Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
skip to main content
research-article

A Hybrid Optical-Electrical Analog Deep Learning Accelerator Using Incoherent Optical Signals

Published: 03 May 2023 Publication History

Abstract

Optical deep learning (DL) accelerators have attracted significant interests due to their latency and power advantages. In this article, we focus on incoherent optical designs. A significant challenge is that there is no known solution to perform single-wavelength accumulation (a key operation required for DL workloads) using incoherent optical signals efficiently. Therefore, we devise a hybrid approach, where accumulation is done in the electrical domain, and multiplication is performed in the optical domain. The key technology enabler of our design is the transistor laser, which performs electrical-to-optical and optical-to-electrical conversions efficiently. Through detailed design and evaluation of our design, along with a comprehensive benchmarking study against state-of-the-art RRAM-based designs, we derive the following key results:
(1) For a four-layer multilayer perceptron network, our design achieves 115× and 17.11× improvements in latency and energy, respectively, compared to the RRAM-based design. We can take full advantage of the speed and energy benefits of the optical technology because the inference task can be entirely mapped onto our design.
(2) For a complex workload (Resnet50), weight reprogramming is needed, and intermediate results need to be stored/re-fetched to/from memories. In this case, for the same area, our design still outperforms the RRAM-based design by 15.92× in inference latency, and 8.99× in energy.

