1. This site uses cookies. By continuing to use this site, you are agreeing to our use of cookies. Learn More.

Rumor: AMD Epyc2 processors could get 64 cores over 8+1 dies

Discussion in 'Frontpage news' started by Hilbert Hagedoorn, Oct 31, 2018.

  1. Hilbert Hagedoorn

    Hilbert Hagedoorn Don Vito Corleone Staff Member

    Messages:
    36,111
    Likes Received:
    5,133
    GPU:
    AMD | NVIDIA
    chispy and Silva like this.
  2. sverek

    sverek Ancient Guru

    Messages:
    5,309
    Likes Received:
    2,161
    GPU:
    NOVIDIA -0.5GB
    I wonder if data centers waiting for it, instead of jumping on Zen1 :D
     
  3. djmcave

    djmcave New Member

    Messages:
    7
    Likes Received:
    3
    GPU:
    AMD 7950
    With every CTX being produced individually it should keep costs down... Wondering if they intend to do the same on the GPUs.
     
    Silva likes this.
  4. sverek

    sverek Ancient Guru

    Messages:
    5,309
    Likes Received:
    2,161
    GPU:
    NOVIDIA -0.5GB
    Can you glue GPUs together? Wouldn't it be crossfire?
     

  5. Fediuld

    Fediuld Member Guru

    Messages:
    106
    Likes Received:
    48
    GPU:
    MSI 1080 Armor OC /8GB
    AMD has developed Infinity Fabric for GPUs, and was announced back in August with all the 7nm GPUs supporting it. In addition to pcie4.0. (next round of ryzen boards support it)
    So the bandwidth is there, after all CF didn't needed a separate bridge since Hawaii in 2013.
     
    Silva and tunejunky like this.
  6. HWgeek

    HWgeek Master Guru

    Messages:
    439
    Likes Received:
    314
    GPU:
    Gigabyte 6200 Turbo Fotce @500/600 8x1p
  7. Fox2232

    Fox2232 Ancient Guru

    Messages:
    9,739
    Likes Received:
    2,199
    GPU:
    5700XT+AW@240Hz
    It would be crazy if they decoupled CPU cores from uncore this way. Because from what I have seen Cores themselves can clock higher, it is all that stuff around which does not like it on 2700X.
     
    tunejunky likes this.
  8. Evildead666

    Evildead666 Maha Guru

    Messages:
    1,231
    Likes Received:
    234
    GPU:
    Vega64/EKWB/Noctua
    Yup, this is going to be the new normal.
    This way, you get the System Controller with everything you need, on a slightly older process, due ot it not needing to be going at break-neck speed, in fact it would be better because the PCIe Controllers and SATA controllers wouldn't be bothered by the CPU speeds anymore.
    The CPU's would be able to be done much cheaper on the latest fab processes, with much faster chips, and better yields.
    GPU's would be the exact same idea, just with more "cores" per "GPU-CCX".
    Four cores per CPU-CCX now, maybe ~2048 cores per GPU-CCX ? (about Polaris 30 type, but with Navi)
     
    tunejunky likes this.
  9. Arbie

    Arbie Member Guru

    Messages:
    169
    Likes Received:
    58
    GPU:
    GTX 1060 6GB
    [Sorry if this comment steps on any toes... it is removable]

    AdoredTV on Youtube has some very good presentations, including a brand new one on this topic - which he previewed some time ago.

    (Though anyone not a native speaker of English may have a 'herd toim' following it).
     
    HonoredShadow likes this.
  10. Venix

    Venix Master Guru

    Messages:
    938
    Likes Received:
    321
    GPU:
    Palit 1060 6gb
    8 cores in 64 nm^2 ??? isn't that waaaaaaay too low ?
     

  11. tunejunky

    tunejunky Master Guru

    Messages:
    881
    Likes Received:
    314
    GPU:
    RadeonVII gtx1080ti

    Yes you can, it is roadmapped.
    No, it wouldn't be crossfire, it would act as a single gpu in exactly the same way as threadripper and ryzen.

    this is the high-end 7nm gpu from AMD that will be announced at the end of next year.

    scalability is the single highest goal at AMD.
    there will not be any performance goals that cannot be met because of Moore's Law, which was the driving force behind the design.
    they can just add graphic cores.

    so for the first time ever in a gpu there will be "moar cores". and double gpu's do not count because those are crossfired or SLI'd.
     
  12. tunejunky

    tunejunky Master Guru

    Messages:
    881
    Likes Received:
    314
    GPU:
    RadeonVII gtx1080ti
    very true at 12nm.
    if they use a "hub" design for the controller a la "epyc 2" as shown, that would be a major difference.
    also remaining to be seen is whether or not HBM2 is going to be used and/or if the related costs have come down. there very well may be a "HBM 3" made at a smaller node as well, which would lower the cost (after production costs are earned back).
     
  13. tunejunky

    tunejunky Master Guru

    Messages:
    881
    Likes Received:
    314
    GPU:
    RadeonVII gtx1080ti
    i was thinking re: gpu on the above comments Fox
     
  14. nevcairiel

    nevcairiel Master Guru

    Messages:
    601
    Likes Received:
    190
    GPU:
    MSI 1080 Gaming X
    Its not exactly news. Uncore and actual CPU cores have been using seperate clock domains in various CPUs everywhere.
     
  15. waltc3

    waltc3 Maha Guru

    Messages:
    1,001
    Likes Received:
    294
    GPU:
    AMD 50th Ann 5700XT
    My first thought was wondering why the system controller wasn't also 7nm, as it surely is a much simpler circuit design than a single cpu. But according to the diagram, if they did that where would they physically position the cores relative to the controller?...Just an errant thought...
     

  16. Picolete

    Picolete Master Guru

    Messages:
    270
    Likes Received:
    61
    GPU:
    R9 290 Sapphire Tri-x
    The controller it's rumored to be 14nm because it's bigger than the other chips and the process is not mature enough for such a large chip on 7nm and decent yields
     
    Silva likes this.
  17. Fox2232

    Fox2232 Ancient Guru

    Messages:
    9,739
    Likes Received:
    2,199
    GPU:
    5700XT+AW@240Hz
    Not that I wrote it for purpose of clock. What I wrote about is minimizing area of dies which host CPU cores and put as much of uncore to central "hub". That way you have all CCXes in sync much better. And There is saving of transistors too. And cost of 7nm would affect only minimum needed part of CPU. On top of that uncore is not power hungry, therefore 14/12nm is fine and it does not need 7nm. So no reason to pay for 7nm transistors which can be moved to central "hub".
     
    tunejunky likes this.
  18. WareTernal

    WareTernal Master Guru

    Messages:
    246
    Likes Received:
    38
    GPU:
    XFX RX 580 GTS BE
    So they are maybe going to ditch the '2 NUMA node' setup? Better late than never :)
     
  19. azraei97

    azraei97 New Member

    Messages:
    6
    Likes Received:
    4
    GPU:
    R9 380 4GB
    For now AMD still can't do multi chip GPU working as work like in the CPU. AMD already talk about this. Navi also unlikely to get multichip design

    https://www.pcgamesn.com/amd-navi-monolithic-gpu-design
     
  20. chispy

    chispy Ancient Guru

    Messages:
    8,758
    Likes Received:
    891
    GPU:
    RTX 2080Ti - RX 580
    128 threads would be Epyc " Pun intended " :D
     
    Embra likes this.

Share This Page