Abstract

We consider the task of interconnecting processors to realize efficient parallel algorithms. We propose interconnecting processors using certain graphs called expander graphs, which can provide fast communication from any group of processors to the rest of the network. We show that these interconnections would result in a number of efficient parallel algorithms for sorting, routing, associative memory, and fault-tolerance networks. As the interconnections based on expander graphs are global and irregular, we reason that optical interconnections are preferred to electronic and propose implementation of these interconnections using the programmable optoelectronic multiprocessor architecture.

© 1991 Optical Society of America

Designing massively parallel optical computers: a case study

Aloke Guha and M. W. Derstine
Appl. Opt. 29(14) 2187-2200 (1990)

Scalable optical hypercube-based interconnection network for massively parallel computing

Ahmed Louri and Hongki Sung
Appl. Opt. 33(32) 7588-7598 (1994)

Optical binary de Bruijn networks for massively parallel computing: design methodology and feasibility study

Ahmed Louri and Hongki Sung
Appl. Opt. 34(29) 6714-6722 (1995)

Efficient parallel algorithms for optical computing with the discrete Fourier transform (DFT) primitive

John H. Reif and Akhilesh Tyagi
Appl. Opt. 36(29) 7327-7340 (1997)

Parallel depth buffer algorithm based on a ternary optical computer

Kai Song, Jinliang Zhu, Zhenxing Wang, and Liping Yan
Appl. Opt. 61(23) 6841-6852 (2022)