Title :
Characterization of massively parallel smart pixels systems for the example of a binary associative memory
Author_Institution :
Lehrstuhl fur Rechnerarchitektur und -kommunikation, Friedrich-Schiller-Univ., Jena, Germany
Abstract :
In a theoretical study is shown that computing systems consisting of a huge number of small processing elements exploit better the potential of high dense optical interconnections than systems with large but few processors. This is demonstrated for the example of a binary associative memory that needs sparsely coded vectors to maximize the memory capacity. Furthermore this sparse coding reduces current problems concerning the power consumption in micro laser arrays. An estimation shows that both on GaAs based monolithically and on silicon based hybrid smart pixels solutions for such an associative memory offer short term reachable goals that are competitive with existing all electronic systems
Keywords :
content-addressable storage; laser arrays; optical interconnections; parallel architectures; smart pixels; GaAs based monolithically; associative memory; binary associative memory; electronic systems; high dense optical interconnections; massively parallel smart pixels systems; memory capacity; micro laser arrays; power consumption; short term reachable goals; silicon based hybrid smart pixels solutions; small processing elements; sparse coding; sparsely coded vectors; Associative memory; Biomedical optical imaging; Concurrent computing; High performance computing; Optical arrays; Optical computing; Optical interconnections; Parallel processing; Smart pixels; Stimulated emission;
Conference_Titel :
Massively Parallel Processing Using Optical Interconnections, 1995., Proceedings of the Second International Conference on
Conference_Location :
San Antonio, TX
Print_ISBN :
0-8186-7101-7
DOI :
10.1109/MPPOI.1995.528630