This volume gives an overview of the state-of-the-art with respect to the development of all types of parallel computers and their application to a wide range of problem areas.
The international conference on parallel computing ParCo97 (Parallel Computing 97) was held in Bonn, Germany from 19 to 22 September 1997. The first conference in this biannual series was held in 1983 in Berlin. Further conferences were held in Leiden (The Netherlands), London (UK), Grenoble (France) and Gent (Belgium).
From the outset the aim with the ParCo (Parallel Computing) conferences was to promote the application of parallel computers to solve real life problems. In the case of ParCo97 a new milestone was reached in that more than half of the papers and posters presented were concerned with application aspects. This fact reflects the coming of age of parallel computing.
Some 200 papers were submitted to the Program Committee by authors from all over the world. The final programme consisted of four invited papers, 71 contributed scientific/industrial papers and 45 posters. In addition a panel discussion on Parallel Computing and the Evolution of Cyberspace was held. During and after the conference all final contributions were refereed. Only those papers and posters accepted during this final screening process are included in this volume.
The practical emphasis of the conference was accentuated by an industrial exhibition where companies demonstrated the newest developments in parallel processing equipment and software. Speakers from participating companies presented papers in industrial sessions in which new developments in parallel computing were reported.
Inhaltsverzeichnis
1;Cover;1 2;CONTENTS;10 3;Preface;6 4;Sponsors, Exhibitors and Participants in the Industrial Track;7 5;Committees;8 6;PART 1: INVITED PAPERS;18 6.1;Chapter 1. Parallel and Distributed Computing using Pervasive Web and Object;20 6.2;Chapter 2. Parallel Database Techniques in Decision Support and Data Mining;50 6.3;Chapter 3. Parallel Multimedia Computing;62 6.4;Chapter 4. Europort-D: Commercial Benefits of Using Parallel Technology;78 7;PART 2: APPLICATIONS;96 7.1;Chapter 5. Parallel Processing for Scanning Genomic Data-Bases;98 7.2;Chapter 6. Application of a Multi-Processor System for Recognition of EEG-Activities in Amplitude, Time and Space in Real-Time;106 7.3;Chapter 7. Solving Large-Scale Network Transportation Problems on a Cluster of Workstations;114 7.4;Chapter 8. Parallel Probabilistic Computations on a Cluster of Workstations;122 7.5;Chapter 9. Photorealistic Rendering in Heterogeneous Networks;130 7.6;Chapter 10. Fractal Compression of Satellite Images: Combining Parallel Processing and Geometric Searching;138 7.7;Chapter 11. Parallel computation of inviscid 3D flows with unstructured domain partitioning: performance on SGI-Power Challenge Supercomputer;146 7.8;Chapter 12. Performanee and Load Balancing of Diverse Parallel Implementations of the Plasma Code HINT;154 7.9;Chapter 13. Performing DNS of Turbulent Combustion with Detailed Chemistry on Parallel Computers;162 7.10;Chapter 14. Radio Wave Propagation Simulation on the Cray T3D;172 7.11;Chapter 15. Parallel Computation of the Electromagnetic Field of Hand-Held Mobile Telephones Radiating Close to the Human Head;180 7.12;Chapter 16. Parallelization of a Nonlinear Robust Optimization Algorithm;188 7.13;Chapter 17. Parallelizing CFX-TfC, a State of the Art Industrial CFD Package;196 7.14;Chapter 18. Parallel Simulation of Flows in Sewer Network Systems;204 7.15;Chapter 19. Parallel Multigrid in the Simulation of Metal Flow;212 7.16;Chapter 20. An Enhancement of SIMD Machine for Executing SPMD Progra
