From: Omri Schwarz <omri@byophisycs.lanl.gov>
Newsgroups: comp.parallel.mpi
Subject: Re: Shared Memory with MPI [Question from an uninitiated one]
Date: Tue, 25 Aug 1998 10:56:03 -0600
Organization: Los Alamos National Laboratory
Message-Id: <35E2ECA2.ADCF0EE6@byophisycs.lanl.gov>
References: <35E1A319.9B5EB747@byophisycs.lanl.gov>
    <6rsqil$4uk@news3.newsguy.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit


Greg Lindahl wrote:

> Omri Schwarz <omri@byophisycs.lanl.gov> writes:
>
> > Hi, looking all around my MPI refs, ["Using MPI", the HP manual,
> > URL's all around] I could find refs on how to simulate shared memory,
> > but not on how
> > to use it. My code constantly refers to, but does not modify, a huge
> > array,
> > but the processors should be able to refer to the same memory block.
>
> If you want shared memory, you should use shared memory, especially if
> you don't want to replicate any of this data. You can use one of the
> user-level distributed shared memory packages if your machine does not
> have physically shared memory. Use the right tool for the job.
>
> -- g
>

The question is, how do I pass the pointer by reference
rather than copy the whole array to each process?

Do MPI_Address variables work for this?