CS 594-31778

Understanding Parallel Computing:  Spring 2005 – 3 Credits

Wednesdays from 1:30 – 4:15

Room C211

Prof. Jack Dongarra with help from Drs. George Bosilca, Graham Fagg, Victor Eijkhout, Julien Langou, Shirley Moore, Dan Terpstra, and Felix Wolf

Email: dongarra@cs.utk.edu

Phone: 865-974-8295

Fax: 865-974-8296

Office hours: Wednesday 11:00 - 1:00, or by appointment

TA: Fengguang Song, song@cs.utk.edu

O : 307 Claxton Complex, 974-0517

OH: 10am-11am TR, or by request


Class Roster

 If your name is not on the list or some information is incorrect, please send mail to TA:

Matthew Lee Aldridge    aldridge@cs.utk.edu  

Ramkrishna Chakrabarty  rc@cs.utk.edu

Huadong Liu             hliu@cs.utk.edu  

Andy Perkins            aperkins@cs.utk.edu 

Jon Scharff             scharff@cs.utk.edu 

Sergei Shinkarev        shinkare@cs.utk.edu  

Fengguang Song (TA)     song@cs.utk.edu   

Jiayi Wu                wu@cs.utk.edu  

Yun Zhang               yzhang@cs.utk.edu  


And the course mailing list: cs594pa@klutz.cs.utk.edu  



cover imageBook for the Class:



The Sourcebook of Parallel Computing, Edited by Jack Dongarra, Ian Foster, Geoffrey Fox, William Gropp, Ken Kennedy, Linda Torczon, Andy White, October 2002, 760 pages, ISBN 1-55860-871-0, Morgan Kaufmann Publishers.









Lecture Notes: (Tentative outline of the class)


1.      January 12

 Class Introduction

 Introduction to High Performance Computing

 Chapter 1

 Homework 1 (due January 26, 2005)

 Tar file of timer

2.      January 19

Finish up old slides

Programming Architectures

Homework 2 (due February 2, 2005)

Chapter 10

Chapter 11

3.      January 26 (We are meeting at the regular time and place (no seminar):

Parallel Programming Considerations

Memory Hierarchy and Cache

Homework 3 (due February 9, 2005)

Chapter 3

Chapter 14

4.      February 2

The first hour of class will be for the seminar by:

Dr. Julien Langou, 1:30 p.m. - 2:30 p.m.

Claxton Complex, Room 205

“Recent Improvements on the Kernel Operations Used in Iterative Methods”

Memory Hierarchy and Cache continued

Homework 4 (due February 16, 2005)   

Strassen’s Algorithm

5.      February 9

Message Passing (updated 2/10/05)

Homework 05 (due February 23, 2005)

Chapter 10

6.      February 16

Message Passing continued (updated 2/23)

For Homework see last slide from lecture

How to do homework  (due March 2, 2005)

Chapter 11

7.      February 23

Remainder of slides from Week 5

Dense Linear Algebra

Chapter 20

8.      March 2

Dense Linear Algebra continued part 1, part 2

Chapter 20

9.      March 9

Iterative Linear Algebra Methods

Chapter 20

10.  March 16

Iterative Linear Algebra Methods continued

Chapter 21

March 23 – Spring Break

11.  March 30

Grid Computing

Homework 08 (due April 13, 2005)

Chapter 14 pp 409 - 442

12.  April 6

Grid Computing continued; Felix Wolf

13.  April 13

Tools for Debugging and Performance Analysis; part1, part2, part3

Homework 09 (due April 20, 2005)

Felix Wolf and Dan Terpstra

Chapter 15

14.  April 20

Tools for Debugging and Performance Analysis; part1, part2

Homework 10


15.  April 25– Last Class (Note this is Monday)

Class reports

We will start at 1:00 and plan to finish by 5:00

·  Projects (due April 2005)
Preliminary list of projects click here.

Additional Reading Materials

Message Passing Systems.

The PVM home page.

The MPI home page.
This is the best place to get info on MPI from, including implementations and the MPI forum itself.

The implementation that you should use, that is installed on the TORC (Tennessee Oak Ridge Cluster) cluster is MPICH .
A duplex postscript version of the MPI 1.1 API (with thanks to the LAM team) is available. There is also a version of MPI developed here at UTK which has the ability to recover from faults. See: http://icl.cs.utk.edu/ft-mpi/


Other useful reference material


· Here’s a pointer to specs on various processors: http://www.geek.com/procspec/procspec.htm


A good introduction to message passing systems.

