Nvidia Slide reveals numbers on Single and Double precision for Flagship pascal GPU

Discussion in 'Frontpage news' started by Hilbert Hagedoorn, Feb 17, 2016.

  1. Hilbert Hagedoorn

    Hilbert Hagedoorn Don Vito Corleone Staff Member

    Messages:
    38,960
    Likes Received:
    7,631
    GPU:
    AMD | NVIDIA
  2. fantaskarsef

    fantaskarsef Ancient Guru

    Messages:
    11,732
    Likes Received:
    3,713
    GPU:
    2080Ti @h2o
    Interesting that Maxwell's not mentioned in that slide but they show Fermi and Kepler... Wonder how this would rank, who knows, maybe very close to Pascal.
     
  3. Denial

    Denial Ancient Guru

    Messages:
    12,998
    Likes Received:
    2,393
    GPU:
    EVGA 1080Ti
    For big Pascal the numbers don't seem that unreasonable given that they essentially skipped a generation with double precision. I doubt a card this big will launch this year though.

    I wonder how Pascal is going to work anyway. Are they going to make gaming cards full precision, with cut down double like they do now? or are the gaming cards going to have mixed precision on them along with double and full? Isn't that like a waste of die space?

    Maxwell doesn't have a card that has dedicated DP on it -- they are all cut down.
     
    Last edited: Feb 17, 2016
  4. Krteq

    Krteq Master Guru

    Messages:
    660
    Likes Received:
    204
    GPU:
    RX Vega 56 +64 BIOS
    It's an estimated computing performance taken from slides from June 2015.
     

  5. fantaskarsef

    fantaskarsef Ancient Guru

    Messages:
    11,732
    Likes Received:
    3,713
    GPU:
    2080Ti @h2o
    Of course you are right, totally forgot about that!
     
  6. Denial

    Denial Ancient Guru

    Messages:
    12,998
    Likes Received:
    2,393
    GPU:
    EVGA 1080Ti
    Yeah, it says that in the article...
     
  7. Noisiv

    Noisiv Ancient Guru

    Messages:
    7,130
    Likes Received:
    772
    GPU:
    2070 Super
    Not bad, but these are pro cards, operating 24/7
    SP flops need to be multiplied by ~1.25 to account for higher clocks on consumer version.

    Volta (Sierra/Summit) as early as 2017.
    https://www.olcf.ornl.gov/summit/

    [​IMG]
     
  8. svictorcc

    svictorcc Member

    Messages:
    10
    Likes Received:
    0
    GPU:
    msi gtx 970
    Imho, and considering some other infos, i'm almost sure Pascal GP100 will launch this year and before GP104.
     
  9. AnarchoPrimitiv

    AnarchoPrimitiv New Member

    Messages:
    3
    Likes Received:
    0
    GPU:
    Radeon 390x 8GB
    14nm? I thought it was supposed to be 16nm?

    Pascal is 14nm? I thought it was supposed to be 16nm (and Polaris[AMD] is supposed to be 14nm)? That's what all the news on other sites has been confirming for the last several months.
     
  10. Lane

    Lane Ancient Guru

    Messages:
    6,361
    Likes Received:
    3
    GPU:
    2x HD7970 - EK Waterblock
    Damn old slide, it seems ... June 2015 and based on even older projection.

    Not that thoses number are not believable. its around 50% SP gain.

    This said the author is not part of Nvidia. ( even if it cite Nivida engineer )
     
    Last edited: Feb 17, 2016

  11. geogan

    geogan Master Guru

    Messages:
    674
    Likes Received:
    116
    GPU:
    Gigabyte GTX 1070
    From what I know Nvidia cripped or removed double precision form their consumer level Geforce cards so they didn't cut into lucrative sales of their way more expensive pro cards, but AMD did not do this.

    Hence my humble dual GPU HD7990 card has a DP performance of over 2000 whereas the Tesla K20X only has 1310 and how much is a Tesla K20X these days? Over two grand? and originally costing?
     
  12. Denial

    Denial Ancient Guru

    Messages:
    12,998
    Likes Received:
    2,393
    GPU:
    EVGA 1080Ti
    I think it's more apt to compare the HD7990 to the Titan Black, which was also $1000, is only ~150Gflops less DP performance, but ~100w less power - though it did launch a year later.

    Nvidia shifted away from DP performance because most of the HPC market shifted towards neural networks, which perform best in mixed precision. I mean yeah, differentiating their products was also probably a large factor, but it's not like Maxwell even had a DP card.

