TECHNICAL PAPERS



TUESDAY, NOVEMBER 19

Session 1: 10:30 a.m.-Noon

1A Biology Applications

Parallel Hierarchical Molecular Structure Estimation
Cheng Che Chen and Russ B. Altman, Stanford University;  Jaswinder Pal Singh, 
Princeton University
A Data-Parallel Implementation of O(N) Hierarchical N-body Methods
Yu Hu, Harvard University;  S. Lennart Johnsson, University of Houston and 
Harvard University
The Design of a Portable Scientific Tool:
A Case Study Using SnB 
Steven M. Gallo and Russ Miller, State University of New York at Buffalo;  
Charles M. Weeks, Hauptman Woodward Medical Research Institute
1B Performance I

RUNTIME Performance of Parallel Array assignment: An Empirical Study
Siddhartha Chatterjee and Lei Wang, The University of North Carolina at Chapel Hill
James M. Stichnoth, Carnegie Mellon University
ScaLAPACK: A Portable Linear Algebra Library for Distributed Memory Computers - 
Design Issues and Performance
Jack Dongarra, Laura Blackford, A. Cleary, S. Hammarling, University of Tennessee, 
Knoxville; Jaeyoung Choi, Soongsil University, Seoul, Korea; J. Demmel, I. Dillon, 
University of California, Berkeley; G. Henry, Intel SSPD
Network Performance Modeling for PVM Clusters
Mark J. Clement, Phyllis E. Crandall, Michael R. Steed
Session 2: 1:30 p.m.-3:00 p.m.

2A Visualization & Education

Scalable Algorithms for Interactive Visualization of Curved Surfaces	
Dinesh Manocha, Subodh Kumar and Chun-Fa Chang, University of North Carolina
STREN: A Highly Scalable Parallel Stereo Terrain Renderer for Planetary  Mission 
Simulations
Ansel Teng and Meemong Lee, Jet Propulsion Lab
Scott Whitman, Cray Research Inc.
Education in High Performance Computing via the WWW:  Designing and Using Technical 
Materials Effectively
Susan Mehringer, Cornell Theory Center
2B Compiler Analysis
Compiler-directed Shared-Memory Communication for Iterative Parallel Applications
Guhan Viswanathan and James R. Larus, University of Wisconsin-Madison
Dynamic Data Distribution with Control Flow Analysis
Jordi Garcia, Eduard Ayguade and Jesus Labarta,
Universitat Politecnica de Catalunya
Transformations for Imperfectly Nested Loops
Induprakas Kodukula and Keshav Pingali, Cornell University
Session 3: 3:30 p.m.-5:00 p.m.

3A Geophysical Applications

Earthquake Ground Motion Modeling on Parallel Computers
Omar Ghattas, Hesheng Bao, Jacobo Bielak, Loukas F. Kallivokas, David R. O'Hallaron, 
Jonathan R. Shewchuk and Jifeng Xu, Carnegie Mellon University
Performance Analysis and Optimization on the UCLA Parallel Atmospheric General 
Circulation Model Code
John Lou, California Institute of Technology;  John Farrara, University of 
California
Climate Data Assimilation on a Massively Parallel Supercomputer
Hong Q. Ding and Robert D. Ferraro, Jet Propulsion Laboratory
3B Tools
Performance Analysis Using the MIPS R10000 Performance Counters
Marco Zagha, Silicon Graphics, Inc.
Profiling A Parallel Language Based on Fine-Grained Communication
Kaus E. Schauser, Bjoern Haake and Chris Scheiman, University of California at 
Santa Barbara
Modeling, Evaluation and Testing of Paradyn Instrumentation System
Abdul Waheed, Michigan State University

Wednesday, November 20

Session 4: 10:00 a.m.-Noon

4A Performance II

An Analytical Model of the HINT Performance Metric
Quinn O. Snell and John L. Gustafson, Ames Laboratory
Communication Patterns and Models in Prism:  A Spectral Element-Fourier Parallel 
Navier-Stokes Solver
George Em Karniadakis and Constantinos Evangelinos, 
Brown University
The C3I Parallel Benchmark Suite - Introduction and Preliminary Results
Rakesh Jha, Brian VanVoorst, Luiz S. Pires, Wing Au, Minesh Amin, Honeywell 
Technology Center;  Richard C. Metzger, USAF Rome Laboratory;  David A. Castanon, 
ALPHATECH, Inc.;  Vipin Kumar, University of Minnesota
The Performance of the NEX SX-4 on the NCAR Benchmark Suite
Steven W. Hammond, Richard D. Loft, NCAR; 
Philip D. Tannenbaum, HNSX Supercomputers, Inc.

4B Networking & Architecture

Minimal Adaptive Routing with Limited Injection on Toroidal k-ary n-cubes
Fabrizio Petrini and Marco Vanneschi, Universita di Pisa
Low-Latency Communication on the IBM RISC System/6000 SP
Chi-Chao Chang, Grzegorz Czajkowski, Chris Hawblitzell and Thorsten von Eicken, 
Cornell University
CompileD Communication for All-optical  TDM Networks
Xin Yuan, Rami. Melhem and Rajiv. Gupta,The Univ. of Pgh.
Increasing the Effective Bandwidth of Complex Memory Systems IN Multivector 
Processors
Anna M. del Corral and Jose M. Llaberia, 
Universitat Politecnica de Catalunya

Session 5: 1:30 p.m.-3:00 p.m.

