{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T08:03:02Z","timestamp":1776931382758,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T00:00:00Z","timestamp":1760659200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["1127353"],"award-info":[{"award-number":["1127353"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000015","name":"DOE U.S. Department of Energy","doi-asserted-by":"publisher","award":["DE-FOA-0002460, DE-SC0025645"],"award-info":[{"award-number":["DE-FOA-0002460, DE-SC0025645"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000185","name":"Defense Advanced Research Projects Agency","doi-asserted-by":"publisher","award":["JUMP 2.0"],"award-info":[{"award-number":["JUMP 2.0"]}],"id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,18]]},"DOI":"10.1145\/3725843.3756120","type":"proceedings-article","created":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T17:19:56Z","timestamp":1760721596000},"page":"1704-1718","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Towards Closing the Performance Gap for Cryptographic Kernels Between CPUs and Specialized Hardware"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-0190-4041","authenticated-orcid":false,"given":"Naifeng","family":"Zhang","sequence":"first","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2358-3336","authenticated-orcid":false,"given":"Sophia","family":"Fu","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3529-8973","authenticated-orcid":false,"given":"Franz","family":"Franchetti","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,17]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/3560827.3563379"},{"key":"e_1_3_3_2_3_2","unstructured":"Ahmad Al\u00a0Badawi and Yuriy Polyakov. 2023. Demystifying bootstrapping in fully homomorphic encryption. Cryptology ePrint Archive (2023)."},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-47721-7_24"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"crossref","unstructured":"Nathan Binkert Bradford Beckmann Gabriel Black Steven\u00a0K Reinhardt Ali Saidi Arkaprava Basu Joel Hestness Derek\u00a0R Hower Tushar Krishna Somayeh Sardashti et\u00a0al. 2011. The gem5 simulator. ACM SIGARCH computer architecture news 39 2 (2011) 1\u20137.","DOI":"10.1145\/2024716.2024718"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","unstructured":"L\u00a0Susan Blackford Antoine Petitet Roldan Pozo Karin Remington R\u00a0Clint Whaley James Demmel Jack Dongarra Iain Duff Sven Hammarling Greg Henry et\u00a0al. 2002. An updated set of basic linear algebra subprograms (BLAS). ACM Trans. Math. Software 28 2 (2002) 135\u2013151. 10.1145\/567806.567807","DOI":"10.1145\/567806.567807"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3474366.3486926"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-70278-0_1"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-70694-8_15"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","unstructured":"Ilaria Chillotti Nicolas Gama Mariya Georgieva and Malika Izabach\u00e8ne. 2020. TFHE: fast fully homomorphic encryption over the torus. Journal of Cryptology 33 1 (2020) 34\u201391. 10.1007\/s00145-019-09319-x","DOI":"10.1007\/s00145-019-09319-x"},{"key":"e_1_3_3_2_11_2","unstructured":"George Chrysos. 2014. Intel\u00ae xeon phi\u2122 coprocessor-the architecture. Intel Whitepaper 176 2014 (2014) 43\u201350."},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3656019.3676898"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/PACT52795.2021.00032"},{"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","doi-asserted-by":"publisher","unstructured":"Franz Franchetti Tze\u00a0Meng Low Doru\u00a0Thom Popovici Richard\u00a0M Veras Daniele\u00a0G Spampinato Jeremy\u00a0R Johnson Markus P\u00fcschel James\u00a0C Hoe and Jos\u00e9\u00a0MF Moura. 2018. SPIRAL: Extreme performance portability. Proc. IEEE 106 11 (2018) 1935\u20131968. 10.1109\/JPROC.2018.2873289","DOI":"10.1109\/JPROC.2018.2873289"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"crossref","unstructured":"Franz Franchetti Markus Puschel Yevgen Voronenko Srinivas Chellappa and Jos\u00e9\u00a0MF Moura. 2009. Discrete Fourier transform on multicore. IEEE Signal Processing Magazine 26 6 (2009) 90\u2013102.","DOI":"10.1109\/MSP.2009.934155"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2006.31"},{"key":"e_1_3_3_2_18_2","volume-title":"2024 33th International Conference on Parallel Architectures and Compilation Techniques (PACT)","author":"Fu Sophia","year":"2024","unstructured":"Sophia Fu, Naifeng Zhang, and Franz Franchetti. 2024. Accelerating High-Precision Number Theoretic Transforms using Intel AVX-512. In 2024 33th International Conference on Parallel Architectures and Compilation Techniques (PACT)."