Workshop 1: All Day Monday
HCW '99

Co-sponsored by
IEEE Computer Society through the Technical Committee on Parallel Processing
and the U.S. Office of Naval Research

Proceedings published by the IEEE Computer Society Press
Industrial Supporter: NOEMIX

Heterogeneous computing systems range from diverse elements within a single computer to coordinated, geographically distributed machines with different architectures. A heterogeneous computing system provides a variety of capabilities that can be orchestrated to execute multiple tasks with varied computational requirements. Applications in these environments achieve performance by exploiting the affinity of different tasks to different computational platforms or paradigms, while considering the overhead of inter-task communication and the coordination of distinct data sources and/or administrative domains. The topics of interest include, but are not limited to, task profiling, network profiling, configuration tools, scheduling tools, analytic benchmarking, programming paradigms, problem mapping, processor assignment and scheduling, fault tolerance, programming tools, Quality of Service (QoS) metrics, processor selection criteria, compiler assistance, and application studies. The workshop proceedings will be published by the IEEE Computer Society Press. The proceedings will also be available on the Web and on the IPPS/SPDP'99 CD-ROM.

Organizing Committee:
General Chair: John K. Antonio, Texas Tech University
Program Chair: Viktor K. Prasanna, University of Southern California

Steering Committee:
H.J. Siegel, Purdue University, Chair
Francine Berman, UCSD
Jack Dongarra, University of Tennessee and Oak Ridge National Lab
Richard F. Freund, NOEMIX
Debra Hensgen, Naval Postgraduate School
Paul Messina, Caltech
Jerry Potter, Kent State University
Viktor K. Prasanna, USC
Vaidy Sunderam, Emory University

Publicity Chair:
Muthucumaru Maheswaran, University of Manitoba

Program Committee:
Gul A. Agha, University of Illinois at Urbana-Champaign
Ishfaq Ahmad, The Hong Kong University of Science and Technology
Francine Berman, University of California at San Diego
Hank Dietz, Purdue University
Jack Dongarra, University of Tennessee and Oak Ridge National Lab
Ian Foster, Argonne National Laboratory
Dennis Gannon, Indiana University
Andrew Grimshaw, University of Virginia
Babak Hamidzadeh, University of British Columbia
Salim Hariri, University of Arizona
Debra Hensgen, Naval Postgraduate School
Carl Kesselman, ISI/University of Southern California
Noe Lopez-Benitez, Texas Tech University
Muthucumaru Maheswaran, University of Manitoba
Veljko Milutinovic, University of Belgrade
Fusun Ozguner, The Ohio State University
Beth Plale, Georgia Institute of Technology
Cauligi Raghavendra, The Aerospace Corporation
Daniel A. Reed, University of Illinois at Urbana-Champaign
Jaspal Subhlok, Carnegie Mellon University
Rajeev Thakur, Argonne National Laboratory
Charles C. Weems, University of Massachusetts
Jon B. Weissman, University of Texas at San Antonio



Opening Remarks
8:30 - 8:45

Session 1
8:45 - 10:00

Comparisons for Mapping Heuristics
Chair: Jon Weissman, University of Texas at San Antonio, TX, USA

Task Scheduling Algorithms for Heterogeneous Resources
Haluk Topcuoglu, Syracuse University, NY, USA
Salim Hariri, The University of Arizona, Tucson, AZ, USA
Min-You Wu, University of Central Florida, Orlando, FL, USA

A Comparison Study of Static Mapping Heuristics for a Class of Meta-tasks on Heterogeneous Computing Systems
Tracy D. Braun, Howard Jay Siegel, Noah Beck, and Ladislau Boloni, Purdue University, West Lafayette, IN, USA
Richard F. Freund, NOEMIX, Poway, CA, USA
Debra Hensgen, Naval Postgraduate School, Monterey, CA, USA
Muthucumaru Maheswaran, University of Manitoba, Winnipeg, Canada
Albert I. Reuther, James P. Robertson, Mitchell D. Theys, and Bin Yao, Purdue University, West Lafayette, IN, USA

