AMD: Southern Islands (7*** series) Speculation/ Rumour Thread

Discussion in 'Architecture and Products' started by UniversalTruth, Dec 17, 2010.

  1. MfA

    MfA Legend

    Which DRAM manufacturer would be ready to invest in GPU memory optimized for silicon interposers or stacking though? For mobiles I can see one of them stepping up to the plate, GPUs ... dunno. Without Qimonda I doubt we would have even had GDDR5 and we know what happened to them.
     
  2. 3dilettante

    3dilettante Legend Alpha

    Samsung and Micron have stacked memory initiatives.
    Intel is rumored to be looking into using a silicon interposer for a CPU.
    Intel and Micron seem to be joined tightly on stacked memory, so I do not know if Micron would partner with AMD on this.
    Maybe this is a test chip on a Samsung/IBM/GF initiative for interposers and stacked memory?
     
  3. MfA

    MfA Legend

    Mobile shit is shit.
     
  4. 3dilettante

    3dilettante Legend Alpha

    Maybe it's for mobile shit GPUs?
    Some of the value chips have memory controllers that can interface with multiple memory types besides GDDR5.
     
  5. Urian

    Urian Regular

    Well... can we know the size of the chip package?
     
  6. 3dilettante

    3dilettante Legend Alpha

    The bottom of that shot has some text that looks like "Amkor Confidential".
    Actually, Amkor has a marketing shot of its 3D TSV tech that bears a strong resemblance to this one, although that example only had one set of stacked memory.
     
  7. DarthShader

    DarthShader Regular

    I think it's pretty obvious that they will make that move, fast L3 or not. The same goes for APUs, those have even more to gain from seperate high bandwidth memory for the GPU part.
     
  8. Jawed

    Jawed Legend

    OK I'm gonna say it, "console" [​IMG]
     
  9. rpg.314

    rpg.314 Veteran

    There seem to be 4 identical rectangular dies, two on the right and two on the bottom. Are those DRAM dies?
     
  10. rpg.314

    rpg.314 Veteran

    Probably.
     
  11. Ninjaprime

    Ninjaprime Regular

    I was thinking the same thing... Xboxnext GPU prototype? Qualifies as "far future."
     
  12. Kaotik

    Kaotik Drunk Member Legend

    It could be for Wii U too as suggested by someone at Muropaketti, even though it's not "far future" really.
     
  13. Alexko

    Alexko Veteran Subscriber

    That's what I thought too. We already know the Wii U has an AMD GPU, but it's a kind of RV770-ish thing, and this looks bigger (assuming 40 nm or smaller).

    So maybe the next Xbox or Playstation.
     
  14. mczak

    mczak Veteran

    I think anything tagged with "far future" should be 28nm (or below but I can't see how they could get a prototype with below).
    Wii U sounds like not "far future" to me, but OTOH I don't think there would be anything close to a gpu prototype for the next Xbox or Playstation at this point.
     
  15. Jawed

    Jawed Legend

    I dare say a key point here is that ultra-high bandwidth courtesy of this RAM arrangement obviates EDRAM as seen with Xenos.

    Additionally, power levels should be "reasonable", rather than 250W+ as seen with discrete. So cooling won't be a nightmare for the early iterations. Though this layout is more forgiving of GPU power (at least in engineering terms) than a variant with memory stacked atop the GPU die.

    [​IMG]
     
  16. Acert93

    Acert93 Artist formerly known as Acert93 Legend

    The site appears down... does anyone mind explaining the general design of the interposer to me? (From what I can gather from this thread the link has info about kind of chip-to-chip interface, possibly some stacked memory?)
     
  17. Ninjaprime

    Ninjaprime Regular

    My understanding is its like a tiny on-die motherboard, allowing you to put the CPU on one side and RAM on the other, without having to embed the RAM eDRAM-style. Basically, you get the low latency/high bandwidth like eDRAM but you don't have to do special masks and processes like eDRAM, the RAM can be made seperately.
     
  18. rpg.314

    rpg.314 Veteran

  19. MfA

    MfA Legend

    It's simply a new form of multi-chip-module, but instead of using a glorified PCB to put the chips for the module on they use another HUGE chip (made in an older process to keep costs down).
     
  20. Jawed

    Jawed Legend

    If you're a GPU maker, what features of DRAM as we currently know it, are desirable in a memory subsystem enabled by an interposer?

    It seems to me that this is an opportunity to create something with the performance and granularity of "L4 cache" but sized as entire system memory.

    In other words, why wouldn't a GPU manufacturer make the memory chips too? AMD and NVidia already know how to build caches...
     
Loading...

Share This Page

Loading...