Title :
Polymorphic-torus architecture for computer vision
Author :
Li, Hungwen ; Maresca, Massimo
Author_Institution :
IBM Res., San Jose, CA, USA
fDate :
3/1/1989 12:00:00 AM
Abstract :
A massively parallel fine-grained SIMD (single-instruction multi-data-stream) computer for machine vision computations is described. The architecture features a polymorphic-torus network which inserts an individually controllable switch into every node of the 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 solution time that is superior or equivalent to that of popular vision architectures such as mesh, tree, pyramid and hypercube for many vision algorithms discussed. Implementation of the architecture is given to illustrate its VLSI efficiency
Keywords :
VLSI; computer vision; parallel algorithms; parallel architectures; SIMD; VLSI efficiency; circuit switching; computer vision; dynamically reconfigurable network; hypercube; machine vision; mesh; parallel architectures; polymorphic-torus network; pyramid; tree; Circuits; Computer architecture; Computer networks; Computer vision; Concurrent computing; Machine vision; Network topology; Parallel architectures; Switches; Very large scale integration;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on