Newsgroups: comp.parallel.pvm
From: subraman@cs.iastate.edu (Krishnan Subramaniam)
Subject: RE: PVM performance models
Organization: Iowa State University, Ames, Iowa
Date: 27 May 95 21:47:23 GMT
Message-ID: <subraman.801611243@shazam.cs.iastate.edu>

Hi,
	I have a couple of programs that take quite long to run
of the order of 1000 seconds! So I'm looing for any clues on
how to model communication costs in PVM. All I use now is
"intuition" and "common sense" to select size of messages and to
schedule to sends/recvs. But does any one know of a clean scientific
way to estimate communication costs etc on PVM ? (besides running
EXTENSIVE tests).

Thanks,
Krishnan.
--
Krishnan R Subramaniam
Voice Mail : 515 - 296 4209.
Email	   : subraman@cs.iastate.edu   
HTML  	   : http://www.public.iastate.edu/~rsk/

