Nvidia Ampere Discussion [2020-05-14]

Discussion in 'Architecture and Products' started by Man from Atlantis, May 14, 2020.

Tags:
  1. Benetanegia

    Regular Newcomer

    Joined:
    Sep 4, 2015
    Messages:
    394
    Likes Received:
    425
    Basing perf/w on TDP instead of actual measurements seems pointless too, especially since they're apparently reporting TGP instead of TDP. 2080 S, 2080 Ti and Titan RTX all had 250 TDP. Power consumption was not the same.
     
  2. Scott_Arm

    Legend

    Joined:
    Jun 16, 2004
    Messages:
    14,798
    Likes Received:
    6,984
    I didn't notice that. What was the TGP of a 2080 ti? TDP is listed at 250W.
     
  3. PSman1700

    Legend Newcomer

    Joined:
    Mar 22, 2019
    Messages:
    5,043
    Likes Received:
    2,242
    Not it matters anyway, im seeing 20-36TF gpus with 80 to 100% increase over Turing, aside from RT, dlss etc huge improvements, at good prices.
    Indeed biggest leap ever. Even going from a 2080Ti to a 3070 is a huge upgrade, 2080 to 3080 even more so. Im sure we will see 3080Ti/s later on.
     
    Cuthalu and pharma like this.
  4. Malo

    Malo Yak Mechanicum
    Legend Veteran Subscriber

    Joined:
    Feb 9, 2002
    Messages:
    8,369
    Likes Received:
    4,802
    Location:
    Pennsylvania
    Wow Kool aid much?
     
    disco_ and ToTTenTranz like this.
  5. Geeforcer

    Geeforcer Harmlessly Evil
    Veteran

    Joined:
    Feb 6, 2002
    Messages:
    2,320
    Likes Received:
    525
    Or have they learned a valuable lesson from the Turning’s “cryptomania-Ievel prices during crypto correction” fiasco?
     
    Lightman and Cuthalu like this.
  6. rSkip

    Newcomer

    Joined:
    Jan 10, 2012
    Messages:
    17
    Likes Received:
    35
    Location:
    Shanghai
    Added lines and perf/w labels to the 1.9x perf/watt slide. (Keep in mind that TU102 doesn't scale as well to 320W, that 1.32x perf/w is comparing worst to worst at different power.)
    ampere_ppw.png
     
  7. Frenetic Pony

    Regular Newcomer

    Joined:
    Nov 12, 2011
    Messages:
    739
    Likes Received:
    417
    Just ignore them, I keep forgetting to.

    Anyway, as for the architecture itself: This really seems to show the weakness of having a single arch going for machine learning/compute and gaming at the same time. The IPC has dropped dramatically, probably bottlenecked by lack of SRAM and/or bandwidth to memory, showing the fundamental arch isn't designed around graphics but instead looks more like AMD's own CDNA split, concentrated on compute without the need for a giant amount of cache to go with it. Really it kind of looks like Volta 2.0 adapted to compete with RDNA2, though so far it seems to be doing a decent if not perfect job of it. And Nvidia surely has a lot of resources, I wouldn't be surprised if they split their architectures soon enough as well.
     
    ToTTenTranz likes this.
  8. Love_In_Rio

    Veteran

    Joined:
    Apr 21, 2004
    Messages:
    1,627
    Likes Received:
    226
    Nvidia has always used TGP. 2080 TI has a TGP (per Nvidia) of 250 watts and a 3070 of 220.
     
    #1068 Love_In_Rio, Sep 2, 2020
    Last edited: Sep 2, 2020
  9. eastmen

    Legend Subscriber

    Joined:
    Mar 17, 2008
    Messages:
    12,711
    Likes Received:
    3,632
    I dunno bro. You think its really bigger than stg 2000 to Riva 128 ?
     
    Lightman and Putas like this.
  10. Scott_Arm

    Legend

    Joined:
    Jun 16, 2004
    Messages:
    14,798
    Likes Received:
    6,984
    It may be one of the biggest leaps at a price point, but architecture doesn’t seem like it. That said, it’s only the former that matters to a consumer.
     
