August 28 (Monday)
==================
8:00 - 10.00 Registration
------------------------------------------------------------
9:00 - 10:30 | Tutorial 1 | Tutorial 2 | Tutorial 4 |
------------------------------------------------------------
10:30 - 11:00 Coffee Break
------------------------------------------------------------
11:00 - 12:30 | Tutorial 1 | Tutorial 2 | Tutorial 4 |
------------------------------------------------------------
12:30 - 14:00 Lunch
------------------------------------------------------------
14:00 - 15:30 | Tutorial 1 | Tutorial 3 | Tutorial 5 |
------------------------------------------------------------
15:30 - 16:00 Coffee Break
------------------------------------------------------------
16:00 - 17:30 | Tutorial 1 | Tutorial 3 | Tutorial 5 |
------------------------------------------------------------
17:00 - 19:30 Registration
August 29 (Tuesday)
===================
8:00 - Registration
------------------------------------------------------------
8:45 - 9:00 | Opening |
------------------------------------------------------------
9:00 - 10:00 | Keynote: Greg Papadopoulos, Sun Microsystems |
------------------------------------------------------------
10:00 - 10:30 Coffee Break
------------------------------------------------------------
10:30 - 12:30 | Language Implementation I | Architecture Design |
------------------------------------------------------------
12:30 - 14:00 Lunch
------------------------------------------------------------
14:00 - 16:00 | Semantics and Tools | Interconnection Networks I |
------------------------------------------------------------
16:00 - 16:30 Coffee Break
------------------------------------------------------------
16:30 - 18:00 | Parallel Algorithms I | Cache Systems |
------------------------------------------------------------
18:30 Departure for Reception
19:00 - 21:30 Welcome Reception
August 30 (Wednesday)
=====================
------------------------------------------------------------
9:00 - 10:00 | Keynote: Gert Smolka, DFKI |
------------------------------------------------------------
10:00 - 10:30 Coffee Break
------------------------------------------------------------
10:30 - 12:30 | Loop Parallelization | Load Bal. & Par. Alg. II | V. S. |
------------------------------------------------------------
12:30 - 14:00 Lunch
------------------------------------------------------------
14:00 - 16:00 | Compiling Techniques | Applications | P. S. |
------------------------------------------------------------
16:00 - 16:15 Coffee Break
------------------------------------------------------------
16:15 - 16:30 | Best Paper Award Presentation |
------------------------------------------------------------
17:30 Departure for Banquet
18:00 - 22:00 Banquet
August 31 (Thursday)
====================
------------------------------------------------------------
9:00 - 10:00 | Keynote: Björn Engquist, KTH and UCLA |
------------------------------------------------------------
10:00 - 10:30 Coffee Break
------------------------------------------------------------
10:30 - 12:00 | Language Implementation II | Interconnection Networks II |
------------------------------------------------------------
12:00 - 13:30 Lunch
------------------------------------------------------------
13:30 - 15:00 | Scheduling | Fault Tolerance and SIMD Array|
------------------------------------------------------------
------------------------------------------------------------
15:15 - 16:15 | Panel Discussion: Future of Parallel Processing |
------------------------------------------------------------
"P.S." = Poster Session"V.S." = Vendor Session
Tutorial 1 (full day): Per Stenström
"Multiprocessors and Multicomputers - Programming
and Design"
Tutorial 2 (half day): Chris Jesshope
"Scalable Parallel Computers"
Tutorial 3 (half day): Richard Hofmann
"ZM4/SIMPLE: a Universal Hardware Monitor and Trace Evaluation
Package for Parallel and Distributed Systems"
Tutorial 4 (half day): Erland Fristedt and Per Oster
"Parallel Applications"
Tutorial 5 (half day): Kam-Fai Wong
"Parallel Database Systems Engineering"
Tuesday: Greg Papadopoulos
Mainstream Parallelism: Taking Sides on the SMP/MPP/Cluster Debate
Greg Papadopoulos (Ph.D., MIT EECS) is the Chief Technology Officer for Sun Microsystems' Server Group. He has spent the last fifteen years developing scalable general and special purpose systems. Prior to joining Sun in the Fall 1994, he was Senior Architect at Thinking Machines Corporation and an Associate Professor at MIT. In addition, Greg is co-founder of three companies, including PictureTel Corp.