Dynamic Matching and Scheduling of a Class of Meta-Tasks onto Heterogeneous Computing Systems
Muthucumaru Maheswaran, University of Manitoba, Winnipeg, Canada
Shoukat Ali and Howard Jay Siegel, Purdue University, West Lafayette, IN, USA
Debra Hensgen, Naval Postgraduate School, Monterey, CA, USA
Richard F. Freund, NOEMIX, Poway, CA, USA

10:00 - 10:30

Session 2
10:30 - 12:10

Design Tools
Chair: Ishfaq Ahmad, Hong Kong University of Science and Technology, Hong Kong

An On-Line Performance Visualization Technology
Aleksandar Bakic, Matt W. Mutka, and Diane T. Rover, Michigan State
University, East Lansing, MI, USA

Heterogeneous Distributed Virtual Machines in The Harness Metacomputing Framework
Mauro Migliardi and Vaidy Sunderam, Emory University, Atlanta, GA, USA

Parallel C++ Programming System on Cluster of Heterogeneous Computers
Yutaka Ishikawa, Atsushi Hori, Hiroshi Tezuka, Shinji Sumimoto, Toshiyuki Takahashi, and Hiroshi Harada, Real World Computing Partnership, Takezono, Japan

Are CORBA Services Ready to Support Resource Management Middleware for Heterogeneous Computing?
Alpay Duman, Debra Hensgen, David St. John, and Taylor Kidd, Naval Postgraduate School, Monterey, CA, USA

12:10 - 1:40

Session 3
1:40 - 2:55

Modeling & Analysis
Chair: Steve Chapin, University of Virginia, Charlottesville, VA, USA

Statistical Prediction of Task Execution Times Through Analytic Benchmarking for Scheduling in a Heterogeneous Environment
Michael A. Iverson, Fusun Ozguner, and Lee Potter, The Ohio State University, Columbus, OH, USA

Simulation of Task Graph Systems based on Stochastic Petri Nets
Noe Lopez-Benitez and Ja-Young Hyon, Texas Tech University, Lubbock, TX, USA

Communication Modeling of Heterogeneous Networks of Workstations for Performance Characterization of Collective Operations
M. Banikazemi, J. Sampathkumar, S. Prabhu, D.K. Panda, and P. Sadayappan, The Ohio State University, Columbus, OH, USA

2:55 - 3:15


Session 4
3:15 - 4:30

Task Assignment & Scheduling
Chair: Fusun Ozguner, The Ohio State University, Columbus, OH

Design of a Framework for Task Assignment in Heterogeneous Computing Systems Using Learning Automata
Raju D. Venkataramana, University of South Florida, Tampa, FL, USA
N. Ranganathan, The University of Texas at El Paso, El Paso, TX, USA

On the Robustness of Metaprogram Schedules
Ladislau Boloni and Dan C. Marinescu, Purdue University, West Lafayette, IN, USA

A Unified Resource Scheduling Framework for Heterogeneous Computing Environment
Ammar Alhusaini and Viktor K. Prasanna, University of Southern California, Los Angeles, CA, USA
C.S. Raghavendra, The Aerospace Corporation, Los Angeles, CA, USA

4:30 - 4:45

Session 5
4:45 - 6:25
Invited Case Studies
Chair: Noe Lopez-Benitez, Texas Tech University, Lubbock, TX, USA

Metacomputing with MILAN
Arash Baratloo, New York University, New York, NY, USA
Partha Dasgupta, Arizona State University, Tempe, AZ, USA and New York University, New York, NY, USA
Vijay Karamcheti and Zvi M. Kedem, New York University, New York, NY, USA

An Overview of the Management System for Heterogeneous Networks (MSHN)
Debra Hensgen, Taylor Kidd, David St. John, and Matthew C. Schnaidt, Naval Postgraduate School, Monterey, CA, USA
H.J. Siegel, Tracy Braun, Shoukat Ali, and Jong-Cook Kim, Purdue University, West Lafayette, IN, USA
Cynthia Irvine and Tim Levin, Naval Postgraduate School, Monterey, CA, USA
Viktor K. Prasanna, Prashanth B. Bhat, and Ammar Alhusaini, University of Southern California, Los Angeles, CA, USA
Richard F. Freund and Mike Godfrey, NOEMIX, Poway, CA, USA

QUIC: A Quality of Service Infrastructure for Communication in NOWs
R. Krishnamurthy, W.K. Norton, K. Schwan, V. Sarat, R. West, and S. Yalamanchili, Georgia Institute of Technology, Atlanta, GA, USA

