Trobec / Vajteršic / Zinterhof Parallel Computing

Numerics, Applications, and Trends
1. Auflage 2009
ISBN: 978-1-84882-409-6
Verlag: Springer-Verlag
Format: PDF
Kopierschutz: Adobe DRM (»Systemvoraussetzungen)

E-Book, Englisch, 520 Seiten

The use of parallel programming and architectures is essential for simulating and solving problems in modern computational practice. There has been rapid progress in microprocessor architecture, interconnection technology and software devel- ment, which are in?uencing directly the rapid growth of parallel and distributed computing. However, in order to make these bene?ts usable in practice, this dev- opment must be accompanied by progress in the design, analysis and application aspects of parallel algorithms. In particular, new approaches from parallel num- ics are important for solving complex computational problems on parallel and/or distributed systems. The contributions to this book are focused on topics most concerned in the trends of today’s parallel computing. These range from parallel algorithmics, progr- ming, tools, network computing to future parallel computing. Particular attention is paid to parallel numerics: linear algebra, differential equations, numerical integ- tion, number theory and their applications in computer simulations, which together form the kernel of the monograph. We expect that the book will be of interest to scientists working on parallel computing, doctoral students, teachers, engineers and mathematicians dealing with numerical applications and computer simulations of natural phenomena.

Autoren/Hrsg.

