bottlenecked like fuck. I can change the graphics settings from ultra low to ultra high and it has absolutely no impact on frame rate.

      Comment


      • #13
        Originally posted by blackout23 View Post
        Terrible idea. It's a crap wrapper port which is CPU bottlenecked like fuck. I can change the graphics settings from ultra low to ultra high and it has absolutely no impact on frame rate.
        yea...but still, witcher is a great looking game. and a fun to play one.

        and (some) people with nvidia said it ran decent.
        Last edited by Adriannho; 10 January 2015, 04:25 PM.

        Comment


        • #14
          Unreal 4 demos?

          Comment


          • #15
            Originally posted by phoronix View Post
            Phoronix: Running Benchmarks On Newer, Popular AAA Linux Games***

            With the numerous Linux graphics driver/hardware benchmarks done at Phoronix each week, one of the frequent requests is to use more popular Linux game titles available via Steam than the current selection of Linux game tests and OpenGL tech demos...

            http://www.phoronix.com/vr.php?view=MTg4NTY
            Well, It's a step in the right direction. Certainly it's better than the status quo.

            Although, It's just like you said, It still wouldn't mean anything. What would the benches show? Not gameplay, not graphics performance, not cpu performance, not memory performance....

            I want to see actual gameplay. I know, I know....

            Comment


            • #16
              Originally posted by commiethebeastie View Post
              Unreal 4 demos?
              Agree!
              Though there are still some mesa bugs with them..the fix might have a performance impact later.

              Comment


              • #17
                Originally posted by Adriannho View Post
                yea...but still, witcher is a great looking game. and a fun to play one.

                and (some) people with nvidia said it ran decent.
                I have a NVIDIA card still doesn't change the fact that it's CPU bottle necked like crazy. I got about 35-40 FPS on 2560x1440 but graphics settings don't have any influence on performance with this game.

                Comment


                • #18
                  That was fast!

                  Thanks for listening Michael!!

                  Comment


                  • #19
                    Originally posted by brunis View Post
                    Thanks for listening Michael!!
                    It's always been on the table coming up with some way to get more automated benchmarks... After latest communication with Valve this week, hopeful we'll be able to get traces working.
                    Michael Larabel
                    https://www.michaellarabel.com/

                    Comment


                    • #20
                      Traces of popular games like that would be much appreciated, thank you.

                      It's far from perfect, but better than what we have now.

                      I don't think it's any more artificial than running something like a Unigine demo, and trying to approximate the results from that over towards running a real game. Probably quite a bit less, although it remains to be seen what kind of overhead or strange artifacts these traces might cause in benchmarking.


                      On a somewhat related note - can you run these tests often in what you report? I know you said you have a CS:GO test profile, some others for some Valve games, and you recently did one for Civ5, but you never really seem to run any of those tests. At most you seem to occasionally have a "special" article where you only include those tests and not your normal ones.

                      Comment

                      Working...
                      X