Adaptive Distributed Applications on Heterogeneous Networks
Thomas Gross and Peter Steenkiste, Carnegie Mellon University, Pittsburgh, PA, USA
Jaspal Subhlok, University of Houston, Houston, TX, USA

Workshop 2: All Day Monday


Workshop Chair:

Frank Mueller, Humboldt University Berlin, Germany


Steering Committee:
Hermann Hellwagner, University of Klagenfurt, Austria
Hans Michael Gerndt, Research Center Juelich, Germany

Program Committee:
Arndt Bode, Technical University Munich, Germany
Helmar Burkhart, University of Basel, Switzerland
John Carter, University of Utah, USA
Karsten Decker, CSCS/SCSC, Switzerland
Hans Michael Gerndt, Research Center Juelich, Germany
Hermann Hellwagner, University of Klagenfurt, Austria
Francois Irigoin, Ecole des Mines de Paris, France
Vijay Karamcheti, New York University, USA
Peter Keleher, University of Maryland, USA
Ulrich Kremer, Rutgers University, USA
James Larus, University of Wisconsin-Madison, USA
R. Perrott, Queen's University of Belfast, United Kingdom
Thierry Priol, INRIA, France
Domenico Talia, ISI-CNR, Italy
Hans Zima, University of Vienna, Austria

HIPS'99 is a full-day workshop focusing on high-level programming for networks of workstations and of massively parallel machines. Its goal is to bring together researchers working in the areas of applications, language design, compilers, system architecture, and programming tools to discuss new developments in programming such systems.

Workshop Schedule (tentative), Monday April 12, 1999

8:30-10:00 - Session 1

10:00-10:30 - Break

10:30-12:00 - Session 2

12:00-13:15 - Lunch (on your own ?)

13:15-14:00 - Session 3

14:00-15:00 - Invited Talk: A Discipline of Multiprogramming
Jayadev Misra (University of Texas at Austin, USA)

15:00-15:30 - Break

15:30-17:00 - Session 4

For further information, please contact:

Frank Mueller
Humboldt University Berlin
Institut fuer Informatik
Unter den Linden 6
10099 Berlin, Germany
Vox: +49 (30) 2093-3011
Fax: +49 (30) 2093-3010


Workshop 3: All Day Monday


Workshop Co-Chairs:

Albert Y. Zomaya, The University of Western Australia
Fikret Ercal, University of Missouri-Rolla
Stephan Olariu, Old Dominion University

Proceedings published by Springer-Verlag and available on IPPS/SPDP CD-ROM.

Steering Committee:
Peter Fleming, University of Sheffield, United Kingdom
Frank Hsu, Fordham University
Oscar Ibarra, University of California, Santa Barbara
Viktor Prasanna, University of Southern California
Sartaj Sahni, University of Florida, Gainesville
Hartmut Schmeck, University of Karlsruhe, Germany
H.J. Siegel, Purdue University
Les Valiant, Harvard University

Program Committee:
Ishfaq Ahmad, Hong Kong University of Science and Technology
David Andrews, University of Arkansas
Prithviraj Banerjee, Northwestern University
Juergen Branke, University of Karlsruhe, Germany
Jehoshua (Shuki) Bruck, California Institute of Technology
Jens Clausen, Technical University of Denmark, Denmark
Sajal Das, University of North Texas
Hossam El-Gindy, University of Newcastle, Australia
Hesham El-Rewini, University of Nebraska at Omaha
Afonso Ferreira, CNRS, LIP-ENS, France
Ophir Frieder, Illinois Institute of Technology
Eileen Kraemer, Washington University in St. Louis
Mohan Kumar, Curtin University of Technology, Australia
Richard Lipton, Princeton University
John H. Reif, Duke University
P. Sadayappan, Ohio State University
Assaf Schuster, Technion, Israel
Franciszek Seredynski, Polish Academy of Sciences, Poland
Peter M.A. Sloot, University of Amsterdam, The Netherlands
Ivan Stojmenovic, Ottawa University, Canada
El-ghazali Talbi, Laboratoire d'Informatique Fondamentale de Lille, France
Weiping Zhu, University of Queensland, Australia

Techniques based on biological paradigms can provide efficient solutions to a wide variety of problems in parallel processing. A vast literature exists on biology-inspired approaches to solving an impressive array of problems and, more recently, a number of studies have reported on the success of such techniques for solving difficult problems in all key areas of parallel processing.

