Newsgroups: comp.parallel.pvm
From: mjfrazer@despot.uwaterloo.ca (Mark Frazer)
Subject: Re: Performace issue with PVM based applications
Organization: University of Waterloo
Date: Mon, 24 Jun 1996 14:31:49 GMT
Message-ID: <DtIDp1.o5I@novice.uwaterloo.ca>

In article <4qisja$moi@geraldo.cc.utexas.edu>,
Saghir Ahmed Shaikh <shaikh@brando.ece.utexas.edu> wrote:
>Well could you suggest a strategy where I can show the both sides of the
>story. i.e. the actual happening (which I described earlier) and
>theoretical case when the 10 hosts show better performance than 5 hosts.

You've already saturated your network using 5 hosts.  Communication is
you bottleneck at this point, not computation.  Try adding some accounting
to your program to see how much stuff they send over the network.

mark

-- 
Mark Frazer    Electrical and Computer Engineering    University of Waterloo
MJFrazer@Dictator.UWaterloo.Ca       http://www.pads.uwaterloo.ca/~mjfrazer/