Wednesday: Gert Smolka
The Oz Programming Model
The Oz Programming Model (OPM) is a concurrent programming model that subsumes functional and object-oriented programming as facets of a general model. This is particularly interesting for concurrent object-oriented programming, for which no comprehensive and formal model existed until now. There is a conservative extension of OPM providing the problem-solving capabilities of constraint logic programming. OPM has been developed together with a concomitant programming language Oz designed for applications that require complex symbolic representations, organization into multiple agents, and soft real-time control. An efficient, robust, and interactive implementation of Oz is freely available.
Gert Smolka is Professor of Computer Science at the Universität des Saarlandes at Saarbrücken and head of the Programming Systems Lab of the DFKI. He received his Dr. rer. nat. in Computer Science in 1989 from the Universität Kaiserslautern. He is a member of the executive committee of the European Network of Excellence in Computational Logic and served in many international programming committees.
Gert Smolka has published papers on computational logic, logic programming, type systems, knowledge representation and reasoning, formalisms for computational linguistics, constraints, concurrency, and programming languages and systems. Since 1991, Gert Smolka is leading the design and implementation of Oz, the first concurrent language combining a rich object system with advanced features for symbolic processing and problem solving. He and his group have now begun work towards a distributed version of Oz supporting the construction of open systems.
(Paper the talk is based on, Prof. Smolka's home page
Thursday: Björn Engquist
Parallelism in Computational Algorithms and the Physical World
Most processes in the real world are local and contain a high degree of parallelism. A simple example is weather prediction. The weather at any location depends on the weather at earlier times in the neighborhood. The computational algorithms should map these processes efficiently onto the current parallel architecture. Many modern computational methods are hierarchial and contain some global interconnection even if the underlying process is local. The overall efficiency depends on how well this connectivity is supported by the architecture. Different classes of modern methods in scientific computing and their parallel implementation will be discussed.
Björn Engquist is Professor in Numerical Analysis at the Royal Institute of Technology, Stockholm and the University of California, Los Angeles. He recieved his PhD from Uppsala University 1975 and was Professor there 1981-85. He has written two books and more than fifty research papers in the fields of Scientific Computing and Numerical Analysis. In particular he has worked on the numerical simulation of differential equations with applications in fluid mechanics and electro mechanics. He was the first recipient of the SIAM award in Scientific Computing 1982 and a Guggenheim Fellow 1992. Presently he is the Director of the Center of Excellence PSCI and the Center for Parallel Computers at the Royal Institute of Technology.
The accepted papers are grouped as follows:
Relating Data-Parallelism and (And-) Parallelism in Logic Programs
Manuel V. Hermenegildo and Manuel Carro
On the Duality Between Or-parallelism and And-parallelism in Logic Programming
Enrico Pontelli and Gopal Gupta
Functional Skeletons for Parallel Coordination
John Darlington, Yi-ke Guo, Hing Wing To and Jin Yang
Bounds on Memory Bandwidth in Streamed Computations
Sally A. McKee, Wm. A. Wulf and Trevor C. Landon
StarT-NG: Delivering Seamless Parallel Computing
Derek Chiou, Boon S. Ang, Robert Greiner, Arvind, James C. Hoe, Michael J. Beckerle, James E. Hicks and Andy Boughton
Costs and Benefits of Multithreading with Off-the-Shelf RISC Processors
Olivier C. Maquelin, Herbert H.J. Hum and Guang R. Gao