Rather remarkably, most bio-based techniques are inherently parallel. Thus, solutions based on such methods can be conveniently implemented on parallel architectures.

This workshop seeks to provide an opportunity for researchers to explore the connection between bio-based techniques and the development of solutions to problems that arise in parallel processing. Topics of
interest include, but are not limited to:
- Biologically-based methods for solving parallel processing problems (e.g., ant algorithms, genetic algorithms, cellular automata, DNA and molecular computing, neural networks) for solving parallel processing problems (scheduling, data organization and partitioning, communication and routing, VLSI layout, etc.)
- Other methods based on natural phenomena such as simulated annealing and other artificial life techniques applied to solve problems in parallel processing are also of interest
- Parallel/distributed platforms for biologically-based computations
- Techniques for integrating conventional parallel and biologically-based paradigms
- Tools and algorithms for parallelizing biologically-based techniques
- Applications and case studies combining traditional parallel and distributed computing and biologically-based techniques
- Theoretical work related to solution optimality, convergence issues, and time/space complexities of parallel algorithms that employ biologically-based methods

For further information, check the Web pages at:
or contact one of the Workshop co-chairs:

Albert Y. Zomaya
Parallel Computing Research Laboratory
Department of Electrical and Electronic Engineering
The University of Western Australia
Nedlands, Perth
Western Australia 6907
Vox: +61-8-9380-3875
Fax: +61-8-9380-1088

Fikret Ercal
Department of Computer Science
University of Missouri
Rolla, MO 65409-0350 USA
Vox: +1-573-341-4857
Fax: +1-573-341-4501

Stephan Olariu
Department of Computer Science
Old Dominion University
Norfolk, VA 23529-0162 USA
Vox: +1-757-683-4417
Fax: +1-757-683-4900

Workshop 4: All Day Monday and Tuesday


Sponsored by the U.S. Naval Surface Warfare Center

Program Co-Chairs:
Binoy Ravindran, Virginia Tech, USA
Jan Gustafsson, Malardalen University, Sweden
Hiroaki Takada, Toyohashi University of Technology, Japan

Keynote Presentations:
"Distributed Real-Time Systems Architecture - Rules & Tools"
Douglass Locke, Lockheed Martin Corporation, USA

"Composability in the Time-Triggered Architecture"
Hermann Kopetz, Technische Universität Wien, Austria

"Towards Flexible Real-Time Processing by Developing Imprecise Computation
Kenji Toda, Electrotechnical Laboratory, Japan

"Distributed Real-Time Computer Systems in the Real World"

E. Douglas Jensen, MITRE Corporation (Chair)
Jay Bayne, Johnson Controls
Julien Maisonneuve, Alcatel
Douglass Locke, Lockheed Martin Corporation
Rob Rennie, Object Automation

This year's WPDRTS will feature manuscripts that demonstrate original unpublished research pertaining to real-time systems that have parallel and/or distributed architectures. Of interest are experimental and commercial systems, their scientific and commercial applications, and theoretical foundations. The presentations will cover topics of:

- Architecture
- Benchmarking
- Command and control systems
- Communications and networking
- Databases
- Embedded systems
- Fault tolerance
- Formal methods
- High assurance systems
- Instrumentation
- Languages
- Multimedia
- New paradigms
- Object orientation
- Reengineering
- Scheduling and resource management
- Signal and image processing
- Software architectures
- Systems engineering
- Tools and environments
- Validation and simulation
- Visualization

General Chair:
David Andrews, Univ of Arkansas, USA

Steering Committee:
Dieter Hammer, Eindhoven Univ Tech, The Netherlands
Bruce Lewis, US Army
Mike Masters, NSWCDD, USA
Lalit Patnaik, Indian Institute of Science
Behrooz Shirazi, UTA, USA
John Stankovic, Univ of Virginia, USA
Lonnie Welch, UTA, USA (Chair)

