Announcement

Collapse
No announcement yet.

The New R300 Register Allocator Is Still Being Developed

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

  • #16
    Originally posted by Kjella View Post
    When AMD or Intel releases a new CPU, Linux supports it with little to no effort as long as you don't need it to take advantage of new instructions and such. The same can not be said of graphics, unless drivers are written for each new generation they won't work at all. Of course code doesn't disappear but if you measure the quality of drivers compared to how recent the generation is, then yes it might certainly regress not just stagnate.

    The R500 is now the 5th most recent generation after N. Islands, Evergreen, R700 and R600, when Southern Islands is released they'd be the 6th most recent. Unless new code is written fast enough to keep up Linux will only function well on graphics cards found in museums and not on recent PCs. So I disagree with you, there's certainly a critical mass and below that things get worse, not better. And vendors willing to disclose their specs, of course - I think if AMD changed their mind you'd agree things would go downhill, fast.
    From my limited understanding of HW i get the impression that x86 chips are more close to each other than the various GPUs from different manufacturers. Even if thats not true the manufacturers cannot afford their CPUs not running on linux and hence they play with the kernel rules. They all provide patches to the mainline kernel and don't depend on volunteers.

    In the graphics side of things most companies do their own thing. They either have blobs or do their own thing without trying to work on a widely accepted solution (Intel situation with classic Mesa). At least AMD provides documents and has a few devs on the payroll even thought its not enough to keep up with the fast paced GPU development.

    What slightly bugs me in the whole situation is that noone has tried to address the problem. ie the FSF, the Linux foundation or all the open source foundation can probably pay a dev or two -+ ask the community to chip in- in order to get a feature full OpenCL or OpenGL state tracker for G3D (or whatever is needed).

    Comment


    • #17
      Originally posted by 89c51 View Post
      From my limited understanding of HW i get the impression that x86 chips are more close to each other than the various GPUs from different manufacturers. (...) What slightly bugs me in the whole situation is that noone has tried to address the problem.
      CPUs are pretty much just hardware with a fixed interface, they must run low-level x86/x86_64 code compiled by others. Graphics companies can change their hardware and software at will, as long as they end up with something DirectX/OpenGL compliant. The AMD hardware and software guys talk to each other, we change the hardware so and you change the drivers so. There's no stable hardware interface and that's not really a problem that can be "solved". All you can hope for is to have enough open source developers to shadow what the binary driver developers are doing - or at least the most essential parts.

      Comment


      • #18
        Originally posted by benmoran View Post
        Yes exactly.

        But... I have an HD5770, and I REALLY don't want to install Catalyst. I think I might do it for a little while though, just to play the new Frozenbyte Humble Bundle games.
        i do have a hd4650 and hd5670 right now and I don't want to install the Catalyst. and no i also buy the humble indie bundle and i still do not install the catalyst

        Comment


        • #19
          Originally posted by Kjella View Post
          The R500 is now the 5th most recent generation after N. Islands, Evergreen, R700 and R600, when Southern Islands is released they'd be the 6th most recent. Unless new code is written fast enough to keep up Linux will only function well on graphics cards found in museums and not on recent PCs. So I disagree with you, there's certainly a critical mass and below that things get worse, not better. And vendors willing to disclose their specs, of course - I think if AMD changed their mind you'd agree things would go downhill, fast.
          you don't get an important point... an R700 is an r600 with extras and a southern island chip is an r600 with extras and an northern island chip is an r600 with extras.

          the general architecture chances are only r300,r600,r900

          and r900 will come in 2012 as a complete new architecture without any r600 parts.

          Comment


          • #20
            Maybe better get a nv card to play with nouveau instead, much faster

            Comment


            • #21
              Originally posted by Kjella View Post
              All you can hope for is to have enough open source developers to shadow what the binary driver developers are doing - or at least the most essential parts.
              but thats exactly what causes -and will continue to cause if it doesn't get solved- all the problems with the open source stack

              lack of manpower

              Comment


              • #22
                Originally posted by Kano View Post
                Maybe better get a nv card to play with nouveau instead, much faster
                if you pay me the bump-gate harm ? and power consuming costs because of bad hardware..

                sure you can start to pay reparations a new nv card and a monthly payment should be fine.

                Comment


                • #23
                  Even a lowend 9400 gt with nouveau beats a my hd 5670. It is about 3-4 times faster with trine and has correct rendering.

                  Comment


                  • #24
                    But isn't this performance advantage only limited to a small range of cards?

                    I don't know how often you test, but there has been a lot of improvement in the last couple of years. My HD4550 does Prey at high quality and high definition and manages to make it playable.

