HPDC-5 ADVANCED PROGRAM

FIFTH IEEE INTERNATIONAL SYMPOSIUM ON
HIGH PERFORMANCE DISTRIBUTED COMPUTING (HPDC-5)

OnCenter, Syracuse, New York
August 6-9, 1996

The IEEE International Symposium on High Performance Distributed Computing (HPDC) provides a forum for presenting the latest research findings that unify parallel and distributed computing. In HPDC environments, parallel or distributed computing techniques are applied to the solution of computationally intensive applications across networks of computers.

SPONSORS:

IN COOPERATION WITH:


PRE-SYMPOSIUM TUTORIALS
TUESDAY, AUGUST 6

Full Day Tutorials: (9:00 a.m. - 4:30 p.m.)

Tutorial 1 The Java Programming Language and Environment
Sanjiva Weerawarana, Purdue University
Tutorial 2 Designing and Building Parallel Programs:
An Introduction to Parallel Programming
Ian Foster, Bill Gropp, Carl Kesselman, Charles Koelbel.

Morning Half-Day Tutorials (8:30 - 12:00 PM)
Tutorial 3 Distributed Multimedia Systems
Jorg Liebeherr, University of Virginia
Tutorial 4 ATM Networking
Patrick Dowd, University of Maryland

Afternoon Half-Day Tutorials (1:00 - 4:30 PM)
Tutorial 5 Mobile Computing
Prathima Agrawal, Cormac Sreenan, Mani Srivastava
Lucent Bell Laboratories
Tutorial 6 Internet protocols for networked multimedia applications
Martina Zitterbart, Technical University of Braunschweig, Germany


7:00 - 9:00 p.m. Evening Reception and Informal Demos

WEDNESDAY, AUGUST 7

8:00 - 10:00 a.m. Registration
9:00 - 10:00 a.m. KEYNOTE SPEECH: Wm. A. Wulf
University of Virginia
10:00 - 10:30 a.m. BREAK
10:30 - 12:00 noon Concurrent Sessions (1A, 1B, 1C)

Session 1A: COLLABORATION TOOLS (Multimedia Track)
Chair:Jorg Liebeherr, University of Virginia

  1. The Network Video Terminal D. Sisalem, H. Schulzrinne, GMD-FOKUS
  2. A World-Wide Distributed System Using Java and the Internet K. M. Chandy, A. Rifkin, B. Dimitrov, H. Lee, J. Mandelson, M. Richardson, P. A. G. Sivilotti, W. Tanaka, L. Weisman California Institute of Technology
  3. Virtual Collaborative Simulation Environment for Integrated Product and Process Development B. Christensen, Deneb Robotics
  4. Tools for Distributed Collaborative Environments: A Research Agenda Ian Foster, M. Papka, R. Stevens, Argonne National Laboratory
Session 1B: APPLICATIONS I
Chair: Manish Parashar, University of Texas, Austin
  1. Runtime Support for Parallelization of Data-Parallel Applications on Adaptive and Nonuniform Computational Environments Maher Kaddoura, Sanjay Ranka, Syracuse University
  2. Massively Parallel Fast Multipole Algorithm in Three Dimensions Eric Jui-Lin Lu, Daniel Okunbor, University of Missouri
  3. I/O Requirements of Scientific Applications: An Evolutionary View Evgenia Smirni, Ruth A. Aydt, Andrew A. Chien, Daniel A. Reed University of Illinois at Urbana-Champaign
Session 1C: DISTRIBUTED AND PARALLEL PROGRAMMING
Chair: Jongbaek Park, Samsung, Korea
  1. A Task Migration Implementation for the Message-Passing Interface Samuel H. Russ, Jonathan Robinson, Mississippi State University
  2. High Performance Fortran and Possible Extensions to Support Conjugate Gradient Algorithms Kivanc Dincer, G. C. Fox, K. A. Hawick, NPAC, Syracuse University
  3. A Source-Level Transformation Framework for RPC-Based Distributed Programs Tae-Hyung Kim, James M. Purtilo, University of Maryland

12:00 noon - 1:30 p.m. LUNCH Sponsored by: Cabletron
1:30 - 3:00 p.m. Single Track Session Session 2: METACOMPUTING TRACK
Chair: Vaidy Sunderam, Emory University
  1. Legion: The Next Step Toward a World-Wide Virtual Computer Andrew Grimshaw, University of Virginia
  2. Scheduling from the Perspective of the Application Francine Berman and Richard Wolski, U. C. San Diego
  3. Enabling Technologies for Web-Based Ubiqitious Supercomputing Ian Foster and Steven Tuecke, Argonne National Laboratory

