Advances in High Performance Computing

Most of the papers in this volume were presented at the NATO Advanced Research Workshop High Performance Computing: Technology and Application, held in Cetraro, Italy from 24 to 26 of June, 1996. The main purpose of the Workshop was to discuss some key scientific and technological developments in high performance computing, identify significant trends and defme desirable research objectives. The volume structure corresponds, in general, to the outline of the workshop technical agenda: general concepts and emerging systems, software technology, algorithms and applications. One of the Workshop innovations was an effort to extend slightly the scope of the meeting from scientific/engineering computing to enterprise-wide computing. The papers on performance and scalability of database servers, and Oracle DBMS reflect this attempt We hope that after reading this collection of papers the readers will have a good idea about some important research and technological issues in high performance computing. We wish to give our thanks to the NATO Scientific and Environmental Affairs Division for being the principal sponsor for the Workshop. Also we are pleased to acknowledge other institutions and companies that supported the Workshop: European Union: European Commission DGIII-Industry, CNR: National Research Council of Italy, University of Calabria, Alenia Spazio, Centro Italiano Ricerche Aerospaziali, ENEA: Italian National Agency for New Technology, Energy and the Environment, Fujitsu, Hewlett Packard-Convex, Hitachi, NEC, Oracle, and Silicon Graphics-Cray Research. Editors January 1997 vii LIST OF CONTRIBUTORS Ecole Nonnale Su¢rieure de Lyon, 69364 Abarbanel. Robert M. Front Matter....Pages i-xi Front Matter....Pages 1-1 Performance and Scalability of Database Servers: an Introduction....Pages 3-25 Evolution of the HPC Market....Pages 27-44 Scalable Shared-Memory Multiprocessing and the Silicon Graphics S 2 MP Architecture....Pages 45-59 Exemplar S-and X-Class: 2nd Generation of High-Performance Systems with a Global Shared Memory Architecture....Pages 61-76 Oracle Solutions for Database Management System in Parallel Processing Environment....Pages 77-86 Front Matter....Pages 87-87 PARJEN96: A Parallel Software Tool for Automatic Differentiation....Pages 89-113 VLSI Solvers for Some PDE Problems....Pages 115-131 A Comparison Between Domain Decomposition and Fully Implicit Approaches for a Parallel 3D Upwind Flow Solver....Pages 133-148 Hyper-Systolic Processing on the Quadrics: Improving Inter-Processor Communication by Simulated Annealing....Pages 149-166 Front Matter....Pages 167-167 Resource Management Tools in Cluster Computing....Pages 169-183 Explicit Management of Memory Hierarchy....Pages 185-199 Granularity Control in the LOGFLOW Parallel Prolog System....Pages 201-218 An Environment for Structured Parallel Programming....Pages 219-234 Extending Data-Parallel Languages for Irregularly Structured Applications....Pages 235-251 Automatic Coarse-Grained Parallelization Techniques....Pages 253-270 Front Matter....Pages 271-271 High—Performance Computing for the Computer Aided Design of Financial Products....Pages 273-301 Applying High Performance Computing in Electromagnetics....Pages 303-320 Aspects of Image Processing for Multimedia Applications....Pages 321-333 Parallel 3D Finite Element Computation of Unsteady Flows Past a Sphere....Pages 335-352 Back Matter....Pages 353-355 The book discusses some key scientific and technological developments in high performance computing, identifies significant trends, and defines desirable research objectives. It covers general concepts and emerging systems, software technology, algorithms and applications. Coverage includes hardware, software tools, networks and numerical methods, new computer architectures, and a discussion of future trends. Beyond purely scientific/engineering computing, the book extends to coverage of enterprise-wide, commercial applications, including papers on performance and scalability of database servers and Oracle DBM systems. Audience: Most papers are research level, but some are suitable for computer literate managers and technicians, making the book useful to users of commercial parallel computers.