From Simd To Distributed Memory Mimd

his paper presents a technique that may be used to transform SIMD shared memory parallel s algorithms to MIMD distributed memory algorithms. This technique formulates a sequence of teps to help alter the the global view required of the programmer for SIMD processing to the - d more local one necessary for MIMD programming. Exercises based on this technique aid stu ents in understanding the fundamental differences between the two types of architectures. A 1. INTRODUCTION s much of the initial research in parallel computing has been done on Single Instruction Multiple Data (SIMD) r hardware, many textbooks focus on algorithms for this type of machine. Today many colleges are purchasing elatively inexpensive parallel hardware that has distributed memory and is Multiple Instruction Multiple Data t m (MIMD) in nature. Such systems commonly utilize INMOS transputers. This paper describes an approach tha ay be used to transform certain SIMD parallel algorithms to MIMD distributed memory alg..