Abstract

Algorithms and architectures are described for optical matrix–matrix and matrix–vector processing. Implementations are based on quadratic residue number system coding which has the remarkable property that computations in the real and imaginary channels are performed in parallel without any interactions. This approach significantly reduces the complexity of implementation. Residue-based processing provides increased dynamic range and a reduced number of computations with high speed and parallelism of the optics fully utilized. Several architectures of optical processors described in this paper include systolic and data flow arrays.

© 1989 Optical Society of America

Optical systolic array processor using residue arithmetic

James Jackson and David Casasent
Appl. Opt. 22(18) 2817-2821 (1983)

Fast Fourier transforms with factored residue look-up tables

Akis P. Goutzoulis
Appl. Opt. 28(19) 4167-4175 (1989)

Frequency-multiplexed and pipelined iterative optical systolic array processors

David Casasent, James Jackson, and Charles Neuman
Appl. Opt. 22(1) 115-124 (1983)

Optical computing using optical flip-flops in Fourier processors: use in matrix multiplication and discrete linear transforms

Shigeru Ando, Seishi Sekine, Motohito Mita, and Satoshi Katsuo
Appl. Opt. 28(24) 5363-5373 (1989)

Residue arithmetic processing utilizing optical Fredkin gate arrays

Mir M. Mirsalehi, Joseph Shamir, and H. John Caulfield
Appl. Opt. 26(18) 3940-3946 (1987)