References

[1]
Aayush Ankit, Izzat El Hajj, Sai Rahul Chalamalasetti, Geoffrey Ndu, Martin Foltin, R. Stanley Williams, Paolo Faraboschi, Wen-mei W. Hwu, John Paul Strachan, Kaushik Roy, et al. 2019. PUMA: A programmable ultra-efficient memristor-based accelerator for machine learning inference. In Proceedings of the 24th International Conference on Architectural Support for Programming Languages and Operating Systems. 715–731.
[2]
Amir Arbabi, Young Mo Kang, Ching-Ying Lu, Edmond Chow, and Lynford L. Goddard. 2011. Realization of a narrowband single wavelength microring mirror. Appl. Phys. Lett. 99, 9 (2011).
[3]
Rajeev Balasubramonian, Andrew B. Kahng, Naveen Muralimanohar, Ali Shafiee, and Vaishnav Srinivas. 2017. CACTI 7: New tools for interconnect exploration in innovative off-chip memories. ACM Trans. Archit. Code Optim. 14, 2 (2017).
[4]
Daniel J. Blumenthal, Rene Heideman, Douwe Geuzebroek, Arne Leinse, and Chris Roeloffzen. 2018. Silicon nitride in silicon photonics. Proc. IEEE 106, 12 (Dec.2018), 2209–2231.
[5]
Julian Bueno, Sheler Maktoobi, Luc Froehly, Ingo Fischer, Maxime Jacquot, Laurent Larger, and Daniel Brunner. 2018. Reinforcement learning in a large-scale photonic recurrent neural network. Optica 5, 6 (2018), 756–760.
[6]
John A. Carlson, Coleman G. Williams, Maanav Ganjoo, and John M. Dallesasse. 2019. Epitaxial bonding and transfer processes for large-scale heterogeneously integrated electronic-photonic circuitry. J. Electrochem. Soc. 166, D3158 (2019).
[7]
Julie Chang, Vincent Sitzmann, Xiong Dun, Wolfgang Heidrich, and Gordon Wetzstein. 2018. Hybrid optical-electronic convolutional neural networks with optimized diffractive optics for image classification. Sci. Rep. 8, 1 (2018), 12324.
[8]
Qixiang Cheng, Jihye Kwon, Madeleine Glick, Meisam Bahadori, Luca P. Carloni, and Keren Bergman. 2020. Silicon photonics codesign for deep learning. Proc. IEEE 108, 8 (2020), 1261–1282. DOI:
[9]
Zhen Dong, Zheng Zhou, Zefan Li, Chen Liu, Peng Huang, Lifeng Liu, Xiaoyan Liu, and Jinfeng Kang. 2019. Convolutional neural networks based on RRAM devices for image recognition and online learning tasks. IEEE Trans. Electron Dev. 66, 1 (2019), 793–801. DOI:
[10]
M. Feng, H. W. Then, N. Holonyak Jr, G. Walter, and A. James. 2017. Resonance-free optical response of a vertical cavity transistor laser. Appl. Phys. Lett. 111, 12 (2017).
[11]
Ryan Hamerly, Liane Bernstein, Alexander Sludds, Marin Soljačić, and Dirk Englund. 2019. Large-scale optical neural networks based on photoelectric multiplication. Phys. Rev. X 9, 2 (2019), 021032.
[12]
Tyler W. Hughes, Momchil Minkov, Yu Shi, and Shanhui Fan. 2018. Training of photonic neural networks through in situ backpropagation and gradient measurement. Optica 5, 7 (2018), 864–871.
[13]
Mohammad Reza Jokar, Junyi Qiu, Frederic T. Chong, Lynford L. Goddard, John M. Dallesasse, Milton Feng, and Yanjing Li. 2019. Direct-modulated optical networks for interposer systems. In Proceedings of the 13th IEEE/ACM International Symposium on Networks-on-Chip.
[14]
Mohammad Reza Jokar, Lunkai Zhang, John M. Dallesasse, Frederic T. Chong, and Yanjing Li. 2020. Baldur: A power-efficient and scalable network using all-optical switches. In Proceedings of the 2020 IEEE International Symposium on High Performance Computer Architecture (HPCA’20). 153–166.
[15]
Norman P. Jouppi, Cliff Young, Nishant Patil, David Patterson, Gaurav Agrawal, Raminder Bajwa, Sarah Bates, Suresh Bhatia, Nan Boden, Al Borchers, et al. 2017. In-datacenter performance analysis of a tensor processing unit. In Proceedings of the 2017 ACM/IEEE 44th Annual International Symposium on Computer Architecture (ISCA’17). IEEE, 1–12.
[16]
M. Ataul Karim and Paul D. Franzon. 2014. A 0.65 mW/Gbps 30 Gbps capacitive coupled 10 mm serial link in 2.5D silicon interposer. In Proceedings of the 2014 IEEE 23rd Conference on Electrical Performance of Electronic Packaging and Systems. 131–134. DOI:
[17]
Haibo Liang, Richard Soref, Jianwei Mu, Xun Li, and Wei-Ping Huang. 2015. Electro-optical phase-change 2 × 2 switching using three- and four-waveguide directional couplers. Appl. Opt. 54, 19 (Jul 2015), 5897–5902.
[18]
Xing Lin, Yair Rivenson, Nezih T. Yardimci, Muhammed Veli, Yi Luo, Mona Jarrahi, and Aydogan Ozcan. 2018. All-optical machine learning using diffractive deep neural networks. Science 361, 6406 (2018), 1004–1008.
[19]
Weichen Liu, Wenyang Liu, Yichen Ye, Qian Lou, Yiyuan Xie, and Lei Jiang. 2019. HolyLight: A nanophotonic accelerator for deep learning in data centers. In Proceedings of the 2019 Design, Automation & Test in Europe Conference & Exhibition (DATE’19). 1483–1488. DOI:
[20]
