Introduction to Parallel Computing using MPI
Math 700 - Special Topics in Applied and Numerical Mathematics
Matthias K. Gobbert, Susan E. Minkoff, and Madhu Nayakkankuppam
Fall 2001 - Schedule Number 3620
This page can be reached via my homepage at
http://www.math.umbc.edu/~gobbert.
Grading Information
Final scores and grades ordered by the last four digits of your student number:
scores and grades
Final Projects
The class presentations of the final projects will be held on
December 11 and 12 in MP 401 starting at 04:00 p.m.
See the Program for the titles,
abstracts, and (later) links to download the project reports.
Information for Download
Instructions: Open the file by clicking on the link; plain text
should appear in your browser window. Then use the ``File -> Save As''
functionality of your browser to save the data to a file. Or use the
right mouse button to directly save the file without opening it first.
The details may vary depending on your browser software and operating
system. Contact me if there is a persisting problem.
Homework 3:
Lecture Notes by Madhu Nayakkankuppam:
Homework 4:
- hw4.pdf homework assignment
- main.c serial program as starting point
- compile compilation instructions for main.c
including syntax to link to the BLAS libraries on our system
Homework 5:
Basic Information
- Instructors:
- Matthias K. Gobbert,
Math/Psyc 416, (410) 455-2404, gobbert@math.umbc.edu,
office hours: TTh 03:00-03:50 or by appointment
- Susan E. Minkoff,
Math/Psyc 440, (410) 455-3029, sminkoff@math.umbc.edu,
office hours: MW 03:00-04:00
- Madhu Nayakkankuppam,
Math/Psyc 427, (410) 455-3298, madhu@math.umbc.edu,
office hours: TTh 09:00-10:00 or by appointment
- Lectures: TTh 04:00-05:15, MP 401
- Prerequisites: Math 620, Math 630, Math 650,
fluency in programming either C or Fortran and
proficiency in using the Unix/Linux operating system,
or instructor approval
- Textbook: Peter S. Pacheco,
Parallel Programming with MPI,
Morgan Kaufmann, 1997.
A copy of the textbook is on reserve in the library.
- Grading policy:
See also the general policies and procedures for more information.
Overview
In recent years, parallel computing has become an almost ubiquitous
way to perform computer simulations involving large amounts of data or
intensive calculations. The basic purpose of using several processors
is to speed up computations of large problems by distributing the
work. But large problems typically involve vast quantities of data
as well; by distributing the work and data across several processors,
previously unsolvable problems can now be tackled in reasonable time.
The first parallel machines could typically only be afforded by
well-financed government agencies, national laboratories, and
large corporations. Today, however, due to the dramatic drop in
personal computer prices, parallel computing has become accessible
to all by the availability of inexpensive dual-processor PCs. It is
then only slightly more expensive to couple several of these into a
distributed-memory cluster.
The most common library of parallel computing instructions for
any type of parallel machine architecture is the Message Passing
Interface (MPI). This course will provide interested students a basic
introduction to parallel computing using MPI on a distributed-memory
cluster of Linux PCs. We anticipate about half the semester will
be spent on introducing the basic features of MPI. Project-oriented
assignments will be given to establish practical experience with MPI.
In order to truly appreciate the power of parallel computing, it is
useful to see it used in practice. Therefore, we intend to invite
several other researchers from a variety of related application areas
to give presentations about how they use parallel computing to solve
their application problems.
Other Information
Official UMBC Honors Code
By enrolling in this course, each student assumes the responsibilities of
an active participant in UMBC's scholarly community in which everyone's
academic work and behavior are held to the highest standards of honesty.
Cheating, fabrication, plagiarism, and helping others to commit these acts
are all forms of academic dishonesty, and they are wrong. Academic
misconduct could result in disciplinary action that may include, but is
not limited to, suspension or dismissal.
To read the full Student Academic Conduct Policy, consult the
UMBC Student Handbook, the Faculty Handbook, or the UMBC Policies
section of the UMBC Directory.
Copyright © 2001 by Matthias K. Gobbert. All Rights Reserved.
This page version 2.6, December 2001.