AMD: RDNA 3 Speculation, Rumours and Discussion

Discussion in 'Architecture and Products' started by Jawed, Oct 28, 2020.

  1. Alexko

    Veteran Subscriber

    Joined:
    Aug 31, 2009
    Messages:
    4,532
    Likes Received:
    957
    Isn't that pretty much what Infinity Cache is in RDNA2?
     
    Lightman likes this.
  2. ToTTenTranz

    Legend Veteran

    Joined:
    Jul 7, 2008
    Messages:
    12,048
    Likes Received:
    7,009

    Oh well, I guess I'll just wait another 15 months then.
    Perhaps I'll be able to buy a 6800XT at MSRP by then.
     
    Kej, Cuthalu, Picao84 and 2 others like this.
  3. Kaotik

    Kaotik Drunk Member
    Legend

    Joined:
    Apr 16, 2003
    Messages:
    9,778
    Likes Received:
    3,947
    Location:
    Finland
    The what now? Everything I've seen is saying PS5 is inferior to PC-RDNA2/Xbox Series when it comes to geometry, not better?

    edit:
    as for the "DLSS answer", personally I hope DLSS and any such image quality degrading nonsense will just be buried, but they already have "tensor cores" in CDNA which apparently fit DLSS-type loads well

    edit2: The impression I've gotten from PS5 geometry is Vega/RDNA on steroids, while RDNA2 takes it further with mesh shaders etc?
     
    #83 Kaotik, Jan 24, 2021
    Last edited: Jan 24, 2021
    tinokun, Wesker and BRiT like this.
  4. andermans

    Newcomer

    Joined:
    Sep 11, 2020
    Messages:
    25
    Likes Received:
    42
    I wonder why people seem to couple a DLSS answer to a GPU generation again and again. RDNA2 has the same machine learning instructions as RDNA1 (including 8/4-bit variants) and unless RDNA3 goes full tensor-cores/mAI or dedicated upscaling HW there shouldn't be a significant HW barrier to bringing this to the entire RDNA lineup.

    Also now that AMD is consistently enabling primitive shaders with culling, is the geometry actually a problem for these GPUs? If there is indeed a >2x perf target then sure there might be some need to make it scale with that, but there are a large number of scaling limitations that they have to rethink with a larger chip and MCM. (e.g. throughput of launching waves, keeping the CUs fed with data etc.)

    Edit for the above with respect to mesh shaders: RDNA1 had most of the core capabilities, just some missing bits to be 100% feature complete to actually be able to expose it to applications through the Direct3D API. I would assume that such a thing would be exposed for consoles in their native API though.
     
    Lightman and Kaotik like this.
  5. Kaotik

    Kaotik Drunk Member
    Legend

    Joined:
    Apr 16, 2003
    Messages:
    9,778
    Likes Received:
    3,947
    Location:
    Finland
    RDNA2 shares the machine learning capabilities of Navi12 (and Vega20). Navi 10 & 14 (which most people think when you say RDNA) are inferior on that front and don't include faster INT4/8 support
     
  6. Frenetic Pony

    Regular Newcomer

    Joined:
    Nov 12, 2011
    Messages:
    679
    Likes Received:
    363
    Yeah, that's exactly what it is. These rumors don't make much sense. Another vast increase in performance per watt in just two years to hit 400 watts alone. "An answer to DLSS" which they uhhh, already announced. And such a ridiculously large "chiplet" makes no sense whatsoever. The point of MCM is a cost down, increase those yield to 90%+, get those engineering costs down, etc. Making two giant low yield dies at the same time doesn't fit that at all.
     
    Picao84, CeeGee and xpea like this.
  7. Leoneazzurro5

    Newcomer

    Joined:
    Aug 18, 2020
    Messages:
    226
    Likes Received:
    249
    If each die is 80CU but it's made on a smaller process node (as it should be) don't you think it will be not in the 500mm^2 ballpark but much smaller?
     
    Jawed and Lightman like this.
  8. CarstenS

    Legend Veteran Subscriber

    Joined:
    May 31, 2002
    Messages:
    5,360
    Likes Received:
    3,096
    Location:
    Germany
    Maybe it's just not enabled in the gaming-focused products?

    edit:
    RDNA whitepaper, p.14: "Some variants of the dual compute unit expose additional mixed-precision dot-product modes in the ALUs, primarily for accelerating machine learning inference. A mixed-precision FMA dot2 will compute two half-precision multiplications and then add the results to a single-precision accumulator. For even greater throughput, some ALUs will support 8-bit integer dot4 operations and 4-bit dot8 operations, all of which use 32-bit accumulators to avoid any overflows."
     

    Attached Files:

    Lightman likes this.
  9. Kaotik

    Kaotik Drunk Member
    Legend

    Joined:
    Apr 16, 2003
    Messages:
    9,778
    Likes Received:
    3,947
    Location:
    Finland
    The whitepaper is referring to DCUs used by Navi12 there. They're different versions of the architecture, it was same with Vega generation, ".1" versions if you like of said architectures, but with RDNA2 they just included it in everything.
     
