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

Development of an Optoelectronic Parallel Data Sorter based on CMOS/InGaAs Smart Pixel Arrays

Not Accessible

Your library or personal account may give you access

Abstract

As part of the Scottish Collaborative Initiative in Optoelectronic Sciences (SCIOS) we have been developing an optoelectronic parallel data sorter as a technology demonstrator [1]. This system is based on 32 x 32 arrays of smart pixels produced by flip-chip solder bump assembly of InGaAs/GaAs MQW modulator/detectors with Si CMOS electronics. These devices are linked by an optical system which implements a perfect shuffle interconnection. The functionality of each of the processing nodes is selected by a combination of global electronic control signals and local optical control information which is circulated along with the data. The system aims at a clock frequency of 100 MHz which would give a sorting capacity of up to 1024 16 bit words in less than 20 µs. This corresponds to an I/O data rate of 200 Gbit/s for each of the chips in the system. The programme also includes the construction of a smaller 16-channel test system based on 4 x 4 smart pixel arrays. This paper present progress on the construction and initial tests of both these demonstrators.

© 1997 Optical Society of America

PDF Article
More Like This
Hybrid Technology for Optoelectronic Parallel Processing : Basic Considerations and Future Trends

M.P.Y. Desmulliez, P.W. Foulk, and B.S. Wherrett
OTuE.7 Optics in Computing (IP) 1997

GaAs Smart Pixel Arrays for High Performance Optoelectronic Computing Modules

D. S. McCallum, J. W. Kim, P. S. Guilfoyle, W. H. Chang, J. Mu, and M. Feng
OFB.3 Optics in Computing (IP) 1997

Smart Pixel Array Network Interface (SAPIENT) for 2D Parallel Data Packet Networks

C.-H. Chen, B. Hoanca, C.B. Kuznia, J.-M. Wu, and A.A. Sawchuk
OThD.11 Optics in Computing (IP) 1997

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.