{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T15:40:08Z","timestamp":1755877208912,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T00:00:00Z","timestamp":1717027200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Guangzhou-HKUST(GZ) Joint Funding Program","award":["2023A03J0013"],"award-info":[{"award-number":["2023A03J0013"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,30]]},"DOI":"10.1145\/3650200.3656609","type":"proceedings-article","created":{"date-parts":[[2024,6,3]],"date-time":"2024-06-03T14:11:54Z","timestamp":1717423914000},"page":"352-362","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["NEOCNN: NTT-Enabled Optical Convolution Neural Network Accelerator"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4097-9367","authenticated-orcid":false,"given":"Xianbin","family":"Li","sequence":"first","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9144-4376","authenticated-orcid":false,"given":"Yinyi","family":"Liu","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2625-6111","authenticated-orcid":false,"given":"Fan","family":"Jiang","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0740-0974","authenticated-orcid":false,"given":"Chengeng","family":"Li","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8561-6896","authenticated-orcid":false,"given":"Yuxiang","family":"Fu","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7622-6714","authenticated-orcid":false,"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong Special Administrative Region of China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9089-7752","authenticated-orcid":false,"given":"Jiang","family":"Xu","sequence":"additional","affiliation":[{"name":"Microelectronics Thrust, Hong Kong University of Science and Technology (Guangzhou), China"}]}],"member":"320","published-online":{"date-parts":[[2024,6,3]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"[n. d.]. DALL \u00b7 E: Creating Images from Text."},{"key":"e_1_3_2_1_2_1","unstructured":"[n. d.]. Introducing ChatGPT."},{"key":"e_1_3_2_1_3_1","volume-title":"TRON: Transformer Neural Network Acceleration with Non-Coherent Silicon Photonics. In GLSVLSI. 15\u201321.","author":"Afifi Salma","year":"2023","unstructured":"Salma Afifi, Febin Sunny, Mahdi Nikdast, and Sudeep Pasricha. 2023. TRON: Transformer Neural Network Acceleration with Non-Coherent Silicon Photonics. In GLSVLSI. 15\u201321."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1974.1162555"},{"key":"e_1_3_2_1_5_1","volume-title":"FAB: An FPGA-based Accelerator for Bootstrappable Fully Homomorphic Encryption","author":"Agrawal Rashmi","year":"2023","unstructured":"Rashmi Agrawal, Leo de Castro, Guowei Yang, Chiraag Juvekar, Rabia Yazicigil, Anantha Chandrakasan, Vinod Vaikuntanathan, and Ajay Joshi. 2023. FAB: An FPGA-based Accelerator for Bootstrappable Fully Homomorphic Encryption. In HPCA. IEEE, 882\u2013895."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-018-0028-z"},{"key":"e_1_3_2_1_7_1","volume-title":"On-Chip Optical Convolutional Neural Networks. arXiv preprint arXiv:1808.03303","author":"Bagherian Hengameh","year":"2018","unstructured":"Hengameh Bagherian, Scott Skirlo, Yichen Shen, Huaiyu Meng, Vladimir Ceperic, and Marin Soljacic. 