| Preface | p. xi |
| Compilation and Architectural Support | |
| Multithreaded Parallelism with OpenMP | p. 3 |
| Introduction | p. 3 |
| Background | p. 5 |
| Performance Studies | p. 8 |
| Conclusion and Further Work | p. 10 |
| Source Listing | p. 12 |
| Linear Data Distribution based on Index Analysis | p. 15 |
| Introduction | p. 15 |
| Overview of Data Distribution | p. 16 |
| Motivation | p. 17 |
| Linear Data Distribution | p. 18 |
| Index Conversion and Iteration Space Conversion | p. 24 |
| Experimental Results for Linear Distribution | p. 26 |
| Summary | p. 28 |
| Quantification of Memory Communication | p. 31 |
| Introduction | p. 31 |
| Related Work | p. 33 |
| Motivating Example | p. 34 |
| Experimental Details | p. 36 |
| Quantifying Communication Cost | p. 37 |
| Identifying Memory Communication Buffers | p. 39 |
| Conclusions and Future Work | p. 42 |
| The Need for Adaptive Dynamic Thread Scheduling | p. 45 |
| Introduction | p. 46 |
| Related Work | p. 47 |
| Adaptive Dynamic Thread Scheduling with the Detector Thread | p. 48 |
| Methodology | p. 52 |
| Experimental Results | p. 55 |
| Summary and Conclusion | p. 58 |
| Numerical Computation | |
| Performance Analysis of a BiCGSTAB Solver for Multiple-Marine-Propeller Simulation with Several MPI Libraries and Platforms | p. 63 |
| Introduction | p. 63 |
| Computational Configurations | p. 65 |
| Using the MPI Libraries | p. 67 |
| Results and Discussion | p. 71 |
| Conclusions | p. 77 |
| A New BLAS-3 Based Parallel Algorithm for Computing the Eigenvectors of Real Symmetric Matrices | p. 79 |
| Introduction | p. 80 |
| Review of the Conventional Inverse Iteration Method | p. 81 |
| The Householder Inverse Iteration Method | p. 83 |
| The Blocked Algorithm | p. 86 |
| Numerical Results | p. 87 |
| Conclusion | p. 91 |
| Load Balancing | |
| Load Balancing in SPMD Applications: Concepts and Experiments | p. 95 |
| Introduction | p. 95 |
| Classification of Load Balancing Algorithms | p. 96 |
| Load Imbalancing Index | p. 99 |
| Load Balancing in a Scientific SPMD Application | p. 99 |
| Concluding Remarks | p. 106 |
| Dynamic Load Balance Strategy: Application to Nonlinear Optics | p. 109 |
| Introduction | p. 109 |
| Nonlinear Maxwell-Lorentz Equations | p. 110 |
| Numerical Approach | p. 112 |
| Message Passing Approach | p. 115 |
| Applications | p. 117 |
| Conclusion | p. 124 |
| Message-Passing Parallel Adaptive Quantum Trajectory Method | p. 127 |
| Introduction | p. 128 |
| The Hydrodynamic Formulation of Quantum Mechanics | p. 129 |
| Simulation of Wavepacket Dynamics | p. 130 |
| The Moving Weighted Least Squares Algorithm | p. 132 |
| Loop Scheduling | p. 132 |
| Experiments | p. 135 |
| Concluding Remarks | p. 137 |
| Performance Evaluation | |
| Verifying Large-Scale System Performance during Installation using Modelling | p. 143 |
| Introduction | p. 143 |
| Performance Modelling | p. 144 |
| The Alpha-Server ES45 Supercomputing System | p. 147 |
| The Application and the Model | p. 148 |
| Use of the SAGE Model to Validate System Performance | p. 148 |
| Summary | p. 155 |
| Mixed Level Modelling and Simulation of Large Scale HW/SW Systems | p. 157 |
| Introduction | p. 157 |
| Performance Estimation Techniques | p. 158 |
| Our Modelling Approach | p. 160 |
| Mixed Level System Simulation Environment | p. 162 |
| Preliminary Results | p. 163 |
| Conclusions and Future Work | p. 164 |
| Grid Computing | |
| Engineering an Autonomic Partitioning Framework for Grid-based SAMR Applications | p. 169 |
| Introduction | p. 169 |
| Problem Description | p. 171 |
| ARMaDA: An Autonomic SAMR Partitioning Framework | p. 174 |
| An Experimental Evaluation of Autonomic Partitioning Policies | p. 180 |
| Summary and Conclusions | p. 185 |
| A Resource Discovery Service For a Mobile Agents Based Grid Infrastructure | p. 189 |
| Introduction | p. 189 |
| The Grid And Web Services Models | p. 190 |
| A Magda Overview | p. 192 |
| The Discovery And Invocation Service | p. 194 |
| Related Work | p. 197 |
| xDGDL: Towards an XML-based DataGrid Description Language | p. 201 |
| Introduction | p. 201 |
| A Novel File Hierarchy | p. 202 |
| xDGDL - the XML Data Grid Description Language | p. 205 |
| A Practical xDGDL Example | p. 209 |
| An Application of xDGDL | p. 211 |
| Conclusions and Future Work | p. 212 |
| Scientific and Engineering Applications | |
| A Large-scale MD Simulation for Formation Process of Carbon Cluster on a Parallel Computer | p. 217 |
| Introduction | p. 218 |
| Basic information | p. 218 |
| Parallelization Process | p. 225 |
| Parallelization Results | p. 227 |
| Approximation of Execution Times and Outstanding Problems | p. 229 |
| Conclusion | p. 230 |
| Comparing Various Parallelizing Approaches for Tribology Simulations | p. 231 |
| Introduction | p. 231 |
| Parallelization Approaches | p. 233 |
| Molecular Dynamics | p. 238 |
| Experiments and Analysis | p. 242 |
| Conclusion and Future Work | p. 244 |
| Sequential Code | p. 249 |
| OpenMP Code | p. 251 |
| MPI Code | p. 251 |
| Strings DSM Code | p. 252 |
| High Performance Air Pollution Simulation on Shared Memory Systems | p. 253 |
| Introduction | p. 253 |
| Air Pollution Modelling | p. 254 |
| Sequential Profile of the STEM-II Program | p. 255 |
| Optimization of the Sequential Code | p. 258 |
| Parallel Code Using OpenMP | p. 261 |
| An Ant Colony Optimization Based Routing Algorithm in Mobile Ad hoc Networks and its Parallel Implementation | p. 267 |
| Introduction | p. 268 |
| Background | p. 269 |
| Parallel ACO Routing Algorithm | p. 273 |
| Experimental Results | p. 277 |
| Conclusions | p. 280 |
| Parallelizing Serializable Transactions Based on Transaction Classification in Real-time Database Systems | p. 285 |
| Introduction | p. 285 |
| Nature of Delays | p. 286 |
| The Proposed Model | p. 288 |
| Definitions for Real-time Database System | p. 290 |
| Ordering of Transactions in a Distributed System | p. 291 |
| An Algorithm to Construct LAG | p. 292 |
| Performance Evaluation | p. 294 |
| Summary and Conclusions | p. 297 |
| Adaptive Selection of Materialized Queries in a Mediator for the Integration of Distributed Information Resources | p. 299 |
| Introduction | p. 299 |
| Related Work | p. 301 |
| Decayed Usage Patterns | p. 303 |
| Implementation Plans | p. 305 |
| Experiments and Analysis of Results | p. 310 |
| Conclusion | p. 312 |
| Index | p. 315 |
| Table of Contents provided by Ingram. All Rights Reserved. |