Nvidia BigK GK110 Kepler Speculation Thread

Discussion in 'Architecture and Products' started by A1xLLcqAgt0qc2RyMz0y, Apr 21, 2012.

  1. lanek

    Veteran

    Joined:
    Mar 7, 2012
    Messages:
    2,121
    Location:
    Switzerland

    Some parts can be accelerated by GPGPU computing for the 3D render for 3Dmax ( Iray with CUDA for the example )... I dont know why i write AUtocad, when i was think to Autodesk. ( plugins exist too, as for physic, OpenCL library exist for Maya etc ).
     
  2. Kaotik

    Kaotik Drunk Member
    Legend

    Joined:
    Apr 16, 2003
    Messages:
    6,528
    So what's the configuration then?
    It uses "192-core SMX" but we know GK104 SMX was 192 FP32 cores and 8 FP64 cores, that's definately not enough FP64 for GK110
     
  3. ToTTenTranz

    Legend Veteran Subscriber

    Joined:
    Jul 7, 2008
    Messages:
    6,115
    I'm watching the nVidia presentation.

    Jeez, Dave Perry is one of those guys who talks like he finishes every sentence with a question mark.. how irritating!

    Is it my impression or is this presentation more about services that can use cloud computing rather than Kepler itself?

    What's this thing about virtual gpu? How is it better than a remote desktop?
     
  4. ninelven

    Veteran

    Joined:
    Dec 27, 2002
    Messages:
    1,590
    I think the 192-core SMX was just in reference to GK104. GK110 will probably be 1/2 rate DP like Fermi. Anyway, it appears to be a huge die with many "cores."
     
  5. Man from Atlantis

    Regular

    Joined:
    Jul 31, 2010
    Messages:
    730
    i see 5 GPCs, upper mid one(wonder what is it? fully dedicated 1:1 DP units? as a plus other CCs run half speed or 1/4) is looking totally different.. it's in asymetric pattern kinda like GT200 unlike Fermi and GK104.. i try to figure die size by pcie area and i found 509mm2 but it's off as what JHH says biggest gpu we've ever built
     
  6. AnarchX

    Veteran

    Joined:
    Apr 19, 2007
    Messages:
    1,557
  7. fellix

    fellix Hey, You!
    Veteran

    Joined:
    Dec 4, 2004
    Messages:
    3,337
    Location:
    Varna, Bulgaria
    But still 6 setup pipes means 48 fragments scan-out capacity, that nicely matches the ROP throughput.

    Anyway:

    [​IMG]

    :lol:
     
  8. ninelven

    Veteran

    Joined:
    Dec 27, 2002
    Messages:
    1,590
    Very rough estimate on the die size got me ~565mm^2.
     
  9. Alexko

    Veteran

    Joined:
    Aug 31, 2009
    Messages:
    3,928
    So we're looking at 2880SPs, probably at 700MHz or so; perhaps more on GeForces—assuming they make GeForces with it.
     
  10. Man from Atlantis

    Regular

    Joined:
    Jul 31, 2010
    Messages:
    730
    nicely done fellix +rep :D

    2880CCs, 180TMUs, 48ROPs, 384bit MC, FP64 2 TFlops@700MHz
     
  11. fellix

    fellix Hey, You!
    Veteran

    Joined:
    Dec 4, 2004
    Messages:
    3,337
    Location:
    Varna, Bulgaria
    [​IMG]

    My calculation says ~520mm² -- on par with GF100.
    The GK104's SMX is definitely smaller, it seems.
     
  12. Man from Atlantis

    Regular

    Joined:
    Jul 31, 2010
    Messages:
    730
  13. Kaotik

    Kaotik Drunk Member
    Legend

    Joined:
    Apr 16, 2003
    Messages:
    6,528
    It has to be, it has only 8 FP64 cores and 192 FP32 cores, GK110 SMX has to has a lot more FP64
     
  14. silent_guy

    Veteran

    Joined:
    Mar 7, 2006
    Messages:
    3,416
    Are current virtual machines servers like Vmware able to use GPUs for 3D rendering? Not talking about stuff like Parallels or Vmware Fusion, but the big iron stuff?
     
  15. psurge

    Regular

    Joined:
    Feb 6, 2002
    Messages:
    896
    Location:
    LA, California
    Sounds like BigK has the ability to launch kernels from within kernels (the HyperQ stuff mentioned in the keynote). Any more info on that?
     
  16. fellix

    fellix Hey, You!
    Veteran

    Joined:
    Dec 4, 2004
    Messages:
    3,337
    Location:
    Varna, Bulgaria
    SMX comparison:

    [​IMG]

    I think NV left the TMU configuration intact from GK104, which would mean 240 FP16 samples per clock!
     
  17. Blazkowicz

    Legend Veteran

    Joined:
    Dec 24, 2004
    Messages:
    5,357
    currently you have to use an IOMMU that sits on the motherboard, Intel calls it Vt-d, and pass around the whole graphics card to a VM. hypervisor such as Xen or Vmware (ESXi variant) has to support it. same tech allows to use a real network card, storage controller or usb controller.

    but doing that, it's one GPU per VM, and one VM per GPU, with implementation limitations that can kick in (it's tricky due to specific nature of the VGA BIOS, so for how many cards will this work? depends on hypervisor, graphics card and motherboard)
    the IOMMU translates addressing, commands meant for the VM's address space into real addressing for the physical graphics card, and vice versa.
    also if you want to beam framebuffer up through the network, you'll have to do it yourself it's not covered by the technique.

    here, and I wondered before if I understood that well from the presentation, an MMU sits in the GPU and communicates with the hypervisor so the transition from virtual to real addressing is done there. so apparently you can use as many physical GPU as you want, and on top of that as many virtual (i.e. as seen by the VM) GPUs as you want.

    it's in the scenario of VDI, i.e. one VM per user. I find this to be needless waste (unless Windows 7 pro or enterprise is allowed, saving a lot on licensing). why not have 20 users per VM. but maybe you can have multiple virtual GPUs per VM, I don't know.

    [nice that you find something like Xen to be "big iron", I know of a nice installation of it on a pentium E2200 with 2GB ram, running 5 VMs with almost no down time for a few years :)]
     
  18. AnarchX

    Veteran

    Joined:
    Apr 19, 2007
    Messages:
    1,557
  19. iMacmatician

    Regular

    Joined:
    Jul 24, 2010
    Messages:
    627
    Location:
    United States of America
    15 SMXs is a weird number, not only is it not a power of 2 but it's the farthest one can get from a power of 2, in the sense that 15 = 2^3 + 2^2 + 2^1 + 1. I was expecting the possibility of a non-power of 2 after GT200 but I didn't know they could do this.

    Similar to GF100 in at least that respect then.

    I'm curious, is there any reason not to expect 6 GHz memory on at least one of the first GPUs based on GK110?
     
  20. Kaotik

    Kaotik Drunk Member
    Legend

    Joined:
    Apr 16, 2003
    Messages:
    6,528
    That 2880 shaders is just assuming similar SMX configuration as GK104, which can't be true.
    If it's 192 with half-clockrate FP64 it's possible, but otherwise the 192 figure has to be wrong
     

Share This Page

Loading...