AMD CDNA Discussion Thread

Discussion in 'Architecture and Products' started by Frenetic Pony, Nov 16, 2020.

  1. Ethatron

    Regular Subscriber

    Joined:
    Jan 24, 2010
    Messages:
    921
    Likes Received:
    356
    It's like to make doubles a first class citizen, which use 2x VGPRs.
    The registers typically hold single-precision (32-bit) floating-point (FP) data, but are also designed for efficiently handling mixed precision. For larger 64-bit (or double precision) FP data, adjacent registers are combined to hold a full wavefront of data.
     
    Lightman likes this.
  2. yuri

    Regular Newcomer

    Joined:
    Jun 2, 2010
    Messages:
    272
    Likes Received:
    280
    Yea, this would also make sense.

    Samples of MI200 already exist. Apparently, these are used in HPE Cray EX class of supercomputers. It's interesting that the samples are already being labeled as "MCM". So is it a doubled MI100 or a CDNA2-based MCM-native chip?

    Also the "HPC customized" Zen 3-based CPU - Trento - is being paired with the MI200.
     
    Lightman likes this.
  3. Bondrewd

    Veteran Newcomer

    Joined:
    Sep 16, 2017
    Messages:
    1,129
    Likes Received:
    510
    Aka Shasta.
    This.
    There's the proper 2-piece MI200 aka the MCM one and the baby MI200 aka the SCM one.
     
    Lightman likes this.
  4. DegustatoR

    Veteran

    Joined:
    Mar 12, 2002
    Messages:
    2,214
    Likes Received:
    1,617
    Location:
    msk.ru/spb.ru
    MCM makes a lot of sense for HPC markets.
     
  5. DegustatoR

    Veteran

    Joined:
    Mar 12, 2002
    Messages:
    2,214
    Likes Received:
    1,617
    Location:
    msk.ru/spb.ru
  6. Bondrewd

    Veteran Newcomer

    Joined:
    Sep 16, 2017
    Messages:
    1,129
    Likes Received:
    510
    Poor MI100 won't even get to live much.
    :sadface: for yesteryear ROCm 4.0 delays.
     
    Leovinus likes this.
  7. yuri

    Regular Newcomer

    Joined:
    Jun 2, 2010
    Messages:
    272
    Likes Received:
    280
    Lightman likes this.
  8. Bondrewd

    Veteran Newcomer

    Joined:
    Sep 16, 2017
    Messages:
    1,129
    Likes Received:
    510
    A100 80GB already uses it.
     
  9. DegustatoR

    Veteran

    Joined:
    Mar 12, 2002
    Messages:
    2,214
    Likes Received:
    1,617
    Location:
    msk.ru/spb.ru
  10. Leovinus

    Newcomer

    Joined:
    May 31, 2019
    Messages:
    142
    Likes Received:
    73
    Location:
    Sweden
  11. CarstenS

    Legend Veteran Subscriber

    Joined:
    May 31, 2002
    Messages:
    5,362
    Likes Received:
    3,101
    Location:
    Germany
    IMHLO: Nothing is a hard as graphics on a competitively interactive scale.

    With basically everything else done in GPU, you can mask or afford some kind of latency or uneven distribution of workloads. Even the much-cited recommender systems only have to satisfy a single measure of latency once in while (in terms of GPU timings), not continously deliver single-digit-ms latency to a single user.

    edit: Yeah, that's a big THANK YOU to all hard- and software engineers making those chips so we can enjoy our favourite games on them to the fullest.
     
    #51 CarstenS, Mar 6, 2021
    Last edited: Mar 6, 2021
    Lightman likes this.
  12. Kaotik

    Kaotik Drunk Member
    Legend

    Joined:
    Apr 16, 2003
    Messages:
    9,792
    Likes Received:
    3,959
    Location:
    Finland
    To my understanding those scientific workloads rarely even care whether there's 1 or more chips doing the calculations, so yes and no - Yes as in, it's easy testing ground for MCM since workloads don't care and No, it's not that useful testing ground because games do care.
     
    Leovinus likes this.
  13. DegustatoR

    Veteran

    Joined:
    Mar 12, 2002
    Messages:
    2,214
    Likes Received:
    1,617
    Location:
    msk.ru/spb.ru
    In a sense that a pure compute workload is a lot easier to put on as many processing nodes as possible than graphics yes. But this isn't really related to graphics much so it's not so much of a "testing ground" from s/w perspective - it is a testing ground for h/w though and possibly a testing ground for h/w approaches which would make MCM suitable for graphics.
     
    Leovinus likes this.
  14. Lurkmass

    Regular Newcomer

    Joined:
    Mar 3, 2020
    Messages:
    309
    Likes Received:
    348
    Lightman likes this.
  15. ethernity

    Newcomer

    Joined:
    May 1, 2018
    Messages:
    88
    Likes Received:
    207
    Lightman likes this.
  16. Bondrewd

    Veteran Newcomer

    Joined:
    Sep 16, 2017
    Messages:
    1,129
    Likes Received:
    510
    Genoa should work fine too.
     
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...