Announcement

Collapse
No announcement yet.

NVIDIA's Linux Driver Can Deliver Better OpenGL Performance Than Windows 8.1

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

  • #11
    Originally posted by tpruzina View Post
    You couldn't be more wrong there. Why compare apples and bannanas when you can compare apples to apples?
    Is it likely that Unigine is more optimized on DX? Yes.

    Tests has proven though that OpenGL and DirectX are on par performance wise while both do pretty much the same thing albeit in slightly different manner.
    That is completely unrelated to this test though, which compares the very same codepaths on two different systems.

    In fact, most of NVIDIA's driver code is exactly same on both systems, with exception of kernel interfaces that work with hardware.


    Also Nvidia doesn't use a state tracker system. Their OpenGL infrastructure can read D3D to with small patches.

    Comment


    • #12
      Originally posted by schmidtbag View Post
      So as of right now the closed source nvidia drivers and the open source intel drivers are on par or superior to windows, and we haven't even switched to wayland yet. AMD I'm sure will be behind, but will catch up eventually - they're making good progress and the new amdgpu driver should really help speed things up on their end.
      I know people keep explaining this but: Wayland isn't going to make this sort of scenario faster. These are almost certainly full screen direct rendering, thus not touching X.
      BTW, I used Wayland for the first time and aside from some input issues (which I was aware of being limitations with the installed version of libinput) it was fantastic. I've never seen scrolling smoother in ff (yes, due to glamour but the experience was better than sna), and I never noticed any garbage caused by transitions/animations.
      Wayland is going to be so nice.

      Comment


      • #13
        Originally posted by startzz View Post
        plus nvidia broke opengl performance with latest driver series
        they did?

        Comment


        • #14
          Originally posted by schmidtbag View Post
          So as of right now the closed source nvidia drivers and the open source intel drivers are on par or superior to windows, and we haven't even switched to wayland yet. AMD I'm sure will be behind, but will catch up eventually - they're making good progress and the new amdgpu driver should really help speed things up on their end.
          Need to wait a bit longer to see if AMD's recent driver push bears fruit.

          Comment


          • #15
            Unigine Tropics at 4K was also much faster with the latest NVIDIA Linux driver than the latest NVIDIA Windows driver. It's not as if the NVIDIA Linux driver is newer than the Windows driver, but the Linux driver is actually a month older than the latest Windows driver: 343.22 vs. 344.48 WHQL.
            If he used different driver versions, I'm not sure we can conclude anything meaningful from the results, since there could just as easily be a regression in the newer driver.

            Comment


            • #16
              Originally posted by rdnetto View Post
              If he used different driver versions, I'm not sure we can conclude anything meaningful from the results, since there could just as easily be a regression in the newer driver.
              We can conclude nvidia is not always perfect, they made regressions too like all others

              Comment


              • #17
                D
                Originally posted by tpruzina View Post
                You couldn't be more wrong there. Why compare apples and bannanas when you can compare apples to apples?
                Is it likely that Unigine is more optimized on DX? Yes.

                Tests has proven though that OpenGL and DirectX are on par performance wise while both do pretty much the same thing albeit in slightly different manner.
                That is completely unrelated to this test though, which compares the very same codepaths on two different systems.

                In fact, most of NVIDIA's driver code is exactly same on both systems, with exception of kernel interfaces that work with hardware.

                Because we need to start comparing pure speed at the same visual quality, and dx11 on windows has an enormous advantage on that.
                On valley there are something like at least 200-300 points of difference between opengl and dx11 on windows, for the same visuals, same engine.
                We believed valve's story on "linux/opengl is faster" because he's engine used an outdated, depreciated technology that won't seem to die on windows: dx9.

                Dx10/11 is actually a lot faster than dx9, if you build an engine from the ground up for it.
                Comparing opengl to dx11 would show how much work nvidia/amd have to do in terms of opengl optimizations.

                Comment


                • #18
                  Originally posted by Michael
                  Following this article will be the AMD Linux vs. Windows testing that will include the open-source Radeon driver too
                  Please capture the CPU and GPU usage for each combo. As you say, it's just setting an env var (plus installing radeontop suid if you don't already have it). Having them in the openbenchmarking data is enough.

                  Originally posted by startzz View Post
                  No one cares about these tests either, these are just useless, we need some real life usage, so opengl sucks, besides, there is no good games for linux, plus nvidia doesnt care about opengl for windows, blah blah poor troll
                  Why are you even here? Toms is >> that way.

                  Comment


                  • #19
                    Originally posted by johnc View Post
                    they did?
                    Yes, they broke opengl performance for windows - there isnt much opengl games for windows, they are all very poorly optimized, and they kind of suck because of noob developers, and i dont play them, so its only what i read on nvidia forums, that some people are getting fps cut in half, like 50 instead of 100, or 200 instead of 400.

                    But it doesnt really matter, cause no one cares about opengl for windows, so these tests are useless in many ways:
                    1) nvidia doesnt care abot it,
                    2) developers doesnt care about it,
                    3) gamers doesnt care about it,
                    4) linux has nowhere else to go,
                    5) its the same as comparing air temperature on earth vs some other universe.

                    So theoretically it might look like you can compare opengl in linux vs windows, but in reality those things are not comparable in practical ways, apples vs oranges.
                    Last edited by startzz; 01 November 2014, 06:28 AM.

                    Comment


                    • #20
                      Originally posted by startzz View Post
                      Yes, they broke opengl performance for windows - there isnt much opengl games for windows, they are all very poorly optimized, and they kind of suck because of noob developers, and i dont play them, so its only what i read on nvidia forums, that some people are getting fps cut in half, like 50 instead of 100, or 200 instead of 400.
                      That drop is usual when driver devs play with memory managment, adding additional features and unintentionally broke something, support newer asics (and wanna advertising it at best, then they intentionally did'not care much about old ), etc. One time when things became so awfull to maintain, they just dropped it to legacy... usual stuff .

                      Those kind of things happens with DX support too, so nothing unusual

                      Comment

                      Working...
                      X