From mboxrd@z Thu Jan  1 00:00:00 1970
Message-ID: <13426df10710170913wd5f4c3fiad26e5e4ba7e4c70@mail.gmail.com>
Date: Wed, 17 Oct 2007 09:13:14 -0700
From: "ron minnich" <rminnich@gmail.com>
To: "Fans of the OS Plan 9 from Bell Labs" <9fans@cse.psu.edu>
Subject: Re: [9fans] parallel/distributed computation
In-Reply-To: <20071017144235.GE5034@gluon>
MIME-Version: 1.0
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: 7bit
Content-Disposition: inline
References: <20071017144235.GE5034@gluon>
Topicbox-Message-UUID: d36e6b5e-ead2-11e9-9d60-3106f5b1d025

On 10/17/07, lejatorn@gmail.com <lejatorn@gmail.com> wrote:
> Hi all,
>
> As I'm working in a geophysics lab, one of my point of interests
> regarding plan9 would be heavy scientific computation, especially
> parallel computing.
>
> So, first is there any fortran compiler on plan9? Second, is there any
> support for parallel computing, like mpi (even libs for that in C would
> be something)?

You have two choices.

1) write it from scratch
2) port gcc and then all of gnubin -- and then all of the various
parallel computing software

if you want industrial strength versions of this type of thing, you
won't do (1) better than the  scads of people doing it now (well, your
code will sure look better than openmpi.org, but it won't do mpi
better).

So you might want to start with the gcc port. Not because we want gcc,
mind, but because we need gcc -- because there are way too many bits
that have to be done, and not enough people to do them.

ron