Nvidia Turing Architecture [2018]

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

Tags:
  1. DavidGraham

    Veteran

    Joined:
    Dec 22, 2009
    Messages:
    2,786
    Likes Received:
    2,584
    What's the current triangle rate for Titan RTX? how is it even calculated nowadays?
     
  2. DavidGraham

    Veteran

    Joined:
    Dec 22, 2009
    Messages:
    2,786
    Likes Received:
    2,584
    Any luck guys?
     
  3. techuse

    Newcomer

    Joined:
    Feb 19, 2013
    Messages:
    64
    Likes Received:
    19
    I thought it was unchanged from pascal
     
  4. fellix

    fellix Hey, You!
    Veteran

    Joined:
    Dec 4, 2004
    Messages:
    3,490
    Likes Received:
    400
    Location:
    Varna, Bulgaria
    The setup rate and fragment output is the same as in Pascal. The geometry processing (culling/tessellation/projection) throughput is a bit higher, since Turing has much more multi-processors to balance the workload within a GPC.

    Under heavy tessellation, the TU104 slightly edges GP102:

    [​IMG]
     
    #264 fellix, Aug 8, 2019
    Last edited: Aug 8, 2019
    trinibwoy, Malo and DavidGraham like this.
  5. CarstenS

    Veteran Subscriber

    Joined:
    May 31, 2002
    Messages:
    4,798
    Likes Received:
    2,056
    Location:
    Germany
    How much of that is clock speed related?
     
  6. techuse

    Newcomer

    Joined:
    Feb 19, 2013
    Messages:
    64
    Likes Received:
    19
    I think most of it. 1 geo unit for every 2 SMs in turing right? That gives a 2080 24 against the 28 of a 1080ti. The higher clockspeeds and maybe some slight efficiency improvements seem to line up with the tessellation benchmarks. Im not aware of any reviews that tested geometry throughput with anything other than tessmark and the microsoft tessellation benchmark used by PCGamesHardware. Other than mesh shading, nvidia doesnt mention geometry improvements in any of its documents.
     
  7. pharma

    Veteran Regular

    Joined:
    Mar 29, 2004
    Messages:
    2,930
    Likes Received:
    1,626
    There were a handful of reviews that used other tests ... Comptoir-hardware used PixMark Julia 32, GIMark and Tessmark.
    http://www.comptoir-hardware.com/ar...st-nvidia-geforce-rtx-2080-super.html?start=3

    Edit: Updated link to include current cards.
     
    #267 pharma, Aug 9, 2019
    Last edited: Aug 9, 2019
  8. fellix

    fellix Hey, You!
    Veteran

    Joined:
    Dec 4, 2004
    Messages:
    3,490
    Likes Received:
    400
    Location:
    Varna, Bulgaria
    The geometry workload is distributed at SM level, no shared hardware for that. Nvidia simply throttles the SMs of how much cycles they can spend on geometry and since Turing has plenty of them, it would be an overkill (and power draining) to keep processing primitives at full tilt if the next pipeline stage can't consume that much data. That is evident, by looking at how the number of SMs per GPC cluster has been rising steadily since Kepler.
    Even within a generation there is a difference: 3 cycles per polygon for each SM in GM200 and 2 cycles for GM204.
     
    DavidGraham likes this.
  9. ToTTenTranz

    Legend Veteran Subscriber

    Joined:
    Jul 7, 2008
    Messages:
    9,996
    Likes Received:
    4,570
    Nvidia doesn't need to push geometry performance any higher. They can just stop lobbying for games to use effects that generate sub-pixel triangles like hairworks on Witcher 3.
     
  10. jlippo

    Veteran Regular

    Joined:
    Oct 7, 2004
    Messages:
    1,341
    Likes Received:
    438
    Location:
    Finland
    They will start to lobby for mesh shaders and replacing of the geometry pipeline instead.
     
  11. techuse

    Newcomer

    Joined:
    Feb 19, 2013
    Messages:
    64
    Likes Received:
    19
    I wasnt aware they artificially throttled geometry rates. In one of PCGamesHardware GPU reviews a while back they had a special bench showing geometry rates for various levels of culling and geforce cards fell further behind AMD as culling percentages got lower. I think AMD cards were over twice as fast at 0% culled.
     
  12. fellix

    fellix Hey, You!
    Veteran

    Joined:
    Dec 4, 2004
    Messages:
    3,490
    Likes Received:
    400
    Location:
    Varna, Bulgaria
    The test with 0% culling was hitting the setup pipelines full time, so in this case the limit was not in geometry processing. Older generations of Nvidia GPUs were still rasterizing at half-rate (sans tessellation) and AMD could have benchmarked better then.
     
    w0lfram and techuse like this.
  13. techuse

    Newcomer

    Joined:
    Feb 19, 2013
    Messages:
    64
    Likes Received:
    19
    Whats the rasterization rate for pascal and turing? Has it changed since maxwell
     
  14. fellix

    fellix Hey, You!
    Veteran

    Joined:
    Dec 4, 2004
    Messages:
    3,490
    Likes Received:
    400
    Location:
    Varna, Bulgaria
    No performance changes, only feature updates like higher tier conservative rasterization support.
     
    techuse likes this.
  15. techuse

    Newcomer

    Joined:
    Feb 19, 2013
    Messages:
    64
    Likes Received:
    19
    Is the half rate likely to ever be a bottleneck in any realistic gaming scenario?
     
  16. pharma

    Veteran Regular

    Joined:
    Mar 29, 2004
    Messages:
    2,930
    Likes Received:
    1,626
    Nvidia Could Be Working on Another GeForce RTX GPU

    https://www.tomshardware.com/news/nvidia-geforce-rtx-t10-8-tu102,40166.html
     
    w0lfram likes this.
  17. w0lfram

    Newcomer

    Joined:
    Aug 7, 2017
    Messages:
    157
    Likes Received:
    33
    Interesting.
     
  18. pharma

    Veteran Regular

    Joined:
    Mar 29, 2004
    Messages:
    2,930
    Likes Received:
    1,626
    NVIDIA Beats Intel to Integer Scaling, but not on all Cards
    https://www.techpowerup.com/258445/nvidia-beats-intel-to-integer-scaling-but-not-on-all-cards
     
    #278 pharma, Aug 20, 2019
    Last edited: Aug 20, 2019
    Lightman and Silent_Buddha like this.
  19. pharma

    Veteran Regular

    Joined:
    Mar 29, 2004
    Messages:
    2,930
    Likes Received:
    1,626
    techuse likes this.
  20. trinibwoy

    trinibwoy Meh
    Legend

    Joined:
    Mar 17, 2004
    Messages:
    10,430
    Likes Received:
    433
    Location:
    New York
    Cool I suppose but still feels like cheating. VRS makes the most sense to me for foveated rendering in VR.
     
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...