Cascadable all-optical NAND gates using diffractive networks

Abstract

Owing to its potential advantages such as scalability, low latency and power efficiency, optical computing has seen rapid advances over the last decades. Here, we present the design and analysis of cascadable all-optical NAND gates using diffractive neural networks. We encoded the logical values at the input and output planes of a diffractive NAND gate using the relative optical power of two spatially-separated apertures. Based on this architecture, we numerically optimized the design of a diffractive neural network composed of 4 passive layers to all-optically perform NAND operation using diffraction of light, and cascaded these diffractive NAND gates to perform complex logical functions by successively feeding the output of one diffractive NAND gate into another. We numerically demonstrated the cascadability of our diffractive NAND gates by using identical diffractive designs to all-optically perform AND and OR operations, which can be formulated as mathrm{AND}left({I}_{1}, {I}_{2}right)=mathrm{NAND}left(mathrm{NAND}left({I}_{1}, {I}_{2}right), mathrm{NAND}left({I}_{1},{I}_{2}right)right) and mathrm{OR}left({I}_{1}, {I}_{2}right)=mathrm{NAND}left(mathrm{NAND}left({I}_{1}, {I}_{1}right), mathrm{NAND}left({I}_{2},{I}_{2}right)right), respectively. We also designed an all-optical half-adder that takes two logical values as input and returns their sum and the carry using cascaded diffractive NAND gates. Cascadable all-optical NAND gates composed of spatially-engineered passive diffractive layers can serve optical computing platforms.