J.J. Dongarra, G.E. Fagg, R. Hempl and D. Walker, Chapter in Wiley Encyclopedia of Electrical and Electronics Engineering,. ( postscript version )

``Message Passing Interfaces'', Special issue of Parallel Computing , vol 20(4), April 1994.

A paper by members of the PVM team on the differences between PVM and MPI.

Geist, G.A, J.A. Kohl, P.M. Papadopoulos, `` PVM and MPI: A Comparison of Features '', Calculateurs Paralleles , 8(2), pp. 137--150, June, 1996.

Papers by members of the MPI team on the differences between PVM and MPI.

``Why are PVM and MPI So Different'', William Gropp and Ewing Lusk (submitted to The Fourth European PVM - MPI Users' Group Meeting)


``PVM and MPI are completely different'', William Gropp and Ewing Lusk, to appear in the journal Future Generation Computer Systems, 1998.

Ian Foster, Designing and Building Parallel Programs, see http://www-unix.mcs.anl.gov/dbpp/

Alice Koniges, ed., Industrial Strength Parallel Computing, ISBN1-55860-540-1, Morgan Kaufmann Publishers, San Francisco, 2000. Ananth Gramma et al., Introduction to Parallel Computing

Michael Quinn, Parallel Programming, see http://web.engr.oregonstate.edu/~quinn/Comparison.htm

David E. Culler & Jaswinder Pal Singh, Parallel Computer Architecture, see http://www.cs.berkeley.edu/%7Eculler/book.alpha/index.html

George Almasi and Allan Gottlieb, Highly Parallel Computing



Standard Books on Message Passing

``MPI - The Complete Reference, Volume 1, The MPI-1 Core, Second Edition'',
by Marc Snir, Steve Otto, Steven Huss-Lederman, David Walker, Jack Dongarra, MIT Press, September 1998, ISDN 0-262-69215-5.

``Using MPI,''
by William Gropp, Ewing Lusk, and Anthony Skjellum, published by MIT Press, October 1994; ISBN 0-262-57104-8.

``MPI: The Complete Reference - 2nd Edition: Volume 2 - The MPI-2 Extensions'',
by William Gropp, Steven Huss-Lederman, Andrew Lumsdaine, Ewing Lusk, Bill Nitzberg, William Saphir, and Marc Snir, published by The MIT Press, September, 1998; ISBN 0-262-57123-4.

On-line Documentation and Information about Machines

·         Overview of Recent Supercomputers, Aad J. van der Steen and Jack J. Dongarra, 2004.


·         Upcoming Supercomputers



·         Catalog of Commercial Hardware and Software Vendors


Other Parallel Information Sites

·  NHSE - National HPCC Software Exchange

·  Netlib Repository at UTK/ORNL

·  BLAS Quick Reference Card



·  GAMS - Guide to Available Math Software

·  Center for Research on Parallel Computation (CRPC)

·  Supercomputing & Parallel Computing: Conferences

·  Supercomputing & Parallel Computing: Journals

·  High Performance Fortran (HPF) reports

·  High Performance Fortran Resource List

·  Fortran 90 Resource List


·  Major Science Research Institutions from Caltech


·  Message Passing Interface (MPI) Forum

·  High Performance Fortran Forum

·  OpenMP

·  PVM

·  Parallel Tools Consortium

·  DoD High Performance Computing Modernization Program

·  DoE Accelerated Strategic Computing Initiative (ASCI)

·  National Computational Science Alliance

Related On-line Textbooks

·  Templates for the Solution of Linear Systems: Building Blocks for Iterative Methods, SIAM Publication, Philadelphia, 1994.

·  PVM - A Users' Guide and Tutorial for Networked Parallel Computing, MIT Press, Boston, 1994.

·  MPI : A Message-Passing Interface Standard

·  LAPACK Users' Guide (Second Edition), SIAM Publications, Philadelphia, 1995.

·  MPI: The Complete Reference, MIT Press, Boston, 1996.

· [new]Using MPI: Portable Parallel Programming with the Message-Passing Interface by W. Gropp, E. Lusk, and A. Skjellum

·  Parallel Computing Works, by G. Fox, R. Williams, and P. Messina (Morgan Kaufmann Publishers)

·  Computational Science Education Project

·  Designing and Building Parallel Programs. A dead-tree version of this book is available by Addison-Wesley.

