Re: [AMBER] Multiple simulations on one GPU

From: Piotr Fajer <pfajer.fsu.edu>
Date: Tue, 29 Oct 2019 16:59:54 +0000

Aiden,

I routinely run 2 pmemd.cuda jobs per GPU with about 20-30% loss versus a single job per GPU. Heavier loading starts being linear because of timesharing. You can follow the GPU loading with nvidia-smi as you know, and the inf files will give you the ns/day throughput.

Peter

´╗┐On 10/29/19, 11:56 AM, "Aiden Aceves" <ajaceves.gmail.com> wrote:

    Hello,
    I have one single and very powerful GPU. Is there a way to run
    multiple simulations
    in parallel on it? I know I could proceed in series, but given that the GPU
    is mostly underutilized in terms of memory and processing power (based on
    its power draw during the run), I thought it might help to run multiple
    simulations simultaneously.
    Thanks,
    Aiden Aceves
    _______________________________________________
    AMBER mailing list
    AMBER.ambermd.org
    https://urldefense.com/v3/__http://lists.ambermd.org/mailman/listinfo/amber__;!5Xm4_O-4tfk!jIPIMlwvjaNsKndVAqhGtXYkdtaI_Sm4Powvq4ojuvPxCcRSfgjTDNbNeFh7HAU$
    

_______________________________________________
AMBER mailing list
AMBER.ambermd.org
http://lists.ambermd.org/mailman/listinfo/amber
Received on Tue Oct 29 2019 - 10:30:02 PDT
Custom Search