Advanced Computer Architectures

Despite the tremendous advances in performance enabled by modern architectures, there are always new applications and demands arising that require ever-increasing capabilities. Keeping up with these demands requires a deep-seated understanding of contemporary architectures in concert with a fundamental understanding of basic principles that allows one to anticipate what will be possible over the system's lifetime. Advanced Computer Architectures focuses on the design of high performance supercomputers with balanced coverage of the hardware, software structures, and application characteristics.This book is a timeless distillation of underlying principles punctuated by real-world implementations in popular current and past commercially available systems. It briefly reviews the basics of uniprocessor architecture before outlining the most popular processing paradigms, performance evaluation, and cost factor considerations. This builds to a discussion of pipeline design and vector processors, data parallel architectures, and multiprocessor systems. Rounding out the book, the final chapter explores some important current and emerging trends such as Dataflow, Grid, biology-inspired, and optical computing. More than 220 figures, tables, and equations illustrate the concepts presented.Based on the author's more than thirty years of teaching and research, Advanced Computer Architectures endows you with the tools necessary to reach the limits of existing technology, and ultimately, to break them.

Introduction

1

(14)

I.1 Computing Paradigms

2

(4)

I.2 The Need for Advanced Architectures

6

(7)

I.2.1 Hardware

7

(2)

I.2.2 Software

9

(1)

I.2.3 Systems

10

(3)

I.3 Book Overview

13

(1)

References

14

(1)

1 Uniprocessor Architecture Overview

15

(34)

1.1 Uniprocessor Model

15

(3)

1.2 Enhancements to the Uniprocessor Model

18

(11)

1.2.1 Arithmetic Logic Unit

19

(1)

1.2.2 Memory

20

(3)

1.2.3 Control Unit

23

(3)

1.2.4 I/O Subsystem

26

(1)

1.2.5 Interconnection Structures

27

(1)

1.2.6 System Considerations

28

(1)

1.3 Example Systems

29

(16)

1.3.1 Intel Corporation's Itanium

29

(9)

1.3.2 MIPS Computer System's R10000

38

(7)

1.4 Summary

45

(1)

Problems

45

(2)

References

47

(2)

2 Models and Terminology

49

(24)

2.1 Effect of Application on the Architecture

49

(1)

2.2 Application Characteristics

50

(2)

2.3 Processing Paradigms

52

(3)

2.4 Flynn's Taxonomy

55

(8)

2.4.1 Single Instruction Stream, Multiple Data Stream

59

(1)

2.4.2 Multiple Instruction Stream, Multiple Data Stream

60

(3)

2.5 Computer Networks

63

(1)

2.6 Performance Evaluation

64

(4)

2.6.1 Benchmarks

65

(3)

2.7 Cost Factor

68

(2)

2.8 Summary

70

(1)

Problems

70

(1)

References

71

(2)

3 Pipelining

73

(50)

3.1 Pipeline Model

73

(12)

3.1.1 Pipeline Types

77

(8)

3.2 Pipeline Control and Performance

85

(11)

3.2.1 Collision Vectors

88

(2)

3.2.2 Control

90

(1)

3.2.3 Performance

91

(3)

3.2.4 Multifunction Pipelines

94

(2)

3.3 Other Pipeline Problems

96

(11)

3.3.1 Data Interlocks

96

(6)

3.3.2 Conditional Branches

102

(4)

3.3.3 Multiple Instruction Buffers

106

(1)

3.3.4 Interrupts

107

(1)

3.4 Dynamic Pipelines

107

(7)

3.4.1 Instruction Deferral

108

(5)

3.4.2 Performance Evaluation

113

(1)

3.5 Example Systems

114

(5)

3.5.1 Control Data Corporation STAR-100

114

(1)

3.5.2 Control Data Corporation 6600

115

(2)

3.5.3 Sun Microsystem's Niagara Microprocessor

117

(2)

3.6 Summary

119

(1)

Problems

119

(3)

References

122

(1)

4 Vector Processors

123

(44)

4.1 Vector Processor Models

124

(4)

4.2 Memory Design Considerations

128

(5)

4.3 Architecture of the Cray Series

133

(11)

