Nvidia Pascal Speculation Thread

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

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

    Veteran

    Joined:
    Apr 19, 2007
    Messages:
    1,559
    Likes Received:
    34
  2. CSI PC

    Veteran Newcomer

    Joined:
    Sep 2, 2015
    Messages:
    2,050
    Likes Received:
    844
    Yeah the Drive PX2 is definitely a more serious bit of hardware-software with the jump up in its AlexNet capability in comparison to the Tegra X1 and worthy of serious recognition, NVIDIA seem really serious about breaking into this market in a successful way, and I can see other uses for this beyond cars with use in other transport systems as part of the warning/protection/assist systems and also possibly military projects (have my doubts NVIDIA can break into this).
    Cheers
     
  3. CSI PC

    Veteran Newcomer

    Joined:
    Sep 2, 2015
    Messages:
    2,050
    Likes Received:
    844
    Well Deep Learning concept can be fun.
    Here is an example of a simple neural network learning to play Mario Brothers; it starts from nothing and standing still to 24 hours later where it could beat the level in a very efficient way.
    Fun to watch and listen to.

    Audi commented using the complete NVIDIA solution (includes the DIGITS developer-platform box) ; "in less than four hours we achieved over 96 percent accuracy using Ruhr University Bochum’s traffic sign database.While others invested years of development to achieve similar levels of perception with classical computer vision algorithms "
    Cheers
     
  4. Voxilla

    Regular

    Joined:
    Jun 23, 2007
    Messages:
    711
    Likes Received:
    282
    Meanwhile it seems we have been slightly misled about the PX2 as there are strong indications that the discrete GPUs on the shown PCB are actually GM204, as the MXM package looks exactly as a GTX 980M. Also the inscriptions on the die, and it's size, indicate this :-(
     
  5. I.S.T.

    Veteran

    Joined:
    Feb 21, 2004
    Messages:
    3,174
    Likes Received:
    389
    Oh man I remember when that came out. The site it came from got a boost in members.

    Still an amazing video.
     
  6. A1xLLcqAgt0qc2RyMz0y

    Regular

    Joined:
    Feb 6, 2010
    Messages:
    988
    Likes Received:
    280
    Sigh. It's a mock-up. :roll:

    PX2 won't be available till year end and it will be all Pascal then.
     
  7. firstminion

    Newcomer

    Joined:
    Aug 7, 2013
    Messages:
    217
    Likes Received:
    46
     
  8. Kaotik

    Kaotik Drunk Member
    Legend

    Joined:
    Apr 16, 2003
    Messages:
    8,184
    Likes Received:
    1,841
    Location:
    Finland
    It was mockup with woodscrews (not literally, but the 2 GPUs on the back were GM204's, not Pascals)
     
  9. fuboi

    Newcomer

    Joined:
    Aug 6, 2011
    Messages:
    90
    Likes Received:
    46
    They're called CUDA™ Twisties™, not woodscrews. Please reference your review guides.
     
  10. JF_Aidan_Pryde

    Regular

    Joined:
    Feb 6, 2002
    Messages:
    601
    Likes Received:
    3
    Location:
    New York
    Dumb question—how is it that Drive PX 2 has 6x the ImageNet performance of Titan X when it only has ~3x the "deep learning ops" performance?
    On which actual hardware performance metric (ram, flops, dl-flops) does it have 6x over Titan X?
     
  11. xpea

    Regular Newcomer

    Joined:
    Jun 4, 2013
    Messages:
    372
    Likes Received:
    309
    something related to their new mysterious DL TOPS thing (Deep Learning TeraOPS) on Pascal, where 1 TFLOPS = 3 DL TOPS. How they do this trick is still a secret story but if it's true, they will have a huge advantage in this generation...
     
  12. JF_Aidan_Pryde

    Regular

    Joined:
    Feb 6, 2002
    Messages:
    601
    Likes Received:
    3
    Location:
    New York
    But it doesn't add up even with "deep learning ops". PX 2 has ~3x more "deep learning OPS" vs. Titan X but it has ~6x more AlexNet performance. There'a another magical "2x" something going on.
     
  13. LordEC911

    Regular

    Joined:
    Nov 25, 2007
    Messages:
    789
    Likes Received:
    74
    Location:
    'Zona
    Edited my terrible response. I don't think I'm awake yet.

    Looks like no one knows.
     
    #553 LordEC911, Jan 6, 2016
    Last edited: Jan 6, 2016
  14. psurge

    Regular

    Joined:
    Feb 6, 2002
    Messages:
    939
    Likes Received:
    35
    Location:
    LA, California
    Then there's the Titan X specs, which presumably destroy those of a Tegra X1 - doesn't a TX1 have about 1TF of FP16 performance? But the Titan X AlexNet score barely beats that of a Tegra X1.
     
  15. Voxilla

    Regular

    Joined:
    Jun 23, 2007
    Messages:
    711
    Likes Received:
    282
    I found some info regarding the mysterious Deep Learning OPs.
    Apparently Pascal can do processing on 8-bit integers.
    It's easy to understand that can be up to 4 times faster compared to 32-bit floating point operations.
    See: http://www.eetimes.com/author.asp?section_id=36&doc_id=1328609&
    "The NVIDIA deep learning algorithms can use specialized mixed precision instructions as low as 8-bit integer to deliver up to 24 trillion operations per second. The 8-bit integer operations are new in the Pascal GPU."
     
    firstminion likes this.
  16. fellix

    fellix Hey, You!
    Veteran

    Joined:
    Dec 4, 2004
    Messages:
    3,490
    Likes Received:
    400
    Location:
    Varna, Bulgaria
    Does that mean Pascal will support both 10 and 16-bit minimum precision modes in D3D12?
     
  17. JF_Aidan_Pryde

    Regular

    Joined:
    Feb 6, 2002
    Messages:
    601
    Likes Received:
    3
    Location:
    New York
    Where are you getting that from? Last year CES slides showed Tegra X1 having 30 images/sec for AlexNet. This year's slides show 450 images/sec for Titan X. That's 15x delta, on par with FP32 perf delta.
     
  18. Kaotik

    Kaotik Drunk Member
    Legend

    Joined:
    Apr 16, 2003
    Messages:
    8,184
    Likes Received:
    1,841
    Location:
    Finland
    Not necessarily, supporting 8bit INT and 16bit FP doesn't mean you support 10bit FP
     
  19. psurge

    Regular

    Joined:
    Feb 6, 2002
    Messages:
    939
    Likes Received:
    35
    Location:
    LA, California
    Post 541 in this thread. I guess marketing slide to marketing slide is more apples to apples... But 15x doesn't make much sense either, as X1 is supposed to have twice the FP16 throughput as FP32 ...
     
  20. CSI PC

    Veteran Newcomer

    Joined:
    Sep 2, 2015
    Messages:
    2,050
    Likes Received:
    844
    Reasearch AlexNet (papers on it out there), notice one already provided a link with measurements for the Tegra JTX1 earlier in comparison to Intel 6700k at phoronix.
    It is still not ideal (better than relying on say just TFLOPs though due to its specific focus) but not something NVIDIA are making out of thin air; here is a paper to do with it: http://www.cs.toronto.edu/~fritz/absps/imagenet.pdf
    Worth noting NVIDIA are talking about images processed/second for context, accuracy is more to do with their DIGITS platform.

    Cheers
     
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...