AMD: R9xx Speculation

Discussion in 'Architecture and Products' started by Lukfi, Oct 5, 2009.

  1. fellix

    Veteran

    Joined:
    Dec 4, 2004
    Messages:
    3,552
    Likes Received:
    514
    Location:
    Varna, Bulgaria
    Let's hope they've done something to improve the compression, at least. :???:
     
  2. Triskaine

    Newcomer

    Joined:
    Mar 28, 2010
    Messages:
    59
    Likes Received:
    57
    One SIMD still has 80 SP's, but now with 4D ALU's, which means that wavefront size has increased to 80. :runaway:

    Why would they do that? 64 was already big, now Branch-Granularity will suck even more compared to GF100. :frown:

    But at least the 6770 will soundly beat the 5850 with those specs, that's for sure.
     
  3. Jawed

    Legend

    Joined:
    Oct 2, 2004
    Messages:
    11,708
    Likes Received:
    2,132
    Location:
    London
    Revised slide is confusing

    20 VLIW-4s per SIMD? :shock: That's very strange.
     
  4. Jawed

    Legend

    Joined:
    Oct 2, 2004
    Messages:
    11,708
    Likes Received:
    2,132
    Location:
    London
    80 is a really really nasty number for hardware thread size. If this is true then a whole pile of code that enjoys the "squareness" of 64 or 256 sized workgroups is going to be a nightmare. A total fucking bitch, in fact. Not to mention the mismatch in banks for 32KB of LDS, which doesn't divide into 20s in any meaningful way.

    I don't believe this.
     
  5. Triskaine

    Newcomer

    Joined:
    Mar 28, 2010
    Messages:
    59
    Likes Received:
    57
    I don't want to believe this either, but that's the only possible way to interprete that slide.
     
  6. John021

    Newcomer

    Joined:
    Jan 1, 2010
    Messages:
    29
    Likes Received:
    0

    Common people do not understand this..:sad: what does it means in terms of performance, power or something else?

    Do drivers for these cards will be a nightmare to make?
     
  7. PatrickL

    Veteran

    Joined:
    Mar 3, 2003
    Messages:
    1,315
    Likes Received:
    13
    Who said theses slides were not another fake attempt ?
     
  8. CarstenS

    Legend Subscriber

    Joined:
    May 31, 2002
    Messages:
    5,800
    Likes Received:
    3,920
    Location:
    Germany
    This doesn't look like a typical AMD slide either. At least not the ones I know from the past. They have mostly been structured with a liitle bit of information per slide and - very importantly - the improvements in each area highlighted.
     
  9. Arnold Beckenbauer

    Veteran Subscriber

    Joined:
    Oct 11, 2006
    Messages:
    1,756
    Likes Received:
    722
    Location:
    Germany
    So this picture says, HD6770 can give you 2304 GFLOPS. How is this possible?
    ...


    Crap, something went wrong.
     
    #2189 Arnold Beckenbauer, Sep 26, 2010
    Last edited by a moderator: Sep 26, 2010
  10. mao5

    Regular

    Joined:
    Apr 14, 2004
    Messages:
    276
    Likes Received:
    5
  11. UniversalTruth

    Veteran

    Joined:
    Sep 5, 2010
    Messages:
    1,747
    Likes Received:
    22
    Ok. :lol: I want the real one then. :evil: :lol:
     
  12. mao5

    Regular

    Joined:
    Apr 14, 2004
    Messages:
    276
    Likes Received:
    5
    already in some posts
     
  13. Triskaine

    Newcomer

    Joined:
    Mar 28, 2010
    Messages:
    59
    Likes Received:
    57
    This says otherwise:

    http://www.wolframalpha.com/input/?i=1280*2*0.9
     
  14. Man from Atlantis

    Regular

    Joined:
    Jul 31, 2010
    Messages:
    960
    Likes Received:
    853
    give the real one then
     
  15. no-X

    Veteran

    Joined:
    May 28, 2005
    Messages:
    2,451
    Likes Received:
    471
    There's no mention about transistor count and power consumption... it's also untypical, that 2/3 of the slide are consumed by specifications of previous gen. products. This slide also mentions 5 Gbps modules for all products, despite HD5xxx slides always mentioned exact numbers (e.g. 4.8 Gbps for HD5870).
     
  16. mboeller

    Regular

    Joined:
    Feb 7, 2002
    Messages:
    923
    Likes Received:
    3
    Location:
    Germany
    Where?
     
  17. MarkoIt

    Regular

    Joined:
    Mar 1, 2007
    Messages:
    392
    Likes Received:
    0
    It's probably another fake slide.. it's not enough polished to be real.
    but if what mao5 is true, that the official pdf are around it won't be much before we get real leaks. It would be about time, launch is in less than 3 weeks!
     
  18. EduardoS

    Newcomer

    Joined:
    Nov 8, 2008
    Messages:
    131
    Likes Received:
    0
    Another fake, but 80*4 = 64*5, I think there is enough rumors to dismiss the 4D ALUs rumor, it's 5D again, at least for this generation.

    And I'm not sad about this... But drivers could improve, it's taking too long to see a decent compiler for this.
     
  19. caveman-jim

    Regular

    Joined:
    Sep 19, 2005
    Messages:
    305
    Likes Received:
    0
    Location:
    Austin, TX
    it is?!
     
  20. neliz

    neliz GIGABYTE Man
    Veteran

    Joined:
    Mar 30, 2005
    Messages:
    4,904
    Likes Received:
    23
    Location:
    In the know
    I surely hope that's wrong.
     
Loading...

Share This Page

  • About Us

    Beyond3D has been around for over a decade and prides itself on being the best place on the web for in-depth, technically-driven discussion and analysis of 3D graphics hardware. If you love pixels and transistors, you've come to the right place!

    Beyond3D is proudly published by GPU Tools Ltd.
Loading...