Newsgroups: comp.parallel.pvm
From: pikus@heron.physics.ucsb.edu (Fedor G. Pikus)
Subject: Re: PVM on Meiko CS-2
Organization: University of California, Santa Barbara
Date: 9 Jan 95 19:06:40 GMT
Message-ID: <pikus.789678400@heron.physics.ucsb.edu>

mapdjb@bath.ac.uk (D J Batey) writes:

>Has anyone had experience with Meiko's CS2-PVM implementation?
>Specifically I have been having problems with using pvm_spawn -- my
>spawned process segv's as soon as it attempts file access, whereas it
>works perfectly if I start it using prun.

>-- Duncan Batey ----------------------------- School of Mathematics, --
>-- Postgraduate Research Student ------ University of Bath, England. --
>--"I'm suffering from mood poisoning; it must be something I hate..."--

I'm using it right now, I think it's one of the best implementations of
PVM there are (I wish Paragon would have a comparable one). PVM is
built-in, no pvmd to run, nothing. The only limitation of spawn
I know of is that you can call it only once (i.e. you have to spawn all
your processes in one call). 
Regards, Fedor