3:00 - 3:30 p.m. BREAK
3:30 - 5:00 p.m. Concurrent Sessions (3A, 3B, 3C)
Session 3A: MULTIMEDIA APPLICATIONS
Chair: Ahmed Tantawy, IBM
  1. "Media-on-Demand" Multimedia Electronic Mail: A Tool for Collaboration on the Web K. N. Tsoi, S. M. Rahman, Monash University
  2. A Light-Weight Application Sharing Infrastructure for Graphics Intensive Applications M. C. Hao, D. Lee, J. S. Sventck, Hewlett-Packard Labs
  3. A Broadband Multimedia TeleLearning System R. Wang, A. Karmouch, University of Ottawa
  4. A Theoretical and Practical Approach to MPEG-4 Syntactic Description Language (MSDL) R. J. Schaefer, J. Laier, M. Glesner, S. Panis, Siemens AG
Session 3B: TOOLS AND PRACTICE
Chair: Dick Metzger, Rome Laboratory
  1. TOP-C: A Task-Oriented Parallel C Interface Gene Cooperman, Northeastern University
  2. CNI: A High-Performance Network Interface for Workstation Clusters Mary Bailey, Prasenjit Sarkar, University of Arizona
  3. Parallel User Interfaces for Parallel Applications Mark T. Vandevoorde, MIT Lab. for Computer Science Deepak Kapur, SUNY at Albany
Session 3C: NETWORKS FOR DISTRIBUTED APPLICATIONS
Chair: Daniel J McAuliffe, Rome Laboratory
  1. Distributed Supercomputing using ACTS Manu Konchady, NASA Goddard Space Flight Center
  2. Mobile Processing in Open Systems Peter S. Sapaty, University of Surrey
  3. Employing Logic-Enhanced Memory for High-Performance ATM Network Interface Nandit Soparkar, H. Agusleo, University of Michigan

6:00 - 9:00 p.m. DINNER and HPDC DEMONSTRATIONS

THURSDAY, AUGUST 8

9:00 - 10:00 a.m. KEYNOTE SPEECH: Karl-Heinz Winkler,
Los Alamos National Laboratory
10:00 - 10:30 a.m. BREAK
10:30 a.m. - 12:00 noon Concurrent Sessions (4A, 4B, 4C)

Session 4A: MULTIMEDIA NETWORKS
Chair: Rolf Stadler, Columbia University

  1. Multimedia Multiparty Services to Native ATM Desktops H. Ouibrahim, AT&T Network Systems International
  2. Collection and Modeling of the Join/Leave Behavior of Multicast Group Members in the MBone K. Almeroth, M. H. Ammar, Georgia Tech
  3. Programmability and Service Creation for Multimedia Networks A. A. Lazar, K.-S. Lim, Columbia University
  4. On-Demand Hypermedia/Multimedia Service over Broadband Networks C. Bouras, V. Kapoulas, D. Miras, V. Ouzounis, P. Spirakis, A. Tatakis Computer Technology Institute
Session 4B: LANGUAGES AND ALGORITHMS Chair: Abdelaziz Chihoub, Siemens Corporate Research
  1. Engineering Parallel Algorithms: A Practical Approach in a Programming Environment Niandong Fang, University Basel
  2. An Imperative Language with Algorithmic Skeletons for Efficient Distributed Programming George H. Botorog, Herbert Kuchen, Aachen University of Technology
  3. Robust and Distributed Genetic Algorithm for Ordering Problems Anup Kumar, Alok Srivastava, Aditi Singru, University of Louisville R. K. Ghosh, Indian Institute of Technology
  4. Run-Time Statistical Estimation of Task Execution Times for Heterogeneous Distributed Computing Michael Iverson, Fusun Ozguner, The Ohio State University Gregory J. Follen, Interdisciplinary Technology Office
Session 4C: Networks of Workstations I
Chair: Steve Chapin, Kent University
  1. Performance Comparison of Desktop Multiprocessing and Workstation Cluster Computing Phyllis E. Crandall, Sumithasri Eranti V., University of Connecticut Mark A. Clement, Brigham Young University
  2. Customized Dynamic Load Balancing for a Network of Workstations Mohammed J. Zaki, Wei Li, Srinivasan Parthasarathy University of Rochester
  3. Commodity Clusters: Performance Comparison Between PC's and Workstations John Laroco, Robert Armstrong, Doe Acct/Sandia National Laboratories Russell Carter

