VIP会员
内容简介
Kai Hwang, Zhiwei Xu: Scalable Parallel Computing: Technology, Architecture, Programming.Copyright ?1998 by The McGraw-Hill Companies, Inc. All rights reserved. Jointlypublished by China Machine Press/McGraw -Hill. This edition may be sold in the People Republic of China only. This book cannot be re-exported and is not for sale outside the People Republic of China.
目录
Table?ofContents about?the?Authors?IV Foreword?XV Preface?xvi Guide?to?Instructors/Readers?xix Part?I?Scalability?and?Clustering?1 Chapter?1?Scalable?Computer?Platforms?and?Models?3 1.1?Evolution?of?Computer?Architecture?5 1.?1.?1?Computer?Generations?5 1.?1.2?Scalable?Computer?Architectures?6 1.?1.3?Converging?System?Architectures?8 1.2?Dimensions?of?Scalability?9 1.2.1?Resource?Scalability?9 1.2.2?Application?Scalability?11 1.2.3?Technology?Scalability?12 1.3?Parallel?Computer?Models?13 1.3.1?Semantic?Attributes?14 1.3.2?Performance?Attributes?17 1.3.3?Abstract?Machine?Models?18 1.3.4?Physical?Machine?Models?26 1.4?Basic?Concepts?of?Clustering?30 1.4.1?Cluster?Characteristics?30 1.4.2?Architectural?Comparisons?31 1.4.3?Benefits?and?Difficulties?of?Clusters?32 1.5?Scalable?Design?Principles?37 1.5.1?Principle?of?Independence?37 1.5.2?Principle?of?Balanced?Design?39 1.5.3?Design?for?Scalability?44 1.6?Bibliographic?Notes?and?Problems?47 Chapter?2?Basics?of?Parallel?Programming?51 2.1?Parallel?Programming?Overview?51 2.?1.1?Why?Is?Parallel?Programming?Difficult52 2.1.2?Parallel?Programming?Environments?55 2.1.3?Parallel?Programming?Approaches?56 2.2?Processes,?Tasks,?and?Threads?59 2.2.1?Definitions?of?an?Abstract?Process?59 2.2.2?Execution?Mode?62 2.2.3?Address?Space?63 2.2.4?Process?Context?65 2.2.5?Process?Descriptor?66 2.2.6?Process?Control?67 2.2.7?Variations?of?Process?70 2.3?Parallelism?Issues?71 2.3.1?Homogeneity?in?Processes?72 2.3.2?Static?versus?Dynamic?Parallelism?74 2.3.3?Process?Grouping?75 2.3.4?Allocation?Issues?76 2.4?Interaction/Communication?Issues?77 2.4.1?Interaction?Operations?77 2.4.2?Interaction?Modes?80 2.4.3?Interaction?Patterns?82 2.4.4?Cooperative?versus?Competitive?Interactions?84 2.5?Semantic?Issues?in?Parallel?Programs?85 2.5.1?Program?Termination?85 2.5.2?Determinacy?of?Programs?86 2.6?Bibliographic?Notes?and?Problems?87 Chapter?3?Performance?Metrics?and?Benchmarks?91 3.1?System?and?Application?Benchmarks?91 3.?1.1?Micro?Benchmarks?92 3.1.2?Parallel?Computing?Benchmarks?96 3.1.3?Business?and?TPC?Benchmarks?98 3.1.4?SPEC?Benchmark?Family?100 3.2?Performance?versus?Cost?102 3.2.1?Execution?Time?and?Throughput?103 3.2.2?Utilization?and?Cost-Effectiveness?104 3.3?Basic?Performance?Metrics?108 3.3.1?Workload?and?Speed?Metrics?108 3.3.2?Caveats?in?Sequential?Performance?111 3.4?Performance?of?Parallel?Computers?113 3.4.1?Computaiional?Characteristics?113 3.4.2?Parallelism?and?Interaction?Overheads?115 3.4.3?Overhead?Quantification?118 3.5?Performance?of?Parallel?Programs?126 3.5.1?Performance?Metrics?126 3.5.2?Available?Parallelism?in?Benchmarks?131 3.6?Scalability?and?Speedup?Analysis?134 3.6.1?Amdahl’s?Law:?Fixed?Problem?Size?134 3.6.2?Gustafson’s?Law:?Fixed?Time?136 3.6.3?Sun?and?Ni’s?Law:?Memory?Bounding?139 3.6.4?Isoperformance?Models?144 3.7?Bibliographic?Notes?and?Problems?148 Part?