In-memory photonic dot-product engine with electrically programmable weight banks

Electronically reprogrammable photonic circuits based on phase-change chalcogenides present an avenue to resolve the von-Neumann bottleneck; however, implementation of such hybrid photonic-electronic processing has not achieved computational success. Here, we achieve this milestone by demonstrating an in-memory photonic-electronic dot-product engine, one that decouples electronic programming of phase-change materials (PCMs) and photonic computation. Specifically, we develop non-volatile electronically reprogrammable PCM memory cells with a record-high 4-bit weight encoding, the lowest energy consumption per unit modulation depth (1.7 nJ/dB) for Erase operation (crystallization), and a high switching contrast (158.5%) using non-resonant silicon-on-insulator waveguide microheater devices. This enables us to perform parallel multiplications for image processing with a superior contrast-to-noise ratio (>= 87.36) that leads to an enhanced computing accuracy (standard deviation sigma <= 0.007). An in-memory hybrid computing system is developed in hardware for convolutional processing for recognizing images from the MNIST database with inferencing accuracies of 86% and 87%. Hybrid photonic-electronic systems are essential for high-throughput neuromorphic computing. Here, the authors report an in-memory photonic-electronic dot-product engine with decoupled electronic programming of the phase-change memory cells and parallel photonic computation with high-bit operation, low energy consumption, and high accuracy.