[Beowulf] Performance characterising a HPC application

Richard Walsh rbw at ahpcrc.org
Mon Mar 26 13:58:59 PDT 2007

Greg Lindahl wrote:
> Note that the new MVAPICH has message coalescing, which causes its
> 2-node streaming bandwidth and message rate to rise. Note that real
> apps rarely have that message pattern -- instead, they send a single
> message each to lots of other nodes before synchronizing. Message rate
> benchmarks like "base" HPCC Gups get no benefit from message
> coalescing.
    The point is a good one when you are talking about spoofing a
benchmark intended to
    measure latency (poorly designed in the suggested case), but of
course aggregation is
    a legitimate optimization technique because not all message patterns
are of the Gups
    variety just as not all memory references are absent locality. 
Aggregation is of course
    not bad per se.

    It is useful in a message context in the same way the vector
instructions are useful in a memory
    reference context.  Automatic "message" aggregation is an
optimization technique being
    used in UPC compiler development.


> _______________________________________________
> Beowulf mailing list, Beowulf at beowulf.org
> To change your subscription (digest mode or unsubscribe) visit http://www.beowulf.org/mailman/listinfo/beowulf



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.

More information about the Beowulf mailing list