Reconfigurable analog computing paradigm based on planar optical waveguides

The all-optical/optoelectronic hybrid intelligent computing with high speed and low power consumption characteristics has emerged as a promising solution for the bottleneck of Moore's Law. However, the low deployment flexibility and low integration limit the further development of optical computing systems, and it is urgent to match the new artificial intelligence theory with the physical characteristics of light itself. In this paper, we proposed a reconfigurable computing architecture based on planar optical waveguide, called wave network, which can be used for hardware development of optical switches, optical logic devices or neural networks. Inspired by the neuronal perceptron model, the elements of wave network are analyzed from the point of view of basic pixel units. Wave network has the processing capability of pulse input and time sequence input. To achieve low-power weight mapping, non-volatile materials with CMOS compatiblity characteristics are introduced above the waveguide (etc. phase change materials, multiferroics materials, and resistive switching materials). This hybrid structure provides a large-scale, low-cost, rapid development platform for the new photonic computing paradigm. And the simulation results show that the properties of the waveguide remain stable at different geometric scales and have the potential of scaling down.