Introduction

Abstract

During the past decades microprocessor performance has improved dramatically in comparison to the performance of larger parallel systems. From a hardware point of view, this trend has made parallel systems increasingly attractive since high performance computers can be built by combining large numbers of microprocessors that have been bought at commodity prices. This design details vary greatly from one computer to another, but most recent computers adopt the MIMD (Multiple Instruction streams Multiple Data streams) model in which each processor may perform different computations on different data. Some computers use a shared address space for memory; others require that processors communicate via explicit message sending and receiving. It is even possible to use a network of workstations as a parallel computer system since they are often available. All of these designs are intended for medium-grain or coarse-grain computations in which processors execute a substantial number of instructions between communications or other interactions with other processors. If the computation grain becomes too small, performance may suffer.