Trobec, Roman

Vajteršic, Marián

Zinterhof, Peter

Inhaltsverzeichnis

1;Preface;6
2;List of Contributors;8
3;Contents;11
4;About the Editors;20
5;Chapter 1 Overview – Parallel Computing: Numerics, Applications, and Trends;22
5.1;1.1 Introduction;22
5.2;1.2 Book Chapters;34
5.3;1.3 Conclusions;53
5.4;References;57
6;Chapter 2 Introduction to Parallel Computation;64
6.1;2.1 Introduction;65
6.2;2.2 Parallel Versus Sequential Computation;66
6.3;2.3 Parallel Computational Models;67
6.4;2.4 Parallel Algorithm Design Methods;73
6.5;2.5 Theoretical Underpinnings;76
6.6;2.6 Parallel Algorithms for Conventional Computations;81
6.7;2.7 Parallel Algorithms for Unconventional Computations;87
6.8;2.8 Non-Universality in Computation;98
6.9;2.9 Conclusion;100
6.10;References;101
7;Chapter 3 Tools for Parallel and Distributed Computing;102
7.1;3.1 Introduction;103
7.2;3.2 Related Work;104
7.3;3.4 SCALEA;109
7.4;3.5 ZENTURIO;112
7.5;3.6 AKSUM;114
7.6;3.7 Grid-Prophet;119
7.7;3.8 Experiments;124
7.8;3.9 Conclusions;132
7.9;References;132
8;Chapter 4 Grid Computing;137
8.1;4.1 Introduction;137
8.2;4.2 Challenges in Grid Computing;143
8.3;4.3 Tools and Applications;149
8.4;4.4 Conclusions and Future Trends;159
8.5;References;160
9;Chapter 5 Parallel Structured Adaptive Mesh Refinement;166
9.1;5.1 Introduction;167
9.2;5.2 An Introduction to SAMR;169
9.3;5.3 Details of SAMR;174
9.4;5.4 Computer Science Aspects of SAMR;177
9.5;5.5 Some Results;183
9.6;5.6 Conclusions and FutureWork;188
9.7;References;189
10;Chapter 6 Applications and Parallel Implementation of QMC Integration;193
10.1;6.1 Introduction;194
10.2;6.2 Monte Carlo and Quasi Monte Carlo Methods in Numerical Integration Over [0,1)s;195
10.3;6.3 QMC Methods for Integrals over Rs with aWeight Function;200
10.4;6.4 QMC Integration on Parallel Systems;206
10.5;6.5 Numerical Experiments;209
10.6;6.6 Application of the Diaphony in Parallel Computation;226
10.7;6.7 Conclusion;229
10.8;References;231
11;Chapter 7 Parallel Evolutionary Computation Framework for Single- and Multiobjective Optimization;234
11.1;7.1 Introduction;235
11.2;7.2 Optimization Problems;236
11.3;7.3 Evolutionary Algorithms;239
11.4;7.4 Parallel Single- and Multiobjective Evolutionary Algorithms;241
11.5;7.5 Casting Process Optimization Task;246
11.6;7.6 Parallel Evolutionary Computation Framework;247
11.7;7.7 Empirical Evaluation;250
11.8;7.8 Conclusion;256
11.9;References;257
12;Chapter 8 WaLBerla: Exploiting Massively Parallel Systems for Lattice Boltzmann Simulations;258
12.1;8.1 Motivation;259
12.2;8.2 Introduction to the Lattice Boltzmann Method;260
12.3;8.3 Domain Partitioning Using Patches;262
12.4;8.4 Communication Concept;264
12.5;8.5 Performance Studies;266
12.6;8.6 Conclusion;275
12.7;References;276
13;Chapter 9 Parallel Pseudo-Spectral Methods for the Time-Dependent Schrödinger Equation;278
13.1;9.1 Introduction;278
13.2;9.2 Time Stepping and Split Operator Technique;281
13.3;9.3 Variable Transformations and Spectral Bases;282
13.4;9.4 Parallelizing Many Dimensional FFTs;284
13.5;9.5 Creating a Framework for Combining Discretization Methods;288
13.6;9.6 A Numerical Example;292
13.7;9.7 Conclusion;295
13.8;References;295
14;Chapter 10 Parallel Approaches in Molecular Dynamics Simulations;297
14.1;10.1 Split Integration Symplectic Method;298
14.2;10.2 Parallel Computers;306
14.3;10.3 Parallel Molecular Dynamics Computer Simulations;310
14.4;10.4 Parallelization of SISM;315
14.5;10.5 Conclusions;317
14.6;References;318
15;Chapter 11 Parallel Computer Simulations of Heat Transfer in Biological Tissues;322
15.1;11.1 Introduction;323
15.2;11.2 Principal Steps in Computer Simulation;326
15.3;11.3 Numerical Solution of Partial Differential Equations;329
15.4;11.4 Diffusion Equation;336
15.5;11.5 Bio-Heat Equation;345
15.6;11.6 Geometric Modeling of a Knee;348
15.7;11.7 Simulation Methods and Parameters;351
15.8;11.8 Variation of Simulation Parameters;353
15.9;11.9 Simulation Results;355
15.10;11.10 Validation of Results;360
15.11;11.11 Parallel Implementation;362
15.12;11.12 Conclusions;369
15.13;References;371
16;Chapter 12 Parallel SVD Computing in the Latent Semantic Indexing Applications for Data Retrieval;374
16.1;12.1 Introduction;374
16.2;12.2 Two Updating Problems in LSI;376
16.3;12.3 Two Downdating Problems in LSI;378
16.4;12.4 Kogbetliantz Method for Triangular Matrices;381
16.5;12.5 Parallel Two-sided Block-Jacobi SVD Algorithm with Dynamic Ordering;392
16.6;12.6 LSI Implemented on a Grid;398
16.7;12.7 LSI Implemented on a Distributed System;403
16.8;12.8 Conclusions;409
16.9;References;410
17;Chapter 13 Short-Vector SIMD Parallelization in Signal Processing;411
17.1;13.1 Introduction;411
17.2;13.2 General Vectorization Approaches;415
17.3;13.3 Convolution Type Algorithms;418
17.4;13.4 Recursive Algorithms;433
17.5;13.5 Block Algorithms;437
17.6;13.6 Mixed Algorithms;442
17.7;13.7 Conclusion;445
17.8;References;446
18;Chapter 14 Financial Applications: Parallel Portfolio Optimization;448
18.1;14.1 Introduction;449
18.2;14.2 Asset and Liability Management by Stochastic Programming;450
18.3;14.3 Parallel Solution Approaches: Decomposition;459
18.4;14.4 Parallel Solution Approaches: Interior Point Based Algorithms;461
18.5;14.5 Parallel Solution Approaches: Heuristics and Evolutionary Algorithms;471
18.6;14.6 Other Approaches;471
18.7;14.7 Detailed Comparison of Parallel Interior Point Approaches;472
18.8;14.8 Conclusions;478
18.9;References;479
19;Chapter 15 The Future of Parallel Computation;483
19.1;15.1 Introduction;484
19.2;15.2 Quantum Computing;487
19.3;15.3 Parallelism in Quantum Computing;497
19.4;15.4 Examples;500
19.5;15.5 Looking Ahead;519
19.6;References;520
20;Index;523