Polymorphic-Torus Architecture for Computer Vision

Abstract

This paper describes a new massively parallel fine-grained SIMD computer for machine vision computations. The architecture features a polymorphic-torus network which inserts an individually controllable switch into every node of a two-dimensional torus such that the network is dynamically reconfigurable to match the algorithm. Reconfiguration is accomplished by circuit switching and is achieved at fine-grained level. Using both the processor coordinate in the torus and the data for reconfiguration, the polymorphic-torus achieves superior or as good solution time than popular vision architectures such as mesh, tree, pyramid and hypercube for many vision algorithms discussed in this paper. Implementation of the architecture is given to illustrate its VLSI efficiency. © 1989 IEEE