{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T06:00:51Z","timestamp":1769839251577,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":49,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62302477"],"award-info":[{"award-number":["62302477"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,8]]},"DOI":"10.1145\/3721145.3729517","type":"proceedings-article","created":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T12:57:17Z","timestamp":1755867437000},"page":"1092-1105","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["JBSA: A Bit-Serial Accelerator for Deep Neural Networks Using Superconducting SFQ Logic"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-8895-9630","authenticated-orcid":false,"given":"Yang","family":"Su","sequence":"first","affiliation":[{"name":"ShanghaiTech University, Shanghai, China; Shanghai Innovation Center for Processor Technologies, Shanghai, China, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9533-2173","authenticated-orcid":false,"given":"Sheng","family":"Li","sequence":"additional","affiliation":[{"name":"ShanghaiTech University, Shanghai, China; Shanghai Innovation Center for Processor Technologies, Shanghai, China, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3649-8977","authenticated-orcid":false,"given":"Huilong","family":"Jiang","sequence":"additional","affiliation":[{"name":"State Key Lab of Processors, Institute of Computing Technology, CAS, Beijing, China, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8014-6356","authenticated-orcid":false,"given":"Haofei","family":"Yin","sequence":"additional","affiliation":[{"name":"ShanghaiTech University, Shanghai, China; Shanghai Innovation Center for Processor Technologies, Shanghai, China, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3744-2083","authenticated-orcid":false,"given":"Rongliang","family":"Fu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5845-6965","authenticated-orcid":false,"given":"Junying","family":"Huang","sequence":"additional","affiliation":[{"name":"State Key Lab of Processors, Institute of Computing Technology, CAS, Beijing, China, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4598-1685","authenticated-orcid":false,"given":"Xiaochun","family":"Ye","sequence":"additional","affiliation":[{"name":"State Key Lab of Processors, Institute of Computing Technology, CAS, Beijing, China, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8778-7149","authenticated-orcid":false,"given":"Zhimin","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Lab of Processors, Institute of Computing Technology, CAS, Beijing, China, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2679-7236","authenticated-orcid":false,"given":"Jie","family":"Ren","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Functional Materials for Informatics, Shanghai Institute of Microsystem and Information Technology, CAS, Shanghai, China; University of Chinese Academy of Sciences , Beijing, China, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4190-9080","authenticated-orcid":false,"given":"Xiaoping","family":"Gao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Functional Materials for Informatics, Shanghai Institute of Microsystem and Information Technology, CAS, Shanghai, China, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7348-5625","authenticated-orcid":false,"given":"Tsung-Yi","family":"Ho","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5219-0908","authenticated-orcid":false,"given":"Dongrui","family":"Fan","sequence":"additional","affiliation":[{"name":"State Key Lab of Processors, Institute of Computing Technology, CAS, Beijing, China; University of Chinese Academy of Sciences, Beijing, China, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2025,8,22]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3123982"},{"key":"e_1_3_3_2_3_2","unstructured":"Paul Alcorn. 2017. Hot Chips 2017: A Closer Look At Google\u2019s TPU v2. http:\/\/www.tomshardware.com\/news\/tpu-v2-google-machine-learning 35370.html."},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","unstructured":"Giorgos Armeniakos Georgios Zervakis Dimitrios Soudris and J\u00f6rg Henkel. 2022. Hardware Approximate Techniques for Deep Neural Network Accelerators: A Survey. Comput. Surveys 55 4 Article 83 (2022) 36\u00a0pages. 10.1145\/3527156","DOI":"10.1145\/3527156"},{"key":"e_1_3_3_2_5_2","unstructured":"Parhami Behrooz. 2000. Computer Arithmetic: Algorithms and Hardware Designs. Oxford University Press 19 (2000) 512583\u2013512585."},{"key":"e_1_3_3_2_6_2","unstructured":"Ali Bozbey Mustafa\u00a0Altay Karamuftuoglu Sasan Razmkhah and Murat Ozbayoglu. 2020. Single Flux Quantum Based Ultrahigh Speed Spiking Neuromorphic Processor Architecture. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1812.10354 (2020)."},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00037"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322270"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","unstructured":"Ke Chen Yue Gao Haroon Waris Weiqiang Liu and Fabrizio Lombardi. 2023. Approximate Softmax Functions for Energy-Efficient Deep Neural Networks. IEEE Transactions on Very Large Scale Integration Systems (TVLSI) 31 1 (2023) 4\u201316. 