Nvidia DLSS antialiasing discussion *spawn*

Discussion in 'Architecture and Products' started by DavidGraham, Sep 19, 2018.

Tags:
  1. dorf

    Newcomer

    Joined:
    Dec 21, 2019
    Messages:
    41
    Likes Received:
    108
    Yea, I guess that would have been better than mere resolution scaled images - didn't come to think of it. Oh well, cant go back to the same exact scene again and don't feel like starting over so the postage stamps is all I'm left with.
     
    pharma likes this.
  2. w0lfram

    Newcomer

    Joined:
    Aug 7, 2017
    Messages:
    217
    Likes Received:
    38
    Do all cards do DLSS the same..?
     
  3. iroboto

    iroboto Daft Funk
    Legend Regular Subscriber

    Joined:
    Mar 6, 2014
    Messages:
    10,373
    Likes Received:
    10,013
    Location:
    The North
    The model is the same yes. The amount of hardware required to execute the model is not.
     
  4. Benetanegia

    Regular Newcomer

    Joined:
    Sep 4, 2015
    Messages:
    288
    Likes Received:
    189
    Surely, you're speaking relatively to the amount of total units? Cause otherwise, I'm pretty sure that statement would be wrong.
     
  5. iroboto

    iroboto Daft Funk
    Legend Regular Subscriber

    Joined:
    Mar 6, 2014
    Messages:
    10,373
    Likes Received:
    10,013
    Location:
    The North
    As in the number of tensor cores between varying cards is not the same.
     
    pharma likes this.
  6. Benetanegia

    Regular Newcomer

    Joined:
    Sep 4, 2015
    Messages:
    288
    Likes Received:
    189
    Yes, but I don't think more tensor cores are required on larger chips? More TCs just finish the task faster, I'm sure. Or am I missing something?

    EDIT: Like, hyphotetically, the number of tensor cores could be limited by drivers to be the same on all cards and the model would then execute the same and not somehow worse.
     
  7. iroboto

    iroboto Daft Funk
    Legend Regular Subscriber

    Joined:
    Mar 6, 2014
    Messages:
    10,373
    Likes Received:
    10,013
    Location:
    The North
    Generally speaking yes more tensor cores would finish the job faster. The more tensor cores you have the faster you can get through the density of the network. If it’s thin, it’s not going to matter much, but if it’s deep, then having more cores will result in faster performance than less. Bandwidth is also a large factor.

    So what I meant was exactly this topic with respect to DLSS being the same across the cards. The answer is yes, it is the same model being run across all GPUs, and that the answer is that more hardware runs it faster (generally speaking).

    but to answer your question; I have no clue if larger chips require more tensor cores :). That’s beyond me lol
     
    #907 iroboto, Apr 10, 2020
    Last edited: Apr 10, 2020
    pharma and Benetanegia like this.
  8. Benetanegia

    Regular Newcomer

    Joined:
    Sep 4, 2015
    Messages:
    288
    Likes Received:
    189
    That makes sense. The wording of your first post made me think you were implying that there was indeed a difference.
     
  9. w0lfram

    Newcomer

    Joined:
    Aug 7, 2017
    Messages:
    217
    Likes Received:
    38
    That is not what I asked though. Would a 2080 do DLSS faster/better than a 2070...?
     
  10. Scott_Arm

    Legend

    Joined:
    Jun 16, 2004
    Messages:
    14,160
    Likes Received:
    5,455
    Yah, it should do it faster because it has more tensor cores.
     
  11. iroboto

    iroboto Daft Funk
    Legend Regular Subscriber

    Joined:
    Mar 6, 2014
    Messages:
    10,373
    Likes Received:
    10,013
    Location:
    The North
    Yes. It has more tensor power. It should complete the network faste
     
  12. dorf

    Newcomer

    Joined:
    Dec 21, 2019
    Messages:
    41
    Likes Received:
    108
    From the GTC presentation:

    [​IMG]
     
  13. pharma

    Veteran Regular

    Joined:
    Mar 29, 2004
    Messages:
    3,528
    Likes Received:
    2,215
    Missed this when the DLSS reviews came out. Google translation ... :???:
    https://www.pcgameshardware.de/Nvid...arrior-5-DLSS-Test-Control-DLSS-Test-1346257/
     
    Man from Atlantis, PSman1700 and BRiT like this.
  14. TheAlSpark

    TheAlSpark Moderator
    Moderator Legend

    Joined:
    Feb 29, 2004
    Messages:
    21,577
    Likes Received:
    7,127
    Location:
    ಠ_ಠ
    So INT8 confirmed?
     
  15. dorf

    Newcomer

    Joined:
    Dec 21, 2019
    Messages:
    41
    Likes Received:
    108
    "SM FP16+Tensor Pipe Throughput" is the phrase I'm seeing in Nsight. Is that specific enough to say INT8? Or maybe they found something I'm not seeing.
     
  16. Radolov

    Newcomer

    Joined:
    Jul 30, 2019
    Messages:
    11
    Likes Received:
    13
    The only thing I've ever seen NVIDIA write about is FP16 Tensor Ops with FP16 accumulate.

    When they presented DLSS at gamescom 2018 they had a slide about DLSS where they say that they have "~500 Billion FP16 Ops". But that might be for training and not for execution. The number 500 occurs in the volta whitepaper, "DGX Station is a whisper-quiet, water-cooled workstation that packs four NVIDIA Volta-powered Tesla V100 GPUs delivering up to 500Tensor TFLOPS for deep learning applications."

    From "NVIDIA DLSS: Control and Beyond" :
    "Our next step is optimizing our AI research model to run at higher FPS. Turing’s 110 Tensor teraflops are ready and waiting for this next round of innovation."
    From "NVIDIA DLSS 2.0: A Big Leap In AI Rendering"
    "With Turing’s Tensor Cores delivering up to 110 teraflops of dedicated AI horsepower, the DLSS network can be run in real-time simultaneously with an intensive 3D game"

    In the Turing whitepaper they say that they have "113.8 Tensor TFLOP of FP16 matrix math with FP16 accumulation". So i guess that is number that they reference.

    But I mean, if someone has proof that it's only using INT8 I guess everyone would be happy to see it?
     
  17. manux

    Veteran Regular

    Joined:
    Sep 7, 2002
    Messages:
    2,061
    Likes Received:
    927
    Location:
    Earth
    Turing added int8 and int4 modes to tensor cores. int8 is double fp16 throughput and int4 is double int8 throughput.
     
    BRiT and CarstenS like this.
  18. Man from Atlantis

    Regular

    Joined:
    Jul 31, 2010
    Messages:
    753
    Likes Received:
    79
    Is there anyway to launch Minecraft Windows 10 on Nsight?

    I ran Control but it pauses anytime i alt-tab. So I can't capture an ingame frame on Nsight to analyse.
     
    #918 Man from Atlantis, Apr 20, 2020
    Last edited: Apr 20, 2020
  19. Radolov

    Newcomer

    Joined:
    Jul 30, 2019
    Messages:
    11
    Likes Received:
    13
    Maybe I was a bit unclear, but I meant in the context of DLSS (and hence why I only named DLSS examples). I will try to be more clear going forward.
     
    manux likes this.
  20. Malo

    Malo Yak Mechanicum
    Legend Veteran Subscriber

    Joined:
    Feb 9, 2002
    Messages:
    7,614
    Likes Received:
    3,677
    Location:
    Pennsylvania
    Perhaps the original article is incorrect.
     
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...