1. Welcome to TechPowerUp Forums, Guest! Please check out our forum guidelines for info related to our community.

AMD "Hawaii" Architecture Diagram Leaked

Discussion in 'News' started by btarunr, Oct 14, 2013.

  1. btarunr

    btarunr Editor & Senior Moderator Staff Member

    Joined:
    Oct 9, 2007
    Messages:
    28,742 (11.14/day)
    Thanks Received:
    13,676
    Location:
    Hyderabad, India
    An alleged company slide detailing the architecture of AMD's upcoming "Hawaii" GPU was leaked to the web, revealing a monstrous combination of components. The GPU maintains the same component hierarchy as "Tahiti." The most distinguishing feature here is that whereas "Tahiti" features two shader engines, "Hawaii" features four. What it translates to, is double the geometry processing power, four independent geometry processors with a tessellation unit each, and double the number of ROPs, at 64. Each shader unit features 11 compute units (CU), the number-crunching machinery of the GPU. Each CU holds 4 TMUs (texture memory units), and 64 stream processors.

    The four shader engines of "Hawaii" are tied to a unified command processing structure, a 1 megabyte L2 cache, a 512-bit wide GDDR5 memory interfaces, and the ancillaries, that include the PCI-Express 3.0 x16 bus interface, six display controllers (six TMDS links in all), CrossFireX XDMA, and multimedia accelerators that include UVD (accelerates high-def video), VCE (video codec engine, accelerates multimedia codecs), and the new TrueAudio hardware DSP.

    [​IMG] [​IMG] [​IMG] [​IMG] [​IMG]

    Source: 3DCenter.org
     
    Aquinus says thanks.
  2. Delta6326

    Delta6326

    Joined:
    May 21, 2008
    Messages:
    3,831 (1.63/day)
    Thanks Received:
    667
    Location:
    Iowa, USA
    Beastly.
     
  3. Lionheart

    Lionheart

    Joined:
    Apr 30, 2008
    Messages:
    4,065 (1.71/day)
    Thanks Received:
    812
    Location:
    Milky Way Galaxy
    That description just makes me want one of these even more :cry:
     
  4. MxPhenom 216

    MxPhenom 216 Corsair Fanboy

    Joined:
    Aug 31, 2010
    Messages:
    10,066 (6.61/day)
    Thanks Received:
    2,277
    Location:
    Seattle, WA
    :twitch: :eek: :twitch: :D
     
  5. jigar2speed

    jigar2speed

    Joined:
    Mar 6, 2012
    Messages:
    192 (0.20/day)
    Thanks Received:
    30
    On paper this GPU seems be a computing beast. O_O
     
    Last edited: Oct 14, 2013
  6. 1d10t

    1d10t

    Joined:
    Sep 28, 2012
    Messages:
    193 (0.25/day)
    Thanks Received:
    42
    Interesting fact that this is still on 28nm :toast:

    -=edited=-

    Don't confusing yourself with your uArch processor :slap:
    it explain well you didn't have proper cooling for your own :troll: :nutkick:
     
    Last edited: Oct 14, 2013
  7. McSteel

    McSteel

    Joined:
    Nov 19, 2012
    Messages:
    603 (0.85/day)
    Thanks Received:
    288
    The power density would have been too great on 22nm, it'd be extremely difficult to cool the GPU properly.
     
  8. buggalugs

    buggalugs

    Joined:
    Jul 19, 2008
    Messages:
    949 (0.41/day)
    Thanks Received:
    152
    Location:
    Australia
    Yep, I want....

    If somebody can tell me how a 512 bit memory interface uses less area than a 384 bit one that would be great.

    I assume they're talking about the memory interface at the GPU end not the board.
     
  9. NC37

    NC37

    Joined:
    Oct 30, 2008
    Messages:
    1,198 (0.55/day)
    Thanks Received:
    266
    A GPU with L2 cache...huh...thats something I didn't expect to see. Wonder if they did that based on their experience working with APUs.

    If AMD wasn't rehashing some of the 7x00 series models for this gen then I'd almost think we may finally be coming out of the stagnation period that we've been in since Fermi launched. Not that it has been bad, we've had some great GPUs. But it is about time we moved on.
     