Qiuwen Lou, Chenyun Pan, John McGuinness, Andras Horvath, Azad Naeemi, Michael Niemier, and X. Sharon Hu. 2019. A mixed signal architecture for convolutional neural networks. ACM J. Emerging Technol. Comput. Syst. (JETC), Vol. 15. 1–26.
[21]
Armin Mehrabian, Yousra Al-Kabani, Volker J. Sorger, and Tarek El-Ghazawi. 2018. PCNNA: A photonic convolutional neural network accelerator. In Proceedings of the 2018 31st IEEE International System-on-Chip Conference (SOCC’18). 169–173. DOI:
[22]
Shuhei Ohno, Kasidit Toprasertpong, Shinichi Takagi, and Mitsuru Takenaka. 2020. Si microring resonator crossbar arrays for deep learning accelerator. Jpn. J. Appl. Phys. 59, SG (2020), SGGE04.
[23]
Shuhei Ohno, Kasidit Toprasertpong, Shinichi Takagi, and Mitsuru Takenaka. 2021. Si microring resonator crossbar array for on-chip inference and training of optical neural network. arXiv:2106.04351. https://arxiv.org/abs/2106.04351
[24]
Indranil Palit, Qiuwen Lou, Robert Perricone, Michael Niemier, and X. Sharon Hu. 2019. A uniform modeling methodology for benchmarking DNN accelerators. In Proceedings of the 2019 IEEE/ACM International Conference on Computer-Aided Design (ICCAD’19). 1–7.
[25]
Xiaochen Peng and Shimeng Yu. 2018. Benchmark of RRAM based architectures for dot-product computation. In 2018 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS’18). 378–381. DOI:
[26]
Albert Reuther, Peter Michaleas, Michael Jones, Vijay Gadepally, Siddharth Samsi, and Jeremy Kepner. 2020. Survey of machine learning accelerators. In Proceedings of the 2020 IEEE High Performance Extreme Computing Conference (HPEC’20). 1–12. DOI:
[27]
Indu Saxena and Emile Fiesler. 1995. Adaptive multilayer optical neural network with optical thresholding. Opt. Eng. (1995), 2435–2440.
[28]
Ali Shafiee, Anirban Nag, Naveen Muralimanohar, Rajeev Balasubramonian, John Paul Strachan, Miao Hu, R. Stanley Williams, and Vivek Srikumar. 2016. ISAAC: A convolutional neural network accelerator with in-situ analog arithmetic in crossbars. In Proceedings of the ACM/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA’16).
[29]
Yichen Shen, Nicholas C. Harris, Scott Skirlo, Mihika Prabhu, Tom Baehr-Jones, Michael Hochberg, Xin Sun, Shijie Zhao, Hugo Larochelle, Dirk Englund, et al. 2017. Deep learning with coherent nanophotonic circuits. Nat. Photonics 11, 7 (2017), 441.
[30]
Kyle Shiflett, Dylan Wright, Avinash Karanth, and Ahmed Louri. 2020. PIXEL: Photonic neural network accelerator. In Proceedings of the 2020 IEEE International Symposium on High Performance Computer Architecture (HPCA’20). 474–487. DOI:
[31]
P. R. Stanfield, A. J. Leenheer, C. P. Michael, R. Sims, and M. Eichenfield. 2019. CMOS-compatible, piezo-optomechanically tunable photonics for visible wavelengths and cryogenic temperatures. Opt. Express 27, 20 (Sept.2019), 28588–28605.
[32]
Febin Sunny, Asif Mirza, Mahdi Nikdast, and Sudeep Pasricha. 2021. CrossLight: A cross-layer optimized silicon photonic neural network accelerator. In Proceedings of the 2021 58th ACM/IEEE Design Automation Conference (DAC’21). 1069–1074. DOI:
[33]
Febin P. Sunny, Asif Mirza, Mahdi Nikdast, and Sudeep Pasricha. 2021. ROBIN: A robust optical binary neural network accelerator. ACM Trans. Embedded Comput. Syst. (TECS) 20, 5s (2021), 1–24.
[34]
Febin P. Sunny, Ebadollah Taheri, Mahdi Nikdast, and Sudeep Pasricha. 2021. A survey on silicon photonics for deep learning. J. Emerg. Technol. Comput. Syst. 17, 4 (June2021), Article 61, 57 pages. DOI:
[35]
Vivienne Sze, Yu-Hsin Chen, Tien-Ju Yang, and Joel S. Emer. 2017. Efficient processing of deep neural networks: A tutorial and survey. Proc. IEEE (2017), 2295–2329.
[36]
Alexander N. Tait, Mitchell A. Nahmias, Bhavin J. Shastri, and Paul R. Prucnal. 2014. Broadcast and weight: An integrated network for scalable photonic spike processing. J. Lightwave Technol. 32, 21 (2014), 4029–4041. DOI:
[37]
Alexander N. Tait, Allie X. Wu, Thomas Ferreira de Lima, Ellen Zhou, Bhavin J. Shastri, Mitchell A. Nahmias, and Paul R. Prucnal. 2016. Microring weight banks. IEEE J. Sel. Top. Quantum Electron. 22, 6 (2016), 312–325. DOI:
[38]
Han Wui Then, Milton Feng, and Nick Holonyak. 2013. The transistor laser: Theory and experiment. Proc. IEEE 101, 10 (2013), 2271–2298.
[39]
Shaofu Xu, Jing Wang, and Weiwen Zou. 2021. Optical convolutional neural network with WDM-based optical patching and microring weighting banks. IEEE Photonics Technol. Lett. 33, 2 (2021), 89–92. DOI:
[40]
Meiran Zhao, Huaqiang Wu, Bin Gao, Qingtian Zhang, Wei Wu, Shan Wang, Yue Xi, Dong Wu, Ning Deng, Shimeng Yu, et al. 2017. Investigation of statistical retention of filamentary analog RRAM for neuromophic computing. In 2017 IEEE International Electron Devices Meeting (IEDM’17). 39.4.1–39.4.4.

