In this paper, we consider the use of residue arithmetic to increase the accuracy and reduce the dynamic range requirements of optical matrix-vector processors. We show that matrix-vector operations and iterative algorithms can be performed totally in residue notation. We suggest an architecture using a frequency-multiplexed optical systolic array feedback processor. As our case study, we consider the solution of three simultaneous equations.
© 1983 Optical Society of America
James Jackson and David Casasent, "Optical systolic array processor using residue arithmetic," Appl. Opt. 22, 2817-2821 (1983)