NVidia Ada Speculation, Rumours and Discussion

Discussion in 'Architecture and Products' started by Jawed, Jul 10, 2021.

Tags:
  1. itsmydamnation

    Veteran

    Joined:
    Apr 29, 2007
    Messages:
    1,349
    Likes Received:
    470
    Location:
    Australia
    Then why have University's like ANU who have only ever had Nvidia GPU's in there HPC clusters also going MI200? I guess not only is big government stupid but so is academia.

    But also what's your point MI200 does packed FP32 and has the most HBM / bandwidth of any GPU.
     
    Lightman likes this.
  2. CarstenS

    Legend Subscriber

    Joined:
    May 31, 2002
    Messages:
    5,800
    Likes Received:
    3,920
    Location:
    Germany
    The rumors I know are based on a slide for the australian supercomputer Setonix as reported on by hpcwire.com; the data itself has been around for much longer though. If you do the math on that one, an MI200 will be at about 55 FP64-TFLOPS, so 5x A100 w/o Tensor cores.
     
    #262 CarstenS, Aug 5, 2021
    Last edited: Aug 5, 2021
    Lightman and Tarkin1977 like this.
  3. pharma

    Veteran

    Joined:
    Mar 29, 2004
    Messages:
    4,889
    Likes Received:
    4,536
    Which makes it that more mysterious since AMD did not release official specs when MI200 was announced shipping to customers on July 28, so still a lot of speculation. Unless something went wrong what's the point in keeping this from the public or potential customers?
     
  4. Tarkin1977

    Newcomer

    Joined:
    Mar 10, 2018
    Messages:
    15
    Likes Received:
    15
  5. CarstenS

    Legend Subscriber

    Joined:
    May 31, 2002
    Messages:
    5,800
    Likes Received:
    3,920
    Location:
    Germany
  6. JasonLD

    Regular

    Joined:
    Apr 3, 2004
    Messages:
    463
    Likes Received:
    105
    50PFlops is probably CPU+GPU combined though.
     
    pharma, PSman1700 and DavidGraham like this.
  7. CarstenS

    Legend Subscriber

    Joined:
    May 31, 2002
    Messages:
    5,800
    Likes Received:
    3,920
    Location:
    Germany
    Yes, sure. At 200k Milan-cores, that's roughly 9 PFlops for the CPU (with 2,75 TFLops for a single 64core Epyc 7763) and leaves 41 for GPU.
    (50-9)/750 = 0,05466 PFlops or 54,66 TFlops
     
    Lightman likes this.
  8. JasonLD

    Regular

    Joined:
    Apr 3, 2004
    Messages:
    463
    Likes Received:
    105
    I see. I just calculated the numbers and see you already subtracted CPU numbers out of it.
    Isn't MI200 still going to be on 7nm though? I really doubt MI200 would achieve almost 5 times of FP64 performance of MI100 even if it is MCM of 2 dies if it is still on 7nm.
     
  9. Kaotik

    Kaotik Drunk Member
    Legend

    Joined:
    Apr 16, 2003
    Messages:
    10,244
    Likes Received:
    4,465
    Location:
    Finland
    MI200 does fullrate FP64 which already quadruples the performance at the same clocks
     
    Lightman likes this.
  10. Jawed

    Legend

    Joined:
    Oct 2, 2004
    Messages:
    11,714
    Likes Received:
    2,135
    Location:
    London
    Will? No, I really hope not.

    My belief is that the step change in per-pixel quality and consistency that ray tracing based techniques can bring will split devs into two camps: those that will continue as if nothing happened and those who are willing to go back to the drawing board. I expect that traditional fixed-function hardware will underlie this new perspective but it will be plugged-in to support ray-traced rendering. There'll be a lot of navel-gazing focused on what that hardware can really do when used properly.

    I think we're exiting the "ray tracing is tacked-on" mode of graphics development. I'm hopeful that in a couple of years we'll play the fruits of this.

    When I've finished the three Witchers, I have a few 2007 games I want to play: Bioshock, Call of Juarez, Crysis and STALKER. And then it'll be 2009...
     
