No announcement yet.

Radeon HD 7000 Series Linux Driver Support

  • Filter
  • Time
  • Show
Clear All
new posts

  • Radeon HD 7000 Series Linux Driver Support

    Phoronix: Radeon HD 7000 Series Linux Driver Support

    For those wondering what AMD's open-source Linux graphics driver developers are likely working on.....

  • #2
    Tom's a wee hottie


    • #3
      What about ati graphics cards on sandy bridge processors?

      In windows 7 you can choose what apps to run in high performance mode from catalyst, thus you have capability of both. In Linux I expect them to at least make that possible rather than throwing catalyst drivers that don't work on any modern processors. If you ship ati cards on new computers it is dual graphics by default (with intel HD 3000 being default). So what are they doing, putting their head inside sand and assuming the world is all well. I have completely disabled ati cards on Linux. If I disable Intel and enable ati driver (using vgaswitcheroo switch), computer just freezes or does not boot in graphics. If it could boot with ati on I could install their catalyst driver. I even updated my bios, hoping I could switch specific VGA on or off from bios, as dell listed here under Fixes and Enhancements

      1.enable Discrete AMD VGA fixed mode Support

      What does that even mean, when I see no option to do that.

      Even if would require me to restart the computer for each switch that's fine.


      • #4
        Originally posted by Qaridarium
        "The AMD Radeon HD 7000 series will be 28nm-based GPUs and are expected to ship with support for x86 addressing in a unified CPU/GPU address space, integrate PowerTune support, RISC MIMD instructions replacing VLIW SIMD instructions for GPGPU computing, XDR2 video RAM, PCI Express 3.0 support, and various other interesting changes. "

        no you are wrong michael the 7870 for example is only a 6970 4D VLIW SIMD card shrinked to 28nm and maybe more shaders and stuff.

        only the 7950 and 7970 are the new " RISC MIMD instructions" architecture with "with support for x86 addressing in a unified CPU/GPU address space" and XDR2 video RAM and PCI Express 3.0

        and you also wrong in time and date because the new architecture will not come in 2011.

        only the hd7870 come in the end of 2011.
        Isn't the hd7870 part of the new architecture? We don't need the entire lineup to have it. We just need 1 model.

        By the way, didn't Fermi have support for these things a while ago? It seems like AMD is behind.


        • #5
          Originally posted by Shining Arcanine View Post
          By the way, didn't Fermi have support for these things a while ago? It seems like AMD is behind.
          NVidia has been moving away from a graphics architecture and towards a compute architecture for a while now. Fermi indeed brought a lot of those features. This is AMD finally deciding to go the same direction.

          To be honest, I'm not sure how I feel about it - I think a lot of the great price/performance we got from ATI over the last couple generations was precisely because they were focusing on graphics performance while NVidia worred about compute features most people never used. Hopefully that doesn't become a problem for ATI now.


          • #6
            XDR2 video RAM
            Oh noes! Isn't that RAMBUS technology? Somehow when I think of RAMBUS a nasty feeling creeps into my stomach. (patents, lawsuits, high priced memory and so on)
            Stop TCPA, stupid software patents and corrupt politicians!


            • #7
              high priced and high speed


              • #8

                Originally posted by Qaridarium
                no the hd7870 is the old VLIW 4D architecture

                only the hd7950 and hd7970 are build in the new architecture.

                the fermi only do have some features bot not all and not the key features.

                the fermi do not have x86 64bit shared ram space.
                the fermi do not have the new ram
                the fermi is not directX 12.

                and so one and so one
                Fermi doesn't need weird x86 space, NV have nice working virtual memory (you can back pages with CPU and GPU memory transparently) and a 40 bit address space since GeForce 8.

                And it's Direct3D 11.1, not 12 - and there's not really any great changes there ... well, they added back "logical operations in a render target", which OpenGL had since version 1.1.


                • #9
                  Originally posted by Qaridarium
                  bullshit the next nvidia gpu will have x86_64 64bit space support.
                  its useful because this allows the cpu to use vram as normal ram and the gpu can use the normal ram as vram.
                  without streaming coping data between spaces.
                  You misunderstood the so call 64bit space support. It doesn't give anything to the cpu. For discret GPU it just means you can make the gpu address space equal to your cpu address space. But it's not completely true. NVidia have part of this since long time in form of virtual address space. But to go all the way down where GPU can access all system page of a process you need a lot more than a new GPU. You need new iommu and new pci protocol to support that.

                  And CPU access to VRAM is likely not what they had in mind.

                  Note also that most of marketing about all this is aimed at next generation APU where some of this does make lot more sense.


                  • #10
                    The ones that were just canceled?