Nvidia Pascal Announcement

Discussion in 'Architecture and Products' started by huebie, Apr 5, 2016.

Tags:
  1. pharma

    Veteran Regular

    Joined:
    Mar 29, 2004
    Messages:
    2,930
    Likes Received:
    1,626
  2. I.S.T.

    Veteran

    Joined:
    Feb 21, 2004
    Messages:
    3,174
    Likes Received:
    389
    Do we have a paper launch or launch date for these yet?
     
  3. Kaotik

    Kaotik Drunk Member
    Legend

    Joined:
    Apr 16, 2003
    Messages:
    8,184
    Likes Received:
    1,841
    Location:
    Finland
    GTX 1050 Ti mid Oct, GTX 1050 late Oct, according to HWBattle
     
  4. iMacmatician

    Regular

    Joined:
    Jul 24, 2010
    Messages:
    773
    Likes Received:
    200
    From WCCFTech: "NVIDIA Rumored To Release Pascal Refresh With GDDR5X and Faster Clocks – Volta To Feature HBM2 and GDDR6 Support, 16 GB Standard Capacity [for a 256-bit bus]."

     
  5. ImSpartacus

    Regular Newcomer

    Joined:
    Jun 30, 2015
    Messages:
    252
    Likes Received:
    199
  6. lanek

    Veteran

    Joined:
    Mar 7, 2012
    Messages:
    2,469
    Likes Received:
    315
    Location:
    Switzerland
    Not much that what have been shown by Samsung ..

    In case you had not see it....

    Hotchips 28 via computerbase.de: https://www.computerbase.de/2016-08/samsung-gddr6-14-16-gbps-2018/

    [​IMG]

    [​IMG] [​IMG] [​IMG]
     
    #2086 lanek, Sep 28, 2016
    Last edited: Sep 28, 2016
    Razor1 and pharma like this.
  7. ieldra

    Newcomer

    Joined:
    Feb 27, 2016
    Messages:
    149
    Likes Received:
    116
    I.S.T. and ImSpartacus like this.
  8. ImSpartacus

    Regular Newcomer

    Joined:
    Jun 30, 2015
    Messages:
    252
    Likes Received:
    199
    Razor1 and I.S.T. like this.
  9. ieldra

    Newcomer

    Joined:
    Feb 27, 2016
    Messages:
    149
    Likes Received:
    116
    It looks like there's going to be an 8-way DPA instruction and that this SoC includes only 64b cores

    512 cores x 8 ops per cycle x 2ghz = 20 TOP/s

    It's roughly one fifth the size of GP104 so by my very rough estimate it's doubling perf/w (quadruple if you consider new instruction)

    Btw I saw 20TOP/s claimed for this SoC but now I can't find the claim lol

    edit:
    ~16 TOP/s not 20 according to my calculation at 2ghz
     
    #2089 ieldra, Sep 28, 2016
    Last edited: Sep 28, 2016
    Razor1 and iMacmatician like this.
  10. iMacmatician

    Regular

    Joined:
    Jul 24, 2010
    Messages:
    773
    Likes Received:
    200
    It's on a separate slide (referenced by AnandTech).

    [​IMG]

     
    Razor1, nnunn and ieldra like this.
  11. Esrever

    Regular Newcomer

    Joined:
    Feb 6, 2013
    Messages:
    594
    Likes Received:
    298
    Did nvidia ever get to the 10x maxwell performance in pascal?
     
  12. lanek

    Veteran

    Joined:
    Mar 7, 2012
    Messages:
    2,469
    Likes Received:
    315
    Location:
    Switzerland
    The 10x was a invented metrics... lately Nvidia do slides as they could do it if they was in the smartphone market.. 2x more Vram bandwith, 2x performance / wattts, 4x performance at FP16 + 2x more Vram capacity = 10x more performance ( 2+2+4+2 )
     
    #2092 lanek, Sep 28, 2016
    Last edited: Sep 28, 2016
  13. ieldra

    Newcomer

    Joined:
    Feb 27, 2016
    Messages:
    149
    Likes Received:
    116
    It was actually 10x faster at training AlexNet and yes they did achieve that (almost)

    https://blogs.nvidia.com/blog/2015/03/17/pascal/
     
    pharma and Razor1 like this.
  14. firstminion

    Newcomer

    Joined:
    Aug 7, 2013
    Messages:
    217
    Likes Received:
    46
  15. Razor1

    Veteran

    Joined:
    Jul 24, 2004
    Messages:
    4,232
    Likes Received:
    749
    Location:
    NY, NY
    think they are talking about the old titan x's regarding int 8 calculations.
     
  16. Razor1

    Veteran

    Joined:
    Jul 24, 2004
    Messages:
    4,232
    Likes Received:
    749
    Location:
    NY, NY
  17. Esrever

    Regular Newcomer

    Joined:
    Feb 6, 2013
    Messages:
    594
    Likes Received:
    298
    That is what they said but where does it actually show any tests or benchmarks? As far as I can tell they put nvlink as the reason it somehow gets 10x instead of 5x which makes me wonder if they are comparing 2 GPUs vs 1 because their half precision performance doesn't go up nearly 10x on paper.
     
  18. pharma

    Veteran Regular

    Joined:
    Mar 29, 2004
    Messages:
    2,930
    Likes Received:
    1,626
    pjbliverpool likes this.
  19. iMacmatician

    Regular

    Joined:
    Jul 24, 2010
    Messages:
    773
    Likes Received:
    200
    That 10x number includes a doubling in the number of GPUs due to NVLink. The part of the slide where NVLink is mentioned is cut off in the picture in the blog.

    [​IMG]
     
    nnunn, pharma and no-X like this.
  20. ieldra

    Newcomer

    Joined:
    Feb 27, 2016
    Messages:
    149
    Likes Received:
    116
    I think they were comparing racks,so it was a dgx-1
    Yeah and they reported a 12x speedup using DGX-1 vs a maxwell based rack which I think had half as many GPUs
     
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...