+353-1-416-8900REST OF WORLD
1-800-526-8630U.S. (TOLL FREE)

Large–Scale Computing Techniques for Complex System Simulations. Wiley Series on Parallel and Distributed Computing

  • ID: 2175030
  • Book
  • December 2011
  • 220 Pages
  • John Wiley and Sons Ltd
1 of 4
Discover the Latest Computing Technology Needed to Design State–of–the–Art complex system simulations

Complex system simulations increasingly support informed decision–making in such fields as finance, economics, biology, astronomy, and many more. With this book as their guide, readers can master large–scale computing technologies and then use them to develop complex system simulations. Large–Scale Computing Techniques for Complex System Simulations not only presents the current state of the technology, it also points to new directions for research in the field as well as emerging applications.

This text examines a remarkably wide range of computing technologies and applications. Its presentation of computing technologies emphasizes distributed computing approaches, but also considers supercomputing and other novel technologies. On the applications side, the book discusses modeling and simulation of both natural and man–made complex systems. Specifically, the book presents such critical topics as:

  • e–Infrastructure ecosystems

  • Accelerated many–core GPU computing on three continents

  • SimWorld agent–based grid experimentation systems

  • Collaborative distributed multi–scale applications

  • Large–scale data intensive computing

  • QosCosGrid e–science infrastructure

Throughout the text, readers will find state–of–the–art software technologies alongside best practices, tools, and middleware services to help them perform advanced complex system research using simulations. Moreover, the authors have included numerous examples of actual applications and their performance results to help readers design and perform their own simulations.

Bridging the gap between computer technology and complex system simulation, Large–Scale Computing Techniques for Complex System Simulations serves as a design blueprint, user guide, and research agenda for all researchers, practitioners, scientists, and students interested in developing simulations that can accurately reflect and predict complex systems.

Note: Product cover images may vary from those shown
2 of 4
Foreword xi

Preface xv

Contributors xix

1. State–of–the–Art Technologies for Large–Scale Computing 1Florian Feldhaus, Stefan Freitag, and Chaker El Amrani

1.1 Introduction 1

1.2 Grid Computing 2

1.3 Virtualization 6

1.4 Cloud Computing 8

1.5 Grid and Cloud: Two Complementary Technologies 12

1.6 Modeling and Simulation of Grid and Cloud Computing 13

1.7 Summary and Outlook 15

References 16

2. The e–Infrastructure Ecosystems: Providing Local Support to Global Science 19
Erwin Laure and Åke Edlund

2.1 The Worldwide e–Infrastructure Landscape 19

2.2 BalticGrid: A Regional e–Infrastructure, Leveraging on the Global Mothership EGEE 21

2.3 The EGEE Infrastructure 25

2.4 Industry and e–Infrastructures: The Baltic Example 29

2.5 The Future of European e–Infrastructures: The European Grid Initiative (EGI) and the Partnership for Advanced Computing in Europe (PRACE) Infrastructures 31

2.6 Summary 33

Acknowledgments 34

References 34

3. Accelerated Many–Core GPU Computing for Physics and Astrophysics on Three Continents 35
Rainer Spurzem, Peter Berczik, Ingo Berentzen, Wei Ge, Xiaowei Wang, Hsi–Yu Schive, Keigo Nitadori, Tsuyoshi Hamada, and José Fiestas

3.1 Introduction 36

3.2 Astrophysical Application for Star Clusters and Galactic Nuclei 38

3.3 Hardware 40

3.4 Software 41

3.5 Results of Benchmarks 42

3.6 Adaptive Mesh Refinement Hydrosimulations 49

3.7 Physical Multiscale Discrete Simulation at IPE 49

3.8 Discussion and Conclusions 53

Acknowledgments 54

References 54

4. An Overview of the SimWorld Agent–Based Grid Experimentation Systems 59
Matthew Scheutz and Jack J. Harris

4.1 Introduction 59

4.2 System Architecture 62

4.3 System Implementation 67

4.4 A SWAGES Case Study 71

4.5 Discussion 74

4.6 Conclusions 78

References 78

5. Repast HPC: A Platform for Large–Scale Agent–Based Modeling 81
Nicholson Collier and Michael North

5.1 Introduction 81

5.2 Agent Simulation 82

5.3 Motivation and Related Work 82

5.4 From Repast S to Repast HPC 90

5.5 Parallelism 92

5.6 Implementation 94

5.7 Example Application: Rumor Spreading 101

5.8 Summary and Future Work 107

References 107

6. Building and Running Collaborative Distributed Multiscale Applications 111
Katarzyna Rycerz and Marian Bubak

6.1 Introduction 111

6.2 Requirements of Multiscale Simulations 112

6.3 Available Technologies 116

6.4 An Environment Supporting the HLA Component Model 119

6.5 Case Study with the MUSE Application 124

6.6 Summary and Future Work 127

Acknowledgments 128

References 129

7. Large–Scale Data–Intensive Computing 131
Mark Parsons

7.1 Digital Data: Challenge and Opportunity 131

7.2 Data–Intensive Computers 132

7.3 Advanced Software Tools and Techniques 134

7.4 Conclusion 139

Acknowledgments 139

References 139

8. A Topolpgy–Aware Evolutionary Algorithm for Reverse–Engineering Gene Regulatory Networks 141
Martin Swain, Camille Coti, Johannes Mandel, and Werner Dubitzky

8.1 Introduction 141

8.2 Methodology 143

8.3 Results and Discussion 155

8.4 Conclusions 160

Acknowledgments 161

References 161

9. QosCosGrid e–Science Infrastructure for Large–Scale Complex System Simulations 163
Krzysztof Kurowski, Bartosz Bosak, Piotr Grabowski, Mariusz Mamonski, Tomasz Piontek, George Kampis, László Gulyás, Camille Coti, Thomas Herault, and Franck Cappello

9.1 Introduction 163

9.2 Distributed and Parallel Simulations 165

9.3 Programming and Execution Environments 168

9.4 QCG Middleware 174

9.5 Additional QCG Tools 179

9.6 QosCosGrid Science Gateways 180

9.7 Discussion and Related Work 182

References 184

Glossary 187

Index 195 

Note: Product cover images may vary from those shown
3 of 4
Werner Dubitzky, PhD, is Chair of Bioinformatics at the Biomedical Sciences Research Institute in the Faculty of Life and Health Sciences at the University of Ulster. His research investigates systems biology, knowledge management in biology, grid computing, and data mining.

Krzysztof Kurowski, PhD, leads the Applications Department at Poznan Supercomputing and Networking Center in Poland. His research is focused on the modeling of advanced applications, scheduling, and resource management in networked environments.

Bernhard Schott, Dipl. Phys., is the EU–Research Program Manager for Platform Computing GmbH.

Note: Product cover images may vary from those shown
4 of 4
Note: Product cover images may vary from those shown