                    It's possible that the CPU-boundedness is preventing better frame rates on more powerful cards, though.

                    Comment


                    • #25
                      As there is no trine benchmark i used openarena to figure out the expected speed with quake live at lowest settings - and had to see that not all drivers are performance tuned, therefore i repeated the tests with settings which disabled vsync (or used max performance mode for nouveau) - a bit hard to read however (2 test systems used, lots of gfx cards/drivers):

                      http://openbenchmarking.org/result/1...GR-1104128GR35

                      I also tested my Ion netbook (first 2 tests ran at 800 mhz, the last 2 at 1600 mhz):

                      http://openbenchmarking.org/result/1...KANO-110419300

                      Comment


                      • #26
                        Something that would help bring more paid developers in would be for parts of Linux open source drivers being used in other things. One of the complaints I've heard leveled at Khronos and OpenGL is that they don't provide a driver component like Microsoft does. What if Khronos used Gallium3d for this component to be provided for all drivers. The only problem is that I doubt this would ever even be considered unless Gallium could approach parity with the blobs. Google might be able to pressure video card makers for their android phones to use first rate open source drivers. If they used mesa and Gallium3d, then we would have more firms helping. Unfortunately, a similar chicken and egg conundrum exists here as my last possibility.

                        Comment


                        • #27
                          Originally posted by Qaridarium View Post
                          you don't get an important point... an R700 is an r600 with extras and a southern island chip is an r600 with extras and an northern island chip is an r600 with extras. the general architecture chances are only r300,r600,r900
                          Then why does HDMI audio work on R600/700 but not on Evergreen or Nothern Island? Why didn't my Evergreen card work at all first, but R600/700 did? Because they're not the same with extras. They're different. Yes, some changes are smaller and some - like general architecture changes - are larger, but they all have changes. Nothing will work on a new generation without an updated driver.

                          Comment


                          • #28
                            Originally posted by Kjella View Post
                            Then why does HDMI audio work on R600/700 but not on Evergreen or Nothern Island? Why didn't my Evergreen card work at all first, but R600/700 did? Because they're not the same with extras. They're different. Yes, some changes are smaller and some - like general architecture changes - are larger, but they all have changes. Nothing will work on a new generation without an updated driver.
                            Right. The fundamental difference between CPUs and GPUs here is that CPUs are expected to do the *same* thing every year (run a slowly changing set of x86 binaries) while GPUs are expected to do *different* things every year or two (new graphics features, new pipeline definitions, more programmable functionality for game developers etc..). If CPUs had a million lines of driver code between the x86 binary and the hardware you would be likely to see the same kind of evolution in the exposed CPU hardware -- instead CPUs evolve less (more execution units rather than totally different architecture) and hide that evolving functionality behind an instruction decoder rather than behind a driver.

                            Comment


                            • #29
                              Originally posted by Kano View Post
                              As there is no trine benchmark i used openarena to figure out the expected speed with quake live at lowest settings - and had to see that not all drivers are performance tuned, therefore i repeated the tests with settings which disabled vsync (or used max performance mode for nouveau) - a bit hard to read however (2 test systems used, lots of gfx cards/drivers):

                              http://openbenchmarking.org/result/1...GR-1104128GR35

                              I also tested my Ion netbook (first 2 tests ran at 800 mhz, the last 2 at 1600 mhz):

                              http://openbenchmarking.org/result/1...KANO-110419300
                              any benchmark over min-fps=60fps is invalid.

                              Comment


                              • #30
                                Originally posted by Kjella View Post
                                Then why does HDMI audio work on R600/700 but not on Evergreen or Nothern Island? Why didn't my Evergreen card work at all first, but R600/700 did? Because they're not the same with extras. They're different. Yes, some changes are smaller and some - like general architecture changes - are larger, but they all have changes. Nothing will work on a new generation without an updated driver.
                                you are just making FAIL arguments we talk about graphic core logics and you fuck around with "HDMI audio" AUDIO===???
                                ooh LOL o come one.

                                for example hd6870 vs 6950 the architecture is the same because :they just cut of the smal-shader-co-processors (5D logic is 1 bigblog+4 smal co processors) and quating the big-blog 6870 big shader and call the new 4 pices of 6870 a 6950 4D shader block.
                                on the shader core the 6950 only do have the 6870 shaders (the big one without the smal co processors)

                                and remember the 6870 only do have the r600 hd 2900 shader architecture means the hd 6950 do have a hd2900 shader but yes they cut of the little shaders for simple shader code.

                                means an hd6950 is an hd2900 with cutting of the "little shaders"

                                yes they need to rework the drivers because the code is for bigblock+minishaders

                                Comment

                                Working...
                                X