Applied parallel computing

Select an Action

Place Hold(s)
Add to My Lists
Email
Print

Title:

Personal Author:

Deng, Yuefan

Publication Information:

Singapore ; Hackensack, NJ : World Scientific, 2013

Physical Description:

x, 207 p. : ill. ; 24 cm.

ISBN:

9789814307604

Subject Term:

Parallel processing (Electronic computers)

High performance computing

Available:*

Library	Item Barcode	Call Number	Material Type	Item Category 1	Status
Searching... PSZ JB	30000010306300	QA76.58 D46 2013	Open Access Book	Book	Searching... Unknown

The book provides a practical guide to computational scientists and engineers to help advance their research by exploiting the superpower of supercomputers with many processors and complex networks. This book focuses on the design and analysis of basic parallel algorithms, the key components for composing larger packages for a wide range of applications.

Preface	p. v
Chapter 1 Introduction	p. 1
1.1 Definition of Parallel Computing	p. 1
1.2 Evolution of Computers	p. 4
1.3 An Enabling Technology	p. 8
1.4 Cost Effectiveness	p. 9
Chapter 2 Performance Metrics and Models	p. 13
2.1 Parallel Activity Trace	p. 13
2.2 Speedup	p. 14
2.3 Parallel Efficiency	p. 15
2.4 Load Imbalance	p. 15
2.5 Granularity	p. 16
2.6 Overhead	p. 17
2.7 Scalability	p. 18
2.8 Amdahl's Law	p. 18
Chapter 3 Hardware Systems	p. 19
3.1 Node Architectures	p. 19
3.2 Network Interconnections	p. 21
3.3 Instruction and Data Streams	p. 28
3.4 Processor-Memory Connectivity	p. 29
3.5 IO Subsystems	p. 29
3.6 System Convergence	p. 31
3.7 Design Considerations	p. 31
Chapter 4 Software Systems	p. 35
4.1 Node Software	p. 35
4.2 Programming Models	p. 37
4.3 Parallel Debuggers	p. 43
4.4 Parallel Profilers	p. 43
Chapter 5 Design of Algorithms	p. 45
5.1 Algorithm Models	p. 46
5.2 Examples of Collective Operations	p. 54
5.3 Mapping Tasks to Processors	p. 56
Chapter 6 Linear Algebra	p. 65
6.1 Problem Decomposition	p. 65
6.2 Matrix Operations	p. 68
6.3 Solution of Linear Systems	p. 81
Chapter 7 Differential Equations	p. 89
7.1 Integration and Differentiation	p. 89
7.2 Partial Differential Equations	p. 92
Chapter 8 Fourier Transforms	p. 105
8.1 Fourier Transforms	p. 105
8.2 Discrete Fourier Transforms	p. 106
8.3 Fast Fourier Transforms	p. 107
8.4 Simple Parallelization	p. 111
8.5 The Transpose Method	p. 112
8.6 Complexity Analysis for FFT	p. 113
Chapter 9 Optimization	p. 115
9.1 Monte Carlo Methods	p. 116
9.2 Parallelization	p. 119
Chapter 10 Applications	p. 123
10.1 Newton's Equation and Molecular Dynamics	p. 124
10.2 Schrodinger's Equations and Quantum Mechanics	p. 133
10.3 Partition Function, DFT and Material Science	p. 134
10.4 Maxwell's Equations and Electrical Engineering	p. 135
10.5 Diffusion Equation and Mechanical Engineering	p. 135
10.6 Navier-Stokes Equation and CFD	p. 136
10.7 Other Applications	p. 136
Appendix A MPI	p. 139
A.1 An MPI Primer	p. 139
A.2 Examples of Using MPI	p. 159
A.3 MPI Tools	p. 161
A.4 Complete List of MPI Functions	p. 167
Appendix B OpenMP	p. 171
B.1 Introduction to OpenMP	p. 171
B.2 Memory Model of OpenMP	p. 172
B.3 OpenMP Directives	p. 172
B.4 Synchronization	p. 174
B.5 Runtime Library Routines	p. 175
B.6 Examples of Using OpenMP	p. 178
B.7 The Future	p. 180
Appendix C Projects	p. 181
Project C.1 Watts and Flops of Supercomputers	p. 181
Project C.2 Review of Supercomputers	p. 181
Project C.3 Top500 and BlueGene Supercomputers	p. 181
Project C.4 Say Hello in Order	p. 182
Project C.5 Broadcast on Torus	p. 183
Project C.6 Competing with MPI on Broadcast, Scatter, etc	p. 183
Project C.7 Simple Matrix Multiplication	p. 183
Project C.8 Matrix Multiplication on 4D Torus	p. 183
Project C.9 Matrix Multiplication and PAT	p. 184
Project C.10 Matrix Inversion	p. 184
Project C.11 Simple Analysis of an iBT Network	p. 185
Project C.12 Compute Eigenvalues of Adjacency Matrices of Networks	p. 185
Project C.13 Mapping Wave Equation to Torus	p. 185
Project C.14 Load Balance in 3D Mesh	p. 186
Project C.15 Wave Equation and PAT	p. 186
Project C.16 Computing Coulomb's Forces	p. 187
Project C.17 Timing Model for MD	p. 187
Project C.18 Minimizing Lennard-Jones Potential	p. 188
Project C.19 Install and Profile CP2K	p. 188
Project C.20 Install and Profile CPMD	p. 189
Project C.21 Install and Profile NAMD	p. 190
Project C.22 FFT on Beowulf	p. 190
Project C.23 FFT on BlueGene/Q	p. 191
Project C.24 Word Analysis	p. 191
Project C.25 Cost Estimate of a 0.1 Pflops System	p. 191
Project C.26 Design of a Pflops System	p. 191
Appendix D Program Examples	p. 193
D.1 Matrix-Vector Multiplication	p. 193
D.2 Long Range N-body Force	p. 195
D.3 Integration	p. 201
References	p. 203
Index	p. 205

Available:*

On Order

Summary

Summary

Table of Contents