Nvidia Pascal Speculation Thread

Discussion in 'Architecture and Products' started by DSC, Mar 25, 2014.

Tags:
Thread Status:
Not open for further replies.
  1. DSC

    DSC
    Banned

    Joined:
    Jul 12, 2003
    Messages:
    689
    Likes Received:
    3
    [​IMG]

    [​IMG]
     
    #1 DSC, Mar 25, 2014
    Last edited by a moderator: Mar 25, 2014
  2. PeterAce

    Regular

    Joined:
    Sep 15, 2003
    Messages:
    489
    Likes Received:
    6
    Location:
    UK, Bedfordshire
    GTC Keynote states that is had NVLINK (a new GPU-GPU link) and 3D Memory (Stacked DRAM).

    Is this GPU a replacement or renamed Volta?
     
  3. AnarchX

    Veteran

    Joined:
    Apr 19, 2007
    Messages:
    1,559
    Likes Received:
    34
    Why should Intel integrate a NVLINK in their HPC CPUs? Or should Pascal servers bases on Denver+ CPUs?
     
  4. Niebotskick

    Newcomer

    Joined:
    Jul 7, 2013
    Messages:
    174
    Likes Received:
    198
    Interesting. Unified Memory has been moved from Maxwell to Volta (Pascal) ?
     
  5. lanek

    Veteran

    Joined:
    Mar 7, 2012
    Messages:
    2,469
    Likes Received:
    315
    Location:
    Switzerland

    CPU - GPU link ....
     
  6. Picao84

    Veteran Regular

    Joined:
    Feb 15, 2010
    Messages:
    1,561
    Likes Received:
    711
    Its both.
     
  7. 3dilettante

    Legend Alpha

    Joined:
    Sep 15, 2003
    Messages:
    8,137
    Likes Received:
    2,936
    Location:
    Well within 3d
    The Anandtech liveblog made mention of very wide bus widths for stacked memory, which is consistent with HBM or some variety of future WideIO than the narrower Hybrid Memory Cube bus.

    I haven't seen mention of an interposer, however, which would be needed for the highest bus widths.
     
  8. Dave Baumann

    Dave Baumann Gamerscore Wh...
    Moderator Legend

    Joined:
    Jan 29, 2002
    Messages:
    14,079
    Likes Received:
    648
    Location:
    O Canada!
    I thought I heard him make reference to "sitting on a wafer"
     
  9. pjbliverpool

    pjbliverpool B3D Scallywag
    Legend

    Joined:
    May 8, 2005
    Messages:
    7,583
    Likes Received:
    703
    Location:
    Guess...
    So NVLink is going to require both compatible motherboards and CPU's? And since theres no chance AMD will support this its basically reliant on Intel doing so.

    Anyone care to wager on how likely that is? Would they need to support this to be able to compete with IBM in the supercomputer market when being used in combination with NV GPU's? Or is it more likely Intel will use a competitve technology?

    I find it hard to get excited about this until there's some hint that we might actually see it in desktop PC's, which so far I'm not seeing.
     
  10. Blazkowicz

    Legend Veteran

    Joined:
    Dec 24, 2004
    Messages:
    5,607
    Likes Received:
    256
    A low latency interconnect is absolutely vital for a supercomputing chip. (even PC users complain of the PCIe)
    AMD has had Hypertransport since 2003, Intel has had QPI from 2009, next-gen Xeon Phi has QPI which is a similar move.

    The most likely use of NVLink in early system is given by their latter block diagram. Up to four GPUs communicate between them, probably accessing each other's data in a NUMA fashion. But communication to what's called "CPU" is done through slow PCI express.

    The candidate for a NVLink-enabled CPU would certainly be an ARMv8 SoC. ARM SoC are friendly to customization, revolve around an internal bus that is thus impossibly fast and where various accelerators and high speed interfaces plug in.. Best known example is maybe AMD Seattle, for now.
    From GPU's viewpoint, the prize is accessing at the least the "system CPU's" 1 TB or so memory.

    An ugly chipset could mash up between QPI and NVLink maybe, but that would increase latency and Intel would have to allow it.
     
  11. MfA

    MfA
    Legend

    Joined:
    Feb 6, 2002
    Messages:
    6,818
    Likes Received:
    480
    I wonder who NVIDIA is working with for the memory. Hynix too? HBM seems the only wide IO memory which will be ready soon (HMC is not wide IO memory).

    PS. guess they might be doing it with eDRAM at IBM ... expensive, but hell that silicon interposer is probably a 1000$ all by itself.
     
  12. McHuj

    Veteran Regular Subscriber

    Joined:
    Jul 1, 2005
    Messages:
    1,443
    Likes Received:
    560
    Location:
    Texas
    This is from one of the press releases linked above. Seems that PowerPC is the first to use NvLink


     
  13. DSC

    DSC
    Banned

    Joined:
    Jul 12, 2003
    Messages:
    689
    Likes Received:
    3
    http://techreport.com/news/26226/nvidia-pascal-to-use-stacked-memory-proprietary-nvlink-interconnect

     
    #15 DSC, Mar 26, 2014
    Last edited by a moderator: Mar 26, 2014
  14. Blazkowicz

    Legend Veteran

    Joined:
    Dec 24, 2004
    Messages:
    5,607
    Likes Received:
    256
    I guess last year's news was easily forgotten or looked over, by me at least.

    http://www.forbes.com/sites/davealt...celerator-and-strategic-partnership-with-ibm/

    From wikipedia's article on the POWER8 we even have a name for the bus. That's CAPI?
    It says it is layered on top of PCIe 3.0 but that would suck. I would think the nvidia GPU (and presumably the POWER8 CPU) use the physical PCIe 3.0 lines but run a different protocol over them.
    Else (likely), a POWER8 variant would be fabbed with a more appropriate bus (that still speaks "CAPI" on a high level but otherwise has the huge speed, low latency and compatibility with the NVLink GPU)

    /edit : wikipedia's sources, I'll let you look for yourself about the CAPI bus (not sure I like how that name sounds)
    http://www.pcworld.idg.com.au/article/524768/ibm_new_power8_doubles_performance_watson_chip/
    http://wccftech.com/ibm-power8-processor-architecture-detailed/
     
    #16 Blazkowicz, Mar 26, 2014
    Last edited by a moderator: Mar 26, 2014
  15. GpuMonkey

    Newcomer

    Joined:
    Sep 8, 2011
    Messages:
    8
    Likes Received:
    0
    Yes
     
  16. DSC

    DSC
    Banned

    Joined:
    Jul 12, 2003
    Messages:
    689
    Likes Received:
    3
  17. spworley

    Newcomer

    Joined:
    Apr 19, 2013
    Messages:
    146
    Likes Received:
    190
    It is indeed Hynix HBM. I confirmed this talking a Hynix rep at GTC. It may be that Pascal uses 2nd gen HBM, which would give 1TByte/sec throughput. This would match with Jen-hsun's rough numbers.
     
  18. Wynix

    Veteran Regular

    Joined:
    Feb 23, 2013
    Messages:
    1,052
    Likes Received:
    57
    I wish these companies would be more forthcoming with HBM details.

    Edit;
    Well that's good to hear.
    Perhaps we can expect ~500GB/s first gen HBM on the upcoming 20nm parts?
     
Loading...
Thread Status:
Not open for further replies.

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...