AMD: Southern Islands (7*** series) Speculation/ Rumour Thread

Discussion in 'Architecture and Products' started by UniversalTruth, Dec 17, 2010.

  1. Sinistar

    Sinistar I LIVE
    Regular Subscriber

    Joined:
    Aug 11, 2004
    Messages:
    660
    Likes Received:
    74
    Location:
    Indiana
    Still listed here
     
  2. Squilliam

    Squilliam Beyond3d isn't defined yet
    Veteran

    Joined:
    Jan 11, 2008
    Messages:
    3,495
    Likes Received:
    114
    Location:
    New Zealand
  3. Alexko

    Veteran Subscriber

    Joined:
    Aug 31, 2009
    Messages:
    4,514
    Likes Received:
    934
    Since when does Dell (or any OEM, for that matter) advertise the amount of memory bandwidth on the graphics card?
     
  4. rpg.314

    Veteran

    Joined:
    Jul 21, 2008
    Messages:
    4,298
    Likes Received:
    0
    Location:
    /
    They could atleast tell us what GPU is in there.

    Would you like to buy an Intel 2GB machine?
     
  5. trinibwoy

    trinibwoy Meh
    Legend

    Joined:
    Mar 17, 2004
    Messages:
    10,561
    Likes Received:
    601
    Location:
    New York
    Yeah that's really weird. Completely inconsistent with their normal GPU descriptions.
     
  6. trinibwoy

    trinibwoy Meh
    Legend

    Joined:
    Mar 17, 2004
    Messages:
    10,561
    Likes Received:
    601
    Location:
    New York
    Anybody else think that Cayman's ALU:TEX ratio is a bit on the low side? The other thing is that Cayman's texturing capacity is obviously way over-specified. I can't see them further doubling the number of texture units so the ALU:TEX could/should increase in SI.

    Option 1: 32 wide SIMDs
    Requires a doubling of register file bandwidth and wavefronts would execute over two cycles instead of four. Doesn't seem impossible.

    Option 2: Multiple SIMDs share a quad-TMU
    Not sure how feasible this is with AMD's predetermined execution latencies for each clause.

    Option 3: ????
     
  7. DarthShader

    Regular

    Joined:
    Jul 18, 2010
    Messages:
    350
    Likes Received:
    0
    Location:
    Land of Mu
    Option 2 has been speculated already a year ago by Jawed, he found some patents too.
     
  8. Thowllly

    Regular

    Joined:
    Feb 6, 2002
    Messages:
    551
    Likes Received:
    4
    Location:
    Norway
    I don't. AFAIK, it has 16 ALUs per texture sampler, thats
    32 flops per bilinear sample (same as GF110, 24:1 for GF114)
    64 flops per trilinear sample (same as GF110, 48:1 for GF114)
    up to 1024 flops per sample with 16xAF (same as GF110, 768:1 for GF114)
    up to 2048 flops per sample with 64bit textures. (GF110 is 1024:1, GF114 is 768:1)
     
  9. trinibwoy

    trinibwoy Meh
    Legend

    Joined:
    Mar 17, 2004
    Messages:
    10,561
    Likes Received:
    601
    Location:
    New York
    Exactly, on paper it's the same as GF110 but in practice it's going to be lower due to lower ALU utilization. Unless texturing on Cayman is extremely inefficient it just has too many units. The 6970 has twice the texturing capacity as a 570 and is only on par performance wise. If they keep this ratio then even more transistors will be wasted doing texturing on SI. Note that the 570 also has lower numbers for bandwidth, fillrate and flops.

    I wouldn't be surprised if full speed FP16 filtering makes its debut as well so that 64-bit ratio can potentially come down too.
     
  10. Man from Atlantis

    Regular

    Joined:
    Jul 31, 2010
    Messages:
    747
    Likes Received:
    60
    DKrwt David Kanter
    Next AMD GPU is much more programmable. no VLIW, real L1 and L2 caches, better branching, etc.

    just seen this at twitter :D
     
  11. trinibwoy

    trinibwoy Meh
    Legend

    Joined:
    Mar 17, 2004
    Messages:
    10,561
    Likes Received:
    601
    Location:
    New York
    Wow nice! It will be a lot of fun to see how they tackle those problems and see whether they can do it more efficiently than nVidia has managed to.

    Wonder how that tidbit got out. Did some good wine loosen tongues at the dinner? :)
     
  12. Alexko

    Veteran Subscriber

    Joined:
    Aug 31, 2009
    Messages:
    4,514
    Likes Received:
    934
    I personally find that very odd, so soon after moving from VLIW5 to VLIW4, which must have been quite time-consuming.
     
  13. psurge

    Regular

    Joined:
    Feb 6, 2002
    Messages:
    947
    Likes Received:
    46
    Location:
    LA, California
  14. Man from Atlantis

    Regular

    Joined:
    Jul 31, 2010
    Messages:
    747
    Likes Received:
    60
    my inner voice tells me it is 8000 series not 7000s..
     
  15. Kaotik

    Kaotik Drunk Member
    Legend

    Joined:
    Apr 16, 2003
    Messages:
    8,873
    Likes Received:
    2,808
    Location:
    Finland
    Or could it be just that the 32nm cancellation, which caused 6000-series delay (IIRC 6 months was at least called somewhere), made them scratch the "original 7000" and start rushing "original 8000" series as "7000s"?
     
  16. wishiknew

    Regular

    Joined:
    May 19, 2004
    Messages:
    334
    Likes Received:
    6
  17. trinibwoy

    trinibwoy Meh
    Legend

    Joined:
    Mar 17, 2004
    Messages:
    10,561
    Likes Received:
    601
    Location:
    New York
    Wonder if they'll stick with the precompiled clause approach and avoid the scheduler and scoreboarding overhead. Could be the best of both worlds.

    This makes complete sense to me. A 64-wide SIMD could run the same scalar instruction on 64 threads/pixels/vertices with the same bandwidth requirements as today's 16-wide VLIW4 and gain higher efficiency in the process. The challenge is branch granularity, they would need to process a wavefront in a single cycle instead of 4.

    Or maybe each SIMD is only 16 wide with 4 of them executing 4 different wavefronts in parallel. Very similar to an nVidia SM but with potentially much lower control overhead if they don't do hardware instruction scheduling.
     
  18. wishiknew

    Regular

    Joined:
    May 19, 2004
    Messages:
    334
    Likes Received:
    6
    Still kinda amazed no one posted those slides from pcper.
     
  19. trinibwoy

    trinibwoy Meh
    Legend

    Joined:
    Mar 17, 2004
    Messages:
    10,561
    Likes Received:
    601
    Location:
    New York
    Ah yes just saw that. So no more clauses. They seem to be embracing a lot of things nVidia has been preaching for years. Guess it'll come down to who has the best implementation.
     
  20. fellix

    fellix Hey, You!
    Veteran

    Joined:
    Dec 4, 2004
    Messages:
    3,505
    Likes Received:
    424
    Location:
    Varna, Bulgaria
    So, AMD is finally getting rid of the static scheduling?
     
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...