2018. On-Chip Optical Convolutional Neural Networks. arXiv preprint arXiv:1808.03303 (2018). arxiv:1808.03303"},{"key":"e_1_3_2_1_8_1","unstructured":"Utsav Banerjee Abhishek Pathak and Anantha\u00a0P Chandrakasan. [n. d.]. 2.3 An Energy-Efficient Configurable Lattice Cryptography Processor for the Quantum-Secure Internet of Things. In ISSCC."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2019.2907907"},{"key":"e_1_3_2_1_10_1","volume-title":"All-Analog Photoelectronic Chip for High-Speed Vision Tasks. Nature","author":"Chen Yitong","year":"2023","unstructured":"Yitong Chen, Maimaiti Nazhamaiti, Han Xu, Yao Meng, Tiankuang Zhou, Guangpu Li, Jingtao Fan, Qi Wei, Jiamin Wu, Fei Qiao, 2023. All-Analog Photoelectronic Chip for High-Speed Vision Tasks. Nature (2023), 1\u201310."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001177"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.1974.1050511"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1364\/OPTICA.3.000622"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Hossein Eslahi Tara\u00a0J. Hamilton and Sourabh Khandelwal. 2022. Ultra Compact and Linear 4-Bit Digital-to-Analog Converter in 22nm FDSOI Technology. In ISCAS. 2778\u20132781.","DOI":"10.1109\/ISCAS48785.2022.9937686"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1364\/OE.27.014009"},{"key":"e_1_3_2_1_16_1","volume-title":"All-Optical Spiking Neurosynaptic Networks with Self-Learning Capabilities. Nature 569, 7755","author":"Feldmann Johannes","year":"2019","unstructured":"Johannes Feldmann, Nathan Youngblood, C\u00a0David Wright, Harish Bhaskaran, and Wolfram\u00a0HP Pernice. 2019. All-Optical Spiking Neurosynaptic Networks with Self-Learning Capabilities. Nature 569, 7755 (2019), 208\u2013214."},{"key":"e_1_3_2_1_17_1","first-page":"1796","article-title":"Toward Hardware-Efficient Optical Neural Networks: Beyond FFT Architecture via Joint Learnability","volume":"40","author":"Gu Jiaqi","year":"2020","unstructured":"Jiaqi Gu, Zheng Zhao, Chenghao Feng, Zhoufeng Ying, Mingjie Liu, Ray\u00a0T Chen, and David\u00a0Z Pan. 2020. Toward Hardware-Efficient Optical Neural Networks: Beyond FFT Architecture via Joint Learnability. IEEE TCAD 40, 9 (2020), 1796\u20131809.","journal-title":"IEEE TCAD"},{"key":"e_1_3_2_1_18_1","first-page":"315","article-title":". Accelerating Deep Convolutional Neural Networks Using Number Theoretic Transform","volume":"70","author":"Hong Seongmin","year":"2022","unstructured":"Seongmin Hong, Yashael\u00a0Faith Arthanto, Joo-Young Kim, 2022. Accelerating Deep Convolutional Neural Networks Using Number Theoretic Transform. IEEE TCAS-I 70, 1 (2022), 315\u2013326.","journal-title":"IEEE TCAS-I"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Jie Huang Hansi Ma Dingbo Chen Huan Yuan Jinping Zhang Zikang Li Jingmin Han Jiagui Wu and Junbo Yang. [n. d.]. Digital Nanophotonics: The Highway to the Integration of Subwavelength-Scale Photonics: Ultra-compact Multi-Function Nanophotonic Design Based on Computational Inverse Design. Nanophotonics 10 3 ([n. d.]) 1011\u20131030.","DOI":"10.1515\/nanoph-2020-0494"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3055814"},{"key":"e_1_3_2_1_21_1","volume-title":"XVDPU: A High Performance CNN Accelerator on Versal Platform Powered by AI Engine. ACM Transactions on Reconfigurable Technology and Systems","author":"Jia Xijie","year":"2022","unstructured":"Xijie Jia, Yu Zhang, Guangdong Liu, Xinlin Yang, Tianyu