Expand this Topic clickable element to expand a topic
Skip to content
Optica Publishing Group

Asynchronous Integrated Optical Multiply Accumulate Unit

Not Accessible

Your library or personal account may give you access

Abstract

Current bulk acousto-optic processors calculate products very rapidly yet they suffer the following limitations: 1) the data is clocked into the processor thereby limiting the ultimate speed of the processor to that of the clock, 2) the processor is limited to matrix calculations, 3) an extremely stable, large platform is needed for the apparatus, and 4) a long time is needed to convert the mixed binary output to useable (at least to the rest of the computer world) pure binary.

© 1985 Optical Society of America

PDF Article
More Like This
Space Integrating Acousto-Optic Matrix-Matrix Multipliers

K. H. Wagner and R. T. Weverka
TuD5 Optical Computing (IP) 1985

Global Communication, Accuracy and Optical Threshold Device Tolerances in Digital Optical Matrix Multipliers

Kelvin Wagner, Robert T. Weverka, and Demetri Psaltis
MA5 Optical Bistability (OBI) 1985

Programmable Real-Time Incoherent Matrix Multiplier for Optical Processing

J. Grinberg, B. H. Soffer, Y. Owechko, and E. Marom
TuD2 Optical Computing (IP) 1985

Select as filters


Select Topics Cancel
© Copyright 2024 | Optica Publishing Group. All rights reserved, including rights for text and data mining and training of artificial technologies or similar technologies.