Announcement

Collapse
No announcement yet.

AMD Radeon HD 6000 Gallium3D Attempts To Compete With Catalyst

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

  • #16
    Originally posted by pingufunkybeat View Post
    And while it's true that more modern stuff (like Unigine) will tax the drivers more, these naked frame-pushing benchmarks are still important because they show the CPU bottlenecks which are one of the main causes of lower performance.
    what stops the devs from fixing the CPU bottlenecks ????

    Comment


    • #17
      The fact that they are only few people and open drivers still lack major functionalities?
      ## VGA ##
      AMD: X1950XTX, HD3870, HD5870
      Intel: GMA45, HD3000 (Core i5 2500K)

      Comment


      • #18
        Originally posted by 89c51 View Post
        what stops the devs from fixing the CPU bottlenecks ????
        Lack of time and manpower, mostly.

        It seems like there is no single main bottleneck which needs to be optimised away cleverly, and then you're done. It's more like a set of small slowdowns which all add up, and need to be found individually and optimised. 1% here, 0.5% there, and so on.

        People like Jerome Glisse have done quite a bit of work at locating such bottlenecks, but it's really hard work, and solutions are not always easy (they might require a redesign, or a different approach).

        So it's something that will continue to improve. Luckily, r300g is already so highly optimised, and many of the same tricks can hopefully be applied to r600g with some effort, when somebody finds the time.

        Comment


        • #19
          Originally posted by Pfanne View Post
          WOW!
          im impressed.
          didnt think the drivers would be around 50% in pretty much every benchmark (even faster in urban terror).
          UrbanTerror has not removable, permanent 125fps cap.
          This is because of quake3/ioquake, that binds fps to physics and network sync.
          Overall, urbanterror has terrible bullet physics by the way and it seems to be very cpu bound.
          The benchmark must be flawed, unless Michael managed to remove it.

          Comment


          • #20
            If the game allows you to make benchmarks maybe they remove the fps cap in "benchmark mode"
            ## VGA ##
            AMD: X1950XTX, HD3870, HD5870
            Intel: GMA45, HD3000 (Core i5 2500K)

            Comment


            • #21
              Originally posted by pingufunkybeat View Post
              Lack of time and manpower, mostly.

              It seems like there is no single main bottleneck which needs to be optimised away cleverly, and then you're done. It's more like a set of small slowdowns which all add up, and need to be found individually and optimised. 1% here, 0.5% there, and so on.

              People like Jerome Glisse have done quite a bit of work at locating such bottlenecks, but it's really hard work, and solutions are not always easy (they might require a redesign, or a different approach).

              So it's something that will continue to improve. Luckily, r300g is already so highly optimised, and many of the same tricks can hopefully be applied to r600g with some effort, when somebody finds the time.
              Exactly this transfers in usage scenario - "I will use opensource and buy amd when I have time". This is not professional approach at all. Compare to phpBB, that Michael refused to use, because they had exactly same approach. You can't develop good code if you do it in your free time, commercial is best. But commercial does not mean proprietary. The whole thing about opensource is about community (of people, companies, organisations) able to help the main drive force behind driver - some main company or organisation. But in case of AMD, community and company are (mostly) separate entities. To stay fair, Nvidia are completely separate.

              Whats left is proprietary driver and amd proprietary driver is still not perfect.

              But, thanks for this, AMD:
              http://www.pcgameshardware.de/screen...ntation-30.png

              A little word "Linux", along with like 60 words ("microsoft","windows","directx") split over the 30 page presentation is still a good start.

              Comment


              • #22
                Originally posted by crazycheese View Post
                UrbanTerror has not removable, permanent 125fps cap.
                All the results are above 125 fps.

                Comment


                • #23
                  Originally posted by darkbasic View Post
                  If the game allows you to make benchmarks maybe they remove the fps cap in "benchmark mode"
                  I found no way to remove it, hence saying....

                  Originally posted by pingufunkybeat View Post
                  All the results are above 125 fps.
                  If you find a way to remove the 125 fps limit in this game, I will salute you. Cause unlike openarena, it seems hardcoded.