Zhang, Jia Zheng, Dongdong Xu, Zhuohuan Liu, Mengke Liu, Xiaoyang Yan, 2022. XVDPU: A High Performance CNN Accelerator on Versal Platform Powered by AI Engine. ACM Transactions on Reconfigurable Technology and Systems (2022)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3143535"},{"key":"e_1_3_2_1_23_1","first-page":"579","article-title":"MeNTT: A Compact and Efficient Processing-in-Memory Number Theoretic Transform (NTT) Accelerator","volume":"30","author":"Li Dai","year":"2022","unstructured":"Dai Li, Akhil Pakala, and Kaiyuan Yang. 2022. MeNTT: A Compact and Efficient Processing-in-Memory Number Theoretic Transform (NTT) Accelerator. VLSI 30, 5 (2022), 579\u2013588.","journal-title":"VLSI"},{"key":"e_1_3_2_1_24_1","unstructured":"Xianbin LI Jiaqi LIU Yuying ZHANG and et. al. [n. d.]. PhotonNTT: Energy-efficient Parallel Photonic Number Theoretic Transform Accelerator. In DATE2024."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/2786763.2694358"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Juzheng Liu Mohsen Hassanpourghadi and Mike Shuo-Wei Chen. 2022. A 10GS\/s 8b 25fJ\/c-s 2850um2 Two-Step Time-Domain ADC Using Delay-Tracking Pipelined-SAR TDC with 500fs Time Step in 14nm CMOS Technology. In ISSCC Vol.\u00a065. 160\u2013162.","DOI":"10.1109\/ISSCC42614.2022.9731625"},{"key":"e_1_3_2_1_27_1","unstructured":"Xinheng Liu Yao Chen Cong Hao Ashutosh Dhar and Deming Chen. [n. d.]. WinoCNN: Kernel Sharing Winograd Systolic Array for Efficient Convolutional Neural Network Acceleration on FPGAs. In ASAP."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Yinyi Liu Jiaxu Zhang Jun Feng Shixi Chen and Jiang Xu. 2022. Reduce Footprints of Multiport Interferometers by Cosine-Sine-Decomposition Unfolding. In OFC. W2A\u20134.","DOI":"10.1364\/OFC.2022.W2A.4"},{"key":"e_1_3_2_1_29_1","volume-title":"Automation & Test in Europe Conference & Exhibition (DATE). IEEE, 1059\u20131064","author":"Liu Yinyi","year":"2022","unstructured":"Yinyi Liu, Jiaxu Zhang, Jun Feng, Shixi Chen, and Jiang Xu. 2022. A Reliability Concern on Photonic Neural Networks. In 2022 Design, Automation & Test in Europe Conference & Exhibition (DATE). IEEE, 1059\u20131064."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1021\/acsphotonics.8b01234"},{"key":"e_1_3_2_1_31_1","unstructured":"Simei Mao Lirong Cheng Fasial\u00a0Nadeem Khan Zihan Geng Qian Li and HY Fu. [n. d.]. Inverse Design of High-Dimensional Nanostructured 2\u00d7 2 Optical Processors Based on Deep Convolutional Neural Networks. Journal of Lightwave Technology ([n. d.])."},{"key":"e_1_3_2_1_32_1","volume-title":"Cramming More Components onto Integrated Circuits","author":"Moore Gordon","year":"1965","unstructured":"Gordon Moore. 2021. Cramming More Components onto Integrated Circuits (1965). (2021)."},{"key":"e_1_3_2_1_33_1","volume-title":"Cryptopim: In-memory Acceleration for Lattice-Based Cryptographic Hardware. In 2020 57th ACM\/IEEE Design Automation Conference (DAC). IEEE, 1\u20136.","author":"Nejatollahi Hamid","year":"2020","unstructured":"Hamid Nejatollahi, Saransh Gupta, Mohsen Imani, Tajana\u00a0Simunic Rosing, Rosario Cammarota, and Nikil Dutt. 2020. Cryptopim: In-memory Acceleration for Lattice-Based Cryptographic Hardware. In 2020 57th ACM\/IEEE Design Automation Conference (DAC). IEEE, 1\u20136."