12:00 noon - 1:30 p.m. LUNCH
1:30 - 3:00 p.m. Single Track Session Session 5: METACOMPUTING TRACK (Invited Papers)
chair: A. Grimshaw, University of Virginia
  1. UbiWorld: An Environment Integrating Virtual Reality, Supercomputing and Design Rick Stevens, Argonne National Laboratory
  2. Web Based High Performance Computing and Communications Geoffrey Fox and Wojtek Furmanski, Syracuse University
  3. Approximate Global States with Applications to Collaboration Eve Schooler and Mani Chandy, California Institute of Technology

3:00 - 3:30 p.m. BREAK
3:30 - 5:00 p.m. Concurrent Sessions (6A, 6B, 6C)
Session 6A: QUALITY OF SERVICE (Multimedia Track)
Chair: Martina Zitterbart, Technical University of Braunschweig, Germany
  1. Quality of Service Negotiation for Distributed Multimedia Presentational Applications A. Hafid, G. von Bochmann Universite de Montreal
  2. Controlling Resources in a Cooperative Multimedia Environment M. Alfano, R. Sigle, R. Ulrich International Computer Science Institute
  3. Meeting QOS Guarantees by End-to-End QOS Monitoring and Adaptation J.-F. Huard, I. Inoue, A. A. Lazar, H. Yamanaka Columbia University
  4. Bandwidth Control for Replicated-Stream Multicast Video Distribution X. Li, M. H. Ammar, Georgia Tech
Session 6B: APPLICATIONS II
Chair: Vikram Saletore, Oregon State University
  1. Task Partitionings for Parallel Triangular Solver on a MIMD Computer Junming Qin, Tony K. Y. Chen, Nanyang Technological University
  2. Prototyping Network Architectures on a Supercomputer M. C. Chan, Rolf Stadler, Columbia University G. Pacifici, IBM T.J. Watson Research Center
  3. An Efficient Clustered Adaptive-Risk Technique for Distributed Simulation Adel S. Elmaghraby, University of Louisville Hussam M. Soliman, King Saud University
  4. Modeling the Effects of Contention on the Performance of Heterogeneous Application Silvia M. Figueira, Francine Berman, Univ. Calif., San Diego
Session 6C: DISTRIBUTED SHARED MEMORY
Chair: C. S. Raghavendra, Washington State University, Pulman
  1. Dynamically Controlling False Sharing in Distributed Shared Memory Vincent W. Freeh, Gregory R. Andrews, The University of Arizona
  2. High-Performance Distributed-Memory Multitarget Tracking Robert L. Popp, Krishna R. Pattipati, Yaakov Bar-Shalom, U. Connecticut Richard R. Gassner, Rome Laboratory
  3. Portable Transparent Checkpointing for Distributed Shared Memory Luis M. Silva, Joao Gabriel Silva, Universidade de Coimbra Simon Chapple, The University of Edinburgh
  4. Shared Memory NUMA Programming on I-WAY Jarek Nieplocha, R. J. Harrison, Pacific Northwest National Laboratory

7:00-9:00 p.m. Reception and (informal) HPDC Demonstrations

FRIDAY, AUGUST 9


9:00 - 10:30 a.m. Concurrent Sessions (7A, 7B, 7C)
Session 7A: NETWORKS AND PROTOCOLS
Chair: Patrick Dowd, University of Maryland
  1. A Study of Caching Proxy Mechanisms Realized on Wide Area Distributed Networks Masato Oguchi, Kinji Ono, NACSIS
  2. ALF/ILP based Automated Implementation of Distributed Applications Christophe Diot, T. Braun, I. Chrisment, F. Gagnon, L. Gautier, INRIA
  3. Nynet Communication System (NCS) : A Multithreaded Message Passing Tool over ATM Network Sung Y. Park, Salim Hariri, Yoonhee Kim, J. Stuart Harris, Rajesh Yadav Syracuse University
Session 7B: I/O SYSTEMS AND STORAGE
Chair: Stuart Elby, NYNEX Science and Technology
  1. Implementation and Performance of a Parallel File System for High Performance Distributed Applications W. B. Ligon, R. B. Ross, Clemson University
  2. Automatic Management of CPU and I/O Bottlenecks in Distributed Applications on ATM Networks Marc A. Nurmi, William E. Bejcek, Rodney N. Gregoire, Kung C. Liu, Mark D. Pohl, Electronic Data Systems Corporation
  3. Impact of Delays in Parallel I/O System: An Empirical Study C. R. Venugopal, S.S.S.P. Rao, Indian Institute of Technology
  4. Approaches for a Reliable High-Performance Distributed-Parallel Storage System Qutaibah Malluhi, Jackson University William E. Johnston, Ernest Orlando Lawrence Berkeley Nat'l Lab.
Session 7C: NETWORKS OF WORKSTATIONS II
Chair: Warren Debani, Rome Laboratory
  1. Tolerating Node Failures on a Network of Workstations using Process Migration K. M. Al-Tawil, M. Bozyigit, S. K. Naseer King Fahd University of Petroleum and Minerals
  2. A Parallel Solution to the Cutting Stock Problem for a Cluster of Workstations Pearl Y. Wang, Lisa Nicklas, Robert Atkins, Sanjeev Setia George Mason University
  3. Migration Impact on Load Balancing - An Experience on Amoeba Weiping Zhu, University of South Australia Piotr Socko, Warsaw University

