Integrated Nanophotonics Architecture for Residue Number System Arithmetic

Residue number system (RNS) enables dimensionality reduction of an arithmetic problem by representing a large number as a set of smaller integers, where the number is decomposed by prime number factorization using the moduli as basic functions. These reduced problem sets can then be processed independently and in parallel, thus improving computational efficiency and speed. Here we show an optical RNS hardware representation based on integrated nanophotonics. The digit-wise shifting in RNS arithmetic is expressed as spatial routing of an optical signal in 2x2 hybrid photonic-plasmonic switches. Here the residue is represented by spatially shifting the input waveguides relative to the routers outputs, where the moduli are represented by the number of waveguides. By cascading the photonic 2x2 switches, we design a photonic RNS adder and a multiplier forming an all-to-all sparse directional network. The advantage of this photonic arithmetic processor is the short (10's ps) computational execution time given by the optical propagation delay through the integrated nanophotonic router. Furthermore, we show how photonic processing in-the-network leverages the natural parallelism of optics such as wavelength-division-multiplexing or optical angular momentum in this RNS processor. A key application for photonic RNS is the functional analysis convolution with widespread usage in numerical linear algebra, computer vision, language- image- and signal processing, and neural networks.

[1]  Volker J. Sorger,et al.  A Universal Multi-Hierarchy Figure-of-Merit for On-Chip Computing and Communications , 2016, ArXiv.

[2]  Volker J. Sorger,et al.  MorphoNoC: Exploring the Design Space of a Configurable Hybrid NoC using Nanophotonics , 2016, Microprocess. Microsystems.

[3]  Volker J. Sorger,et al.  HyPPI NoC: Bringing Hybrid Plasmonics to an Opto-Electronic Network-on-Chip , 2017, 2017 46th International Conference on Parallel Processing (ICPP).

[4]  Volker J. Sorger,et al.  Monolithic III–V on Silicon Plasmonic Nanolaser Structure for Optical Interconnects , 2015, Scientific Reports.

[5]  D Casasent,et al.  Optical residue arithmetic: a correlation approach. , 1979, Applied optics.

[6]  Volker J. Sorger,et al.  Photonic-Plasmonic Hybrid Interconnects: a Low-latency Energy and Footprint Efficient Link , 2015 .

[7]  Mehdi Hosseinzadeh,et al.  Optical RNS adder and multiplier , 2015, Int. J. Comput. Appl. Technol..

[8]  J R Fienup,et al.  Optical residue arithmetic computer with programmable computation modules. , 1979, Applied optics.

[9]  Mehdi Hosseinzadeh,et al.  All optical residue arithmetic with micro ring resonators and its application , 2016 .

[10]  Tarek El-Ghazawi,et al.  Hybrid Photonic-Plasmonic Nonblocking Broadband 5 × 5 Router for Optical Networks , 2017, IEEE Photonics Journal.

[11]  Tarek El-Ghazawi,et al.  The Case for Hybrid Photonic Plasmonic Interconnects (HyPPIs): Low-Latency Energy-and-Area-Efficient On-Chip Interconnects , 2015, IEEE Photonics Journal.

[12]  Volker J. Sorger,et al.  Fundamental Scaling Laws in Nanophotonics , 2016, Scientific Reports.

[13]  Pei Wang,et al.  All-optical switching in subwavelength metallic grating structure containing nonlinear optical materials. , 2008, Optics letters.

[14]  T. Horikawa,et al.  50-Gb/s ring-resonator-based silicon modulator. , 2013, Optics express.

[15]  Volker J. Sorger,et al.  A compact plasmonic MOS-based 2×2 electro-optic switch , 2015, 1506.02337.

[16]  David Hillerkuss,et al.  All-plasmonic Mach–Zehnder modulator enabling optical high-speed communication at the microscale , 2015, Nature Photonics.

[17]  Harvey L. Garner,et al.  RESIDUE NUMBER SYSTEM ENHANCEMENTS FOR PROGRAMMABLE PROCESSORS , 2008 .

[18]  David A. B. Miller.  Attojoule Optoelectronics for Low-Energy Information Processing and Communications , 2017, Journal of Lightwave Technology.

[19]  Volker J. Sorger,et al.  D3NOC: Dynamic Data-Driven Network On Chip in Photonic Electronic Hybrids , 2017, ArXiv.