10.1109\/TVLSI.2022.3224011","DOI":"10.1109\/TVLSI.2022.3224011"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","unstructured":"Ran Cheng Uday\u00a0S. Goteti and Michael\u00a0C. Hamilton. 2019. Superconducting Neuromorphic Computing Using Quantum Phase-Slip Junctions. IEEE Transactions on Applied Superconductivity 29 5 (2019) 1\u20135. 10.1109\/TASC.2019.2892111","DOI":"10.1109\/TASC.2019.2892111"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","unstructured":"Mohammed\u00a0E. Elbtity Peyton\u00a0S. Chandarana Brendan Reidy Jason\u00a0K. Eshraghian and Ramtin Zand. 2022. APTPU: Approximate Computing Based Tensor Processing Unit. IEEE Transactions on Circuits and Systems I: Regular Papers 69 12 (2022) 5135\u20135146. 10.1109\/TCSI.2022.3206262","DOI":"10.1109\/TCSI.2022.3206262"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","unstructured":"Rongliang Fu Junying Huang Haibin Wu Xiaochun Ye Dongrui Fan and Tsung-Yi Ho. 2022. JBNN: A Hardware Design for Binarized Neural Networks Using Single-Flux-Quantum Circuits. IEEE Trans. Comput. 71 12 (2022) 3203\u20133214. 10.1109\/TC.2022.3215085","DOI":"10.1109\/TC.2022.3215085"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","unstructured":"Kris Gaj Eby\u00a0G Friedman and Marc\u00a0J Feldman. 1997. Timing of Multi-Gigahertz Rapid Single Flux Quantum Digital Circuits. Journal of VLSI Signal Processing Systems for Signal Image and Video Technology 16 (1997) 247\u2013276. 10.1023\/A:1007903527533","DOI":"10.1023\/A:1007903527533"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","unstructured":"Xiaoping Gao Qi Qiao Mingliang Wang Minghui Niu Huanli Liu Masaaki Maezawa Jie Ren and Zhen Wang. 2021. Design and verification of SFQ cell library for superconducting LSI digital circuits. IEEE Transactions on Applied Superconductivity 31 5 (2021) 1\u20135. 10.1109\/TASC.2021.3062570","DOI":"10.1109\/TASC.2021.3062570"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507765"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","unstructured":"D\u00a0Scott Holmes Andrew\u00a0L Ripple and Marc\u00a0A Manheimer. 2013. Energy-Efficient Superconducting Computing\u2014Power Budgets and Requirements. IEEE Transactions on Applied Superconductivity 23 3 (2013) 1701610\u20131701610. 10.1109\/TASC.2013.2244634","DOI":"10.1109\/TASC.2013.2244634"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","unstructured":"Junying Huang Rongliang Fu Xiaochun Ye and Dongrui Fan. 2022. A survey on superconducting computing technology: circuits architectures and design tools. CCF Transactions on High Performance Computing 4 (2022) 1\u201322. 10.1007\/s42514-022-00089-w","DOI":"10.1007\/s42514-022-00089-w"},{"key":"e_1_3_3_2_18_2","unstructured":"HPCS\u00a0Lab in Seoul National\u00a0University. 2023. CryoModel. https:\/\/github.com\/SNU-HPCS\/CryoModel."},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00018"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783722"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322219"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","unstructured":"Jinmook Lee Changhyeon Kim Sanghoon Kang Dongjoo Shin Sangyeob Kim and Hoi-Jun Yoo. 2019. UNPU: An Energy-Efficient Deep Neural Network Accelerator With Fully Variable Weight Bit Precision. IEEE Journal of Solid-State Circuits 54 1 (2019) 173\u2013185. 10.1109\/JSSC.2018.2865489","DOI":"10.1109\/JSSC.2018.2865489"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00066"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","unstructured":"K.K. Likharev and V.K. Semenov. 1991. RSFQ Logic\/Memory Family: A New Josephson-Junction Technology for Sub-Terahertz-Clock-Frequency Digital Systems. IEEE Transactions on Applied Superconductivity 1 1 (1991) 3\u201328. 10.1109\/77.80745","DOI":"10.1109\/77.80745"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071036"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/NEWCAS.2018.8585656"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","unstructured":"Oleg\u00a0A. Mukhanov. 2011. Energy-Efficient Single Flux Quantum Technology. IEEE Transactions on Applied Superconductivity 21 3 (2011) 760\u2013769. 10.1109\/TASC.2010.2096792","DOI":"10.1109\/TASC.2010.2096792"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","unstructured":"Thomas Ortlepp Olaf Wetzstein Sonja Engert Juergen Kunert and Hannes Toepfer. 2011. Reduced Power Consumption in Superconducting Electronics. IEEE Transactions on Applied Superconductivity 21 3 (2011) 770\u2013775. 10.1109\/TASC.2011.2117410","DOI":"10.1109\/TASC.2011.2117410"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","unstructured":"S.V. Polonsky V.K. Semenov and A.F. Kirichenko. 1994. Single Flux Quantum B Flip-Flop and Its Possible Applications. IEEE Transactions on Applied Superconductivity 4 1 (1994) 9\u201318. 10.1109\/77.273059","DOI":"10.1109\/77.273059"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/iQ-CCHESS56596.2023.10391745"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","unstructured":"Nitin Rathi Indranil Chakraborty Adarsh Kosta Abhronil Sengupta Aayush Ankit Priyadarshini Panda and Kaushik Roy. 2023. Exploring Neuromorphic Computing Based on Spiking Neural Networks: Algorithms to Hardware. Comput. Surveys 55 12 Article 243 (mar 2023) 49\u00a0pages. 