Announcement

Collapse
No announcement yet.

Here's Why Radeon Graphics Are Faster On Linux 3.12

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

  • #31
    Originally posted by marek View Post
    You can use that, but don't bother me with the benchmark results, because as a driver developer I am not interested. It's not only the graphics driver being benchmarked here, it's also cpufreq. And who knows what cpufreq will do next time.
    You, as a GPU driver developer, may not personally care about low GPU performance results due to the CPU, but AMD as a corporation should care, because it negatively impacts end-user experience of AMD products.

    Comment


    • #32
      Originally posted by Michael View Post
      The testing is about the default for the distribution that most people utilize.
      Even if the default is completely bananas? I mean 90% performance difference due to default governor setting is crazy.

      Comment


      • #33
        Originally posted by chrisb View Post
        You, as a GPU driver developer, may not personally care about low GPU performance results due to the CPU, but AMD as a corporation should care, because it negatively impacts end-user experience of AMD products.
        So what do you expect AMD to do? Provide custom governors for all the cpus out there, that might be used with AMD graphics cards?

        Imho this is a linux kernel issue and should be fixed there, which is what happening already I assume.

        Comment


        • #34
          Originally posted by log0 View Post
          Even if the default is completely bananas? I mean 90% performance difference due to default governor setting is crazy.
          Then it should be fixed or the default setting changed within the kernel.
          Michael Larabel
          http://www.michaellarabel.com/

          Comment


          • #35
            Originally posted by log0 View Post
            Even if the default is completely bananas? I mean 90% performance difference due to default governor setting is crazy.
            Especially when the default is completely bananas. Because the default then needs to be changed, or the default behavior simply fixed.

            Comment


            • #36
              Originally posted by chrisb View Post
              You, as a GPU driver developer, may not personally care about low GPU performance results due to the CPU, but AMD as a corporation should care, because it negatively impacts end-user experience of AMD products.
              If I'm not mistaken, Brigdman once said that he or AMD sees the open drivers as the more adequate, long term, to the consumers. Thus, I assume that, long term, the plan would be to pretty much dump fglrx for radeon cards and apus on linux. If this is right, I would expect AMD to work closely with target distro in order to iron out these naty little bugs. If not for Ubuntu, than at least for SteamOS... Nvidia certainly is doing something similar for their blob.

              Comment


              • #37
                Originally posted by jonnor View Post
                Especially when the default is completely bananas. Because the default then needs to be changed, or the default behavior simply fixed.
                At the same time, you'll never know whether it's the scaling governor or the graphics drivers that are bananas. You'll just know that something in there is.

                Comment


                • #38
                  Originally posted by RussianNeuroMancer View Post
                  As I remember developers from Croteam discover that default ondemand governor slow down their engine in Novermber of 2012. They recommend everyone switch to performance governor before starting Serious Sam 3. Hopefully, we probably doesn't need switch to performance governor any more.
                  Yes they did, they told us to switch off things like cool and quiet in the bios, as I did.

                  Setting the governor to performance also improved things allot.

                  (The biggest performance boost came with one of the latest catalyst drivers though.)

                  AMD phenom II X4 at 3.2 ghz, 4 gig ram, HD5750 1 gig ram. openSUSE 12.3 64bit
                  Last edited by Gps4l; 10-15-2013, 09:30 AM.

                  Comment


                  • #39
                    I'm not sure I really buy the default argument. The default it to have FPS rate limited to the display refresh rate, and rightly so. If there's a call to measure performance with games far below the capabilities of the gfx hw such that they are cpu bound, wouldn't a more meaningful benchmark be overall power utilisation? What use case is the in running at multiple 100s fps more than you can see?
                    Last edited by s_j_newbury; 10-15-2013, 09:39 AM.

                    Comment


                    • #40
                      Originally posted by marek View Post
                      You can use that, but don't bother me with the benchmark results, because as a driver developer I am not interested. It's not only the graphics driver being benchmarked here, it's also cpufreq. And who knows what cpufreq will do next time.
                      You are not interested as a driver developer ? So if a user complains about performance problems, do you just tell him "I don't see it so there is no problem" or do you maybe try to understand what is going on ? You should be glad that someone is testing an average user configuration to spot problems that would be blamed on you.

                      Comment


                      • #41
                        Originally posted by Michael View Post
                        Then it should be fixed or the default setting changed within the kernel.
                        Well, how about communicating this more clearly?

                        Instead of: "Here's Why Radeon Graphics Are Faster On Linux 3.12"

                        Something like: "Why is linux still using the ondemand governor as default?" (... even if it is broken and is making performance benchmarks pretty much useless as cpu loads will vary with different gpus)

                        Comment


                        • #42
                          Originally posted by s_j_newbury View Post
                          I'm not sure I really buy the default argument. The default it to have FPS rate limited to the display refresh rate, and rightly so. If there's a call to measure performance with games far below the capabilities of the gfx hw such that they are cpu bound, wouldn't a more meaningful benchmark be overall power utilisation? What use case is the in running at multiple 100s fps more than you can see?
                          A useful benchmark would be to see how often/seldom the system failed to reach the deadline for a frame at 60 fps.

                          There are some games where running at a framerate higher than 60fps can give advantages, but that is due to internal quirks of the engine, and not an important usecase for ordinary gamers.

                          Comment


                          • #43
                            Originally posted by jonnor View Post
                            A useful benchmark would be to see how often/seldom the system failed to reach the deadline for a frame at 60 fps.
                            I had that in my mind too.

                            Comment


                            • #44
                              Originally posted by log0 View Post
                              Well, how about communicating this more clearly?

                              Instead of: "Here's Why Radeon Graphics Are Faster On Linux 3.12"

                              Something like: "Why is linux still using the ondemand governor as default?" (... even if it is broken and is making performance benchmarks pretty much useless as cpu loads will vary with different gpus)
                              Isn't the whole point that the governor issue *is* being addressed in the kernel already and that's where the performance jump came from ?

                              Comment


                              • #45
                                Originally posted by bridgman View Post
                                Isn't the whole point that the governor issue *is* being addressed in the kernel already and that's where the performance jump came from ?
                                I assume it is addressed, but I've only seen i7 benchmarks here with the default configuration, no comparisons to performance setting. Maybe you know more?

                                Comment

                                Working...
                                X