State Key Laboratory of Advanced Optical Communications System and Networks, School of Electronics, Peking University, Beijing, 100871, China.
Department of Electrical and Computer Engineering, University of California, Santa Barbara, CA, 93106, USA.
Nat Commun. 2023 Jan 5;14(1):66. doi: 10.1038/s41467-022-35506-9.
The emergence of parallel convolution-operation technology has substantially powered the complexity and functionality of optical neural networks (ONN) by harnessing the dimension of optical wavelength. However, this advanced architecture faces remarkable challenges in high-level integration and on-chip operation. In this work, convolution based on time-wavelength plane stretching approach is implemented on a microcomb-driven chip-based photonic processing unit (PPU). To support the operation of this processing unit, we develop a dedicated control and operation protocol, leading to a record high weight precision of 9 bits. Moreover, the compact architecture and high data loading speed enable a preeminent photonic-core compute density of over 1 trillion of operations per second per square millimeter (TOPS mm). Two proof-of-concept experiments are demonstrated, including image edge detection and handwritten digit recognition, showing comparable processing capability compared to that of a digital computer. Due to the advanced performance and the great scalability, this parallel photonic processing unit can potentially revolutionize sophisticated artificial intelligence tasks including autonomous driving, video action recognition and image reconstruction.
并行卷积运算技术的出现，通过利用光学波长的维度，极大地提高了光神经网络（ONN）的复杂性和功能。然而，这种先进的架构在高级集成和片上操作方面面临着显著的挑战。在这项工作中，基于时-波长相结合的方法在微梳驱动的片上光子处理单元（PPU）上实现了卷积。为了支持这个处理单元的运行，我们开发了一种专用的控制和操作协议，从而实现了 9 位的超高权重精度。此外，这种紧凑的架构和高速的数据加载速度实现了超过 1 万亿次每秒每平方毫米（TOPS/mm）的卓越的光子核计算密度。我们展示了两个概念验证实验，包括图像边缘检测和手写数字识别，与数字计算机相比，展示了相当的处理能力。由于其先进的性能和巨大的可扩展性，这种并行光子处理单元有可能彻底改变复杂的人工智能任务，包括自动驾驶、视频动作识别和图像重建。