Program Committee:
Emile Aarts, Eindhoven Univ Tech, The Netherlands
Bruno Achauer, Univ of Linz, Austria
Gul Agha, UIUC, USA
Mehmet Aksit, Twente Univ Tech, The Netherlands
Sriramulu Balaji, ISRO, India
Azer Bestavros, Boston Univ, USA
Maarten Boasson, Hollands Signaalapparaten B.V., The Netherlands
Carl Bruggeman, UTA, USA
Kyung-Hee Choi, Ajou Univ, Korea
Jin-Young Choi, Korea Univ
Juan A. De La Puente, Universidad Politecnica de Madrid, Spain
Klaus Ecker, Univ of Clausthal, Germany
Martin Gergeleit, GMD, Germany
Wolfgang Halang, Univ of Hagen, Germany
Hans Hansson, Malardalens Univ, Sweden
Kenji Ishida, Hiroshima City Univ, Japan
Farnam Jahanian, Univ. Michigan, USA
Kevin Jeffay, UNC Chapel Hill, USA
Rakesh Jha, Honeywell Technology Center, USA
Edwin de Jong, Hollands Signaalapparaten B.V., The Netherlands
Jan Jonsson, Chalmers Univ Tech, Sweden
Joerg Kaiser, Univ of Ulm, Germany
Yoshiaki Kakuda, Hiroshima City Univ, Japan
Carl Kesselman, Caltech, USA
Tei-Wei Kuo, National Chung Cheng Univ, Taiwan
Kwei-Jay Lin, UC Irvine, USA
Miroslaw Malek, Humboldt Univ, Berlin, Germany
Rajib Mall, IIT Kharagpur, India
Scott Midkiff, Virginia Tech, USA
Sang Lyul Min, Seoul National Univ, Korea
Ichiro Mizunuma, Mitsubishi Electric, Japan
Matt Mutka, Mich St Univ, USA
Klara Nahrstedt, UIUC, USA
Tatsuo Nakajima, JAIST, Japan
Yukikazu Nakamoto, NEC, Japan
Edgar Nett, GMD, Germany
Joseph Ng, Hong Kong Baptist Univ, Hong Kong
Brian Noble, Univ. Michigan, USA
David O'Hallaron, CMU, USA
Peter Puschner, Vienna Univ Tech, Austria
Ragunathan Rajkumar, CMU, USA
Krithi Ramamritham, Univ. Massachusetts, USA
Onno van Roosmalen, Eindhoven Univ Tech, The Netherlands
Diane Rover, Mich St Univ, USA
Helmut Rzehak, Univ of Federal Armed Forces, Germany
William Sanders, UIUC, USA
Karsten Schwan, Georgia Tech, USA
Sang Son, Univ of Virginia, USA
Neeraj Suri, Boston Univ, USA
Kazunori Takashio, Univ of Electro-Communications, Japan
Kenji Toda, Electrotechnical Laboratory, Japan
Farn Wang, Academia Sinica, Taiwan
Paul Werme, NSWCDD, USA
Wang Yi, Uppsala Univ, Sweden
Tomohiro Yoneda, Tokyo Inst Tech, Japan
Wei Zhao, Texas A&M Univ, USA

Publication Chair:
Eui-nam Huh, UTA, USA

Publicity Chairs:
Marie-Agnès Peraldi-Frati, I.U.T. Nice, France
Mitch Thornton, Univ of Arkansas, USA
Yoshinori Yamaguchi, Electrotechnical Laboratory, Japan

For further information, please contact:
Binoy Ravindran
The Bradley Department of Electrical and Computer Engineering
Virginia Tech
340 Whittemore Hall (Mail Code 0111)
Blacksburg, VA 24061
Vox: (540) 231-3777

Workshop 5: All Day Monday


Runtime systems are critical to the implementation of parallel programming languages and libraries. They provide the core functionality of a particular programming model and the glue between the model and the underlying hardware and operating system. As such, runtime systems have a large impact on the performance and portability of parallel programming systems.

Despite the importance of runtime systems, there are few forums in which practitioners can exchange their ideas, and these are typically forums showcasing peripheral areas, such as languages, operating systems, and parallel computing. RTSPP provides a forum for bringing together runtime system designers from various backgrounds to discuss the state-of-the-art in designing and implementing runtime systems for parallel programming. This one-day workshop includes technical sessions of refereed papers and panel discussions.

