[Beowulf] Performance characterising a HPC application

[Richard Walsh]

Kozin, I (Igor) wrote:
>> real codes that computes a minimum. However, an alltoall on many 
>> cores/nodes would exercise the same metric (many sends/recvs on the same 
>> NIC at the same time), but would be harder to cheat and be much more 
>> meaningful IMHO.
>>     
>
> Could not agree more. We are certainly seeing that Alltoall 
> is probably the third (after Stream Triad and PingPong) metric 
> you want to know about your system in order to predict/assess real 
> application performance.
>   
    Exchange in IMB/PMB should also be mentioned.  It reflects the needs
    of the Halo exchange algorithms that Greg referred to.

    rbw

> --
>
> Richard B. Walsh
>
> Project Manager
> Network Computing Services, Inc.
> Army High Performance Computing Research Center (AHPCRC)
> rbw at ahpcrc.org  |  612.337.3467
>
> >
> >  "The world is given to me only once, not one existing and one
> >   perceived. The subject and object are but one."
> >
> >   Erwin Schroedinger
>
> -----------------------------------------------------------------------
> This message (including any attachments) may contain proprietary or
> privileged information, the use and disclosure of which is legally
> restricted.  If you have received this message in error please notify
> the sender by reply message, do not otherwise distribute it, and delete
> this message, with all of its contents, from your files.
> ----------------------------------------------------------------------- 
>