Photonic Computing and Communication for Neural Network Accelerators

• Published in: Parallel and Distributed Computing, Applications and Technologies Vol. 13148; pp. 121 - 128
• Main Authors: Xia, Chengpeng, Chen, Yawen, Zhang, Haibo, Zhang, Hao, Wu, Jigang
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer International Publishing AG 2022; Springer International Publishing
• Series: Lecture Notes in Computer Science
• Subjects: Neural network accelerator; Optical interconnection networks; Optical neural networks
• ISBN: 9783030967710; 3030967719
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/978-3-030-96772-7_12

Conventional electronic Artificial Neural Networks (ANNs) accelerators focus on architecture design and numerical computation optimization to improve the training speed. Optical technology with low energy consumption and high transmission speed are expected to play an important role in the next generation of computing architectures. To provide a better understanding of optical technology used in ANN acceleration, we present a comprehensive review for the optical implementations of ANNs accelerator in this paper. We propose a classification of existing solutions which are categorized into optical computing acceleration and optical communication acceleration according to optical effects and optical architectures. Moreover, we discuss the challenges for these photonic neural network acceleration approaches to highlight the most promising future research opportunities in this field.