Program Committee:
General Chair: Laxmikant V. Kale, University of Illinois at Urbana Champaign, USA
Co-Chair: Pete Beckman, Los Alamos National Laboratory, USA
Steering Chair: Matthew Haines, University of Wyoming, USA
Program Chair: Ron Olsson, University of California, Davis, USA

Henri Bal, Vrije Universiteit, The Netherlands
Greg Benson, University of San Francisco, USA
Luc Bougé, École Normale Supérieure of Lyon (ENS Lyon), France
Koen Langendoen, Delft University of Technology, The Netherlands
David Lowenthal, University of Georgia, USA
Frank Mueller, Humboldt-Universitaet zu Berlin, Germany
Raju Pandey, University of California, Davis, USA
Alan Sussman, University of Maryland, USA


08:45 Opening Remarks

9:00-10:00 Session I
Communication in Clusters of Workstations

Efficient Communication in Multithreaded Runtime Systems
Luc Bouge, Jean-Francois Mehaut, and Raymond Namyst, École Normale Supérieure of Lyon (ENS Lyon), France

Application Performance of a Linux Cluster using Converse
Laxmikant Kale, Robert Brunner, James Phillips, and Krishnan Varadarajan, University of Illinois at Urbana Champaign, USA

10:00-10:30 Break

10:30-11:30 Session II
Cluster Computing

An Efficient and Transparent Thread Migration Scheme in the PM2 Runtime System
Gabriel Antoniu, Luc Bouge, and Raymond Namyst, École Normale Supérieure of Lyon (ENS Lyon), France

Parallel Jobs, Sequential Jobs, and Non-Dedicated Clusters of Workstations
Kritchalach Thitikamol and Peter Keleher, University of Maryland, USA

11:30-12:30 Panel I
Critical Issues in Cluster based Parallel Computing

12:30-1:30 Lunch

1:30-3:30 Session III

I/O, Distributed Arrays, Distributed Shared Memory

A Framework for Adaptive Storage I/O on Computational Grids
Huseyin Simitci and Daniel A. Reed, University of Illinois at Urbana Champaign, USA

ARMCI: A Portable Remote Memory Copy Library for Distributed Array Libraries and Compiler Run-time Systems
Jarek Nieplocha and Bryan Carpenter, Pacific Northwest National Laboratory, USA, Syracuse University, USA

Multicast-based Runtime Systems for Highly Efficient Causally Consistent Software-only DSM
Thomas Seidmann, Simultan AG, Switzerland

Adaptive DSM-Runtime Behavior via Speculative Data Distribution
Frank Mueller, Humboldt-Universitaet zu Berlin, Germany

3:30-4:00 Break

4:00-5:00 Panel II
Research Problems in Run-Time Systems

5:00 Open Forum and Closing Remarks

Workshop 6: All Day Monday


Workshop Chair:
Viktor K. Prasanna, University of Southern California (USA)

Program Chair:
Hossam ElGindy, University of Newcastle (Australia)

Goal of the Workshop: Bridging Theory and Practice

Advances in semiconductor and networking technologies have created opportunities for new and effective computing paradigms. Reconfigurable computing is one paradigm that has been the focus of both theoretical analysis and industrial development over the last decade.

On the theoretical side, the use of configurable communication media (e.g., a reconfigurable bus system) allowed the development of solutions for several classes of problems with running times that are superior to those achieved by traditional parallel models using similar resources. A large body of knowledge has been generated as a result of this research.

On the industrial/practical side, devices and systems that support various modes of reconfiguration (e.g., custom, dynamic, and self-configurable) have been developed. Several compute intensive, critical applications have been demonstrated on such systems. System design, application mapping and development of generic techniques and tools are also currently active areas of research.

The need for interaction and exchange between the theoretical and the practical sides, which is the focus of the 6th Reconfigurable Architectures Workshop, is more important than ever at this juncture in the development of both areas.

The topics of interest of the workshop include:

Reconfigurable Computing
- Models
- Algorithms and Complexity
- Fault Tolerance Issues
Programmable Logic Devices and Systems
- Architectures of Reconfigurable Systems
- Implementations
- Adaptable Systems
- Evolvable Hardware
Development Tools and Methods
- High-level Development Support
- Compilation Techniques
- CAD Tools
- Mapping of Parallel Algorithms
- Image Processing, Arithmetic/Geometric/Graph/Randomized Algorithms
- Industrial Applications and Experiences

A panel on "The Future of Reconfigurable Computing: Issues and Non-Issues"
will be chaired by Ranga R. Vemuri, University of Cincinnati (USA).

