Table of Contents

1 Introduction 2 Parallel Programs 3 Programming for Performance 4 Workload-Driven Evaluation 5 Shared Memory Multiprocessors 6 Snoop-based Multiprocessor Design 7 Scalable Multiprocessors8 Directory-based Cache Coherence9 Hardware-Software Tradeoffs 10 Interconnection Network Design 11 Latency Tolerance 12 Future Directions APPENDIX A Parallel Benchmark Suites

Promotional Information

* synthesizes a decade of research and development for practicing engineers, graduate students, and researchers in parallel computer architecture, system software, and applications development
* presents in-depth application case studies from computer graphics, computational science and engineering, and data mining to demonstrate sound quantitative evaluation of design trade-offs
* describes the process of programming for performance, including both the architecture-independent and architecture-dependent aspects, with examples and case-studies
* illustrates bus-based and network-based parallel systems with case studies of more than a dozen important commercial designs

About the Author

David Culler led the Berkeley Network of Workstations (NOW) project, which sparked the current commercial revolution in high-performance clusters. Anoop Gupta co-led the Stanford DASH multiprocessor project, which developed the shared-memory technology increasingly used in commercial machines. Jaswinder Pal Singh led the development of the SPLASH and SPLASH-2 suites of parallel programs, which have defined the workloads and methodology used to drive decisions and evaluate trade-offs in shared- memory parallel architecture.