On the Completeness of a Proof System for a Simple Data-parallel Programming Language
Luc Bougé and David Cachera
An Implementation of Race Detection and Deterministic Replay with MPI
C. Clémençon, J. Fritscher, M.J. Meehan and R. Rühl
Formal and Experimental Validation of a Low Overhead Execution Replay Mechanism
Alain Fagot and Jacques Chassin de Kergommeaux
Optimal Emulation of Meshes on Meshes of Trees
Alf-Christian Achilles
Optimal Embeddings in the Hamming Cube Networks
Sajal K. Das and Aisheng Mao
Hierarchical Adaptive Routing Under Hybrid Traffic Load
Ziqiang Liu
Optimization of PRAM-Programs with Input-Dependent Memory Access
Welf Löwe
Optimal Circular Arc Representations
Lin Chen
Verifying Distributed Directory-based Cache Coherence Protocols: S3.mp, a Case Study
Fong Pong, Andreas Nowatzyk, Gunes Aybay and Michel Dubois
Efficient Software Data Prefetching for a Loop with Large Arrays
Se-Jin Hwang and Myong-Soon Park
Implementing Flexible Computation Rules with Subexpression-level Loop Transformations
Dattatraya Kulkarni, Michael Stumm and Ronald C. Unrau
Synchronization Migration for Performance Enhancement in a DOACROSS Loop
Rong-Yuh Hwang
An Array Partitioning Analysis for Parallel Loop Distribution
Marc Le Fur, Jean-Louis Pazat and Françoise André
Efficient Solutions for mapping parallel programs
P. Bouvry, J. Chassin de Kergommeaux and D. Trystram
Optimal Data Distributions for LU Decomposition
Thomas Rauber and Gudula Rünger
Detecting Quantified Global Predicates in Parallel Programs
Mark Minas
Automatic Vectorization of Communications for Data-parallel Programs
Cécile Germain and Franck Delaplace
The Program Compaction Revisited: the Functional Framework
Marc Pouzet
Featherweight Threads and ANDF Compilation of Concurrency
Ben Sloman and Tom Lake
Analysis of Parallel Scan Processing in Shared Disk Database Systems
Erhard Rahm and Thomas Stöhr
Polynomial Time Scheduling of Low Level Computer Vision Algorithms on Networks of Heterogeneous Machines
Adam R. Nolan and Bryan Everding
Mapping Neural Network Back-Propagation onto Parallel Computers with Computation/Communication Overlapping
Bernard Girau
Quiescence Detection in a Distributed KLIC Implementation
Kazuaki Rokusawa, Akihiko Nakase, Takashi Chikayama
Compiler Optimizations in Reform Prolog: Experiments on the KSR-1 multiprocessor
Thomas Lindgren, Johan Bevemyr and Håkan Millroth
A Formal Study of the Mcube Interconnection Network
Nitin K. Singhvi and Kanad Ghose
Multiwave Interconnection Networks for MCM-Based Parallel Processing
Shinichi Shionoya, Takafumi Aoki and Tatsuo Higuchi
Time Space Sharing Scheduling: A Simulation Analysis
Atsushi Hori, Yutaka Ishikawa, Jörg Nolte, Hiroki Konaka, Munenori Maeda and Takashi Tomokiyo
"Agency Scheduling" - A Model for Dynamic Task Scheduling
Johann Rost, Franz-Josef Markus and Li Yan-Hua
Tolerating Faults in Faulty Hypercubes Using Maximal Fault-Free Subcube-Ring
Jang-Ping Sheu and Yuh-Shyan Chen
Communication in Multicomputers with Nonconvex Faults
Suresh Chalasani and Rajendra V. Boppana
Parallel Prolog with Uncertainty Handling
Katalin Molnar
A Special-Purpose Coprocessor for Qualitative Simulation
Gerald Friedl, Marco Platzner and Bernhard Rinner
Portable Software Tools for Parallel Architectures
Catherine Barnes and Chris Wadsworth
Boosting the Performance of Workstations through WARPmemory
Christoph Siegelin, Ulrich Finger and Ciaran O'Donnel
A Monitoring System for Software-Heterogeneous Distributed Environments
Aleksander Laurentowski, Jakub Szymaszek, Andrzej Uszok and Krzysztof Zieliñski
A Metacircular Data-Parallel Functional Language
Gaétan Hains and John Mullins
Efficient Run-Time Program Allocation on a Parallel Coprocessor
Jurij Silc and Borut Robic
A Program Manipulation System for Fine-Grained Architectures
Vladimir A. Evstigneev and Victor N. Kasyanov
Real-Time Image Compression Using Data-Parallelism
P. Moravie, H. Essafi, C. Lambert-Nebout and J-L. Basille
Congestion Control in Wormhole Networks: First Results
Abdel-Halim Smai