10:30 - 11:00 a.m. BREAK
11:00 a.m.- 12:30 p.m. Concurrent Sessions (8A, 8B, 8C)
Session 8A: WIDE-AREA DISTRIBUTED SYSTEMS
Chair: Marco Annaratone, Digital Equipment Corporation
  1. A Federated Model for Scheduling in Wide-Area Systems Jon B. Weissman, University of Texas at San Antonio Andrew Grimshaw, University of Virginia
  2. The Core Legion Object Model Michael J. Lewis, Andrew Grimshaw, University of Virginia
  3. Software Infrastructure for the I-WAY High-Performance Distributed Computing Experiment Ian T. Foster, Jonathan Geisler, Bill Nickless, Warren Smith Steven Tuecke, Argonne National Laboratory
Session 8B: COMMUNICATIONS: DESIGN AND ARCHITECTURE
Chair: Pramod Varshney, Syracuse University
  1. Design of Multicast Packet Switches for High Speed Multi-Service Networks K. Ravindran, Kansas State University
  2. Missing end-system QoS components: A case-study Sudheer Dharanikota, Kurt Maly, Old Dominion University
  3. Supporting HPDC Applications over ATM Networks with Cell-Based Transport Mechanisms Joan Vila-Sallent, Josep Sole-Pareta, Universitat Politecnica de Catalunya
Session 8C: PARALLEL SYSTEMS
Chair: Rick Metzger, Rome Laboratory
  1. Distributed Scheduling of Remote Processors in Local Area Multiprocessors Saravanan Agasaveeran, ISI Qiang Li, Santa Clara University
  2. Automatic Exploitation of Dual-Level Parallelism on a Network of Multiprocessors Santhosh Kumaran, Michael J. Quinn, Oregon State University
  3. A Design Study of Alternative Network Topologies for the Beowulf Parallel Workstation Thomas Sterling, Chance Reschke, Daniel Ridge, Daniel Savarese Donald Becker, Phillip Merkey, NASA Goddard Space Flight Center

KEYNOTE SPEAKERS

Wednesday Keynote Speech:
Wm. A. Wulf
University of Virginia

Bill Wulf is AT&T Professor of Engineering at the University of Virginia. He formerly was a Professor of Computer Science at Carnegie-Mellon, founded and was CEO of Tartan Laboratories, and was Assistant Director of NSF. His research interests have spanned programming languages, optimizing compilers, computer architecture, and computer security.

His current activities include research into memory systems architecture, steering a fundamental rethinking of the undergraduate CS curriculum, assisting scholars in the humanities exploit information technology, and chairing the Computer Science and Telecommunications Board at the National Research Council. Dr. Wulf is a member of the National Academy of Engineering, a Fellow of the ACM, IEEE, and AAAS.

Thursday Keynote Speech:
Hierarchical Shared Memory Distributed Computing Model
Karl-Heinz Winkler, Los Alamos National Laboratory
1993 - 1996 Project Leader, Information Architecture
1990 - 1993 Program Manager for Advanced Technology, C-DO, Los Alamos National Laboratory
1989 - 1990 Deputy Director for Science, Technology and Education, National Center for Supercomputing Applications, University of Illinois at Urbana-Champaign.
1989 - 1990 Full Professor, Departments of Aeronautical and Astronautical Engineering, Mechanical and Industrial Engineering, and Physics, University of Illinois at Urbana-Champaign.
1988 - 1989 Director, Numerical Laboratory at Los Alamos National Laboratory
1985 - 1988 Principal investigator, Ultra-Speed Graphics Project at Los Alamos National Laboratory
1984 - 1989 Staff member, Los Alamos National Laboratory
1976 - 1984 Staff member, Max-Planck-Institut fuer Astrophysic, Munich.


