Multi-Wavelength Optical Content Addressable Parallel Processor (MW-OCAPP)
Project Motivation
Databases are becoming key elements in the Information Age. Database machines, likewise, are the central enablers for current and future progress in Information Technology. Optics, because of its inherent parallelism, has long been seen as a vehicle for large-scale database processing.
Project Description
MW-OCAPP is designed to provide efficient parallel retrieval and processing of data by moving the bulk of database operations from electronics to optics. It combines a parallel model of computation with the many degrees of processing freedom that light provides. MW-OCAPP uses a polarization and wavelength-encoding scheme to achieve a high level of parallelism. Distinctive features of the proposed architecture include (1) the use of a multiple-wavelength encoding scheme to enhance processing parallelism, (2) multiple-comparand word-parallel and bit-parallel magnitude comparison with an execution-time independent of the data size or word size, (3) the implementation of a suite of eleven database primitives, and (4) multi-comparand two-dimensional data processing. The MW-OCAPP architecture realizes eleven relational database primitives: difference, intersection, union, conditional selection, maximum, minimum, join, product, projection, division and update. Most of these operations execute in constant time independent of the data size.
We are also working on implementing a monolithic system that implements the Equivalency Operation using optical waveguide technology. This system, dubbed EP 3 IC for Equivalency Processing Parallel Photonic Integrated Circuit, is the potential next-generation architecture foundation in the OCAPP line of processors. The system attempts to implement the basic functionality of MW-OCAPP at a fraction of the footprint and power requirements:
Functional Schematic of EP3IC
Raytrace simulation of the EP3IC waveguide structure using ASAP
Publications
P. Y. Choo, A. Detofsky and A. Louri, “Multiwavelength optical content-addressable parallel processor for high-speed parallel relational database processing,” in Applied Optics, vol. 38, no. 26, pp. 5594-5604, Sept. 1999.
P. Choo and A. Louri, “Guided-Wave Multiwavelength Computing Systems,” in Proceedings of Optics for the New Millenium, Providence, RI, 2000, pp. 1-7.
The Equivalency Processing Parallel Photonic Integrated Circuit (EPI3C): A Parallel Digital Equivalence and Fussy Search Module Peng Yin Choo and Ahmed Louri accepted for publication, Applied Imagery Pattern Recognition Annual Workshop, Imagery in the New Mellinnium, Washington D.C., October 16 - 18, 2000.
P. Y. Choo and A. Louri, “Guided-wave multiwavelength polarization-insensitive processing module for a parallel multicomparand perfect-match algorithm,” in Optics Letters, vol. 25, no. 20, pp. 1541-1543, Oct. 2000.
Towards a Monolithic Equivalency Processing Parallel Photonic Integrated Circuit (EP 3 IC) Abram Detofsky, Peng Yin Choo and Ahmed Louri Applied Optics , special issue on Optics in Computing, vol. 39, no. 5, pp. 818-826, February 10, 2000.
P. Y. Choo, A. Detofsky and A. Louri, “Multiwavelength optical content-addressable parallel processor for high-speed parallel relational database processing,” in Applied Optics, vol. 38, no. 26, pp. 5594-5604, Sept. 1999.
P. Y. Choo, A. Detofsky, and A. Louri, “A Multi-Wavelength Optical Content-Addressable Parallel Processor (MW-OCAPP) for High-Speed Parallel Relational Database Processing: Architectural Concepts and Preliminary Experimental System,” in Proceedings of Optics in Computing 1999, Snowmass, CO, 1999, pp. 66-69.
P. Y. Choo, A. Detofsky, and A. Louri, “A Multi-Wavelength Optical Content-Addressable Parallel Processor (MW-OCAPP) for High-Speed Parallel Relational Database Processing: Architectural Concepts and Preliminary Experimental Results,” in Proceedings of the Workshop on Optics in Computer Science (WOCS ‘99), San Juan, PR, 1999, pp. 873-886.
Optical Implementation of a Multi-Comparand Bit-Parallel Magnitude Comparison Algorithm using Wavelength and Polarization-Division Multiplexing with Application to Parallel Database Processing Abram Detofsky, Peng Yin Choo,and Ahmed Louri Optics Letters , vol. 23, no. 17, pp. 1372-1375, September 1, 1998.
P. Y. Choo, A. Detofsky, and A. Louri, “An Optical Architecture Using Multiwavelength and Polarization Encoding for High-Speed Parallel Relational Database Processing,” in Proceedings of the Optics in Computing 1998, Bruges, 1998, pp. 139-143.