Hardware Implementation of Cellular Automata on Systolic Array

Abstract

Cellular Automata is one of the ways of performing computations which necessitates extremely the processing of data at high speeds. Implementing cellular automata on serial bases does not provide the required speed. Conventional processors can't process this enormous amount of data in a short period of time, so a new approach is required to improve computational complexity. Systolic array is a kind of parallel processing approaches which can increase the processing speed. Because processors of systolic set can work simultaneously and have its own local memory, they can improve the processing speed by limiting the number of external memory access in order to execute each of their instructions. This article studies implementing cellular automata on systolic arrays. To do so, once implementing is done by serial base, the other is done by using systolic arrays. The speed of the two methods has been compared with each other, too.