4.3.1 Memory

133

(1)

4.3.2 Processor Interconnection

134

(1)

4.3.3 Central Processor

134

(9)

4.3.4 I/O System

143

(1)

4.3.5 Other Systems in the Series

144

(1)

4.4 Performance Evaluation

144

(3)

4.5 Programming Vector Processors

147

(5)

4.6 Example Systems

152

(10)

4.6.1 Hitachi Super Technical Server

152

(5)

4.6.2 NEC SX Series

157

(3)

4.6.3 Cray X1

160

(2)

4.7 Summary

162

(1)

Problems

163

(2)

References

165

(2)

5 Array Processors

167

(54)

5.1 SIMD Organization

167

(8)

5.1.1 Memory

169

(1)

5.1.2 Control Processor

169

(1)

5.1.3 Arithmetic/Logic Processors

170

(1)

5.1.4 Interconnection Network

170

(2)

5.1.5 Registers, Instruction Set, Performance Considerations

172

(3)

5.2 Data Storage Techniques and Memory Organization

175

(7)

5.3 Interconnection Networks

182

(17)

5.3.1 Terminology and Performance Measures

182

(3)

5.3.2 Routing Protocols

185

(2)

5.3.3 Static Topologies

187

(5)

5.3.4 Dynamic Topologies

192

(7)

5.4 Performance Evaluation and Scalability

199

(5)

5.5 Programming SIMDs

204

(1)

5.6 Example Systems

204

(13)

5.6.1 ILLIAC-IV

205

(2)

5.6.2 Thinking Machine Corporation's CM-2

207

(10)

5.7 Summary

217

(1)

Problems

218

(2)

References

220

(1)

6 Multiprocessor Systems

221

(62)

6.1 MIMD Organization

224

(3)

6.1.1 Shared-Memory Architecture

224

(2)

6.1.2 Message-Passing Architecture

226

(1)

6.1.3 Other Models

226

(1)

6.2 Memory Organization

227

(6)

6.2.1 Cache Coherence

229

(4)

6.3 Interconnection Networks

233

(9)

6.3.1 Bus Network

235

(2)

6.3.2 Loop or Ring

237

(1)

6.3.3 Mesh Network

237

(1)

6.3.4 Hypercube Network

238

(1)

6.3.5 Crossbar Network

238

(1)

6.3.6 Multistage Networks

238

(4)

6.4 Operating System Considerations

242

(13)

6.4.1 Synchronization Mechanisms

246

(6)

6.4.2 Heavy- and Light-Weight Processes

252

(2)

6.4.3 Scheduling

254

(1)

6.5 Programming

255

(5)

6.5.1 Fork and Join

257

(2)

6.5.2 Parbegin/Parend

259

(1)

6.5.3 DOALL

259

(1)

6.5.4 Shared Variables

260

(1)

6.5.5 Send/Receive

260

(1)

6.6 Performance Evaluation and Scalability

260

(8)

6.6.1 Scalability

262

(1)

6.6.2 Performance Models

263

(5)

6.7 Example Systems

268

(8)

6.7.1 Thinking Machine Corporation's CM-5

268

(2)

6.7.2 Cray Research Corporation's T3D

270

(4)

6.7.3 IBM System X

274

(2)

6.8 Summary

276

(1)

Problems

277

(3)

References

280

(3)

7 Current Directions

283

(48)

7.1 Dataflow Architectures

284

(15)

7.1.1 Dataflow Models

285

(5)

7.1.2 Dataflow Graphs

290

(2)

7.1.3 Dataflow Languages

292

(2)

7.1.4 Example Dataflow Systems

294

(5)

7.2 GRID Computing

299

(6)

7.2.1 Open Grid Services Architecture

302

(3)

7.3 Biology Inspired Computing

305

(17)

7.3.1 Neural Networks

305

(12)

7.3.2 DNA Computing

317

(3)

7.3.3 Artificial Immune Systems

320

(2)

7.4 Optical Computing

322

(5)

References

327

(4)

Index

331

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

Advanced Computer Architectures

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

Advanced Computer Architectures

Summary

Table of Contents

Supplemental Materials

Digital License