
This book offers state-of-the-art principles and techniques for designing and programming parallel, vector and scalable computer systems. Written by a leading expert in the field, the authoritative text covers: theory of parallelism - parallel computer models, program and network properties, performance laws and scalability analysis; advanced computer technology-RISC, CISC,Superscalar, VLIW and superpipelined processors, cache coherence, memory hierarchy, advanced pipelining and system interconnects; parallel and scalable architectures-multiprocessors, multicomputers, multivectors and SMD computers and scalable, multithreaded and dataflow architectures; software for parallel programming-parallel models, languages, compilers, message passing, program development, synchronization, parallel UNIX extensions and heterogeneous programming; illustrative examples and problems - over 100 examples with solutions 300 illustrations and 200 homework problems involving designs, proofs and analysis. Answers to selected problems are given. Solutions Manual available to instructors; case studies of real systems - Industrial computers from Cray, Intel, TMC Fujitsu, NEC, Hitachi, IBM, DEC, MasPar, Ncube, BBN, KSR, Stardent and experimental systems from Stanford, MIT, Caltech, Illinois, Wisconsin, USC and ETL in Japan
