{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T23:17:07Z","timestamp":1780355827101,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","funder":[{"name":"National Natural Science Foundation of China for Distinguished Young Scholars","award":["62125208"],"award-info":[{"award-number":["62125208"]}]},{"name":"Strategic Priority Research Program of Chinese Academy of Sciences","award":["XDB0690100"],"award-info":[{"award-number":["XDB0690100"]}]},{"name":"National Key R&D Program of China","award":["2023YFB4503200"],"award-info":[{"award-number":["2023YFB4503200"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,21]]},"DOI":"10.1145\/3695053.3731407","type":"proceedings-article","created":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T16:43:11Z","timestamp":1750437791000},"page":"92-106","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["FAST:An FHE Accelerator for Scalable-parallelism with Tunable-bit"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-9160-8540","authenticated-orcid":false,"given":"Shengyu","family":"Fan","sequence":"first","affiliation":[{"name":"State Key Laboratory of Cyberspace Security Defense, Institute of Information Engineering, CAS, Beijing, China and School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2058-5109","authenticated-orcid":false,"given":"Xianglong","family":"Deng","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Cyberspace Security Defense, Institute of Information Engineering, CAS, Beijing, China and School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6031-4312","authenticated-orcid":false,"given":"Liang","family":"Kong","sequence":"additional","affiliation":[{"name":"Ant Group, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0663-0863","authenticated-orcid":false,"given":"Guiming","family":"Shi","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China and Ant Group, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5389-0823","authenticated-orcid":false,"given":"Guang","family":"Fan","sequence":"additional","affiliation":[{"name":"Ant Group, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9868-5353","authenticated-orcid":false,"given":"Dan","family":"Meng","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Cyberspace Security Defense, Institute of Information Engineering, CAS, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9215-7632","authenticated-orcid":false,"given":"Rui","family":"Hou","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Cyberspace Security Defense, Institute of Information Engineering, CAS, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6440-7550","authenticated-orcid":false,"given":"Mingzhe","family":"Zhang","sequence":"additional","affiliation":[{"name":"Ant Group, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,6,20]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/3605759.3625257"},{"key":"e_1_3_3_2_3_2","unstructured":"Rashmi Agrawal Anantha Chandrakasan and Ajay Joshi. [n. d.]. HEAP: A Fully Homomorphic Encryption Accelerator with Parallelized Bootstrapping. ([n. d.])."},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613424.3614302"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10070953"},{"key":"e_1_3_3_2_6_2","unstructured":"Aikata Aikata Ahmet\u00a0Can Mert Sunmin Kwon Maxim Deryabin and Sujoy\u00a0Sinha Roy. 2023. REED: Chiplet-based accelerator for fully homomorphic encryption. Cryptology ePrint Archive (2023)."},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-68382-4_12"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"crossref","unstructured":"V\u00e1clad\u00a0E Bene\u0161. 1964. Optimal rearrangeable multistage connecting networks. Bell system technical journal 43 4 (1964) 1641\u20131656.","DOI":"10.1002\/j.1538-7305.1964.tb04103.x"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-77870-5_21"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/2554797.2554799"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3319535.3363207"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-10970-7_16"},{"key":"e_1_3_3_2_13_2","unstructured":"Austin Ebel Karthik Garimella and Brandon Reagen. 2023. Orion: A Fully Homomorphic Encryption Compiler for Private Deep Neural Network Inference. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2311.03470 (2023)."