<div>Following may be helpful. Please anyone at Beowulf that thinks his/her notes can help, participate in this subject:</div>
<div>MPI is nothing, but a library of some functions that can be called by a code (written in FORTRAN or C) to pass information between CPUs. On the other hand, Beowlf is nothing but a network of commonplace computers with this library installed on all fo them. Truthfully speaking, i have not a thorough experience in adjusting MPI configurations, but, as far as i know there are no special configurations, and just installing of MPI is enough.
<div>As you told, Beowulf is just this. However, after implementation you can use it depending on your applications. There are 2 possibilities: 1-you (or your staff) yourself write parallel program (FORTRAN/C) and then compile it on Beowulf cluster, or, 2- you use prepared packages like GROMACS, DLPOLY, ESPRESSO, ... which mainly are ready with their source codes.
<div><span class="gmail_quote">On 12/5/06, <b class="gmail_sendername">reza bakhshi</b> <<a href="mailto:email@example.com">firstname.lastname@example.org</a>> wrote:</span>
<blockquote class="gmail_quote" style="PADDING-LEFT: 1ex; MARGIN: 0px 0px 0px 0.8ex; BORDER-LEFT: #ccc 1px solid">Hello Mr. Mousavi,<br>Thank you for your notes, but what I have read about Beowulf told me that<br>we need for example some job scheduling mechanism, distributed programming
<br>(like PVM, MPI, ...). by software infra, i meant in an implemented Beowulf<br>cluster one just needs pvm, mpich2, condor, ... and that's all?<br>or we need more configurations applied on pvm, condor, and any other<br>
utility to gain a full beowulf.<br>I hope these cleared my problem :)<br>Can you (or anyone) help more?<br>Thank you again,<br><br>--Reza Bakhshi<br><br>-----Original Message-----<br>From: "Ruhollah Moussavi Baygi " <
<a href="mailto:email@example.com">firstname.lastname@example.org</a>><br>To: "reza bakhshi" <<a href="mailto:email@example.com">firstname.lastname@example.org</a>><br>Cc: <a href="mailto:email@example.com">
firstname.lastname@example.org</a><br>Date: Sun, 3 Dec 2006 19:43:57 +0330<br>Subject: Re: [Beowulf] More technical information and spec of beowulf<br><br>> Hi Reza!<br>> What do u mean exactly by "Beowulf software infrastructure" ?
<br>><br>> u know Beowulf is just a manner of connecting commonplace computers<br>> (nodes)<br>> together to make a robust system. Then your computational job will be<br>> divided among nodes. As far as I know, there is no especial software
<br>> for<br>> this framework. All you need is a message passing interface (MPI) which<br>> makes it possible for nodes to pass messages together while running<br>> job.<br>><br>> There are a lot of scientific packages (and mainly open source) which
<br>> have<br>> been developed in such a way that you can run in parallel, like<br>> GROMACS,<br>> DLPOLY, AMBER, WIEN2K, and many others. All these packages (at least<br>> their<br>> computational parts), have been compiled by FORTRAN or C/C++ .This is
<br>> due to<br>> the capability of these two compilers which can be run in parallel and<br>> work<br>> with MPI.<br>><br>> However, there are some engineering and finite element software which<br>> are
<br>> absolutely commercial and capable of being run in parallel, among them<br>> are<br>> FLUENT, CFX, and so on.<br>><br>> I hope this could be helpful for you,<br>><br>> Ruhollah Moussavi B.<br>> On 11/30/06, reza bakhshi <
<a href="mailto:email@example.com">firstname.lastname@example.org</a>> wrote:<br>> ><br>> > Hi there,<br>> > How can i find some more detailed technical information on Beowulf<br>> > software infrastructure?
<br>> > Thank you :)<br>> ><br>> ><br>> > _______________________________________________<br>> > Beowulf mailing list, <a href="mailto:Beowulf@beowulf.org">Beowulf@beowulf.org</a><br>> > To change your subscription (digest mode or unsubscribe) visit
<br>> > <a href="http://www.beowulf.org/mailman/listinfo/beowulf">http://www.beowulf.org/mailman/listinfo/beowulf</a><br>> ><br>><br>><br>><br>> --<br>> Best,<br>> Ruhollah Moussavi B.<br>>
<br><br><br></blockquote></div><br><br clear="all"><br>-- <br>Best,<br>Ruhollah Moussavi Baygi<br>Computational Physical Sciences Research Laboratory, Department of NanoScience, IPM