                  Comment


                  • #24
                    Then ask Michael, or download PTS and check what they did to remove the cap.

                    Because there is obviously no 125 FPS cap in this test.

                    Comment


                    • #25
                      Originally posted by jrch2k8 View Post
                      plz remember that the graphic stack team is very small compared to catalyst so they can't fix all magically in 6 months
                      Yeah, that's a shame... but, that doesn't change the fact that the thermal properties of the card and the fans are going harder than they should have to.

                      It's like having non-working drivers.

                      If you're getting higher power consumption or little to no control over temps/power, then this is a stress on the card.

                      That's a problem and what features the card can or cannot do become irrelevant.

                      Comment


                      • #26
                        Another idiotic post by Panix.

                        No, Panix, it's not like having non-working drivers. It just means that you change the profile manually from time to time, that is all.

                        This has been available for years, if you had spent only five minutes of your trolling time reading something instead, you'd know it.

                        Comment


                        • #27
                          Originally posted by pingufunkybeat View Post
                          Then ask Michael, or download PTS and check what they did to remove the cap.

                          Because there is obviously no 125 FPS cap in this test.
                          Why don't you do this instead? No, seriously, I have a bit mess right now, so ... hard. But I have urt installed and I'm pretty sure its 125 fps capped - 60-125 fps are selectable, the engine uses this cap for sync and physics. Quake3 WAS able to remove the cap for local-only gameplay. The problem is.. I wanted to remove it myself some time ago, just to get info where gtx260 gets stuck - and I was not able to find the path.
                          So yes, the cap *should be* there .. or I'm not getting something. The other thing that makes me suspect - is pretty same framerates on all cards... Don't ask how PTS managed to record 160 or 180 fps.. I don't know,.. yet.

                          Comment


                          • #28
                            Originally posted by pingufunkybeat View Post
                            Another idiotic post by Panix.

                            No, Panix, it's not like having non-working drivers. It just means that you change the profile manually from time to time, that is all.

                            This has been available for years, if you had spent only five minutes of your trolling time reading something instead, you'd know it.
                            Hey, would you refrain from calling him idiot? He is not. He, just as me, stated multiple times, that he *would* use open drivers if they *would* be usable with the card he buys, which means *more or less* that the company *cares* about the driver, because the company *wants* you to buy their card. This is situation with amd and windows. As for linux, especially in opensource area, it is not the situation. The power management in open drivers on amd is many times worse than it could be (call it room for improvement or presence of inefficiency).
                            Anyway, his point that a company *should* invest its own money into the driver for it to be usable with their hardware - is true.
                            The thing that he oversees, is that he is comparing closed source nvidia driver to opensource linux driver, which is incorrect, because nvidia does not opensource at all. But because of bad catalyst reputation in the past and still lack of features in fglrx, compared to blob of nvidia in the present, opensource driver seems to be better candidate for the working driver, than catalyst.Yet catalyst does better power management. But it still looses to nvidia blob. So, his message is that amd should do at least one of their drivers working. They do that, even if very strange ways of having two drivers, both of usually lesser quality than nvidia blob. But nvidia has been decelerating lately, so nvidia is by far not the gem, that Panix searches for.

                            Comment


                            • #29
                              Originally posted by pingufunkybeat View Post
                              Another idiotic post by Panix.

                              No, Panix, it's not like having non-working drivers. It just means that you change the profile manually from time to time, that is all.
                              Hey, you're not much better, pal Changing the power profile with the radeon driver is also idiotic; it doesn't do much. At most it goes from 85C to 83C, which is just laughable.

                              It simply doesn't work, OK?

                              Comment


                              • #30
                                It does nothing? It goes from 70C to 45C with my HD5870...
                                With the HD3870 it goes from 70C to 55C and even dynpm did work. Flawlessly.
                                ## VGA ##
                                AMD: X1950XTX, HD3870, HD5870
                                Intel: GMA45, HD3000 (Core i5 2500K)

                                Comment

                                Working...
                                X