Vector-matrix multiplication based on a ternary optical computer

Authors:
Xianchao Wang;Junjie Peng;Yi Jin;Mei Li;Zhangyi Shen;Shan Ouyang
Affiliations:
School of Computer Engineering and Science, Shanghai University, Shanghai, China;School of Computer Engineering and Science, Shanghai University, Shanghai, China;School of Computer Engineering and Science, Shanghai University, Shanghai, China;College of Computer Science and Engineering, Northwestern Polytechnical University, Xi’an, China;School of Computer Engineering and Science, Shanghai University, Shanghai, China;School of Computer Engineering and Science, Shanghai University, Shanghai, China
Venue:
HPCA'09 Proceedings of the Second international conference on High Performance Computing and Applications
Year:
2009

Citing 2
Cited 0

High-Speed VLSI Multiplication Algorithm with a Redundant Binary Addition Tree

IEEE Transactions on Computers
A New Method for Optical Vector-Matrix Multiplier

ICECT '09 Proceedings of the 2009 International Conference on Electronic Computer Technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper implements Optical Vector-Matrix Multiplication (OVMM) completely in parallel on a novel optical computing architecture, Ternary Optical Computer (TOC), by use of the Modified Signed-Digit (MSD) number system. For high efficiency, partial products (PPs) are generated in parallel and the vector inner products (VIPs) are produced by a binary-tree algorithm, and then the OVMM is implemented. The experimental result validates the feasibility and correctness of VMM on TOC. In this system, it is not necessary to gauge light intensities, but judge whether there is light during decoding.