Dr. Kennedys research interests include parallel computing, scientific
programming environments, and optimization of compiled code. He has
published over one hundred fifty technical articles and supervised thirty-four
Ph.D. dissertations on programming support software for high-performance
computer systems. He has supervised the construction of several software
systems for programming parallel machines, including an automatic vectorizer
for Fortran 77, an integrated scientific programming environment with
support for parallel program construction and debugging, and a compiler
infrastructure for Fortran 90 and High Performance Fortran. His current
research focuses on programming tools for parallel computer systems
and high-performance microprocessors, seeking to develop new strategies
for supporting architecture-independent parallel programming, especially
in science and engineering. He currently directs the GrADS Project,
a collaborative eight-institution research effort started in 1999 with
NSF support, which is focused on application development support for
computational grids. He is also the director of the academic component
of the Los Alamos Computer Science Institute, a collaboration with Los
Alamos National Laboratory.
Professor Kennedy was the founding chair of the Rice Computer Science
Department (1984) and Rice Computer and Information Technology Institute
(1987). In 1989, he established the Center for Research on Parallel
Computation (CRPC), a NSF Science and Technology Center, and directed
it throughout its lifetime. He is a member of the National Academy of
Engineering (1990) and a Fellow of the AAAS (1994), the ACM (1995) and
the IEEE (1995). In recognition of his achievements in compilation for
high performance computer systems, he received the 1995 W. W. McDowell
Award, the highest research award of the IEEE Computer Society. In 1999,
received the ACM SIGPLAN Programming Languages Achievement Award, the
third time this award was given.
Professor Kennedys service to the national community includes
time as Co-chair (1997-99) of the Presidents Information Technology
Advisory Committee (PITAC), a member of the Commission on Physical Sciences,
Mathematics, and Applications (1995-97), a member of the Advisory Committee
for the NSF CISE Directorate (1995-97), Chair of the High Performance
Fortran Forum (1992-97), Chair of the NRC Workshop Series on High Performance
Computing and Communications (1993-96). He is also on the Editorial
Boards of three major journals. His service has been recognized through
two national awards: the CRA Distinguished Service Award (1999) and
the RCI Seymour Cray HPCC Industry Recognition Award (1999).
The ParaScope Parallel Programming Environment, (with
K. D. Cooper, M. W. Hall, R. T. Hood, K. McKinley, J. Mellor-Crummey,
L. Torczon, and S. K. Warren. Proceedings of the IEEE 81(2): 244-263,
February 1993.
Interprocedural Analysis and Optimization, (with K.
D. Cooper, M. W. Hall, L. Torczon). The Communications in Pure and
Applied Mathematics 48: 947-1003, 1996.
Compilers, Languages, and Libraries, In The Grid: Blueprint
for a New Computing Infrastructure, (I. Foster and C. Kesselman, editors),
Morgan Kaufmann Publishers, Inc., 181- 204, August 1998.
Telescoping Languages: A Compiler Strategy for Implementation
of High-level Domain- specific Programming Systems, Proceedings
of the International Parallel and Distributed Processing Symposium
2000, Cancun, Mexico, May 2000.
Advanced Compilation for High Performance Computing (with R. Allen),
Morgan Kaufmann, San Francisco, CA, to appear September 2001.
Other Significant Publications:
Improving Register Allocation for Subscripted Variables,
(with D. Callahan and S. Carr). Proceedings of the ACM SIGPLAN 90
Conference on Programming Language Design and Implementation, SIGPLAN
Notices 25(6): 53-65, June 1990.
Improving Cache Performance in Dynamic Applications through
Data and Computation Reorganization at Run Time, (with C. Ding).
Proceedings of the ACM SIGPLAN 99 Conference on Programming
Language Design and Implementation, Atlanta, GA, May 1999.
Improving Memory Hierarchy Performance for Irregular Applications,
(with J. Mellor- Crummey and D. Whalley). Proceedings of the 13th
ACM International Conference on Supercomputing, Rhodes, Greece, 425-433,
June 1999.
Greedy Weighted Fusion, Proceedings of International
Conference on Supercomputing 2000, Santa Fe, NM (May 2000).
The Cost of Being Object-oriented: A Preliminary Study,
(with Z. Budimlic and J. Piper). Scientific Programming 7(2): 87-95,
1999.
Current Collaborators: Vikram Adve (UIUC), Francine Berman (UCSD),
Alok Choudhary (Northwestern), Jack Dongarra (Tennessee), Ian Foster
(Argonne, Chicago), Geoffrey Fox (Syracuse), Dennis Gannon (Indiana),
Lennart Johnsson (UH), Carl Kesselman (USC ISI), Chuck Koelbel (NSF),
Dan Reed (UIUC), Joel Saltz (Maryland), David Whalley (FSU), Rich Wolski
(Tennessee) plus numerous collaborators associated with the following
projects: NSF CRPC, NSF NCSA (the Alliance), NSF NPACI, NSF GrADS, and
the Los Alamos Computer Science Institute.
Thesis Advisees: Steve Carr (MTU), Chen Ding (Rochester), Ervan
Darnell (Oracle), Gina Goff (DoD), Mary Hall (USC ISI), Paul Havlak
(UH), Reinhard von Hanxleden (Daimer Benz AG), Ulrich Kremer (Rutgers),
Lorie Liebrock (MTU), Nat McIntosh (HP) Kathryn McKinley (UMass), Doug
Monk (Trinity Group), Ajay Sethi (Oracle), Jerry Roth (Gonzaga U), and
Chau-Wen Tseng (Maryland). (Total over career: 34)
Thesis Advisors: Jacob T. Schwartz, New York University and
John Cocke, IBM (retired).