Computer Architectures For Spatially Distributed Data Volume 18

Computer Architectures for Spatially Distributed Data

These are the proceedings of a NATO Advanced Study Institute (ASI) held in Cetraro, Italy during 6-17 June 1983. The title of the ASI was Computer Arehiteetures for SpatiaZZy vistributed Vata, and it brouqht together some 60 participants from Europe and America. Presented ~ere are 21 of the lectures that were delivered. The articles cover a wide spectrum of topics related to computer architecture s specially oriented toward the fast processing of spatial data, and represent an excellent review of the state-of-the-art of this topic. For more than 20 years now researchers in pattern recognition, image processing, meteorology, remote sensing, and computer engineering have been looking toward new forms of computer architectures to speed the processing of data from two- and three-dimensional processes. The work can be said to have commenced with the landmark article by Steve Unger in 1958, and it received a strong forward push with the development of the ILIAC III and IV computers at the University of Illinois during the 1960's. One clear obstacle faced by the computer designers in those days was the limitation of the state-of-the-art of hardware, when the only switching devices available to them were discrete transistors. As aresult parallel processing was generally considered to be imprae tieal, and relatively little progress was made.

Computer Architectures for Spatially Distributed Data (Volume 18).

Superconducting Electronics

The genesis of the NATO Advanced Study Institute (ASI) upon which this volume is based, occurred during the summer of 1986 when we came to the realization that there had been significant progress during the early 1980's in the field of superconducting electronics and in applications of this technology. Despite this progress, there was a perception among many engineers and scientists that, with the possible exception of a limited number of esoteric fundamental studies and applications (e.g., the Josephson voltage standard or the SQUID magnetometer), there was no significant future for electronic systems incorporating superconducting elements. One of the major reasons for this perception was the aversion to handling liquid helium or including a closed-cycle helium liquefier. In addition, many critics felt that IBM's cancellation of its superconducting computer project in 1983 was "proof" that superconductors could not possibly compete with semiconductors in high-speed signal processing. From our perspective, the need for liquid helium was outweighed by improved performance, i. e., higher speed, lower noise, greater sensitivity and much lower power dissipation. For many commercial, medical, scientific and military applications, these attributes can lead to either enhanced capability (e.g., compact real-time signal processing) or measurements that cannot be made using any other technology (e.g., SQUID magnetometry to detect neuromagnetic activity).