ms;220 7.17;Chapter 21. Continuous Wavelet Transform on Massively Parallel Arrays;224 7.18;Chapter 22. Parallel Simulation of Coupled Oxidation and Diffusion in VLSI Wafer- Fabrication;228 7.19;Chapter 23. Report on a Parallel Molecular Dynamics Implementation;234 7.20;Chapter 24. Simulation of Energy Deposition in Deep X-Ray Lithography;238 8;PART 3: AUTOMATIC PARALLELISATION AND DATA DISTRIBUTION;242 8.1;Chapter 25. Scheduling Block-Cyclic Array Redistribution;244 8.2;Chapter 26. Parallelization of Irregular Codes Including Out-of-Core Data and Index Arrays;252 8.3;Chapter 27. Compiling the Block-Cyclic Distribution;260 8.4;Chapter 28. Unstructured Templates for Programming Irregular Grid Applications on High Performance Computers;268 8.5;Chapter 29. Hierarchical Static Analysis for Improving the Complexity of Linear Algebra Algorithms;278 8.6;Chapter 30. Semi-Automatic Parallelisation of Dynamic, Graph-based Applications;286 8.7;Chapter 31. About the Parallelization of Climate Models;294 8.8;Chapter 32. Direct Numerical Simulation of Turbulent Reactive Flows Using Massively Parallel Computers;304 8.9;Chapter 33. Automatic Parallelization for Distributed Memory Machines using Genetic Programming;314 9;PART 4: DEBUGGING;318 9.1;Chapter 34. Supporting Parallel Program Debugging through Control and Data Flow Analysis;320 9.2;Chapter 35. Interactive Visualization Environment of Multi-threaded Parallel Programs;328 9.3;Chapter 36. Maintaining Concurrency Information for On-the-fly Data Race Detection;336 9.4;Chapter 37. J iT I : Tracing Memory References for Data Race Detection;344 9.5;Chapter 38. An Integrated Dynamic and Visual Debugging for Parallel Applications;352 10;PART 5: INDUSTRIAL PERSPECTIVE;356 10.1;Chapter 39. High Performance Technical Computing at DIGITAL;358 10.2;Chapter 40. PALLAS Parallel Tools A Uniform Programming Environment from Workstations to Teraflop Computers;366 10.3;Chapter 41. Architectural Overview of the HP Exemplar V-Class Technical Serv
er;376 11;PART 6: LANGUAGES;384 11.1;Chapter 42. Paradigms for the parallel programming of heterogeneous machines through an interface compiler;386 11.2;Chapter 43. Higher Level Programming and Efficient Automatic Parallelization: A Functional Data Flow Approach with FASAN;394 11.3;Chapter 44. On the Portability of Parallel Programs;402 11.4;Chapter 45. Design and Implementation of a Scalable Parallel C Language;410 11.5;Chapter 46. Porting to HPF: Experiences with DBETSY3D within PHAROS;414 12;PART 7: NETWORKS AND COMMUNICATION;418 12.1;Chapter 47. IP Multicast for PVM on Bus Based Networks;420 12.2;Chapter 48. Benchmark Evaluation of the Message-Passing Overhead on Modern Parallel Architectures;428 12.3;Chapter 49. Coupling Industrial Simulation Codes on Parallel Computers using a Communications Library;436 12.4;Chapter 50. Flexible Communication for Parallel Asynchronous Methods with Application to a Nonlinear Optimization Problem;446 12.5;Chapter 51. Runtime Library for Parallel I/O for Irregular Applications;454 12.6;Chapter 52. Communication Performance of Gigabit LAN Workstation Cluster RWC/WSC;458 12.7;Chapter 53. Self-routing in 2-D shuffle networks with dimension-independent switches of size >8x8;462 12.8;Chapter 54. Hyper-Systolic Routing for SIMD Systems;468 12.9;Chapter 55. Metacomputing in a Regional ATM-Testbed - Experience with Reality;472 12.10;Chapter 56. Network Simulation on the CM-5 by Sorting Integer Conflict Functions;476 12.11;Chapter 57. Distributed, Heterogeneous, Dynamic Computing A Case Study;480 13;PART 8: OPERATING SYSTEMS AND THREADS;484 13.1;Chapter 58. Experiences in building Cosy - an Operating System for Highly Parallel Computers;486 13.2;Chapter 59. Architecture virtualization with mobile threads;494 13.3;Chapter 60. Compiler Support for Low-Cost Synchronization Among Threads;502 13.4;Chapter 61. WINPAR - Windows-based Parallel Computing;512 14;PART 9: PARALLEL ALGORITHMS;520 14.1;Chapter 62. A Fast Algorithm for Massively Paralle