5A Hydrodynamics Applications

A Parallel Cosmological Hydrodynamics Code
Paul W. Bode, Univ. of Pennsylvania;  Guohong Xu, University of California at 
Santa Cruz;  Renyue Cen, Princeton University
Transient Dynamics Simulations:  Parallel Algorithms for Contact Detection and 
Smoothed Particle Hydrodynamics
Bruce Hendrickson, Steve Plimpton, Steve Attaway, 
Jeff Swegle, Courtenay Vaughan, Dave Gardner, 
Sandia National Labs
Performance of a Computational Fluid Dynamics Code on NEC and CRAY 
Supercomputers:  Beyond 10 Gigaflops
Ferhat F. Hatay, University of Colorado at Boulder

5B Algorithms

Parallel Preconditioners for Elliptic PDEs
Vivek Sarin and Ahmed Sameh, University of Minnesota
Sparse LU Factorization with Partial Pivoting on Distributed Memory Machines
Cong Fu and Tao Yang, Univ. of California at Santa Barbara
Implementation of Strassen's Algorithm for Matrix Multiplication
Elaine M. Jacobson, Anna Tsao and Thomas Turnbull, Center for Computing Sciences;  
Steven Huss-Lederman, University of Wisconsin-Madison;  Jeremy R. Johnson, Drexel 
University

Session 6: 3:30 p.m.-5:00 p.m.

6A Algorithms II

Global Load Balancing with Parallel Mesh Adaption on Distributed - Memory Systems
Rupak Biswas, NASA Ames Research Center;  Leonid Oliker, Research Institute for 
Advanced Computer Science; Andrew Sohn, Dept. of Computer & Information Science 
Parallel Hierarchical Solvers and Preconditioners for Boundary Element Methods
Ananth Grama, Vipin Kumar, and Ahmed Sameh, 
University of Minnesota
Parallel Multilevel k-way Partitioning Scheme for Irregular Graphs
George Karypis and Vipin Kumar, University of Minnesota

B Parallel Programming Support

Double Standards: Bringing Task Parallelism to HPF Via the Message Passing Interface
Ian Foster and David R. Kohr, Jr., Argonne National Laboratory;  Rakesh Krishnaiyer and 
Alok Choudary, Syracuse University
OMPI: Optimizing MPI Programs Using Partial Evaluation
Hirotaka Ogawa and Satoshi Matsuoka, The University of Tokyo
Particle-in-Cell Simulation Codes in High Performance Fortran
Erol Akarsu, Kivanc Dincer, Geoffrey C. Fox and Tomasz Haupt, Northeast Parallel 
Architectures Center

Thursday, November 21

Session 7: 10:00 a.m.-Noon

7A Scheduling

Application-Level Scheduling on Distributed Heterogeneous Networks
Francine D. Berman, Rich Wolski, Silvia Figueira, Jennifer Schopf and  Gary Shao, 
University of California at San Diego
NetSolve: A Network Server for Solving Computational Science Problems
Henri Casanova, University of Tennessee, Knoxville;  Jack Dongarra, University of 
Tennessee, Knoxville and Oak Ridge National Laboratory
Multimethod Communiction for High Performance Metacomputing
Ian Foster, Jonathan Geisler, Steven Tuecke, Argonne National Laboratory; Karl 
Kesselman, California Institute of Technology
Building A World-Wide Virtual Machine Based on Web and HPCC Technologies
Kivanc Dincer and Geoffrey C. Fox, Northeast Parallel Architectures Center

7B Data Mining & Modeling

Parallel Data Mining for Association Rules on Shared-memory Multi-processors
M.J. Zaki, M. Ogihara, S. Parthasarathy and W. Li, 
University of Rochester
Dynamic Computation Migration in DSM Systems
Wilson C. Hsieh, University of Washington;  M. Frans Kaashoek, MIT Laboratory for 
Computer Science;  
William E. Weihl, DEC Systems Research Center
Performance Modeling for the Panda Array I/O Library
Ying Chen, Marianne Winslett, Szu-wen Kuo, Yong Cho, University of Illinois;  
Mahesh Subramaniam, Oracle Corportion; Kent Seamons, Transarc Corporation
Striping in Disk Array rm2 Enabling the Tolerance of Double Disk Failures
Chan-Ir, POSTECH

Session 8: 3:30 p.m.-5:00 p.m.

8A Particle Dynamics

Lightweight Computational Steering of Very Large Scale Molecular Dynamics 
Simulations
David M. Beazley, University of Utah;  Peter S. Lomdahl, Los Alamos National 
Laboratory
Design of a Large Scale Discrete Element Soil Model for High Performance 
Computing Systems
Alex R. Carrillo, David A. Horner, John F. Peters, John E. West, U.S. Army Engineer 
Waterways Experiment Station
Molecular Simulation of RheologicaProperties Using Massively Parallel 
Supercomputers
P. T.  Cummings, R. K. Bhupathiraju, S.T. Cui and S. Gupta, University of 
Tennessee;  H. D. Cochran, Oak Ridge National Laboratory

8B Data & Scheduling

Virtual Memory Versus File Interfaces for Large, Memory-Intensive Scientific 
Applications
Yoonho Park and Ridgway Scott, University of Houston;  Stuart Sechrest, 
University of  Michigan
Impact of Job Mix on Optimizations for Space Sharing Schedulers
Jaspal Subhlok, Thomas Gross and Takashi Suzuoka, Carnegie Mellon University

SC'96 Home Page | Conference Program Overview | Program at a Glance | Tutorials | Keynote/Plenary/Invited Speakers | Education Program | Networking Infrastructure | Exhibits | Exhibitor Forum | HPC Challenge | Media Information | Information for Presenters | General Information | Conference Registration | Hotel Registration | Pittsburgh Information | SC'96 Committees/Sponsors | Questions? |