·  High Performance Fortran (HPF), a course offered by Manchester and North High Performance Computing Training & Education Centre, United Kingdom

For performance analysis:

·  Raj Jain, The Art of Computer Systems Performance Analysis. John Wiley, 1991.

Papers on performance analysis tools:

·  Ruth A. Aydt, "The Pablo Self-Defining Data Format," November 1997, click here.

·  Jeffrey K. Hollingsworth, Barton P. Miller, Marcelo J. R. Gongalves, Oscar Naim, Zhichen Xu and Ling Zheng, "MDL: A Language and Compiler for Dynamic Program Instrumentation", International Conference on Parallel Architectures and Compilation Techniques, San Francisco, CA, November 1997, click here.

·  Barton P. Miller, Mark D. Callaghan, Jonathan M. Cargille, Jeffrey K. Hollingsworth, R. Bruce Irvin, Karen L. Karavanic, Krishna Kunchithapadam and Tia Newhall. "The Paradyn Parallel Performance Measurement Tools", IEEE Computer 28(11), (November 1995). click here.

·  Steven T. Hackstadt and Allen D. Malony, "Distributed Array Query and Visualization for High Performance Fortran, February 1996.

·  Jerry Yan and Sekhar Sarukkai and Pankaj Mehra, "Performance Measurement, Visualization and Modeling of Parallel and Distributed Programs using the AIMS toolkit", Software Practice and Experience 25(4), April 1995, 429--461


Other Online Software and Documentation

·  Matlab documentation is available from several sources, most notably by typing ``help'' into the Matlab command window. A primer (for version 4.0/4.1 of Matlab, not too different from the current version) is available in either postscript or pdf.

·  Netlib, a repository of numerical software and related documentation

·  Netlib Search Facility, a way to search for the software on Netlib that you need

·  GAMS - Guide to Available Math Software, another search facility to find numerical software

·  Linear Algebra Software Libraries and Collections

·  LAPACK, state-of-the-art software for dense numerical linear algebra on workstations and shared-memory parallel computers. Written in Fortran.

·  CLAPACK, a C version of LAPACK.
(For a partial C++ version, see LAPACK++ on Roldan Pozo's homepage)

·  LAPACK Manual

·  ScaLAPACK, a partial version of LAPACK for distributed-memory parallel computers.

·  ScaLAPACK manual

·  LINPACK and EISPACK are precursors of LAPACK, dealing with linear systems and eigenvalue problems, respectively.

·  SuperLU is a fast implementations of sparse Gaussian elimination for sequential and parallel computers, respectively.

·  Sources of test matrices for sparse matrix algorithms

·  Matrix Market

·  University of Florida Sparse Matrix Collection

·  Templates for the solution of linear systems, a collection of iterative methods, with advice on which ones to use. The web site includes on-line versions of the book (in html and postscript) as well as software.

·  Templates for the Solution of Algebraic Eigenvalue Problems is a survey of algorithms and software for solving eigenvalue problems. The web site points to an html version of the book, as well as software.

·  Updated survey of sparse direct linear equation solvers, by Xiaoye Li

·  MGNet is a repository for information and software for Multigrid and Domain Decomposition methods, which are widely used methods for solving linear systems arising from PDEs.

·  Resources for Parallel and High Performance Computing

·  Millennium a UC Berkeley campus-wide parallel computing resource

·  Resources for CS 267, Applications of Parallel Computers

·  ACTS (Advanced CompuTational Software) is a set of software tools that make it easier for programmers to write high performance scientific applications for parallel computers.

·  PETSc: Portable, Extensible, Toolkit for Scientific Computation

·  NHSE - National High Performance Computing and Communications Software Exchange, pointers to related work across the country.

·  Issues related to Computer Arithmetic and Error Analysis

·  Efficient software for very high precision floating point arithmetic

·  Notes on IEEE Floating Point Arithmetic, by Prof. W. Kahan

·  Other notes on arithmetic, error analysis, etc. by Prof. W. Kahan

·  Report on arithmetic error that cause the Ariane 5 Rocket Crash

·  The IEEE floating point standard is currently being updated. To find out what issues the standard committee is considering, look here.


Jack Dongarra