l, Long-Term, Simulation of Complex Molecular Dynamics Systems;522 14.2;Chapter 63. Massively Parallel Linearly-Implicit Extrapolation Algorithms as a Powerful Tool in Process Simulation;534 14.3;Chapter 64. PARASOL Interface to New Parallel Solvers for Industrial Applications;542 14.4;Chapter 65. Parallel Execution of Embedded Runge-Kutta Methods;550 14.5;Chapter 66. Computational Complexity of Split Symplectic MD Integration Method;558 14.6;Chapter 67. A Parallel Approach Solving the Test Generation Problem for Synchronous Sequential Circuits;566 14.7;Chapter 68. Highly Optimized Code for Lattice Quantum Chromodynamics on the CRAY T3E;574 14.8;Chapter 69. Preconditioned Solvers for Large Eigenvalue Problems on Massively Parallel Computers and Workstation Clusters;582 14.9;Chapter 70. A Scalable Parallel SSOR Preconditioner for Efficient Lattice Computations in Gauge Theories;590 14.10;Chapter 71. Parallel Graph Generation Algorithms for Shared and Distributed Memory Machines;598 14.11;Chapter 72. Parallel Multigrid in an Adaptive PDE Solver Based on Hashing;606 14.12;Chapter 73. A Parallel Implementation of a "Symmetric Matrix Product";618 14.13;Chapter 74. A Parallel Implementation of the Three-Fields Algorithm on a HP-Convex Exemplar SPP1600;624 14.14;Chapter 75. Lattice-Boltzmann Methods for Thermohydrodynamics;632 14.15;Chapter 76. Lanczos Algorithms for Massively Parallel Processors;636 15;PART 10: PARALLEL PROGRAMMING AND VISUALISATION TOOLS;640 15.1;Chapter 77. 3D Visual Tool supporting Derivation of Distributed-Memory Massively Parallel Programs by Stepwise Transformations;642 15.2;Chapter 78. Constructing Space-Time Views from Fixed Size Trace Files Getting the Best of Both Worlds;650 15.3;Chapter 79. A Run-time Support for Object-Oriented Parallel Programming on Networks of Workstations;658 15.4;Chapter 80. Generation of Distributed Object-Oriented Programs;666 16;PART 11: PERFORMANCE;672 16.1;Chapter 81. Performance analysis of SPMD algorithms on a netw
ork of workstations with virtual shared memory;674 16.2;Chapter 82. The Effect of Restricted Instruction Issue Width on an Access Decoupled Architecture;682 16.3;Chapter 83. Performance Analysis of the Palindrome Network;690 16.4;Chapter 84. Reliability and throughput improvement in massively parallel systems;698 16.5;Chapter 85. Quality Assessment of a Parallel System Simulator;702 16.6;Chapter 86. Modelling Superlinear Speedup on Distributed Memory Multiprocessors;706 16.7;Chapter 87. Generation of Performance Models;710 16.8;Chapter 88. Knowledge-based automatic performance analysis of parallel programs;714 17;PART 12: SCHEDULING AND LOAD BALANCING;718 17.1;Chapter 89. Improved Static Multiprocessor Scheduling using Cyclic Task Graphs: A Genetic Approach;720 17.2;Chapter 90. Resource Allocation, Scheduling and Load Balancing based on the PVM Resource Manager;728 17.3;Chapter 91. Mapping and Scheduling of r-arys Trees onto Arrays and Meshes;736 17.4;Chapter 92. Mapping a Generic Systolic Array for Genetic Algorithms onto FPGAs Theory and Practice;740 17.5;Chapter 93. Effect of Task Duplication on the Assignment of Dependency Graphs;744 17.6;Chapter 94. Static Mapping of the Multifrontal Method Applied to the Modified Cholesky Factorization for Sparse Matrices;748 17.7;Chapter 95. Dynamic Load Balancing Strategy for Scalable Parallel Systems;752 17.8;Chapter 96. A Novel Economic-Based Approach to Dynamic Load Distribution in Large Heterogeneous Computer Networks;756 18;Author Index;760 19;Subject Index;763