🚀 go-pugleaf

		COLLEGE OF COMPUTING DISTINGUISHED LECTURE SERIES

David J. Kuck, Professor 
Computer Science and Electrical and Computer Engineering
Center for Supercomputing Research and Development
University of Illinois at Urbana-Champaign


	 "Cedar, Parallel Processing and the Greatest Grand Challenge"


Thursday, January 14
College of Computing, Room 17
3:30 p.m. -- Reception, 4:00 p.m. -- Lecture


Abstract

The key question about the future of supercomputing is not whether
parallelism will be used but how it will be used.  Parallelism is necessary
because the increase in the fastest machine clock speeds over the past few
decades is leveling off.  After years of debate, the Federal High
Performance Computing and Communications Initiative has now been launched. 
While HPCCI has focused much attention on parallel computing of Grand
Challenge applications, it has also promised performance improvements that
seem unachievable.

The Greatest Grand Challenge (GGC) is to design parallel computing systems
that can continue to produce speed increases into the indefinite future,
through parallelism rather than clock speed advances.  To deliver high
parallel system performance, we need well-designed algorithms, system
software, and compatible architectures.  Much work is needed in performance
evaluation and the use of performance results in system design.  The talk
will survey system performance issues and give real machine results using
the Perfect codes as well as examples from the Cedar system.

Bio
 
David J. Kuck is a Professor of Computer Science and Electrical and Computer
Engineering at the University of Illinois at Urbana-Champaign, where he has
been a faculty member since 1965.  From 1984 to 1992, he was Director of the
Center for Supercomputing Research and Development, which he organized in
1984.  He founded Kuck and Associates, Inc., Champaign, IL, in 1979 and is
Chairman of the Board of Directors.  He is currently engaged in the
development and refinement of the Cedar parallel processing system and, in
general, in theoretical and empirical studies of various machine and
software organization problems, including parallel, pipeline and
multiprocessor computation methods, interconnection networks, memory
hierarchies, and the compilation of ordinary programs for parallel machines. 
Dr. Kuck received a B.S.E.E. in 1959 from the University of Michigan and a
Ph.D from Northwestern University in 1963.  He is a Fellow of IEEE and AAAS
and a member of the National Academy of Engineering.

-- 
					
Molly Ford Croft
croft@cc.gatech.edu
College of Computing, Room 149 
(404) 853-2682