Abstract
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.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Chen, L., et al.: Enabling wide-spread communications on optical fabric with megaswitch. In: 14th Symposium on Networked Systems Design and Implementation, pp. 577–593 (2017)
Clements, W.R., Humphreys, P.C., Metcalf, B.J., Kolthammer, W.S., et al.: Optimal design for universal multiport interferometers. Optica 3(12), 1460–1465 (2016)
Dai, F., Chen, Y., Zhang, H., Huang, Z.: Accelerating fully connected neural network on optical network-on-chip (onoc). arXiv preprint arXiv:2109.14878 (2021)
Farrington, N., et al.: Helios: a hybrid electrical/optical switch architecture for modular data centers. In: 2010 ACM SIGCOMM, pp. 339–350 (2010)
Hinton, G.E., Osindero, S., Teh, Y.W.: A fast learning algorithm for deep belief nets. Neural Comput. 18(7), 1527–1554 (2006)
Khani, M., et al.: Sip-ml: high-bandwidth optical network interconnects for machine learning training. In: 2021 ACM SIGCOMM, pp. 657–675 (2021)
Kim, J.Y., Kang, J.M., Kim, T.Y., Han, S.K.: All-optical multiple logic gates with xor, nor, or, and nand functions using parallel soa-mzi structures: theory and experiment. J. Lightwave Technol. 24(9), 3392 (2006)
Kim, Y.W., Choi, S.H., Han, T.H.: Rapid topology generation and core mapping of optical network-on-chip for heterogeneous computing platform. IEEE Access 9, 110359–110370 (2021)
Lawson, C.L., Hanson, R.J.: Solving least squares problems. SIAM (1995)
Lin, X., Rivenson, Y., Yardimci, N.T., Veli, M., et al.: All-optical machine learning using diffractive deep neural networks. Science 361(6406), 1004–1008 (2018)
Mehrabian, A., Al-Kabani, Y., Sorger, V.J., El-Ghazawi, T.: Pcnna: a photonic convolutional neural network accelerator. In: 2018 31st IEEE International System-on-Chip Conference (SOCC), pp. 169–173. IEEE (2018)
Mellette, W.M., McGuinness, R., Roy, A., Forencich, A., Papen, G., Snoeren, A.C., Porter, G.: Rotornet: a scalable, low-complexity, optical datacenter network. In: ACM Special Interest Group on Data Communication, pp. 267–280 (2017)
Psaltis, D., Brady, D., Wagner, K.: Adaptive optical networks using photorefractive crystals. Appl. Opt. 27(9), 1752–1759 (1988)
Reck, M., Zeilinger, A., Bernstein, H.J., Bertani, P.: Experimental realization of any discrete unitary operator. Phys. Rev. Lett. 73(1), 58 (1994)
Shen, Y., et al.: Deep learning with coherent nanophotonic circuits. Nat. Photonics 11(7), 441–446 (2017)
Silver, D., et al.: Mastering the game of go with deep neural networks and tree search. Nature 529(7587), 484–489 (2016)
Tait, A.N., Nahmias, M.A., Shastri, B.J., Prucnal, P.R.: Broadcast and weight: an integrated network for scalable photonic spike processing. J. Lightwave Technol. 32(21), 4029–4041 (2014)
Yang, P., et al.: Rson: an inter/intra-chip silicon photonic network for rack-scale computing systems. In: 2018 Design, Automation & Test in Europe Conference & Exhibition (DATE), pp. 1369–1374. IEEE (2018)
Zuo, Y., Li, B., Zhao, Y., Jiang, Y., Chen, Y.C., Chen, P., et al.: All-optical neural network with nonlinear activation functions. Optica 6(9), 1132–1137 (2019)
Acknowledgement
This work is supported by the National Natural Science Foundation of China under Grant Nos. 62106052 and 62072118.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Xia, C., Chen, Y., Zhang, H., Zhang, H., Wu, J. (2022). Photonic Computing and Communication for Neural Network Accelerators. In: Shen, H., et al. Parallel and Distributed Computing, Applications and Technologies. PDCAT 2021. Lecture Notes in Computer Science(), vol 13148. Springer, Cham. https://doi.org/10.1007/978-3-030-96772-7_12
Download citation
DOI: https://doi.org/10.1007/978-3-030-96772-7_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-96771-0
Online ISBN: 978-3-030-96772-7
eBook Packages: Computer ScienceComputer Science (R0)