AMD EPYC Naples Memory Population Performance Impact

Discussion in 'STH Main Site Posts' started by Patrick Kennedy, Jul 31, 2018.

  1. #1
    eva2000 likes this.
  2. BackupProphet

    BackupProphet Well-Known Member

    Joined:
    Jul 2, 2014
    Messages:
    785
    Likes Received:
    278
    This is awesome stuff Patrick!
     
    #2
  3. BlackArchon

    BlackArchon Member

    Joined:
    Jun 23, 2016
    Messages:
    68
    Likes Received:
    10
    I really have hoped for a few more benchmarks. Also a configuration like two channels populated on die 1 and 3, and no RAM on dies 2 and 4 would be interesting. :)
     
    #3
  4. Patrick

    Patrick Administrator
    Staff Member

    Joined:
    Dec 21, 2010
    Messages:
    11,560
    Likes Received:
    4,490
    Data got repetitive after awhile and this takes quite a long time to generate since it requires physical access to the box to swap DIMMs.


    On the die 1 and 3 I am not sure why it is hard to extrapolate. Single to dual channel is essentially 4 to 8. Two die populated to four is 2 to 4.

    Perhaps when we publish the 32C results we will do more, but two dies with memory access is dumb.

    Also, there is an architectural reason you would never do this. If you are constantly accessing RAM over IF your PCIe bandwidth chokes die to die. You have more or less PCIe 3.0 x16 between each die with current IF. If you are doing PCIe transfer and RAM transfer on the same IF link, one has to suffer because there is not enough bandwidth.
     
    #4
    Blinky 42 and eva2000 like this.
  5. BlackArchon

    BlackArchon Member

    Joined:
    Jun 23, 2016
    Messages:
    68
    Likes Received:
    10
    I'm asking specifically for this configuration because it is rumored that this would be the memory configuration for Threadripper 2. If this is true (and not one channel per die), I'm interested in the performance impact. :)
     
    #5
  6. Patrick

    Patrick Administrator
    Staff Member

    Joined:
    Dec 21, 2010
    Messages:
    11,560
    Likes Received:
    4,490
    I know why people are asking. ;)
     
    #6
  7. TXAG26

    TXAG26 Member

    Joined:
    Aug 2, 2016
    Messages:
    72
    Likes Received:
    9
    @Patrick - any plans to release a similar article that discusses AMD Epyc ROME memory population performance impacts? I think a lot of us would like to know the impact of only populating 4 channels vs 8 channels with the new memory controller on ROME CPUs.
     
    #7
    gigatexal, ari2asem and ZX_81 like this.
  8. TXAG26

    TXAG26 Member

    Joined:
    Aug 2, 2016
    Messages:
    72
    Likes Received:
    9
    Any plans to release a similar article that discusses AMD Epyc ROME memory population performance impacts? I think a lot of us would like to know the impact of only populating 4 channels vs 8 channels with the new memory controller on ROME CPUs.
     
    #8
    gigatexal likes this.
Similar Threads: EPYC Naples
Forum Title Date
STH Main Site Posts AMD EPYC is the New AMD Zen Based Server Brand for Naples May 16, 2017
STH Main Site Posts AMD EPYC 7742 Benchmarks and Review Simply Peerless Yesterday at 6:52 AM
STH Main Site Posts Supermicro H11SSL-NC Rev 2 ATX AMD EPYC Motherboard Wednesday at 11:12 AM
STH Main Site Posts Supermicro AMD EPYC GPU Server and Intel Nervana NNP-T Training Server at SC19 Nov 29, 2019
STH Main Site Posts Gigabyte Shows AMD EPYC 7002 Series GPU Servers at SC19 Nov 28, 2019

Share This Page