1 Introduction
1-1 Transputer-based multiprocessors and parallel architectures
1-2 Flexibility and versatility
1-3 Hardware and software support
1-4 Why use C?
1-5 Chapter organization
2 The transputer
2-1 A processor with memory and I/O ports
2-2 The Processor
2-3 Memory access
2-4 The serial I/O ports
2-5 Technical aspects of the CSA Educational Kit
2-6 Concluding remarks
3 Tutorial: a first program
3-1 The program
3-2 The compilation process
3-3 The linking process

This book describes a set of application and systems software research projects undertaken by the Caltech Concurrent Computation Program (CP) from 1983-1990. This parallel computing activity is organized so that applications with similar algorithmic and software challenges are grouped together. Thus, one can not only learn that parallel computing is effective on a broad range of problems but also why it works, what algorithms are needed, and what features the software should support.

MPI, the Message Passing Interface, is a standardized and portable message-passing system designed by a group of researchers from academia and industry to function on a wide variety of parallel computers. The standard defines the syntax and semantics of a core of library routines useful to a wide range of users writing portable message-passing programs in Fortran 77 or C. Several well-tested and efficient implementations of MPI already exist, including some that are free and in the public domain.

Table of Contents

1. Abstract
2. Overview
1. What is Parallel Computing?
2. Why Use Parallel Computing?
3. Concepts and Terminology
1. von Neumann Computer Architecture
2. Flynn's Classical Taxonomy
3. Some General Parallel Terminology
4. Parallel Computer Memory Architectures
1. Shared Memory
2. Distributed Memory
3. Hybrid Distributed-Shared Memory
5. Parallel Programming Models
1. Overview
2. Shared Memory Model
3. Threads Model
4. Message Passing Model

Welcome to  Designing and Building Parallel Programs ! My goal in this book is to provide a practitioner's guide for students, programmers, engineers, and scientists who wish to design and build efficient and cost-effective programs for parallel and distributed computer systems. I cover both the techniques used to design parallel programs and the tools used to implement these programs. I assume familiarity with sequential programming, but no prior exposure to parallel computing.