LightPro: A Linear Photonic Processor with Full Programmability

TL;DR

LightPro is a fully programmable, scalable silicon photonic processor that uses phase-change materials for dynamic control, optimized via neural architecture search, achieving significant reductions in size and power with high accuracy in AI tasks.

Contribution

The paper introduces a novel fully programmable photonic processor with phase-change material-based tunable couplers and optimized architecture, advancing photonic AI hardware capabilities.

Findings

Achieves up to 85% footprint reduction

Over 50% power consumption improvement

Less than 5% accuracy drop in neural network inference

Abstract

In this paper, we propose a novel fully programmable linear photonic processor, which we call LightPro, with improved scalability, performance, and footprint. At the heart of LightPro are compact, low-loss, and programmable silicon photonic (SiPh) directional coupler (DC) devices that deploy phase-change material (PCM) for programming the DC's splitting ratio. By thermally inducing phase transitions in the PCM, the coupling coefficient of the DC can be dynamically adjusted to achieve different splitting ratios in the device output. Building on this device foundation, we develop a neural architecture search (NAS) and pruning algorithm to optimize the architecture of the processor for performing MVM operations. Our simulation results show that LightPro achieves up to an 85% reduction in footprint and more than 50% improvement in power consumption. In addition, LightPro is evaluated by performing inference with weight matrices trained on MNIST and linearly separable Gaussian datasets, showing less than a 5% drop in accuracy when scaling up the network. Prototyping results, using a commercial photonic processor (iPronics SmartLight), show LightPro's efficiency and performance (e.g., computational accuracy) compared to conventional photonic MVM hardware, demonstrating the experimental evaluation and feasibility of LightPro for next-generation photonic AI accelerators.