},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071017"},{"key":"e_1_3_3_2_15_2","volume-title":"SPSL: Secure and Private Systems for Machine Learning (ISCA Workshop)","author":"Gener Serhan","year":"2021","unstructured":"Serhan Gener, Parker Newton, Daniel Tan, Silas Richelson, Guy Lemieux, and Philip Brisk. 2021. An fpga-based programmable vector engine for fast fully homomorphic encryption over the torus. In SPSL: Secure and Private Systems for Machine Learning (ISCA Workshop)."},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019466"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-40186-3_16"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"crossref","unstructured":"Intak Hwang Jinyeong Seo and Yongsoo Song. 2023. Optimizing HE operations via Level-aware Key-switching Framework. Cryptology ePrint Archive (2023).","DOI":"10.1145\/3605759.3625263"},{"key":"e_1_3_3_2_19_2","unstructured":"Shutong Jin Zhen Gu Guangyan Li Donglong Chen Cetin\u00a0Kaya Ko\u00e7 Ray\u00a0CC Cheung and Wangchen Dai. 2024. Efficient Key-Switching for Word-Type FHE and GPU Acceleration. Cryptology ePrint Archive (2024)."},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"crossref","unstructured":"Wonkyung Jung Sangpyo Kim Jung\u00a0Ho Ahn Jung\u00a0Hee Cheon and Younho Lee. 2021. Over 100x faster bootstrapping in fully homomorphic encryption through memory-centric optimization with gpus. IACR Transactions on Cryptographic Hardware and Embedded Systems (2021) 114\u2013148.","DOI":"10.46586\/tches.v2021.i4.114-148"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589053"},{"key":"e_1_3_3_2_22_2","unstructured":"Jongmin Kim Gwangho Lee Sangpyo Kim Gina Sohn John Kim Minsoo Rhu and Jung\u00a0Ho Ahn. 2022. ARK: Fully Homomorphic Encryption Accelerator with Runtime Data Generation and Inter-Operation Key Reuse. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2205.00922 (2022)."},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-38551-3_3"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527415"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"crossref","unstructured":"Shiann-Rong Kuang and Jiun-Ping Wang. 2009. Design of power-efficient configurable booth multiplier. IEEE Transactions on Circuits and Systems I: Regular Papers 57 3 (2009) 568\u2013580.","DOI":"10.1109\/TCSI.2009.2023763"},{"key":"e_1_3_3_2_26_2","first-page":"12403","volume-title":"International Conference on Machine Learning (ICML)","author":"Lee Eunsang","year":"2022","unstructured":"Eunsang Lee, Joon-Woo Lee, Junghyun Lee, Young-Sik Kim, Yongjune Kim, Jong-Seon No, and Woosuk Choi. 2022. Low-Complexity Deep Convolutional Neural Networks on Fully Homomorphic Encryption Using Multiplexed Parallel Convolutions.. In International Conference on Machine Learning (ICML). 12403\u201312422."},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"crossref","unstructured":"Joon-Woo Lee HyungChul Kang Yongwoo Lee Woosuk Choi Jieun Eom Maxim Deryabin Eunsang Lee Junghyun Lee Donghoon Yoo Young-Sik Kim et\u00a0al. 2022. Privacy-preserving machine learning with fully homomorphic encryption for deep neural network. IEEE Access 10 (2022) 30039\u201330054.","DOI":"10.1109\/ACCESS.2022.3159694"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3617232.3624870"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-06944-4_19"},{"key":"e_1_3_3_2_30_2","unstructured":"Qian Lou Bo Feng Geoffrey Charles\u00a0Fox and Lei Jiang. 2020. Glyph: Fast and accurately training deep neural networks on encrypted data. Advances in neural information processing systems 33 (2020) 9193\u20139202."},{"key":"e_1_3_3_2_31_2","first-page":"7102","volume-title":"International conference on machine learning","author":"Lou Qian","year":"2021","unstructured":"Qian Lou and Lei Jiang. 2021. Hemet: A homomorphic-encryption-friendly privacy-preserving mobile neural network architecture. In International conference on machine learning. PMLR, 7102\u20137110."},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-61489-7_6"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3508352.3549413"},{"key":"e_1_3_3_2_34_2","unstructured":"Jaiyoung Park Michael\u00a0Jaemin Kim Wonkyung Jung and Jung\u00a0Ho Ahn. 2022. AESPA: Accuracy preserving low-degree polynomial activation for fast private inference. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2201.06699 (2022)."