    Lightman and Cuthalu like this.
  11. Pinstripe

    Newcomer

    Joined:
    Feb 24, 2013
    Messages:
    144
    Likes Received:
    124
    Consoles are more and more resembling PC configs, and PC hardware/APIs come closer to console efficiency (DX12_2, RTX IO). So it's less of an issue than in the past.
     
    egoless, PSman1700 and Cuthalu like this.
  12. Qesa

    Newcomer

    Joined:
    Feb 23, 2020
    Messages:
    27
    Likes Received:
    46
    It's probably premature before seeing an SM diagram, but assuming the "slapped another fp32 SIMD in there" rumour is true, we're seeing IPC go down as a direct result of changes between gaming and HPC ampere. One math instruction issued per clock, 3 SIMDs (int32, fp32, fp32) that each take 2 clocks - there is an obvious bottleneck there.
     
  13. techuse

    Regular Newcomer

    Joined:
    Feb 19, 2013
    Messages:
    875
    Likes Received:
    541
    I think devs on this very forum have stated that "low level" PC APIs are not even close to what is available on consoles, particularly PS4. There are several facets of console design that allow a level of efficiency the PC can never match. I dont think we can claim anything about RTX IO at this point in time.
     
    Lightman and ToTTenTranz like this.
  14. Rootax

    Veteran Newcomer

    Joined:
    Jan 2, 2006
    Messages:
    2,166
    Likes Received:
    1,605
    Location:
    France
    I don't get the ipc comments. For all we know, they're bandwith limited...
     
    PSman1700 likes this.
  15. Pinstripe

    Newcomer

    Joined:
    Feb 24, 2013
    Messages:
    144
    Likes Received:
    124
    Of course consoles are still more efficient, but the gap has come closer to the point where Carmack's old tweet about "2x raw power to close the gap" is no longer valid.
     
    PSman1700 likes this.
  16. Erinyes

    Regular

    Joined:
    Mar 25, 2010
    Messages:
    808
    Likes Received:
    276
    The difference in die cost wouldn't be nearly that high, and remember that it's partially offset by the increased PCB, VRM and cooling solution costs.

    One overlooked reason I think Nvidia went with Samsung is simply wafer capacity. Until Huawei's recent issues, TSMC 7nm was at full capacity (and with demand even higher, especially with this year's consoles). Given how much the size of the gaming market has increased in recent years, and the market share of Nvidia, TSMC may not have had the volume required by Nvidia (This is a similar problem faced by AMD with Epyc if you wonder why market share is so low).

    Now would price have played a part too? Sure no doubt, NV likes their margins. And did Samsung really fuck up "7N" that badly that they had to go back to 8nm and derailed the plan a bit? Maybe. I find it hard to believe they actually planned on using a 10nm derivative in late 2020.
     
    no-X likes this.
  17. Love_In_Rio

    Veteran

    Joined:
    Apr 21, 2004
    Messages:
    1,627
    Likes Received:
    226
    This gen Nvidia flops became AMD flops and viceversa.
     
    Lightman likes this.
  18. Leoneazzurro5

    Newcomer

    Joined:
    Aug 18, 2020
    Messages:
    230
    Likes Received:
    259
    At the moment it is not yet completely clear, but the doubling of FP32 has been done by simply adding a SIMD to a SM, so two SIMDs share the same scheduling, and so on. Apart the obvious pressure on the register files, and so on, this may lead to utilization issues n the case the scheduler, for various reasons, cannot co-issue independent instructions to both SIMDs at the same time.
     
    Lightman, madhatter, BRiT and 2 others like this.
  19. Leoneazzurro5

    Newcomer

    Joined:
    Aug 18, 2020
    Messages:
    230
    Likes Received:
    259
    My answer was for Rootax, by the way... it seems I lost the quote somewhere in the process lol.
     
    Rootax likes this.
  20. pjbliverpool

    pjbliverpool B3D Scallywag
    Legend

    Joined:
    May 8, 2005
    Messages:
    8,700
    Likes Received:
    3,198
    Location:
    Guess...
    We can claim exactly the same as what is claimed for the console IO systems. Until we have independent benchmarks, both are simply advertised capabilities from the manufacturers.

    There's no technical reason at this stage to doubt Nvidias claims any more than there is to doubt Sonys or Microsofts.
     
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...