Conference rusure::math

1544.0. "Linear Algebra/Computing talk" by STAR::ABBASI () Mon Jan 20 1992 15:43

TITLE:  " A LOOK AT HIGH-PERFORMANCE COMPUTERS AND THE                          
	  EVOLUTION OF ALGORITHMS FOR LINEAR ALGEBRA PROBLEMS "      

     NUMBER:                            92TSS-04                                
     SCHEDULE:                          Jan 30, 1992                            
     LOCATION:                          JULIE WOLFBERG CONF. ROOM MRO4          

     TIME:                              9:00  - 12:00                           
     CLASS SIZE:                        50                                      
     INSTRUCTOR:                        JACK DONGARRA, UNIV. OF TENN.           
     COST:                              $   0                                   


*************************************************
*   TO REGISTER:	SET HOST MSBCS		*
*   			USERNAME - COURSES	*
*			NO PASSWORD IS NEEDED	*
*************************************************
                                                                                
                                                                                
Presenter: Jack Dongarra, University of Tennessee                               
Tech Host: Ned Anderson, DCSS                                                   
                                                                                
                                                                                
ABSTRACT:                                                                       
--------                                                                        
In this talk we will overview the current state of high-performance             
computing. We will trace the evolution of software for numerical                
linear algebra, starting with the first published subroutine                    
library of Wilkes, Wheeler and Gill in 1950. We look at the                     
important and influential "Handbook" edited by Wilkinson                        
and Reinsch, which formed the basis for the EISPACK and LINPACK                 
projects.  We also look at the development of the Basic Linear                  
Algebra Subprograms (BLAS) from the original BLAS aimed at                      
scalar and vector operations, through the Level 2 BLAS aimed                    
at matrix-vector operations to the recently proposed                            
Level 3 BLAS aimed at matrix-matrix operations.                                 
                                                                                
Throughout this historical tour we look at the effect that                      
machine architectures have had on portable software design,                     
culminating with the challenge that supercomputers and                          
parallelism pose to the developers of portable software,                        
and we consider what basic principals have emerged.                             
                                                                                
                                                                                
BIOGRAPHY:                                                                      
                                                                                
Jack Dongarra holds a joint appointment as Distinguished                        
Professor of Computer Science in the Computer Science Department                
at the University of Tennessee (UT) and as Distinguished                        
Scientist in the Mathematical Sciences Section at Oak Ridge                     
National Laboratory (ORNL) under the UT/ORNL Science                            
Alliance Program. He specializes in numerical algorithms                        
in linear algebra, parallel computing, use of advanced-computer                 
architectures, programming methodology, and tools for                           
parallel computers.  Other current research also involves the                   
development, testing and documentation of high quality                          
mathematical software. He was involved in the design and                        
implementation of the software packages EISPACK, LINPACK, the BLAS,             
and LAPACK; and is currently involved in the design of algorithms               
and techniques for high performance computer architectures.                     
                                                                                
Other experience includes work as a Senior Scientist at                         
Argonne National Laboratory until 1989, a visiting scientist at                 
AERE Harwell Laboratory - England in 1987, a visiting scientist                 
at Center for Supercomputer Research and Development,                           
University of Illinois, Urbana/Champaign, 1985--1987; a visiting                
scientist at IBM's T.J. Watson Research Center in 1981,                         
consultant to Los Alamos Scientific Laboratory in 1978,                         
research assistant with University of New Mexico in 1978,                       
as well as a visiting scientist at Los Alamos Scientific                        
Laboratory in 1977.                                                             
                                                                                
Dongarra received a Ph.D. in Applied Mathematics from the University of New     
Mexico in 1980, a M.S. in Computer Science from the Illinois Institute of       
Technology in 1973, and a B.S. in Mathematics from Chicago State University in  
1972.                                                                           
                                                                                
Professional activities include membership in                                   
the Society for Industrial and Applied Mathematics (SIAM),                      
the Institute of Electrical and Electronics Engineers (IEEE), and               
the Association for Computing Machinery (ACM).                                  
Dongarra has served on the SIAM Council and the ACM SIGNUM Board of Directors.  
He is also Editor-in-Chief of the International Journal of                      
Supercomputer Applications,and an editor for Parallel Computing,                
Journal of Distributed and Parallel Computing, Journal of Supercomputing,       
IMPACT of Computing in Scientific Applications, Communications of the ACM,      
and Research Monographs on Parallel and Distributed Computing.                  
                                                                                
He has published numerous articles, papers, reports and technical memoranda,    
and has given many presentations on his research interests.