    CarstenS likes this.
  10. Bondrewd

    Veteran Newcomer

    Joined:
    Sep 16, 2017
    Messages:
    1,128
    Likes Received:
    508
    We don't know and Snoy surely aren't talking much about it.
    Two?
    Those are just compute tiles and they serve the very specific purpose.
     
  11. ToTTenTranz

    Legend Veteran

    Joined:
    Jul 7, 2008
    Messages:
    12,048
    Likes Received:
    7,009
    Rootax likes this.
  12. function

    function None functional
    Legend Veteran

    Joined:
    Mar 27, 2003
    Messages:
    5,727
    Likes Received:
    4,002
    Location:
    Wrong thread
    When did Matt Hargett say that the PS5's geometry engine is more advanced than the one in RDNA2?
     
  13. Dictator

    Regular Newcomer

    Joined:
    Feb 11, 2011
    Messages:
    407
    Likes Received:
    2,312
    I have not heard any sort of anything from developers about Geometry Engine being some sort of better than RDNA 2 front end change. Not a thing at all.
     
    Newguy, T2098, CeeGee and 14 others like this.
  14. PSman1700

    Veteran Newcomer

    Joined:
    Mar 22, 2019
    Messages:
    4,523
    Likes Received:
    2,077
    Yep.
     
  15. DegustatoR

    Veteran

    Joined:
    Mar 12, 2002
    Messages:
    2,194
    Likes Received:
    1,562
    Location:
    msk.ru/spb.ru
    What I don't get is why people continue putting trust in rumors saying how Sony made something for a modern GPU which is "significantly more advanced" than what one of two industry leaders is able to build. Do Sony even have a GPU engineering department these days?
     
  16. Rootax

    Veteran Newcomer

    Joined:
    Jan 2, 2006
    Messages:
    2,044
    Likes Received:
    1,474
    Location:
    France
    RedGamingTech has been pretty reliable, and his sources kind of "insists" on that, so for now I kind of believe it...
     
    ToTTenTranz likes this.
  17. PSman1700

    Veteran Newcomer

    Joined:
    Mar 22, 2019
    Messages:
    4,523
    Likes Received:
    2,077
    You gotta be kidding. As per usual DF is the way to go for reliable sources.
     
    Cuthalu, Picao84, -Sweeper_ and 3 others like this.
  18. ^M^

    ^M^
    Newcomer

    Joined:
    Jul 6, 2006
    Messages:
    60
    Likes Received:
    17
  19. Rootax

    Veteran Newcomer

    Joined:
    Jan 2, 2006
    Messages:
    2,044
    Likes Received:
    1,474
    Location:
    France
    He's been spot on about all amd/rtg stuff. Pictures, perfs, infinity cache, etc... And when he doesn't trust the sources, he clearly tell you.

    And DF is not in the business of leaking stuff, I don't know why the comparaison ?
     
  20. ToTTenTranz

    Legend Veteran

    Joined:
    Jul 7, 2008
    Messages:
    12,048
    Likes Received:
    7,009
    IIRC, the geometry engine rumors are coming from the same sources that leaked Radeon VII, Infinity Cache, clocks and a bunch of other AMD and Sony stuff well before anyone else and with very good accuracy.

    If this was coming from rumor mongers with a poorer track record like e.g. AdoredTV I wouldn't be giving it much thought.
    Incidentally, the same sources who described Sony's custom Geometry Engine also mentioned the PS5's CPU has unified L3 (which could be responsible for the better measured performance at very high framerates). I think he started mentioning these in his videos during the Summer.

    So when a x-ray picture of the PS5 SoC comes out, if we see separate L3 for each 4-core CCX then I'll assume the Geometry Engine rumor is probably true. If not, then it's probably not true.



    You don't need to go back that far to find secret sauce theories.

    The SeriesX launched 3 months ago, and when DigitalFoundry couldn't observe its predicted 15-20% performance advantage over the PS5 in multiplatform titles, we started hearing about how there's a future devkit that will unlock the full power of the console.
    Aside from Hitman 3 which for all we know it's the exception to the rule (and where we can't really compare both consoles because they're running different resolutions at over 60FPS), we're yet to see anything running better on the SeriesX in any measurably substantial way.


    Regardless, I don't think anyone ever suggested the PS5 has unlocked geometry potential that will put it one step above the competition.
    RGT's statements are simpy that the PS5's geometry engine is more advanced/flexible and the console's apparent lack of RDNA2's VRS stems from hardware design decisions taken around the geometry engine.
    Note: I don't know how the console's geometry engine can influence the shading precision (and at first thought it doesn't even make a lot of sense), but then again I also haven't read Sony's multitude of patents around foveated rendering.
     
    Globalisateur likes this.
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...