  10. TheHunter

    TheHunter

    Joined:
    Apr 10, 2012
    Messages:
    967 (1.04/day)
    Thanks Received:
    366
    Location:
    Europa
    Its nothing new, I think its been around since ATI 5000 series.. Even 6?year old G80 aka 8800gtx had L1, L2 cache.


    Its here mostly for compute and yeah its very small, obviously. :)
     
    Last edited: Oct 14, 2013
  11. acperience7

    Joined:
    Nov 26, 2007
    Messages:
    258 (0.10/day)
    Thanks Received:
    31
    Really curious to see if 2 of these could take advantage of the extra lanes in a 4820k or a 4960x.
     
  12. HisDivineOrder

    HisDivineOrder

    Joined:
    Aug 23, 2013
    Messages:
    90 (0.21/day)
    Thanks Received:
    21

    It appears they optimized the memory interface since GCN 1.0 for GCN 1.1. Makes you wish they'd updated the 7970/R9 280X, 7950/R9 280, 7870/R9 270X, and 7850/R9 270 with GCN 1.1 just to see what improvements would have come from the optimization of diespace. If I recall correctly, the rumored improvements of Volcanic Islands (when it was a full GPU update instead of reheated leftovers with a new high end) were going to be "higher clockspeeds" and/or "smaller dies."

    It kinda makes a bit more sense when given how optimized R9 290X seems to be.
     
  13. W1zzard

    W1zzard Administrator Staff Member

    Joined:
    May 14, 2004
    Messages:
    14,975 (3.92/day)
    Thanks Received:
    11,801
    the memory controller uses less silicon surface area _of the gpu_

    the pcb with the memory controller signals will be much more complicated, crowded and expensive, more than a factor of two, when compared to 256 bit.
     
  14. itsakjt

    itsakjt

    Joined:
    Oct 9, 2010
    Messages:
    1,176 (0.79/day)
    Thanks Received:
    382
    Location:
    Kolkata, India
    Freaking awesome!

    512 bit bus width! That's freaking amazing. I wonder how much these will cost!
     
  15. theoneandonlymrk

    theoneandonlymrk

    Joined:
    Mar 10, 2010
    Messages:
    3,411 (2.01/day)
    Thanks Received:
    572
    Location:
    Manchester uk
    very nice likeing the look of 8 Ace engines and 4 geometry/tess engines, anyone after a 7970:mad:
    also 340Kb cache per Cu compute unit makes for a lot of on die cache x44
     
    More than 25k PPD
  16. EpicShweetness

    EpicShweetness

    Joined:
    Dec 1, 2011
    Messages:
    307 (0.29/day)
    Thanks Received:
    30
    Location:
    Ft Gordon
    So....
    2816 SP's at a clock speed of ??? (maybe 1050)
    64 ROP's
    176 TMU's
    A Bus that is capable of 64 bytes (512 bits) in a single clock, and does 5 billion clocks in a second moving a substantial 320 Gigabytes in that second
    Finally a pool of 4GB VRAM, wow :rockout:

    Shaping up to be an amazing card, less TMU's then a GK110 based product though.
     
  17. TheHunter

    TheHunter

    Joined:
    Apr 10, 2012
    Messages:
    967 (1.04/day)
    Thanks Received:
    366
    Location:
    Europa
    But more ROPs, which means higher pixel fillrate, apparently +64 gpixel/s.,
    I noticed Crysis, Crysis Warhead really likes higher pixel fillrates.


    And from what saw higher TMU's matter only at higher resolution or multi monitor setup
     
  18. suraswami

    suraswami

    Joined:
    Apr 5, 2005
    Messages:
    6,235 (1.78/day)
    Thanks Received:
    832
    Location:
    Republic of Asia (a.k.a Irvine), CA
    If AMD can make a GPU = 7950 with no PCIE power pin and even less power consumption then I will take 2 :D
     

Currently Active Users Viewing This Thread: 1 (0 members and 1 guest)

Share This Page