内容简介

本书由□017年图灵奖得主Patterson和Hennessy共同撰写，是计算机体系结构领域的经典教材，强调软硬件协同设计及其对性能的影响。本书采用MIPS体系结构, 在介绍并行、流水线、存储层次、抽象等基本原理的基础上，新增关于领域专用体系结构（DSA）的讨论，关注安全攻击、开放指令集、开源软硬件和再虚拟化等新趋势和新问题，并更新了所有实例和练习，特别是新增了Google TPU实例。本书适合作为高等院校计算机专业的教材，也适合广大专业技术人员参考。

目录

Preface xv
C H A P T E R S
1 Computer Abstractions and Technology □
1.1 Introduction 3
1.□ Seven Great Ideas in Computer Architecture 10
1.3 Below Your Program 13
1.4 Under the Covers 16
1.5 Technologies for Building Processors and Memory □4
1.6 Performance □8
1.7 Th e Power Wall 40
1.8 Th e Sea Change: Th e Switch from Uniprocessors to Multiprocessors 43
1.9 Real Stuff : Benchmarking the Intel Core i7 46
1.10 Going Faster: Matrix Multiply in Python 49
1.11 Fallacies and Pitfalls 50
1.1□ Concluding Remarks 53
1.13 Historical Perspective and Further Reading 55
1.14 Self-Study 55
1.15 Exercises 59
□ Instructions: Language of the Computer 66
□.1 Introduction 68
□.□ Operations of the Computer Hardware 69
□.3 Operands of the Computer Hardware 7□
□.4 Signed and Unsigned Numbers 79
□.5 Representing Instructions in the Computer 86
□.6 Logical Operations 93
□.7 Instructions for Making Decisions 96
□.8 Supporting Procedures in Computer Hardware 10□
□.9 Communicating with People 11□
□.10 MIPS Addressing for 3□-Bit Immediates and Addresses 118
□.11 Parallelism and Instructions: Synchronization 1□7
□.1□ Translating and Starting a Program 1□9
□.13 A C Sort Example to Put It All Together 138
□.14 Arrays versus Pointers 147
□.15 Advanced Material: Compiling C and Interpreting Java 151
□.16 Real Stuff : ARMv7 (3□-bit) Instructions 151
□.17 Real Stuff : ARMv8 (64-bit) Instructions 155
□.18 Real Stuff : RISC-V Instructions 156
□.19 Real Stuff : x86 Instructions 157
□.□0 Going Faster: Matrix Multiply in C 166
□.□1 Fallacies and Pitfalls 167
□.□□ Concluding Remarks 169
□.□3 Historical Perspective and Further Reading 17□
□.□4 Self Study 17□
□.□5 Exercises 175
3 Arithmetic for Computers 186
3.1 Introduction 188
3.□ Addition and Subtraction 188
3.3 Multiplication 193
3.4 Division 199
3.5 Floating Point □06
3.6 Parallelism and Computer Arithmetic: Subword Parallelism □3□
3.7 Real Stuff : Streaming SIMD Extensions and Advanced Vector Extensions in x86 □34
3.8 Going Faster: Subword Parallelism and Matrix Multiply □35
3.9 Fallacies and Pitfalls □37
3.10 Concluding Remarks □41
3.11 Historical Perspective and Further Reading □45
3.1□ Self Study □45
3.13 Exercises □48
4 The Processor □54
4.1 Introduction □56
4.□ Logic Design Conventions □60
4.3 Building a Datapath □63
4.4 A Simple Implementation Scheme □71
4.5 A Multicycle Implementation □84
4.6 An Overview of Pipelining □85
4.7 Pipelined Datapath and Control □98
4.8 Data Hazards: Forwarding versus Stalling 315
4.9 Control Hazards 3□8
4.10 Exceptions 337
4.11 Parallelism via Instructions 344
4.1□ Putting It All Together: Th e Intel Core i7 6700 and ARM Cortex-A53 358
4.13 Going Faster: Instruction-Level Parallelism and Matrix Multiply 366
4.14 Advanced Topic: An Introduction to Digital Design Using a
Hardware Design Language to Describe and Model a Pipeline and
More Pipelining Illustrations 368
4.15 Fallacies and Pitfalls 369
4.16 Concluding Remarks 370
4.17 Historical Perspective and Further Reading 371
4.18 Self-Study 371
4.19 Exercises 37□
5 Large and Fast: Exploiting Memory Hierarchy 390
5.1 Introduction 39□
5.□ Memory Technologies 396
5.3 Th e Basics of Caches 401
5.4 Measuring and Improving Cache Performance 416
5.5 Dependable Memory Hierarchy 436
5.6 Virtual Machines 44□
5.7 Virtual Memory 446
5.8 A Common Framework for Memory Hierarchy 47□
5.9 Using a Finite-State Machine to Control a Simple Cache 479
5.10 Parallelism and Memory Hierarchies: Cache Coherence 484
5.11 Parallelism and Memory Hierarchy: Redundant Arrays of Inexpensive Disks 488
5.1□ Advanced Material: Implementing Cache Controllers 488
5.13 Real Stuff : Th e ARM Cortex-A8 an......