On Thu, 1 Apr 1999, Robert G. Brown wrote:
> On Thu, 1 Apr 1999, Walter B. Ligon III wrote:
>
> > Being a "dyed-in-the-wool" Beowulf person, I tend to believe that the best
> > approach is to use a larger number of the most cost effective devices you
> > can get. Cost effective including all aspects of hardware and software, not
> > just CPU price and speed. For better or for worse, this is currently Intel.
> > Your mileage may vary.
>
> Chris, I'd generally agree with this philosophy and add only one thing
> -- if your task mix is IPC/network bound and synchronous (as it sounds
> like it might be) your processors may well be idle a fair amount of the
> time waiting for IPC's to complete. In that case, you are better off
> investing relatively more in the network and relatively less in the
> processors to try to tune the two to maximum cost/benefit. The ratio of
> the time the task spends computing to the amount of time it spends
> communicating, and issues like whether or not the communication can be
> parallelized with the computation or the computation blocks until
> communication is completed are important things to consider.
Exactly! And, this is what BERT tells you! So you can see
the difference between processors, networks, compilers, and messaging
API etc. It kind of eliminates the some of the guessing that
goes into building a cluster.
In other words, you can ask "What if I use 24 PII-400's vs
16 Alphas?" BEFORE you buy hardware.
Now BERT is limited to FORTRAN and the list of target
machines is not as large as we would like (we do not have
any Myricom profiles) but it is growing.
Finally all this type of analysis can be done with our
free BERT lite version (http://www.plogic.com/bert.html)
Doug
-------------------------------------------------------------------
Paralogic, Inc. | PEAK | Voice:+610.861.6960
115 Research Drive | PARALLEL | Fax:+610.861.8247
Bethlehem, PA 18017 USA | PERFORMANCE | http://www.plogic.com
-------------------------------------------------------------------
