Electro-Optical DSP of Tera Operations per Second and Beyond (Extended Abstract)

We present a vector-by-matrix multiplier architecture incorporating the high potential of optical computing within electronics. This architecture stems from advances in optical switching technology, optical communication, and laser on silicon, and overcomes previous bottlenecks implied by the speed of transferring information to the optical vector-by-matrix multiplier. Based on this architecture, we present in detail a feasible electro-optical DSP co-processor that can obtain more than 16-Tera integer operations per second. The use of the new architecture for several principal DSP applications is detailed, showing a significant improvement of at least two orders of magnitudes, over existing DSP technologies. Examples of possible applications, including motion estimation engine, string matching, and geometry engine systems, are provided. In addition, the architecture enables an improvement of previous solutions to bounded NP-complete problems by extensively reducing the size of the solver, while preserving an efficient computation time.

[1]  J. Goodman Introduction to Fourier optics , 1969 .

[2]  Thomas H. Wood,et al.  High-speed 2 × 2 electrically driven spatial light modulator made with GaAs/AlGaAs multiple quantum wells(MQWs) , 1987 .

[3]  Mohammad A. Karim,et al.  Optical Computing: An Introduction , 1992 .

[4]  Henry Hoffmann,et al.  On-Chip Interconnection Architecture of the Tile Processor , 2007, IEEE Micro.

[5]  Alan V. Oppenheim,et al.  Discrete-time signal processing (2nd ed.) , 1999 .

[6]  Qian Shinan,et al.  多機能ロングトレースプロファイラの設計 | 文献情報 | J-GLOBAL 科学技術総合リンクセンター , 2007 .

[7]  Natan T. Shaked,et al.  Optical binary-matrix synthesis for solving bounded NP-complete combinatorial problems , 2007 .

[8]  Michael Gschwind Chip multiprocessing and the cell broadband engine , 2006, CF '06.

[9]  S. L. Hurst Optical computer architectures: the application of optical concepts to next generation computers: A.D. McAulay, John Wiley, New York, 1991, 530 pp., £55.00 , 1993 .

[10]  Jongsun Kim,et al.  Design of an Interconnect Architecture and Signaling Technology for Parallelism in Communication , 2007, IEEE Transactions on Very Large Scale Integration (VLSI) Systems.

[11]  Shlomi Dolev,et al.  Optical solution for bounded NP-complete problems. , 2007, Applied optics.

[12]  Thomas H. Cormen,et al.  Introduction to algorithms [2nd ed.] , 2001 .

[13]  Dror G. Feitelson Optical computing - a survey for computer scientists , 1988 .

[14]  Shlomi Dolev,et al.  The Traveling Beams Optical Solutions for Bounded NP-Complete Problems , 2007, FUN.

[15]  Jonathan Pevsner,et al.  Basic Local Alignment Search Tool (BLAST) , 2005 .

[16]  A. W. M. van den Enden,et al.  Discrete Time Signal Processing , 1989 .

[17]  Sriram R. Vangal,et al.  A 5-GHz Mesh Interconnect for a Teraflops Processor , 2007, IEEE Micro.

[18]  Clifford Stein,et al.  Introduction to Algorithms, 2nd edition. , 2001 .