},{"volume-title":"The Fast Fourier Transform","author":"Nussbaumer J","key":"e_1_3_2_1_34_1","unstructured":"Henri\u00a0J Nussbaumer and Henri\u00a0J Nussbaumer. 1982. The Fast Fourier Transform. Springer."},{"key":"e_1_3_2_1_35_1","first-page":"93","article-title":"RM-NTT: An RRAM-Based Compute-in-Memory Number Theoretic Transform Accelerator","volume":"8","author":"Park Yongmo","year":"2022","unstructured":"Yongmo Park, Ziyu Wang, Sangmin Yoo, and Wei\u00a0D Lu. 2022. RM-NTT: An RRAM-Based Compute-in-Memory Number Theoretic Transform Accelerator. IEEE J. Explor 8, 2 (2022), 93\u2013101.","journal-title":"IEEE J. Explor"},{"key":"e_1_3_2_1_36_1","volume-title":"FFT-based Convolution Neural Network on Silicon Photonics Platform. In 2022 IEEE Photonics Conference (IPC). IEEE, 1\u20132.","author":"Peserico Nicola","year":"2022","unstructured":"Nicola Peserico, Russell Schwartz, Hangbo Yang, Xiaoxuan Ma, Mostafa Hosseini, Puneet Gupta, Hamed Dalir, and Volker\u00a0J Sorger. 2022. FFT-based Convolution Neural Network on Silicon Photonics Platform. In 2022 IEEE Photonics Conference (IPC). IEEE, 1\u20132."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480070"},{"key":"e_1_3_2_1_38_1","unstructured":"SEAL 2023. Microsoft SEAL (Release 4.1)."},{"key":"e_1_3_2_1_39_1","unstructured":"Ali Shafiee Anirban Nag Naveen Muralimanohar Rajeev Balasubramonian John\u00a0Paul Strachan Miao Hu R\u00a0Stanley Williams and Vivek Srikumar. [n. d.]. ISAAC: A Convolutional Neural Network Accelerator with in-Situ Analog Arithmetic in Crossbars. ACM SIGARCH Computer Architecture News ([n. d.])."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1038\/nphoton.2017.93"},{"key":"e_1_3_2_1_41_1","volume-title":"LEIA: A 2.05 Mm 2 140mW Lattice Encryption Instruction Accelerator in 40nm","author":"Song Shiming","year":"2018","unstructured":"Shiming Song, Wei Tang, Thomas Chen, and Zhengya Zhang. 2018. LEIA: A 2.05 Mm 2 140mW Lattice Encryption Instruction Accelerator in 40nm CMOS. In CICC. IEEE, 1\u20134."},{"key":"e_1_3_2_1_42_1","volume-title":"Single-Chip Microprocessor That Communicates Directly Using Light. Nature 528, 7583","author":"Sun Chen","year":"2015","unstructured":"Chen Sun, Mark\u00a0T Wade, Yunsup Lee, Jason\u00a0S Orcutt, Luca Alloatti, Michael\u00a0S Georgas, Andrew\u00a0S Waterman, Jeffrey\u00a0M Shainline, Rimas\u00a0R Avizienis, Sen Lin, 2015. Single-Chip Microprocessor That Communicates Directly Using Light. Nature 528, 7583 (2015), 534\u2013538."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/LPT.2022.3164456"},{"key":"e_1_3_2_1_44_1","volume-title":"60 dB High-Extinction Auto-Configured Mach\u2013Zehnder Interferometer. Optics letters 41, 22","author":"Wilkes M","year":"2016","unstructured":"Callum\u00a0M Wilkes, Xiaogang Qiang, Jianwei Wang, Raffaele Santagati, Stefano Paesani, Xiaoqi Zhou, David\u00a0AB Miller, Graham\u00a0D Marshall, Mark\u00a0G Thompson, and Jeremy\u00a0L O\u2019Brien. 2016. 60 dB High-Extinction Auto-Configured Mach\u2013Zehnder Interferometer. Optics letters 41, 22 (2016), 5318\u20135321."},{"volume-title":"Using Fermat Number Transform to Accelerate Convolutional Neural Network","author":"Xu Weihong","key":"e_1_3_2_1_45_1","unstructured":"Weihong Xu, Xiaohu You, and Chuan Zhang. 2017. Using Fermat Number Transform to Accelerate Convolutional Neural Network. In ASICON. IEEE, 1033\u20131036."