    That's why I'm kind of curious to see what they do with Pascal. They are going offer mixed (FP16) full (FP32) and Double (FP64). I wonder if they will come out with a card marketed specifically towards neural networks with FP16/32, a gaming card with FP32, and a workstation card with 32/64.
     
  13. Lane

    Lane Ancient Guru

    Messages:
    6,361
    Likes Received:
    3
    GPU:
    2x HD7970 - EK Waterblock
    I dont know if your report is wrong, but is really a majority of the HPC market, so a majority of HPC servers are really dedicated on Neural Network analysis ?

    This a new growing market, but im not really sure that a majority of HPC servers are now dedicated to research about it. Big data, scientist market, medical research.. i mean, HPC servers are used in nearly one thousand of different " research " type.

    When discussing about it, on BY3d as example, if important in term of research, it was still a niche market in term of servers and center dedicated to it.

    Then come the link with Maxwell, ... neural network computing was not even really used when Maxwell 1 and 2 ( 980 have launch in 09/2014, the maxwell 1 is even older ) .. so even if this arch was developped in something like 2012 ... neural network is too much new, for make it a cause of not have FP64 ..

    The thing is Nvidia was more need an architecture linked to mobile, power efficient, for bring it in the Tegra line up.

    Its even a complete contradiction with pascal return to FP64.. ( Now that Neural network research becomre way more important )
     
    Last edited: Feb 17, 2016
  14. Denial

    Denial Ancient Guru

    Messages:
    12,998
    Likes Received:
    2,393
    GPU:
    EVGA 1080Ti
    I mean it's the majority of the growing market. All kinds of companies, large and small, are getting into it, in all different types of disciplines. And I think it's pretty obvious that Nvidia has shifted it's attention. They wouldn't waste resources on redesigning their architecture specifically for Neural Networks if it was only 1/1000s of the market.

    It's obviously larger then that and has demand in the industry.

    Edit: You Keep editing your post. Neural Networks have been around for way longer then 2012.. There was CUDA accelerated Neural Network applications like Aquila since 2010. In fact I'm pretty sure Nvidia had people from Matlab talk about their Neural Network implementation when the Kepler variants of Tesla launched.
     
    Last edited: Feb 17, 2016
  15. Lane

    Lane Ancient Guru

    Messages:
    6,361
    Likes Received:
    3
    GPU:
    2x HD7970 - EK Waterblock
    Completely right with this.. Thats a big growing market, but the industry dont shift to it.. They addition this to their research panel.

    Thats the big 2016 thing, in term of "attention" around the appliccations of the research... in term of units sales.. thats a bit different.
     

  16. Lane

    Lane Ancient Guru

    Messages:
    6,361
    Likes Received:
    3
    GPU:
    2x HD7970 - EK Waterblock
    I have add a part yes ... because, as Anandtech, i really doubt that Maxwell have been designed only or specially with Neural network in mind, but more as mobile design in mind. ( the lack of FP64 was not because neural network, but it was not affect neural network. )
     
  17. AnarchoPrimitiv

    AnarchoPrimitiv New Member

    Messages:
    3
    Likes Received:
    0
    GPU:
    Radeon 390x 8GB
    14nm vs. 16nm

    I'm going to ask this again since everyone has ignored it, but why is this article stating that Pascal is 14nm when every other news site has been claiming it's 16nm for months now?
     
  18. -Tj-

    -Tj- Ancient Guru

    Messages:
    16,947
    Likes Received:
    1,824
    GPU:
    Zotac GTX980Ti OC
    Volta for me then.. pascal Looks more like a test hbm card for now, so even better later on since it will mature with volta.
     
  19. TyrantofJustice

    TyrantofJustice Ancient Guru

    Messages:
    5,021
    Likes Received:
    26
    GPU:
    RTX 2080 super
    I really want to go polaris as long as i can get a third party one with dual dvi for my korean monitor or i will have to spend a pretty penny on a new monitor that is up to my specs
     
  20. Denial

    Denial Ancient Guru

    Messages:
    12,998
    Likes Received:
    2,393
    GPU:
    EVGA 1080Ti
    Probably because either he wrote it wrong, or he just hasn't kept up with the rumors. It's like 99% going to be 16nm on tsmc. Not that it matters, the two nodes are practically identical.
     

Share This Page