Title :
Canonical variate analysis of large scale systems on a transputer array
Author :
Martin, Daniel P.
Author_Institution :
Comput. Eng., Inc., Woburn, MA, USA
Abstract :
The software development issues involved in two separate implementations of parallel singular value decomposition algorithms on transputer arrays are examined for application to identification and adaptive control of large-scale systems. The machine architecture was tailored to suit the Ocean parallel processing model. Experimental results are presented that indicate that linear speedup occurs when the size of the processor´s local data array size stays constant
Keywords :
adaptive control; identification; large-scale systems; parallel processing; statistical analysis; Ocean parallel processing model; adaptive control; canonical variate analysis; identification; large-scale systems; parallel singular value decomposition algorithms; software development issues; Adaptive arrays; Adaptive control; Application software; Computer architecture; Large-scale systems; Oceans; Parallel processing; Programming; Singular value decomposition; Software algorithms;
Conference_Titel :
Decision and Control, 1990., Proceedings of the 29th IEEE Conference on
Conference_Location :
Honolulu, HI
DOI :
10.1109/CDC.1990.203669