    Lightman likes this.
  11. troyan

    Regular

    Joined:
    Sep 1, 2015
    Messages:
    605
    Likes Received:
    1,125
    Over the Matrix engine the same like nVidia with TensorCores. So general compute doesnt increase by 5x.
     
    PSman1700 likes this.
  12. JasonLD

    Regular

    Joined:
    Apr 3, 2004
    Messages:
    463
    Likes Received:
    105
    Fullrate FP64? That is kind of going opposite direction of where most of the industry is heading....hmm.
     
  13. troyan

    Regular

    Joined:
    Sep 1, 2015
    Messages:
    605
    Likes Received:
    1,125
    CDNA is paid by the goverment. Specific designed chips for one workload is nothing new. AMD doesnt need to provide better software support or even products like nVidia for selling CDNA products.
     
    DavidGraham, DegustatoR and PSman1700 like this.
  14. no-X

    Veteran

    Joined:
    May 28, 2005
    Messages:
    2,451
    Likes Received:
    471
    Almost 5 times compared to A100, not MI100. Exact number depends on final clocks.
     
  15. troyan

    Regular

    Joined:
    Sep 1, 2015
    Messages:
    605
    Likes Received:
    1,125
    it isnt 5x higher. AMD is using their Matrix engine for DP64. The same way nVidia is using TensorCores. 5x higher would be nearly 100TFLOPs.
     
    PSman1700 likes this.
  16. CarstenS

    Legend Subscriber

    Joined:
    May 31, 2002
    Messages:
    5,800
    Likes Received:
    3,920
    Location:
    Germany
    Is there a source for this?
     
  17. troyan

    Regular

    Joined:
    Sep 1, 2015
    Messages:
    605
    Likes Received:
    1,125
    4x more FP64 over the compute units with a vector unit wont happen. You have to scale everything with it and alone data movement off- and on-chip will kill effciency.
     
    OlegSH and PSman1700 like this.
  18. pharma

    Veteran

    Joined:
    Mar 29, 2004
    Messages:
    4,889
    Likes Received:
    4,536
    Isn't MI200 dual chip?
     
    PSman1700 likes this.
  19. OlegSH

    Regular

    Joined:
    Jan 10, 2010
    Messages:
    801
    Likes Received:
    1,630
    I don't know what you find inefficient about RT. RT inefficiency is a myth. It's way more efficient than rasterization in too many cases.
    As for stochastic sampling, there are great improvements in this area - importance sampling, shading caches, coherency sorting, all this improved by a lot in just 3 years.
    Looking at how fast path tracing (and multi-bounce tracing) is right now in hundreds of millions polygons scenes in UE5, Omniverse, etc, it feels as if it is already here, just mix in all mentioned above improvements, add in denoising and push it to prod.

    Honestly, the problem is that your average console developer treats PC as a third tier platform and unless there is an IHV involved, which would help with the workloads you've mentioned, the developer won't do anything for PC.

    I don't think that's the way to go. Those SS hacks, fancy SM based area shadow techniques, compute GI, etc are just another hacks with tons of drawbacks that are layered on top of the energy inefficient computations on general multiprocessors in a time when the Denard scaling is long dead, hence the 500W monsters on the horizon.
    Why bother making more of those fragile and unmaintainable systems when people can't even use existing ones properly in most cases because there are millions of tweakable parameters (apparently many devs can't even setup DLSS properly with just a few parameters).
    I'd rather prefer devs and IHVs putting more time and HW effort into something way more general/unifyed and maintainable, which requires minimum tweaking and has proven to beat any hacks in CG industry.
    Other than this, general/unified algorithm can live up and scale with way more efficient specialized hardware, which is the way to go in future, at least if you want to avoid 1000W monster GPUs in near future, lol.
     
  20. CarstenS

    Legend Subscriber

    Joined:
    May 31, 2002
    Messages:
    5,800
    Likes Received:
    3,920
    Location:
    Germany
    So it's your assumption then.

    Dual die* MCM from the looks of it.

    *not counting HBM
     
    Lightman and pharma like this.
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...