• siazdghw@alien.topB
    link
    fedilink
    English
    arrow-up
    1
    ·
    1 year ago

    I actually want to have a 3D construct where I have lots of cache in a base die, and put the advanced computing on top of it into a 3D sandwich, and now you get the best of a cache architecture and the best of the next generation of Moore’s law

    Not the first time Pat has mentioned a desire for a stacked cache product.

    In no way do I think that just because we’ve now demonstrated 18A

    Lunar Lake? There is a debate on whether Lunar Lake is actually 18A or 20A. They demo’d Lunar Lake last month, but with it being so early there is speculation if it was actually on 18A, but this suggests that it actually was?

    Now, on the other side of it, though, I have to create clean separation between these two businesses and that’s what the internal Foundry model is all about, because I need to be able to go to Qualcomm or AMD or—

    Literally calls out AMD as a potential foundry customer and the cliffhanger or would most likely be Nvidia.

    • Exist50@alien.topB
      link
      fedilink
      English
      arrow-up
      1
      ·
      1 year ago

      Lunar Lake? There is a debate on whether Lunar Lake is actually 18A or 20A. They demo’d Lunar Lake last month, but with it being so early there is speculation if it was actually on 18A, but this suggests that it actually was?

      Neither. It’s N3B.

    • jaaval@alien.topB
      link
      fedilink
      English
      arrow-up
      1
      ·
      1 year ago

      What he proposed isn’t really stacked cache. At least not in the sense AMD does it. It should probably be thought as a separate cache die.