AMD: RDNA 3 Speculation, Rumours and Discussion

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

Tags:
  1. Jawed

    Jawed Legend

    The slides designed to out leakers? :mrgreen:
     
    DegustatoR and BRiT like this.
  2. Bondrewd

    Bondrewd Veteran

    Don't think so, those aren't partner-distributed at all.
    Whoever at Shanghai that spilled the N31 config will probably get a whacking tho...
     
  3. CarstenS

    CarstenS Legend Subscriber

    More like 30% denser. Or this is specific to AMDs SRAM implementation.
     
  4. Entropy

    Entropy Veteran

    At IEDM 2019, the 5nm process was quoted to have 1.84x logic density improvement compared to 1.35x SRAM density improvement.

    Since we only really have two mobile SoCs to go by when it comes to what this means for actual products, their improvement in overall transistor density was roughly 50%. What this means for HP designs is not clear.
     
  5. Bondrewd

    Bondrewd Veteran

    Yea and SRAM scaling there isn't 1.35X either.
     
  6. CarstenS

    CarstenS Legend Subscriber

    Thanks for restating what I just said guys. :)
     
    Lightman likes this.
  7. GCDs not having IMCs is pretty obvious given that's the whole point of chiplets to put the badly scaling analog blocks on the larger cheaper process. Furthermore it would be a clusterfuck to have the L3 on the MCD and then have traffic from that interleave back through the GCDs to DRAM, it's utter nonsense.
     
    CeeGee, trinibwoy, Lightman and 3 others like this.
  8. Jawed

    Jawed Legend

    Like the 3D V-cache you mean?
     
    DegustatoR likes this.
  9. Leoneazzurro5

    Leoneazzurro5 Regular

    In V-cache the cache is stacked on top of the oher cache, so the data path are the shortest possible. If the GCD had its own memory inteface and the stacked cache has to be positioned on the other side of the die like in your sketch, you will add a lot of distance for data paths that will limit frequency and add on power consumption.
     
    BRiT likes this.
  10. As mentioned, V-cache is an extension of the existing L3 - it's just additional banks and zero change to the data flow. That's not what's happening with the MCD. Incidentally I believe AMD will at some point move to a stacked giant L4 in the future, because it cannot be anything else but an L4 because it has to be centralised because of coherency.
     
    Last edited: Jul 31, 2021
    BRiT likes this.
  11. Jawed

    Jawed Legend

    We've discussed the active bridge chiplet before:

    ACTIVE BRIDGE CHIPLET WITH INTEGRATED CACHE - ADVANCED MICRO DEVICES, INC. (freepatentsonline.com)

    and we have seen other patent documents:

    https://forum.beyond3d.com/posts/2212201/

    that relate to distributed tasks and performing DMA operations across distributed processors and their respective PHYs.

    MCD at around 300mm²:
    will not have enough perimeter for 256-bit GDDR6 and all the other GPU IO and 2x 2TB/s (guess) L3 interfaces to each GCD.
     
    Lightman likes this.
  12. Frenetic Pony

    Frenetic Pony Regular

  13. Qesa

    Qesa Newcomer

    N7 has a HD SRAM cell size of 27000 nm^2, so you're looking at a ~28% density improvement on paper.

    Critically, this density is never even close to achieved IRL. With their zen 3 v-cache, AMD fit 64 MB of L3$ in a 36 mm^2 die. That's ~67000 nm^2 per bit, less than half the theoretical density. And, also from AMD, this was about twice the density of the L3 on the zen 3 CCD and RDNA2.
     
    Lightman, CarstenS, no-X and 2 others like this.
  14. Frenetic Pony

    Frenetic Pony Regular

    So while TSMC provides standard reference libraries, actual implementation will be a question mark. Thus any estimation of SRAM size on RDNA3 is... kind of an open question.

    Well, so much for early cost estimations then. Thanks for the info.
     
  15. Greetings to all members of beyond3d forum.
    .
    So from your post I assume Navi 33 has only 128bit GDDR6 bus, right?
    The question is who would want to buy Navi 33 for at least $450 with not even 12GB Vram next year? Even If It performs like RX 6900XT with only 8GB Vram It's a hard sell in my opinion.
     
  16. Kaotik

    Kaotik Drunk Member Legend

    Make it 16 gigs then? GDDR6 supports clamshelling
     
    BRiT and Jawed like this.
  17. Bondrewd

    Bondrewd Veteran

    Uh I mean do you really have a choice?
    It's a mobile first part much the same way N23 is.
     
  18. CarstenS

    CarstenS Legend Subscriber

    I was going by this, which seems to be based on newer data:
    https://en.wikichip.org/wiki/5_nm_lithography_process#N5
    https://fuse.wikichip.org/news/3398/tsmc-details-5-nm/

    And yes, this is reference implementation, that's why I asked, if this 15% figure maybe was based on AMD specific implementation.

    edit: To which, funnily enough, I've not gotten an answer from you know who. Apparently not gotten cleared to leak juicy bits.
     
    Last edited: Aug 1, 2021
    Lightman likes this.
  19. Leoneazzurro5

    Leoneazzurro5 Regular

    Probably bigger, It seems to be on N6 and not on N5 and if you integrate more things than only cache It could be over 400 mm^2

    The whole purpose of stacking is increasing area density and interconnection bandwidth by using vertical connections, thus by not being limited by perimeter or such, that is, only the VRAM bus and I/O connections would be connected to the perimeter of the MCD, while the inter-GCD bandwidth would be achieved through the cache itself and the vertical interconnection paths
     
    Lightman likes this.
  20. Bondrewd

    Bondrewd Veteran

    Nope.
    You're still not thinking the right size.
    Think less AMD Rome and more AMD Navi31.
     
Loading...

Share This Page

Loading...