Distributed Computer-Aided Engineering

Networking of personal computers and workstations is becoming commonplace in academic and industrial environments. A cluster of workstations provides engineers with a familiar, cost-effective environment for high performance computing. However, workstations often have no dedicated link and communicate slowly on a local area network (LAN), such as the Ethernet. Thus, to effectively harness the parallel processing or distributed computing capabilities of workstations, new algorithms need to be developed with a higher computation-to-communication ratio.Distributed Computer-Aided Engineering presents distributed algorithms for three fundamental areas: finite element analysis, design optimization, and visualization - providing a new direction in high performance structural engineering computing.

Chapter 1: Introduction

1

(4)

Chapter 2: Distributed Finite Element Analysis on a Network of Workstations

5

(40)

2.1 Introduction

5

(3)

2.2 FE Analysis and PCG Solution Method

8

(6)

2.2.1 Conjugate gradient methods

9

(2)

2.2.2 Element-by-element approach

11

(3)

2.3 Data Distribution for Distributed FE Analysis

14

(16)

2.3.1 Basic definitions

15

(4)

2.3.2 Data distribution

19

(9)

2.3.3 Data movement

28

(2)

2.4 Distributed PCG Algorithm

30

(13)

2.4.1 Concurrent vector operations

35

(2)

2.4.2 Concurrent matrix-vector product

37

(4)

2.4.3 Redundant computation to reduce communications

41

(1)

2.4.4 Coarsening the task-granularity

42

(1)

2.4.5 Memory requirement

43

(1)

2.5 Final Comments

43

(2)

Chapter 3: Implementation of Distributed Algorithms for Finite Element Analysis on a Network of Workstations

45

(42)

3.1 Introduction

45

(2)

3.2 Object-Oriented Data Structures

47

(10)

3.2.1 Modeling the hierarchy of elements

48

(3)

3.2.2 Knowledge base of connectivities

51

(1)

3.2.3 Creating a list of adjacent nodes of a node

52

(3)

3.2.4 List of adjacent elements of an element

55

(1)

3.2.5 Domain decomposition

56

(1)

3.3 Graphic Visualization Using Hidden Line Removal

57

(3)

3.3.1 Hidden line removal

59

(1)

3.4 Examples and Results

60

(19)

3.4.1 Example 1: Plane stress problem

63

(9)

3.4.2 Example 2: 100-story high rise building structure

72

(1)

3.4.3 Example 3: Taj Mahal structure

72

(7)

3.5 Comments on Performance

79

(8)

Chapter 4: Distributed Genetic Algorithms for Design Optimization

87

(28)

4.1 Introduction

87

(2)

4.2 GA-based Structural Optimization

89

(6)

4.2.1 Objective function evaluation

94

(1)

4.2.2 Genetic search procedure

95

(1)

4.3 Distributed Genetic Algorithm

95

(11)

4.3.1 Dynamic load balancing

97

(9)

4.3.2 Quality of search

106

(1)

4.4 Communication Cost and Performance Estimates

106

(7)

4.4.1 Granularity

107

(2)

4.4.2 Speedup

109

(3)

4.4.3 Augmented Lagrangian GA

112

(1)

4.5 Final Comments

113

(2)

Chapter 5: Distributed Genetic Algorithms on a Cluster of Workstations

115

(32)

5.1 Introduction

115

(1)

5.2 PVM System

116

(2)

5.3 Implementation Model

118

(2)

5.4 Example Structures

120

(14)

5.4.1 Example 1: 17-member truss

123

(3)

5.4.2 Example 2: Geodesic space dome truss

126

(1)

5.4.3 Example 3: 50-story space structure

126

(8)

5.4.4 Example 4: 35-story tower space structure

134

(1)

5.5 Performance Studies

134

(11)

5.5.1 Speedup

135

(4)

5.5.2 Processor-farming model

139

(5)

5.5.3 Observations regarding the PCG solver

144

(1)

5.6 Final Comments

145

(2)

Chapter 6: Concurrent Structural Optimization on a Massively Parallel Supercomputer

147

(36)

6.1 Introduction

147

(2)

6.2 GA-Based Structural Optimization

149

(1)

6.3 CM-5 Architecture and Computing Models

150

(8)

6.3.1 CM-5 architecture

150

(2)

6.3.2 Programming models

152

(4)

6.3.3 Execution models

156

(2)

6.4 Coarse-Grained Concurrent Genetic Algorithm

158

(5)

6.4.1 Virtual channels

159

(1)

6.4.2 Number of processors versus the size of population

160

(1)

6.4.3 Parallel I/O

161

(2)

6.5 Fine-Grained Data Parallel Fitness Function Evaluation

163

(5)

6.5.1 Scatter and gather operations

167

(1)

6.6 Examples and Results

168

(7)

6.6.1 Example 1: 50-story space structure

168

(1)

6.6.2 Example 2: 35-story tower space structure

169

(3)

6.6.3 Example 3: 147-story tower space structure

172

(3)

6.7 Performance Results

175

(8)

6.7.1 Overall processing time

175

(1)

6.7.2 Scalability

176

(3)

6.7.3 Iterative PCG solver

179

(4)

Chapter 7: Concurrent Animation of Seismic Response of Large Structures in a Heterogeneous Computing Environment

183

(18)

7.1 Introduction

183

(2)

7.2 Dynamic Analysis of Structures

185

(2)

7.3 Subspace Iteration Method for Eigenvalue Extraction

187

(9)

7.4 Graphic Animation in a Heterogeneous Environment

188

(8)

7.4.1 Event-driven X Window interface

194

(1)

7.4.2 Parallel Virtual Machine (PVM)

194

(1)

7.4.3 Effective communication strategy

195

(1)

7.5 Example

196

(1)

7.6 Final Comments

197

(4)

Chapter 8: New Directions and Final Thoughts

201

(12)

8.1 Introduction

201

(1)

8.2 Direct Versus Iterative Solvers

202

(1)

8.3 Hybrid Preconditioner for Large-Scale Problems

203

(2)

8.4 Operating Systems War: Unix versus Windows NT

205

(3)

8.5 VRML: 3D Visualization on the Internet

208

(3)

8.6 Network Infrastructure for Distributed Computing

211

(1)

8.7 Final Comments

212

(1)

References

213

(14)

Author Index

227

(6)

Subject Index

233

What is included with this book?

The New copy of this book will include any supplemental materials advertised. Please check the title of the book to determine if it should include any access cards, study guides, lab manuals, CDs, etc.

The Used, Rental and eBook copies of this book are not guaranteed to include any supplemental materials. Typically, only the book itself is included. This is true even if the title states it includes any access cards, study guides, lab manuals, CDs, etc.

FREE SHIPPING

Rent More, Save More! Use code: BBRENTAL

5% off 1 book, 7% off 2 books, 10% off 3+ books

Distributed Computer-Aided Engineering

Summary

Table of Contents

Supplemental Materials

FREE SHIPPING

Rent More, Save More! Use code: BBRENTAL

5% off 1 book, 7% off 2 books, 10% off 3+ books

Distributed Computer-Aided Engineering

Summary

Table of Contents

Supplemental Materials

Digital License