[AG-TECH] Fwd: MPI Workshop

Barbara A. Kucera bkucera at ncsa.uiuc.edu
Wed Sep 18 09:10:30 CDT 2002

>X-Authentication-Warning: mail.ncsa.uiuc.edu: majordomo set sender to 
>owner-pacs at ncsa.uiuc.edu using -f
>X-Envelope-From: landwehr at osc.edu
>X-Envelope-To: <pacs at ncsa.uiuc.edu>
>X-Sender: landwehr at email.osc.edu
>X-Mailer: QUALCOMM Windows Eudora Version 5.1
>Date: Tue, 17 Sep 2002 15:27:11 -0400
>To: pacs at ncsa.uiuc.edu
>From: Elaine Landwehr <landwehr at osc.edu>
>Subject: MPI Workshop
>Cc: sts at osc.edu
>Sender: owner-pacs at ncsa.uiuc.edu
>X-MD5SUM: ce332f174d7ce91811f0540bb9d31043
>OSC is presenting a four-part workshop, Parallel Programming with MPI,
>October 3, 10, 17, and 24, 12:00 pm - 3:00 pm ET, at OSC.
>Since many potential participants cannot set aside two full days out of
>their busy schedules for a workshop. OSC and PACS are experimenting with
>a new workshop format: four weekly half day sessions. Each session is
>approximately three hours long and will be held on consecutive Thursday
>This MPI workshop is sponsored by the Alliance Partners for Advanced
>Computational Services (PACS). Join us at OSC or over the Access Grid at
>one of the participating sites.
>One of the basic methods of programming for parallel computing is the use
>of message passing libraries. These libraries manage transfer of data between
>instances of a parallel program running (usually) on multiple processors in a
>parallel computing architecture.
>MPI is intended as a standard implementation of the "message passing" model of
>parallel computing. This model is extremely general and useful. Essentially,
>any type of parallel computation can be cast in the message passing form.
>This model can be implemented on a wide variety of platforms and generally 
>more control over data location and flow within a parallel applications.
>Topics covered include:
>       Thursday, October 3, 2002 (noon to 3p Eastern)
>           -Message Passing Fundamentals
>           -MPI Program Structure
>           -MPI Messages and Datatypes
>           -Point-to-point Communications: Basic send and receive
>       Thursday, October 10, 2002 (noon to 3p Eastern)
>           -Point-to-point Communications: Alternative methods
>           -Non-Blocking Communcation
>           -Derived Datatypes
>       Thursday, October 17, 2002 (noon to 3p Eastern)
>           -Collective Communication
>       Thursday, October 24, 2002 (noon to 3p Eastern)
>           -Virtual Topologies
>Each session builds on the materials presented in the previous session(s).
>Participants are encouraged to attend all sessions.
>Problem sets will be assigned at the end of each session. Participants are
>strongly encouraged to complete the problems each week and send solutions to
>the instructor for comments.
>Attendees will be able to write and execute parallel codes using MPI.
>Target Audience:
>Scientists and engineers who are interested in programming with MPI.
>The attendee should have experience in programming in Fortran, C, or C++.
>Dr. David Ennis, OSC
>Local Arrangements:
>This workshop is being offered over the Access Grid, an experimental suite
>of hardware, software, and tools to facilitate group collaborative experiences
>over the Internet.
>Fifteen sites will be participating in the MPI workshop.
>If you are interested in attending the workshop from one of the participating
>sites listed below, please go to the URL listed for their local arrangements
>Participating Sites:
>     -OSC (http://alliance.osc.edu/mpi/)
>     -Boston University 
> (http://scv.bu.edu/accessgrid/events/mpi-10-02-register.html)
>     -UNM-HPCERC (http://www.hpcerc.unm.edu/events/2002_mpi/index.html)
>     -NCSA
>     -University of Kentucky (http://www.ccs.uky.edu/ccs/mpi/index.html)
>     -CINECA (http://www.cineca.it/HPSystems/AGNode/PPwMPI/index.html)
>     -Dartmouth College (http://research.dartmouth.edu/collab/schedule.html)
>     -CSIT at Florida State University 
> (http://www.csit.fsu.edu/~burkardt/mpi_workshop.html)
>     -Jackson State University
>     -North Dakota State Unversity 
> (http://www.ndsu.nodak.edu/accessgrid/mpi.html)
>     -PSC (http://www.psc.edu/training/MPI-AG/)
>     -Purdue University
>     -University of Louisville (http://speedsc0.spd.louisville.edu/agnode/)
>     -The University of Montana 
> (http://mroccs.cs.umt.edu/AGN/Events/OSC_MPI_2002.html)
>     -West Virginia University (http://wvvel.csee.wvu.edu/cluster/mpi01/)
>As the workshop draws nearer, lecture and lab materials will be available at
>http://alliance.osc.edu/mpi/.  Web-based evaluation forms will be available.
>Check out the asynchronous MPI course developed by Alliance PACS partners 
>using WebCT
>To learn more about the Access Grid, see http://www.accessgrid.org/.

Barbara A. Kucera
Alliance/EPSCoR Liaison
National Center for Supercomputing Applications (NCSA)
University of Illinois at Urbana-Champaign
(217) 244-0131 * Fax (217) 244-2909

Computer Science is no more about computers than astronomy is about
telescopes. - Edsger W. Dijkstra, computer science professor

More information about the ag-tech mailing list