AMD: Pirate Islands (R* 3** series) Speculation/Rumor Thread

Discussion in 'Architecture and Products' started by iMacmatician, Apr 10, 2014.

Tags:
  1. Grall

    Grall Invisible Member
    Legend

    Joined:
    Apr 14, 2002
    Messages:
    10,801
    Likes Received:
    2,175
    Location:
    La-la land
    102 both ways where?

    Xbone has no double-ported RAM, you can't both read and write simultaneously to either SRAM array or main DRAM.
     
  2. 3dilettante

    Legend Alpha

    Joined:
    Sep 15, 2003
    Messages:
    8,408
    Likes Received:
    4,132
    Location:
    Well within 3d
    It's 204 GB/s, 109 GB/s when running pure reads or pure writes, and 204 GB/s peak if using the interface in both directions to its maximum capacity. In the fully-loaded scenario, there is a bubble on the write path every 8 cycles.
    This has been covered in the console threads since this is a console-specific issue.

    With banking, it is possible to run multiple accesses from storage, even if the individual storage arrays cannot handle more than one access at a time.
     
  3. mosen

    Regular

    Joined:
    Mar 30, 2013
    Messages:
    452
    Likes Received:
    152
    Edit: Ooops! too late !! nvm.
     
    #103 mosen, May 30, 2014
    Last edited by a moderator: May 30, 2014
  4. homerdog

    homerdog donator of the year
    Legend Veteran Subscriber

    Joined:
    Jul 25, 2008
    Messages:
    6,286
    Likes Received:
    1,061
    Location:
    still camping with a mauler
    So Richard Huddy is back at AMD. My theory is that he was an AMD secret agent sent to Intel to gather their graphics secrets, then went back to AMD realizing he had nothing to learn from the blue team on that front. Should have sent a CPU guy...
     
  5. Wynix

    Veteran Regular

    Joined:
    Feb 23, 2013
    Messages:
    1,052
    Likes Received:
    57
    :lol::lol::lol:
     
  6. kalelovil

    Regular

    Joined:
    Sep 8, 2011
    Messages:
    563
    Likes Received:
    99
    Now seems quite an exciting time for Richard Huddy and his skill-set to be back at AMD, what with Mantle, upcoming DirectX 12, and the console design wins.
     
  7. gkar1

    Regular

    Joined:
    Jul 20, 2002
    Messages:
    614
    Likes Received:
    7
  8. LordEC911

    Regular

    Joined:
    Nov 25, 2007
    Messages:
    821
    Likes Received:
    113
    Location:
    'Zona
    Are blocks possibly 100million transistors?
    The numbers work, roughly, for the GPUs. Are the DTV/HD much more simple that they allow much higher density?
     
  9. pTmdfx

    Regular Newcomer

    Joined:
    May 27, 2014
    Messages:
    320
    Likes Received:
    239
    Sounds more likely the tiles of IP to me.
     
  10. silent_guy

    Veteran Subscriber

    Joined:
    Mar 7, 2006
    Messages:
    3,754
    Likes Received:
    1,380
  11. Kaotik

    Kaotik Drunk Member
    Legend

    Joined:
    Apr 16, 2003
    Messages:
    9,243
    Likes Received:
    3,189
    Location:
    Finland
    http://www.chipworks.com/en/technic...og/a-review-of-tsmc-28-nm-process-technology/
    One could see that working for GPUs too?
     
  12. McHuj

    Veteran Regular Subscriber

    Joined:
    Jul 1, 2005
    Messages:
    1,579
    Likes Received:
    801
    Location:
    Texas
  13. silent_guy

    Veteran Subscriber

    Joined:
    Mar 7, 2006
    Messages:
    3,754
    Likes Received:
    1,380
    Yes, but the Xbox One isn't the kind of chip that you push to extremes. If the unknown chip in question is a big die GPU running at the usual high clock speeds, and this is indeed HPM, then what's the point of having a super fast process?
     
  14. McHuj

    Veteran Regular Subscriber

    Joined:
    Jul 1, 2005
    Messages:
    1,579
    Likes Received:
    801
    Location:
    Texas
    It's not that it's just a super fast process, it also has better power numbers especially leakage. For a very large die, leakage will be a significant factor and since we're already pushing hunderds of watts for the GPU, anything that increases performs per watt is good.
     
  15. silent_guy

    Veteran Subscriber

    Joined:
    Mar 7, 2006
    Messages:
    3,754
    Likes Received:
    1,380
    I know HPM is better wrt leakage. But that doesn't help you if it has a higher Vcc (does it?) which results in higher dynamic power. And AFAIK its speed is slower too: it's not a super fast process compared to the fastest no hold barred process. And there's no point in making a super large die with a slower process.

    Edit: according to the TSMC table, HPM has similar speeds as HP, but Vcc is 0.9 vs 0.85V.

    Maybe that's sufficient...
     
    #115 silent_guy, Jul 16, 2014
    Last edited by a moderator: Jul 16, 2014
  16. Alexko

    Veteran Subscriber

    Joined:
    Aug 31, 2009
    Messages:
    4,515
    Likes Received:
    936
    Hawaii is 4XXmm² (I forget how much exactly) and already very close to the 300W limit at 1GHz. So perhaps this even bigger chip is meant to be run at somewhat lower clock speeds, at which point HPM makes sense.

    Or maybe the processes have evolved since they were introduced and HPM is now a better option at 1GHz than it used to be.
     
  17. Kaotik

    Kaotik Drunk Member
    Legend

    Joined:
    Apr 16, 2003
    Messages:
    9,243
    Likes Received:
    3,189
    Location:
    Finland
    There might be architectural changes lowering power consumption, too.
     
  18. itsmydamnation

    Veteran Regular

    Joined:
    Apr 29, 2007
    Messages:
    1,319
    Likes Received:
    416
    Location:
    Australia
    if finfets offer there best performance/power @ ~0.7 volts and your already power constrained it does make sense to start the process of targeting that over 2-3 generations (backend of 28 , 20 and then finally finfet 16).
     
  19. LordEC911

    Regular

    Joined:
    Nov 25, 2007
    Messages:
    821
    Likes Received:
    113
    Location:
    'Zona
    Interesting recent AMD research paper on TOP-PIM: Throughput-Oriented Programmable Processing in Memory.
    Seems to include the 25x improvement of system performance comment that was made recently.

    Things get interesting on page 8 and onward.
    Adding compute units to the logic die found at the bottom of the memory stack.
     
  20. lanek

    Veteran

    Joined:
    Mar 7, 2012
    Messages:
    2,469
    Likes Received:
    315
    Location:
    Switzerland
    Really interesting read, thanks.
     
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...