Program Committee:
Jeff Arnold, Independent Consultant (USA)
Michael Butts, Quickturn Design Systems, Inc. (USA)
Bernard Courtois, Laboratory TIMA, Grenoble (France)
Carl Ebeling, Univ. of Washington (USA)
Reiner Hartenstein, Univ. of Kaiserslautern (Germany)
Brad Hutchings, Brigham Young Univ. (USA)
Hyoung Joong Kim, Kangwon National Univ. (Korea)
Fabrizio Lombardi, Northeastern University (USA)
Wayne Luk, Imperial College (UK)
Patrick Lysaght, Univ. of Strathclyde (Scotland)
William H. Mangione-Smith, Univ. of California, Los Angeles (USA)
Malgorzata Marek-Sadowska, Univ. of California, Santa Barbara (USA)
Margaret Martonosi, Princeton Univ. (USA)
John T. McHenry, National Security Agency (USA)
Alessandro Mei, Univ. of Trento (Italy)
Martin Middendorf, Univ. of Karlsruhe (TH) (Germany)
George Milne, Univ. of South Australia (Australia)
Koji Nakano, Nagoya Institute of Technology (Japan)
Stephan Olariu, Old Dominion Univ. (USA)
Robert Parker, Information Sciences Institute East/USC (USA)
Jonathan Rose, Univ. of Toronto (Canada)
Hartmut Schmeck, Univ. of Karlsruhe (TH) (Germany)
Herman Schmit, Carnegie Mellon Univ. (USA)
Mark Shand, Compaq Systems Research Center (USA)
Jerry L. Trahan, Louisiana State Univ. (USA)
Ramachandran Vaidyanathan, Louisiana State Univ. (USA)

Publicity Chair:
Kiran Bondalapati, University of Southern California (USA)

For more information, please see the RAW'99 homepage at

Workshop 7: All Day Monday


Workshop Co-Chairs:

D. Caromel, I3S, URA CNRS 1376, Universite de Nice Sophia Antipolis, France
S. Chaumette, LaBRI, UMR CNRS 5800, Universite Bordeaux 1, France
G. Fox, NPAC, Syracuse University, USA

Note: Java and all Java-based marks are trademarks or registered trademarks of Sun Microsystems, Inc. in the United States and other countries. This workshop is independent of Sun Microsystems, Inc.

From the experience at IPPS/SPDP'98 held in Orlando, Florida, it appears that Java is becoming more and more important to the IPPS/SPDP community (i.e., for parallel and distributed computing). Many of the papers presented in Orlando referred to Java. Furthermore, the attendance at the tutorial presented there - Parallel and Distributed Computing Using Java - clearly demonstrated the widespread interest.

The success of other workshops focusing on Java also shows the importance of the topic. The ACM 1998 Workshop on Java for High-Performance Network Computing held at Stanford University, February 28th and March 1st, 1998 (following Las Vegas in 1997 and Syracuse in 1996) is a notable example. This workshop focused on high performance computing and inspired the UK workshop on Java for High Performance Network Computing that was held in September 1998 at the University of Southampton.

The workshop to be held at IPPS/SPDP'99 in San Juan focuses on Java for parallel and distributed computing and supportive environments. One of its aims is to bring together the IPPS/SPDP community around Java by providing an opportunity to share experiences and views of current trends and activity in the domain.

