a) For technically knowledgable audience, you could demonstrate some simple benchmarks codes.

b) For a more general audience, you might also look for some parallel open source applications that are specific to the domain of interest. For example for engineering, OpenFOAM (https://openfoam.com/) has some demo setups that can give good motivation. FENICS (https://fenicsproject.org/) and DEAL.II (https://www.dealii.org/) also have some things. If Oil and Gas industry SpecFEM3D (https://geodynamics.org/cig/software/specfem3d/). If computational chemistry NWChem (http://www.nwchem-sw.org/index.php/Main_Page) might be nice. There are of course many other codes as well. If the cluster is mostly used as a task farm to run many single node jobs rather than for a large parallel application, some embarrassingly parallel task is fine (https://en.wikipedia.org/wiki/Embarrassingly_parallel), ideally setup so that upper management can execute it. One such application is Mitsuba (https://www.mitsuba-renderer.org/), some measurements for Mitsuba on a small 2 node setup can be found at https://courses.cs.ut.ee/MTAT.08.037/2015_spring/uploads/Main/Martoja.pdf

Probably most useful is to find out users of the cluster and have one or two of them explain how you have/will help improve company profitability by making their workflow more effective.

On 1/14/20 10:54 PM, Scott Atchley wrote:
Yes, we have built a few of them. We have one here, one at AMSE, and one that travels to schools in one of our traveling science trailers.

On Tue, Jan 14, 2020 at 10:29 AM John McCulloch <jo...@pcpcdirect.com <mailto:jo...@pcpcdirect.com>> wrote:

    Hey Scott, I think I saw an exhibit like what you’re describing at
    the AMSE when I was on a project in Oak Ridge. Was that it?

    John McCulloch | PCPC Direct, Ltd. | desk 713-344-0923

    *From:* Scott Atchley <e.scott.atch...@gmail.com
    <mailto:e.scott.atch...@gmail.com>>
    *Sent:* Tuesday, January 14, 2020 7:19 AM
    *To:* John McCulloch <jo...@pcpcdirect.com
    <mailto:jo...@pcpcdirect.com>>
    *Cc:* beowulf@beowulf.org <mailto:beowulf@beowulf.org>
    *Subject:* Re: [Beowulf] HPC demo

    We still have Tiny Titan <https://tinytitan.github.io> even though
    Titan is gone. It allows users to toggle processors on and off and
    the display has a mode where the "water" is colored coded by the
    processor, which has a corresponding light. You can see the frame
    rate go up as you add processors and the motion becomes much more
    fluid.

    On Mon, Jan 13, 2020 at 7:35 PM John McCulloch
    <jo...@pcpcdirect.com <mailto:jo...@pcpcdirect.com>> wrote:

        I recently inherited management of a cluster and my knowledge
        is limited to a bit of Red Hat. I need to figure out a demo
        for upper management graphically demonstrating the speed up of
        running a parallel app on one x86 node versus multiple nodes
        up to 36. They have dual Gold 6132 procs and Mellanox EDR
        interconnect. Any suggestions would be appreciated.

        Respectfully,

        John McCulloch | PCPC Direct, Ltd.

        _______________________________________________
        Beowulf mailing list, Beowulf@beowulf.org
        <mailto:Beowulf@beowulf.org> sponsored by Penguin Computing
        To change your subscription (digest mode or unsubscribe) visit
        https://beowulf.org/cgi-bin/mailman/listinfo/beowulf


_______________________________________________
Beowulf mailing list, Beowulf@beowulf.org sponsored by Penguin Computing
To change your subscription (digest mode or unsubscribe) visit 
https://beowulf.org/cgi-bin/mailman/listinfo/beowulf
_______________________________________________
Beowulf mailing list, Beowulf@beowulf.org sponsored by Penguin Computing
To change your subscription (digest mode or unsubscribe) visit 
https://beowulf.org/cgi-bin/mailman/listinfo/beowulf

Reply via email to