},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"crossref","unstructured":"Adiwena Putra Yi Chen John Kim Joo-Young Kim et\u00a0al. 2023. Strix: An End-to-End Streaming Architecture with Two-Level Ciphertext Batching for Fully Homomorphic Encryption with Programmable Bootstrapping. arXiv e-prints (2023) arXiv\u20132305.","DOI":"10.1145\/3613424.3614264"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00013"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378523"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"crossref","unstructured":"Lorenzo Rovida and Alberto Leporati. 2024. Encrypted image classification with low memory footprint using fully homomorphic encryption. Cryptology ePrint Archive (2024).","DOI":"10.1142\/S0129065724500254"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/3643651.3659893"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480070"},{"key":"e_1_3_3_2_41_2","first-page":"173","volume-title":"ISCA","author":"Samardzic Nikola","year":"2022","unstructured":"Nikola Samardzic, Axel Feldmann, Aleksandar Krastev, Nathan Manohar, Nicholas Genise, Srinivas Devadas, Karim Eldefrawy, Chris Peikert, and Daniel Sanchez. 2022. CraterLake: a hardware accelerator for efficient unbounded computation on encrypted data.. In ISCA. 173\u2013187."},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640397"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"crossref","unstructured":"Kaustubh Shivdikar Yuhui Bao Rashmi Agrawal Michael Shen Gilbert Jonatan Evelio Mora Alexander Ingare Neal Livesay Jos\u00e9\u00a0L Abell\u00e1n John Kim et\u00a0al. 2023. GME: GPU-based Microarchitectural Extensions to Accelerate Homomorphic Encryption. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2309.11001 (2023).","DOI":"10.1145\/3613424.3614279"},{"key":"e_1_3_3_2_44_2","volume-title":"CACTI 5.1","author":"Thoziyoor Shyamkumar","year":"2008","unstructured":"Shyamkumar Thoziyoor, Naveen Muralimanohar, Jung\u00a0Ho Ahn, and Norman\u00a0P Jouppi. 2008. CACTI 5.1. Technical Report. Technical Report HPL-2008-20, HP Labs."},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"crossref","unstructured":"Qipeng Xie Siyang Jiang Linshan Jiang Yongzhi Huang Zhihe Zhao Salabat Khan Wangchen Dai Zhe Liu and Kaishun Wu. 2024. Efficiency optimization techniques in privacy-preserving federated learning with homomorphic encryption: A brief survey. IEEE Internet of Things Journal 11 14 (2024) 24569\u201324580.","DOI":"10.1109\/JIOT.2024.3382875"},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10070984"},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC55821.2022.9926381"},{"key":"e_1_3_3_2_48_2","first-page":"493","volume-title":"2020 USENIX annual technical conference (USENIX ATC 20)","author":"Zhang Chengliang","year":"2020","unstructured":"Chengliang Zhang, Suyi Li, Junzhe Xia, Wei Wang, Feng Yan, and Yang Liu. 2020. { BatchCrypt} : Efficient homomorphic encryption for { Cross-Silo} federated learning. In 2020 USENIX annual technical conference (USENIX ATC 20). 493\u2013506."},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"crossref","unstructured":"Peng Zhang Teng Huang Xiaoqiang Sun Wei Zhao Hongwei Liu Shangqi Lai and Joseph\u00a0K Liu. 2022. Privacy-preserving and outsourced multi-party k-means clustering based on multi-key fully homomorphic encryption. IEEE Transactions on Dependable and Secure Computing 20 3 (2022) 2348\u20132359.","DOI":"10.1109\/TDSC.2022.3181667"}],"event":{"name":"ISCA '25: Proceedings of the 52nd Annual International Symposium on Computer Architecture","location":"Tokyo Japan","acronym":"SIGARCH '25","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 52nd Annual International Symposium on Computer Architecture"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3695053.3731407","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,21]],"date-time":"2025-06-21T11:07:05Z","timestamp":1750504025000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3695053.3731407"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,20]]},"references-count":48,"alternative-id":["10.1145\/3695053.3731407","10.1145\/3695053"],"URL":"https:\/\/doi.org\/10.1145\/3695053.3731407","relation":{},"subject":[],"published":{"date-parts":[[2025,6,20]]},"assertion":[{"value":"2025-06-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}