The presentations will cover the topics of:

- Java for parallel and distributed computing
- Programming/communication/distribution libraries
- Software tools and environments
- Code transformations, compilers, etc.
- Real world distributed and parallel applications based on Java
- Reflection
- Meta-computing and Internet applications standardization
- Theoretical foundations, formal methods, compiler technology, and performance issues
- Real-time applications, multi-agent systems
- Data mining financial applications
- Software portability, components, and reuse standards for object interoperability

Program Committee:
Jack Dongarra, University of Tennessee, USA
Ian Foster, Argonne National Laboratory, USA
Dennis Gannon, Indiana University, USA
Vladimir Getov, University of Westminster, London, U.K.
Siamak Hassanzadeh, Sun Microsystems Computer Corp., USA
Doug Lea, State University of New York at Oswego, USA
Michael Philippsen, University of Karlsruhe, Germany
George K. Thiruvathukal, Loyola University and Tools of Computing LLC, USA
David Walker, Cardiff University, UK

For further information, please contact:

Denis Caromel
I3S, URA CNRS 1376, Universite de Nice Sophia Antipolis
INRIA, 2004 Rt. des Lucioles BP 93
F-06903 Sophia Antipolis Cedex
Vox: +33 4 92 38 76 31
Fax: +33 4 92 38 79 71

Serge Chaumette
LaBRI, UMR CNRS 5800, Universite Bordeaux I
351 Cours de la Liberation
F-33405 Talence
Vox: +33 5 56 84 69 04
Fax: +33 5 56 84 66 69

Geoffrey Fox, NPAC
111 College Place, Syracuse University
Syracuse NY 13244-4100 USA
Vox: (315) 443-2163
Fax: (315) 443-2163

8 AM - 12 NOON
Tutorial 1

George Cybenko and Robert Gray
Dartmouth College
Hanover, New Hampshire

Who Should Attend:

This tutorial is meant for people interested in learning about state-of-the-art mobile agent technology, what systems are available, what they can be used for and how they perform. People who are developing large, distributed applications and distributed systems software researchers will be interested in this topic.

Course Description:

Mobile agents and mobile code is a new paradigm for distributed computing that complements technologies such as distributed objects, remote compute servers, and distributed programming systems such as PVM and MPI. After outlining the need for mobile agent systems and surveying existing systems, the tutorial will provide an in-depth presentation of a particular system called D'Agents. Examples of its use will be detailed and future trends for mobile agent systems will be discussed.


George Cybenko is the Dorothy and Walter Gramm Professor of Engineering at Dartmouth College. He has been involved in parallel computing for 15 years and has most recently been involved with developing mobile agent systems and applications. Cybenko is Editor-in-Chief of IEEE Computational Science and Engineering.

Robert Gray is a Research Assistant Professor in the Thayer School of Engineering at Dartmouth College. He is the developer of the D'Agents system ( and has pioneered work on security and multi-language support for mobile agent systems. His research work is supported by DARPA and a DOD multidisciplinary university research initiative.

1 PM - 5 PM
Tutorial 2

Vipin Kumar and Mahesh Joshi
University of Minnesota, Minneapolis

Who Should Attend:

This tutorial is meant for academic researchers and professionals who deal with the issues of analyzing high volumes of data for discovering useful and novel information. After an introduction to the field of data mining, the tutorial will focus on serial and parallel high performance algorithms for various tasks involved in data mining.

Course Description:

The last decade has seen an explosive growth in database technology and the amount of data collected. This has created an unprecedented opportunity for "data mining" which is a process of efficient supervised or unsupervised discovery of interesting information hidden in the data. The first part of this tutorial will provide an overview of some of the common tasks in data mining such as classification, clustering, and associations. The state-of-the-art serial algorithms used to accomplish them, will be discussed next. Due to the huge size of data and amount of computation involved in data mining algorithms, parallel processing is often considered an essential component of a successful data mining solution. The second part of the tutorial will present high performance parallel formulations of the algorithms.


Vipin Kumar is currently a Professor of Computer Science at the University of Minnesota. Kumar's current research focuses on parallel computing and data mining. His research has resulted in the development of highly efficient algorithms and software such as Metis, hMetis, and PSPASES. He has authored over 100 research articles, and coedited or coauthored 5 books including the widely used textbook "Introduction to Parallel Computing." Kumar has given over 50 invited talks at various conferences, workshops, national labs, and has served as chair/co-chair for many conferences/workshops in the area of parallel computing and high performance data mining. (URL:

Mahesh Joshi is currently pursuing his Ph.D. degree in Computer Science at the University of Minnesota. His research interests include parallel scientific computing and high performance data mining. He obtained his M.Tech. (five year co-op) degree in EE from IIT, Mumbai, India in 1993. He visited IBM T.J. Watson Research Center, New York for two years to work on high performance parallel algorithms. He is a student member of ACM, SIAM, and IEEE.