Nvidia Turing Architecture [2018]

Discussion in 'Architecture and Products' started by pharma, Sep 13, 2018.

Tags:
  1. jlippo

    Veteran Regular

    Joined:
    Oct 7, 2004
    Messages:
    1,311
    Likes Received:
    406
    Location:
    Finland
    If I understood it correctly visibility samples are full res, texturing/shading is done at target rate.
     
    Benetanegia likes this.
  2. Voxilla

    Regular

    Joined:
    Jun 23, 2007
    Messages:
    708
    Likes Received:
    279
    Looking at the new SM architecture with 16 FP/INT units instead of 32, I'm wondering how long it will take for warps to be reduced from 32 to 16. That could improve thread divergence significantly.
     
  3. CarstenS

    Veteran Subscriber

    Joined:
    May 31, 2002
    Messages:
    4,796
    Likes Received:
    2,054
    Location:
    Germany
    The FP-units did operate in groups of 16 for quite a while already. That's nothing new in Volta/Turing.
    [​IMG]
     
  4. trinibwoy

    trinibwoy Meh
    Legend

    Joined:
    Mar 17, 2004
    Messages:
    10,414
    Likes Received:
    411
    Location:
    New York
    SIMD width is not really indicative of warp size. G80 was 8-wide and took 4 clocks to execute an instruction. It would also increase scheduler cost significantly and break years of optimizations tailored for 32 wide warps.
     
  5. Voxilla

    Regular

    Joined:
    Jun 23, 2007
    Messages:
    708
    Likes Received:
    279
    I understand that, but thread divergence is determined by the number of threads in a warp is it, and not the nr of threads in the sense of nr of SIMD lanes ? In case of the former (as I understood it was), I know scheduling rate will need to increase, but thread divergence should improve a lot as there is only 16 instead of 32 threads to diverge with warp size 16.
     
  6. CarstenS

    Veteran Subscriber

    Joined:
    May 31, 2002
    Messages:
    4,796
    Likes Received:
    2,054
    Location:
    Germany
    FP-group size was 16 since Fermi, but going forwar from maxwell, Nvidia did not make that readily apparent in their diagrams anymore. You really had to ask about it. So, I don't think they will do away the economization of control vs. execution width. I'm actually glad they did not increase it.
     
  7. Voxilla

    Regular

    Joined:
    Jun 23, 2007
    Messages:
    708
    Likes Received:
    279
    Reading a bit more, thread divergence seems to be dictated by warp size, which always has been 32 for NV. It would make sense to reduce warp size to 16 to improve divergence IMHO.
     
    #87 Voxilla, Sep 21, 2018
    Last edited: Sep 21, 2018
  8. DavidGraham

    Veteran

    Joined:
    Dec 22, 2009
    Messages:
    2,718
    Likes Received:
    2,454
    So does RTX not need DXR to work? I am asking because the Ray Tracing in the StarWars demo works on both Pascal and Turing without DXR.
     
  9. Malo

    Malo Yak Mechanicum
    Legend Veteran Subscriber

    Joined:
    Feb 9, 2002
    Messages:
    6,952
    Likes Received:
    3,032
    Location:
    Pennsylvania
    I'm assuming via Nvidia Optix in their drivers? Likely the demo is hand tuned to Optix, which means it probably won't work on Vega once next W10 update hits (and AMD adds DXR to drivers)
     
  10. trinibwoy

    trinibwoy Meh
    Legend

    Joined:
    Mar 17, 2004
    Messages:
    10,414
    Likes Received:
    411
    Location:
    New York
    Nope, it can also run as an acceleration layer for Vulkan RT and Optix.

    Unfortunately the screenshots of the upcoming 3dmark RT benchmark look quite unimpressive. Hopefully someone does a proper DXR or Vulkan benchmark.
     
    pharma, Heinrich4 and DavidGraham like this.
  11. jlippo

    Veteran Regular

    Joined:
    Oct 7, 2004
    Messages:
    1,311
    Likes Received:
    406
    Location:
    Finland
    #91 jlippo, Sep 25, 2018
    Last edited: Sep 25, 2018
    OCASM and pharma like this.
  12. trinibwoy

    trinibwoy Meh
    Legend

    Joined:
    Mar 17, 2004
    Messages:
    10,414
    Likes Received:
    411
    Location:
    New York
  13. Pressure

    Veteran Regular

    Joined:
    Mar 30, 2004
    Messages:
    1,329
    Likes Received:
    261
    Isn't the "look" irrelevant as long as it gives numbers to compare across hardware?
     
  14. doompc

    Joined:
    Mar 19, 2015
    Messages:
    7
    Likes Received:
    6
    The Star War Reflections demo is built using DXR. RTX accelerates DXR but DXR can run on any DX12 GPU using the fallback layer.
     
  15. trinibwoy

    trinibwoy Meh
    Legend

    Joined:
    Mar 17, 2004
    Messages:
    10,414
    Likes Received:
    411
    Location:
    New York
    We already have a benchmark where looks are irrelevant, it’s called math.

    3DMark actually used to be a benchmark in the literal sense by producing visuals that games of the time couldn’t match. It set expectations for what’s possible in the future when using the latest and greatest tech. It hasn’t been that for a long time. Now it just spits out a useless number and doesn’t look good doing it.

    I miss the good old days of Nature and Airship.
     
    Kej, Man from Atlantis, BRiT and 6 others like this.
  16. LeStoffer

    Veteran

    Joined:
    Feb 6, 2002
    Messages:
    1,253
    Likes Received:
    13
    Location:
    Land of the 25% VAT
    Aaaah, the sweet memories of running Nature on a ATI 9700 Pro! Bliss! :smile2:
     
    Man from Atlantis and Lightman like this.
  17. jlippo

    Veteran Regular

    Joined:
    Oct 7, 2004
    Messages:
    1,311
    Likes Received:
    406
    Location:
    Finland
    It will be certainly interesting to see how it will finally happen and does it need a additional change to hardware.
    We might see something nice in couple of days though. (Hoping for turing/oculus presentation.)
    Indeed.

    Would be a lot more interesting if it would give proper timings on what happens within GPU during the test.
    For raytracing the pure tracing speeds and with different kinds of shaders attached. (To see how GPU handles tracing and shading, I'm quite sure software path will get hit in comparison.)

    Old good demos were gorgeous.
     
    #97 jlippo, Sep 26, 2018
    Last edited: Sep 26, 2018
  18. Alexko

    Veteran Subscriber

    Joined:
    Aug 31, 2009
    Messages:
    4,489
    Likes Received:
    907
    Dunno whether that would qualify as a killer app, but I thought that Superhot VR, in spite of its odd and silly name, was really, really fun:

     
  19. Digidi

    Newcomer

    Joined:
    Sep 1, 2015
    Messages:
    220
    Likes Received:
    95
  20. DavidGraham

    Veteran

    Joined:
    Dec 22, 2009
    Messages:
    2,718
    Likes Received:
    2,454
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...