},{"key":"e_1_3_2_1_46_1","volume-title":"11 TOPS Photonic Convolutional Accelerator for Optical Neural Networks. Nature 589, 7840","author":"Xu Xingyuan","year":"2021","unstructured":"Xingyuan Xu, Mengxi Tan, Bill Corcoran, Jiayang Wu, Andreas Boes, Thach\u00a0G Nguyen, Sai\u00a0T Chu, Brent\u00a0E Little, Damien\u00a0G Hicks, Roberto Morandotti, 2021. 11 TOPS Photonic Convolutional Accelerator for Optical Neural Networks. Nature 589, 7840 (2021), 44\u201351."},{"key":"e_1_3_2_1_47_1","volume-title":"Coherent Photonic Crossbar Arrays for Large-Scale Matrix-Matrix Multiplication","author":"Youngblood Nathan","year":"2022","unstructured":"Nathan Youngblood. 2022. Coherent Photonic Crossbar Arrays for Large-Scale Matrix-Matrix Multiplication. IEEE journal of selected topics in quantum electronics : a publication of the IEEE Lasers and Electro-optics Society 29 (2022), 1\u201311."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1002\/adom.202300215"},{"key":"e_1_3_2_1_49_1","volume-title":"Towards Efficient Hardware Implementation of NTT for Kyber on FPGAs. In 2021 IEEE International Symposium on Circuits and Systems (ISCAS). IEEE, 1\u20135.","author":"Zhang Cong","year":"2021","unstructured":"Cong Zhang, Dongsheng Liu, Xingjie Liu, Xuecheng Zou, Guangda Niu, Bo Liu, and Quming Jiang. 2021. Towards Efficient Hardware Implementation of NTT for Kyber on FPGAs. In 2021 IEEE International Symposium on Circuits and Systems (ISCAS). IEEE, 1\u20135."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1364\/OPTICA.446100"},{"volume-title":"Tensor-Product-Based Accelerator for Area-Efficient and Scalable Number Theoretic Transform","author":"Zhang Yuying","key":"e_1_3_2_1_51_1","unstructured":"Yuying Zhang, Sarveswara\u00a0Reddy Sathi, Zili Kou, Sharad Sinha, and Wei Zhang. 2023. Tensor-Product-Based Accelerator for Area-Efficient and Scalable Number Theoretic Transform. In FCCM. IEEE, 174\u2013183."},{"key":"e_1_3_2_1_52_1","volume-title":"End-to-End Optimization for a Compact Optical Neural Network Based on Nanostructured 2\u00d7 2 Optical Processors","author":"Zhao Caiyue","year":"2023","unstructured":"Caiyue Zhao, Jiguang Wang, Simei Mao, Xuanyi Liu, Wai Kin, Victor Chan, and HY Fu. 2023. End-to-End Optimization for a Compact Optical Neural Network Based on Nanostructured 2\u00d7 2 Optical Processors. IEEE Photonics Journal (2023)."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41377-022-00717-8"}],"event":{"name":"ICS '24: 2024 International Conference on Supercomputing","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture"],"location":"Kyoto Japan","acronym":"ICS '24"},"container-title":["Proceedings of the 38th ACM International Conference on Supercomputing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3650200.3656609","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3650200.3656609","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T15:23:50Z","timestamp":1755876230000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3650200.3656609"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,30]]},"references-count":53,"alternative-id":["10.1145\/3650200.3656609","10.1145\/3650200"],"URL":"https:\/\/doi.org\/10.1145\/3650200.3656609","relation":{},"subject":[],"published":{"date-parts":[[2024,5,30]]},"assertion":[{"value":"2024-06-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}