Page 1 of 4 123 ... LastLast
Results 1 to 10 of 36

Thread: Radeon HD 7000 Series Will Bring New 3D Driver

  1. #1
    Join Date
    Jan 2007
    Posts
    14,646

    Default Radeon HD 7000 Series Will Bring New 3D Driver

    Phoronix: Radeon HD 7000 Series Will Bring New 3D Driver

    There's another update to the recent AMD Driver Support State For Radeon HD 7000 Series, Trinity article. The Radeon HD 7000 series will in fact bring a new Gallium3D Linux driver...

    http://www.phoronix.com/vr.php?view=MTAyNTA

  2. #2
    Join Date
    Nov 2010
    Location
    Stockholm, Sweden
    Posts
    400

    Default

    This feels a bit scare for me, owning a Radeon 4850. How well will support for the "older" cards be maintained, etc etc? But since they haven't abandoned the R300 I guess there's not much to fear in the coming years. And eventually I think it's worth buying a new graphics card, even though it's a cheap-ass one with passive cooling, just to get a newer generation card. If I had a R300 today I would probably buy a $30 card since it will quadruple performance and at the same time allow me to use both Catalyst and FOSS drivers.
    On another note: It's very interesting that the 48*0 series is still the best performing generation when running the FOSS drivers.

  3. #3
    Join Date
    Nov 2008
    Location
    California
    Posts
    61

    Lightbulb Gcn, vliw4, & vliw5

    As far as I understand it, only the top-end 7900 chips are using the new GCN arcitecture, while the weaker parts will be using a mix of the VLIW4 arch introduced with Cayman and, curiously, the older VLIW5 arch as well.

  4. #4
    Join Date
    Oct 2009
    Posts
    201

    Default

    Quote Originally Posted by Darkfire Fox View Post
    As far as I understand it, only the top-end 7900 chips are using the new GCN arcitecture, while the weaker parts will be using a mix of the VLIW4 arch introduced with Cayman and, curiously, the older VLIW5 arch as well.
    High-end chips should have a completely new SIMD approach. This is the main reason there should be a new driver.
    Slower chips will use the older VLIW4 architecture and Trinity chips should use VLIW4 architecture.

  5. #5
    Join Date
    Nov 2008
    Location
    California
    Posts
    61

    Default

    Quote Originally Posted by blackshard View Post
    High-end chips should have a completely new SIMD approach. This is the main reason there should be a new driver.
    Slower chips will use the older VLIW4 architecture and Trinity chips should use VLIW4 architecture.
    ...isn't that exactly what I said?

    (well, minus the VLIW5 part)

  6. #6
    Join Date
    Oct 2007
    Location
    Toronto-ish
    Posts
    7,440

    Default

    Just a reminder, current and GCN architectures are both SIMD -- it's just that current GPUs are VLIW SIMD while GCN is non-VLIW SIMD :

    http://developer.amd.com/afds/assets...2620_final.pdf

    See slide 19

    Maybe we need to introduce a new NPLIW architecture (Not Particularly Long Instruction Word) to avoid confusion

  7. #7
    Join Date
    Oct 2008
    Posts
    3,102

    Default Any VLIW5 chips are likely just rebadged from older generations, and not new

    The switch away from VLIW4 means that any shader compiler would be radically different, which is why i suspected they might start a new driver. All the compute features might impact that as well.

  8. #8
    Join Date
    Feb 2011
    Location
    France
    Posts
    196

    Default

    Does this new driver stack will be developed "internally" by AMD or in a "open" manner (I mean a git repo during the development). If I remember, r600g was mainly created by Red Hat guys?

  9. #9
    Join Date
    Jun 2011
    Posts
    104

    Default

    Quote Originally Posted by bridgman View Post
    Just a reminder, current and GCN architectures are both SIMD -- it's just that current GPUs are VLIW SIMD while GCN is non-VLIW SIMD :

    http://developer.amd.com/afds/assets...2620_final.pdf

    See slide 19

    Maybe we need to introduce a new NPLIW architecture (Not Particularly Long Instruction Word) to avoid confusion
    I was under the impression that GCN was MIMD rather than SIMD. Is that not accurate?

    http://www.brightsideofnews.com/news...itectures.aspx

  10. #10
    Join Date
    Dec 2007
    Posts
    2,360

    Default

    It will all be public once we are able to release the initial code.

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts
  •