Nvidia Turing Speculation thread [2018]

Discussion in 'Architecture and Products' started by Voxilla, Apr 22, 2018.

Tags:
Thread Status:
Not open for further replies.
  1. Rootax

    Veteran Newcomer

    Joined:
    Jan 2, 2006
    Messages:
    1,093
    Likes Received:
    530
    Location:
    France
    I guess they'll work on Pascal DXR perfs too. Because even if they work on it, and the perfs are "ok-ish", It would be still lagging behind turing by a large margin I guess, due to the lack of RT hardware, I guess. And they can't let Vega having better DXR perfs than Pascal...
     
  2. Exposed

    Newcomer

    Joined:
    Feb 8, 2002
    Messages:
    23
    Likes Received:
    7
    Slow news week.
     
    OCASM likes this.
  3. Malo

    Malo Yak Mechanicum
    Legend Veteran Subscriber

    Joined:
    Feb 9, 2002
    Messages:
    6,826
    Likes Received:
    2,871
    Location:
    Pennsylvania
    Apparently slides will be available on the 14th
     
    Bludd likes this.
  4. Malo

    Malo Yak Mechanicum
    Legend Veteran Subscriber

    Joined:
    Feb 9, 2002
    Messages:
    6,826
    Likes Received:
    2,871
    Location:
    Pennsylvania
    So now all reviews are going out the 19th with many reviewers only getting their card for a day for testing. As suggested earlier, it would be great if we could get past this day 1 for views and trust their readership to spend more time doing more detailed extensive testing. Or simply have the inevitable suite of benchmark runs only at limited settings for day 1 then consumers actually wait for additional articles (which generate more views anyway) before deciding on purchasing.

    Of course Nvidia are great at generating hype and have created an early Apple-like insatiable need to buy their products before it runs out! While stocks last folks! :roll:

    It will be interesting to see how the RTX is received though considering the very high price tag and focus on new features that have zero immediate use.
     
  5. McHuj

    Veteran Regular Subscriber

    Joined:
    Jul 1, 2005
    Messages:
    1,408
    Likes Received:
    527
    Location:
    Texas
    According to Videocardz (via twitter), RTX 2070 will indeed be TU106 and not a further cut down TU104.

    I doubt TU104 will only be used for one card, I'm speculating some chips are salvaged for a 2070Ti for next year at some point.
     
    iMacmatician likes this.
  6. -Sweeper_

    Newcomer

    Joined:
    Jun 7, 2010
    Messages:
    35
    Likes Received:
    42
    Bits from NVIDIA Turing Architecture whitepaper

    https://videocardz.com/77895/the-new-features-of-nvidia-turing-architecture
     
    Lalaland, fellix, nnunn and 7 others like this.
  7. McHuj

    Veteran Regular Subscriber

    Joined:
    Jul 1, 2005
    Messages:
    1,408
    Likes Received:
    527
    Location:
    Texas
    So the question I have: are GPU shader cores superscalar already or the Turing ones were made superscalar (first ones?)?

    This would imply that a significant chunk of work done by the shader core consists of integer ops. Performance could be squeezed out by the compiler by arranging the compiled shader code to effectively scheduler for this.
     
  8. Konan65

    Joined:
    Sep 9, 2018
    Messages:
    4
    Likes Received:
    1
    I’m wondering if Turing inherits Volta’s approach on thread scheduling in a Warp. With Volta having each thread with its own execution state, the GPU can switch back and forth between thread groups whenever it needs to in order to maximize efficiency. Then the GPU program can sync up later to have all the threads work in parallel. Do we know yet if this is the same for Turing?
    Thanks
     
  9. CarstenS

    Veteran Subscriber

    Joined:
    May 31, 2002
    Messages:
    4,771
    Likes Received:
    2,013
    Location:
    Germany
    I would be surprised, if it weren't in Turing as well. From my understanding, this lends itself quite well to some requirements of raytracing.
     
  10. fellix

    fellix Hey, You!
    Veteran

    Joined:
    Dec 4, 2004
    Messages:
    3,460
    Likes Received:
    345
    Location:
    Varna, Bulgaria
  11. trinibwoy

    trinibwoy Meh
    Legend

    Joined:
    Mar 17, 2004
    Messages:
    10,405
    Likes Received:
    402
    Location:
    New York
    Kepler was superscalar but I don’t think that definition applies to Turing. Based on what nvidia has shared so far Volta/Turing can’t issue multiple instructions per clock from the same warp.

    The execution rate is half the issue rate though which does allow for both INT and FP pipelines to be occupied concurrently.
     
  12. silent_guy

    Veteran Subscriber

    Joined:
    Mar 7, 2006
    Messages:
    3,754
    Likes Received:
    1,379
    Thanks to the miracle of Google:

    From https://devblogs.nvidia.com/inside-volta/ :

    Which gets the reply “This is correct.”

    It doesn’t say explicitly that the instruction have to come from different warps. I always assumed it wasn’t necessary, but that may be simply wrong.

    Either way: since the FP32 and INT are issued in an alternating way, I don’t think you can call it superscalar?
     
  13. trinibwoy

    trinibwoy Meh
    Legend

    Joined:
    Mar 17, 2004
    Messages:
    10,405
    Likes Received:
    402
    Location:
    New York
    Yeah, it doesn’t have to come from other warps but it helps with utilization.

    Kepler is superscalar - has multiple warp schedulers and dispatchers per SM and could issue multiple instructions per clock from one or more warps.

    Maxwell and Pascal are also superscalar - dropped the extra schedulers but still had multiple dispatchers so could issue two instructions per clock from the same warp (needing ILP). Like Kepler, the FP and INT pipelines were a single unit though so couldn’t be used concurrently.

    Volta/Turing dropped the extra dispatcher but split the FP and INT pipelines. They also cut the number of execution pipes in half. No more superscalar but now they can keep both the 16-wide INT and 16-wide FP pipelines busy with a single dispatcher. End result is major gains for mixed FP/INT workloads. How much that actually matters for games should become clearer next week.
     
    Lalaland, Lightman and iamw like this.
  14. CarstenS

    Veteran Subscriber

    Joined:
    May 31, 2002
    Messages:
    4,771
    Likes Received:
    2,013
    Location:
    Germany
    You probably won't be able to see independently verified numbers there, because you would have to be able to switch either concurrent FP/INT execution off or all the other things "Turing" in order to see how much this exact feature alone helps in games. I'd love to be proven wrong though!
     
  15. trinibwoy

    trinibwoy Meh
    Legend

    Joined:
    Mar 17, 2004
    Messages:
    10,405
    Likes Received:
    402
    Location:
    New York
    You're probably right .There are other changes also aimed at improving efficiency like the increased cache bandwidth and shorter pipeline so it'll be hard to attribute gains to one specific thing.
     
  16. BRiT

    BRiT (╯°□°)╯
    Moderator Legend Alpha Subscriber

    Joined:
    Feb 7, 2002
    Messages:
    12,016
    Likes Received:
    8,118
    Location:
    Cleveland
Loading...
Thread Status:
Not open for further replies.

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...