10.1145\/3571155","DOI":"10.1145\/3571155"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","unstructured":"Wojciech Romaszkan Tianmu Li and Puneet Gupta. 2022. SASCHA\u2014Sparsity-Aware Stochastic Computing Hardware Architecture for Neural Network Acceleration. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD) 41 11 (2022) 4169\u20134180. 10.1109\/TCAD.2022.3197503","DOI":"10.1109\/TCAD.2022.3197503"},{"key":"e_1_3_3_2_33_2","unstructured":"Ananda Samajdar Yuhao Zhu Paul Whatmough Matthew Mattina and Tushar Krishna. 2018. SCALE-Sim: Systolic CNN Accelerator Simulator. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1811.02883 (2018)."},{"key":"e_1_3_3_2_34_2","unstructured":"L. Schindler and T. Hall. 2023. ColdFlux RSFQ Logic Cell Library for MIT-LL SFQ Process. https:\/\/github.com\/sunmagnetics\/RSFQlib. Version: 3.0."},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","unstructured":"Michael Schneider Emily Toomey Graham Rowlands Jeff Shainline Paul Tschirhart and Ken Segall. 2022. SuperMind: a survey of the potential of superconducting electronics for neuromorphic computing. Superconductor Science and Technology 35 5 (2022) 053001. 10.1088\/1361-6668\/ac4cd2","DOI":"10.1088\/1361-6668\/ac4cd2"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRC.2017.8123634"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/DAC.2018.8465915"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","unstructured":"Ourania Spantidi Georgios Zervakis Iraklis Anagnostopoulos and J\u00f6rg Henkel. 2022. Energy-Efficient DNN Inference on Approximate Accelerators Through Formal Property Exploration. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD) 41 11 (2022) 3838\u20133849. 10.1109\/TCAD.2022.3197522","DOI":"10.1109\/TCAD.2022.3197522"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","unstructured":"Guang-Ming Tang Kensuke Takata Masamitsu Tanaka Akira Fujimaki Kazuyoshi Takagi and Naofumi Takagi. 2015. 4-bit Bit-Slice Arithmetic Logic Unit for 32-bit RSFQ Microprocessors. IEEE Transactions on Applied Superconductivity 26 1 (2015) 1\u20136. 10.1109\/TASC.2015.2507125","DOI":"10.1109\/TASC.2015.2507125"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378517"},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"publisher","unstructured":"Georgios Tzimpragos Jennifer Volk Dilip Vasudevan Nestan Tsiskaridze George Michelogiannakis Advait Madhavan John Shalf and Timothy Sherwood. 2021. Temporal Computing With Superconductors. IEEE Micro 41 3 (2021) 71\u201379. 10.1109\/MM.2021.3066377","DOI":"10.1109\/MM.2021.3066377"},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","unstructured":"Yaman Umuroglu Davide Conficconi Lahiru Rasnayake Thomas\u00a0B Preusser and Magnus Sj\u00e4lander. 2019. Optimizing Bit-Serial Matrix Multiplication for Reconfigurable Computing. ACM Transactions on Reconfigurable Technology and Systems (TRETS) 12 3 (2019) 1\u201324. 10.1145\/3337929","DOI":"10.1145\/3337929"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00040"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00010"},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"publisher","unstructured":"Wm\u00a0A Wulf and Sally\u00a0A McKee. 1995. Hitting the Memory Wall: Implications of the Obvious. ACM SIGARCH Computer Architecture News 23 1 (1995) 20\u201324. 10.1145\/216585.216588","DOI":"10.1145\/216585.216588"},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00038"},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"publisher","unstructured":"Huilin Zhang Chen Gang Chen Xu Guoliang Gong and Huaxiang Lu. 2023. Brain-Inspired Spiking Neural Network Using Superconducting Devices. IEEE Transactions on Emerging Topics in Computational Intelligence 7 1 (2023) 271\u2013277. 10.1109\/TETCI.2021.3089328","DOI":"10.1109\/TETCI.2021.3089328"},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"publisher","unstructured":"Jiadi Zhu Teng Zhang Yuchao Yang and Ru Huang. 2020. A comprehensive review on emerging artificial neuromorphic devices. Applied Physics Reviews 7 1 (2020) 011312. 10.1063\/1.5118217","DOI":"10.1063\/1.5118217"},{"key":"e_1_3_3_2_49_2","unstructured":"D. Zinoviev P. Bunyk A. Rylyakov K. Likharev and P. Litskevitch. 2023. SUNY RSFQ Cell Library. http:\/\/www.physics.sunysb.edu\/Physics\/RSFQ\/Lib\/index.html."},{"key":"e_1_3_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480041"}],"event":{"name":"ICS '25: 2025 International Conference on Supercomputing","location":"Salt Lake City USA","acronym":"ICS '25","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 39th ACM International Conference on Supercomputing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3721145.3729517","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T12:57:40Z","timestamp":1755867460000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3721145.3729517"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,8]]},"references-count":49,"alternative-id":["10.1145\/3721145.3729517","10.1145\/3721145"],"URL":"https:\/\/doi.org\/10.1145\/3721145.3729517","relation":{},"subject":[],"published":{"date-parts":[[2025,6,8]]},"assertion":[{"value":"2025-08-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}