AMD Sets a 30x Energy Efficiency Goal helped by AI Training and High Performance Computing Apps

Discussion in 'Frontpage news' started by Hilbert Hagedoorn, Sep 29, 2021.

  1. Hilbert Hagedoorn

    Hilbert Hagedoorn Don Vito Corleone Staff Member

    Messages:
    44,027
    Likes Received:
    11,071
    GPU:
    AMD | NVIDIA
    Embra and DannyD like this.
  2. cucaulay malkin

    cucaulay malkin Ancient Guru

    Messages:
    4,961
    Likes Received:
    2,719
    GPU:
    RTX 3060 Ti
    lol what that's 3000% efficiency improvement in 5 years what are they talking about
     
  3. kapu

    kapu Ancient Guru

    Messages:
    5,293
    Likes Received:
    713
    GPU:
    Radeon 6800
    I they ment 30%
     
  4. Imglidinhere

    Imglidinhere Master Guru

    Messages:
    257
    Likes Received:
    18
    GPU:
    12GB RX 6700XT
    If they move the bar again like the last time this statement was made, I think it can be done! xD
     

  5. Denial

    Denial Ancient Guru

    Messages:
    13,752
    Likes Received:
    3,379
    GPU:
    EVGA RTX 3080
    They meant 30x but it's not as challenging when you're pretty far behind in most of those categories. It's not like they are saying Epyc CPUs itself will be 30x more efficient - it's a combination of efficiency improvements in hardware abd software with very specific worksets which can massively benefit from fixed acceleration (for example tensor operations).
     
    Last edited: Sep 29, 2021
    tunejunky and Noisiv like this.
  6. cucaulay malkin

    cucaulay malkin Ancient Guru

    Messages:
    4,961
    Likes Received:
    2,719
    GPU:
    RTX 3060 Ti
    30% would be awful
     
  7. vestibule

    vestibule Master Guru

    Messages:
    718
    Likes Received:
    264
    GPU:
    GTX1070 Zotac mini
    Remember when M$ experimented with submarine type vessels for there servers for cooling and saving on energy. Damn good idea I thought.
     
  8. RED.Misfit

    RED.Misfit Member Guru

    Messages:
    104
    Likes Received:
    49
    GPU:
    MSI 1080 Gaming X
    They did achieve a superior than 25x improvement (31.7x according to them) in mobile CPUs through 2014-2020. (okay, they were coming from far probably at that time with their "architecture & nodes")
     
  9. Horus-Anhur

    Horus-Anhur Ancient Guru

    Messages:
    3,723
    Likes Received:
    4,273
    GPU:
    RTX 2070 Super
    This 30X better efficiency, is probably just in certain taskloads.
    They'll probably add some specialized units and instructions to accelerate some types of calculations.
     
    tunejunky likes this.
  10. tunejunky

    tunejunky Ancient Guru

    Messages:
    2,310
    Likes Received:
    1,059
    GPU:
    RX6900XT, 2070
    this sounds more extreme than the reality of their progress with TSMC and their improvements in uArch.

    if i'm putting dozens (or tens of dozens in future) of cores on an Epyc chip, and that chip itself goes to a sub 3n process, more cores at a higher (12 - 20 %) efficiency just by node alone. not to mention apps and A.I.
    and given that there are two Epyc node shrinkages in that time frame i say highly doable.
     
    Last edited: Oct 1, 2021

Share This Page