LIST OF PLANNED HPDC DEMONSTRATIONS

The organizing committee of HPDC-5 encourages submission of demonstrations pertinent to the conference program. Live demonstration will be featured during the special HPDC demonstration session. They will also be available during most of the conference in a demonstration area we plan to set up.

We will provide the following equipment to support demonstrations:

All these platforms will have Netscape2 browsers and Java environment for Java-based servers. We plan to provide full Internet access with DNS services.

For ATM demos, we will provide a (limited) number of workstations with ATM NICs. The conference site will be connected via one OC3 link to NYNET, the New York State ATM network. It is also possible to arrange for access to vBNS. For such requests, the setup of the remote end of the link will be responsibility of the requestor. The requestor will also responsible for obtaining an approval from NSF and vBNS for the ATM link. HPDC staff will handle local link setup for PVCs ending at the Cornell Theory Center vBNS access point. We are prepared to support connections based on either end-to-end PVCs or on the Classical IP.

It is possible to arrange for more elaborate demo setups. Such requests however must be received by HPDC-5 organizers no later than July 1, 1996. We will try to acommodate complex requests one a per case basis. We reserve the right to decline requests deemed too expensive to arrange.

To register demonstrations and for help in their setup, please, contact Marek Podgorny, marek@npac.syr.edu, tel.: (315) 443-4879

The HPDC demonstrations will feature the following projects:


CONFERENCE LOCATION

HPDC-5 will be held at the ONCenter, Syracuse, N.Y., (800 S. State Street) only a ten minute drive from Syracuse's Hancock International Airport. Syracuse is located in the heart of New York State, with a population of 500,000, located 280 miles northwest of New York City and less than a day's drive from Boston, Philadelphia, Washington, D.C., Toronto and Cleveland. Amtrak and Greyhound terminals are within 15 minutes of downtown Syracuse. Nearby attractions include Skaneateles Lake (a 45 minute drive), nearby Carousel Center with over 170 stores, food court and 12 cinemas, the Everson Museum of Art, Museum of Science and Technology, and the Syracuse University campus. You may take the OnTrack Express Shuttle to the Carousel Center. Visit the Syracuse University web site at http://www.syr.edu/index.html and access information on the Syracuse Region, and maps.

Weather: Weather in August tends to be warm and humid. However, there may be cool or rainy days. You may want to bring clothes appropriate for a change in weather.

Transportation: Those arriving at Hancock International Airport may take a taxi or hotel shuttle bus to the Hotel Syracuse. The Hotel is located 2 blocks from the OnCenter.

Email: Will be provided for Conference attendees at the ONCenter.

HOTEL ACCOMMODATIONS

Please contact the Hotel Syracuse, A Radisson Plaza Hotel, 500 S. Warren St., Syracuse, NY, directly at (315)-422-5121 for room reservations. The HPDC-5 special rate is $69.00 flat (single to quadruple occupancy). In order to receive our special rates be sure to tell the Hotel Syracuse that you are a participant in the HPDC-5 Symposium. Reservations at this rate may be made until July 14, or until all rooms set aside have been reserved. All reservations made after this date will be accepted on a space- available basis only. Free parking is available for overnight guests at the Hotel Syracuse. Please check with the reservation desk.

CONFERENCE COMMITTEE

SYMPOSIUM GENERAL CHAIR:

SYMPOSIUM STEERING COMMITTEE:

PROGRAM COMMITTEE CHAIR:

PUBLICITY CHAIRS:

TUTORIAL CHAIR:

EXHIBITS CHAIR:

REGISTRATION AND LOCAL ARRANGEMENTS:

PROGRAM COMMITTEE:

HPDC FOCUS WORKSHOP ON MULTIMEDIA AND COLLABORATIVE ENVIRONMENTS

WORKSHOP CHAIR:

Jorg Liebeherr, University of Virginia

WORKSHOP PROGRAM COMMITTEE:

HPDC FOCUS WORKSHOP ON METACOMPUTING

WORKSHOP CO-CHAIRS:


AGO177