Cited By

View all
  • (2024)Universal Relocalizer for Weakly Supervised Referring Expression GroundingACM Transactions on Multimedia Computing, Communications, and Applications10.1145/365604520:7(1-23)Online publication date: 16-May-2024
  • (2024)Joint Distortion Restoration and Quality Feature Learning for No-reference Image Quality AssessmentACM Transactions on Multimedia Computing, Communications, and Applications10.1145/364989920:7(1-20)Online publication date: 27-Mar-2024
  • (2023)Dual-Path Rare Content Enhancement Network for Image and Text MatchingIEEE Transactions on Circuits and Systems for Video Technology10.1109/TCSVT.2023.325453033:10(6144-6158)Online publication date: 9-Mar-2023

Index Terms

  1. A Hybrid Optical-Electrical Analog Deep Learning Accelerator Using Incoherent Optical Signals

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM Journal on Emerging Technologies in Computing Systems
    ACM Journal on Emerging Technologies in Computing Systems  Volume 19, Issue 2
    April 2023
    214 pages
    ISSN:1550-4832
    EISSN:1550-4840
    DOI:10.1145/3587888
    • Editor:
    • Ramesh Karri
    Issue’s Table of Contents

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Journal Family

    Publication History

    Published: 03 May 2023
    Online AM: 17 February 2023
    Accepted: 29 January 2023
    Revised: 12 November 2022
    Received: 18 March 2022
    Published in JETC Volume 19, Issue 2

    Permissions

    Request permissions for this article.

    Check for updates

    Author Tags

    1. Optical computing
    2. deep learning accelerator

    Qualifiers

    • Research-article

    Funding Sources

    • NSF
    • center of NRI, a Semiconductor Research Corporation (SRC)
    • NERC and NIST

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • Downloads (Last 12 months)225
    • Downloads (Last 6 weeks)6
    Reflects downloads up to 20 Feb 2025

    Other Metrics

    Citations

    Cited By

    View all
    • (2024)Universal Relocalizer for Weakly Supervised Referring Expression GroundingACM Transactions on Multimedia Computing, Communications, and Applications10.1145/365604520:7(1-23)Online publication date: 16-May-2024
    • (2024)Joint Distortion Restoration and Quality Feature Learning for No-reference Image Quality AssessmentACM Transactions on Multimedia Computing, Communications, and Applications10.1145/364989920:7(1-20)Online publication date: 27-Mar-2024
    • (2023)Dual-Path Rare Content Enhancement Network for Image and Text MatchingIEEE Transactions on Circuits and Systems for Video Technology10.1109/TCSVT.2023.325453033:10(6144-6158)Online publication date: 9-Mar-2023

    View Options

    Login options

    Full Access

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    Full Text

    View this article in Full Text.

    Full Text

    HTML Format

    View this article in HTML Format.

    HTML Format

    Figures

    Tables

    Media

    Share

    Share

    Share this Publication link

    Share on social media