},{"key":"e_1_3_3_2_19_2","unstructured":"Torbj\u00f6rn Granlund. 1996. Gnu mp. The GNU Multiple Precision Arithmetic Library 2 2 (1996)."},{"key":"e_1_3_3_2_20_2","unstructured":"Shai Halevi. 2021. HElib (version 2.1.0). https:\/\/github.com\/homenc\/HElib"},{"key":"e_1_3_3_2_21_2","unstructured":"Mike Hamburg. 2015. Ed448-Goldilocks a new elliptic curve. Cryptology ePrint Archive (2015)."},{"key":"e_1_3_3_2_22_2","unstructured":"William\u00a0B Hart. 2013. Flint: Fast library for number theory. Computeralgebra Rundbrief (2013)."},{"key":"e_1_3_3_2_23_2","unstructured":"Intel. 2023. Intel\u00ae 64 and ia-32 architectures optimization reference manual. 1 (2023) 1\u2013857."},{"key":"e_1_3_3_2_24_2","volume-title":"Intel Intrinsics Guide v3.1","author":"Corporation Intel","year":"2013","unstructured":"Intel Corporation. 2013. Intel Intrinsics Guide v3.1. https:\/\/www.intel.com\/content\/www\/us\/en\/docs\/intrinsics-guide\/index.html Version 3.1."},{"key":"e_1_3_3_2_25_2","unstructured":"Siddharth Jayashankar Edward Chen Tom Tang Wenting Zheng and Dimitrios Skarlatos. 2024. Cinnamon: A Framework For Scale-Out Encrypted AI. (2024)."},{"key":"e_1_3_3_2_26_2","first-page":"293","volume-title":"Doklady Akademii Nauk","author":"Karatsuba Anatolii\u00a0Alekseevich","year":"1962","unstructured":"Anatolii\u00a0Alekseevich Karatsuba and Yu\u00a0P Ofman. 1962. Multiplication of many-digital numbers by automatic computers. In Doklady Akademii Nauk , Vol.\u00a0145. Russian Academy of Sciences, 293\u2013294."},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC50251.2020.00033"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"crossref","unstructured":"Seungmin Lee Youngsok Kim Dukyun Nam and Jong Kim. 2024. Gem5-AVX: Extension of the Gem5 Simulator to Support AVX Instruction Sets. IEEE Access 12 (2024) 20767\u201320778.","DOI":"10.1109\/ACCESS.2024.3359296"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","unstructured":"Neal Livesay Gilbert Jonatan Evelio Mora Kaustubh Shivdikar Rashmi Agrawal Ajay Joshi Jos\u00e9\u00a0L Abell\u00e1n John Kim and David Kaeli. 2023. Accelerating finite field arithmetic for homomorphic encryption on GPUs. IEEE Micro 43 5 (2023) 55\u201363. 10.1109\/MM.2023.3253052","DOI":"10.1109\/MM.2023.3253052"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48965-0_8"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/1995896.1995938"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.23919\/DATE56975.2023.10137020"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","unstructured":"Ali\u00a0\u015eah \u00d6zcan Can Ayduman Enes\u00a0Recep T\u00fcrko\u011flu and Erkay Sava\u015f. 2023. Homomorphic encryption on GPU. IEEE Access 11 (2023) 84168\u201384186. 10.1109\/ACCESS.2023.3265583","DOI":"10.1109\/ACCESS.2023.3265583"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","unstructured":"\u00d6zg\u00fcn \u00d6zerk Can Elgezen Ahmet\u00a0Can Mert Erdin\u00e7 \u00d6zt\u00fcrk and Erkay Sava\u015f. 2022. Efficient number theoretic transform implementation on GPU for homomorphic encryption. The Journal of Supercomputing 78 2 (2022) 2840\u20132872. 10.1007\/s11227-021-03980-5","DOI":"10.1007\/s11227-021-03980-5"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"crossref","unstructured":"Marshall\u00a0C Pease. 1968. An adaptation of the fast Fourier transform for parallel processing. Journal of the ACM (JACM) 15 2 (1968) 252\u2013264.","DOI":"10.1145\/321450.321457"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480070"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527393"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"crossref","unstructured":"Daniel Sanchez and Christos Kozyrakis. 2013. ZSim: Fast and accurate microarchitectural simulation of thousand-core systems. ACM SIGARCH Computer architecture news 41 3 (2013) 475\u2013486.","DOI":"10.1145\/2508148.2485963"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"crossref","unstructured":"Larry Seiler Doug Carmean Eric Sprangle Tom Forsyth Michael Abrash Pradeep Dubey Stephen Junkins Adam Lake Jeremy Sugerman Robert Cavin et\u00a0al. 2008. Larrabee: a many-core x86 architecture for visual computing. ACM Transactions on Graphics (TOG) 27 3 (2008) 1\u201315.","DOI":"10.1145\/1360612.1360617"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613424.3614279"},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/SEED55351.2022.00013"},{"key":"e_1_3_3_2_42_2","unstructured":"Victor Shoup et\u00a0al. 2001. NTL: A library for doing number theory. (2001)."},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS57527.2023.00034"},{"key":"e_1_3_3_2_44_2","unstructured":"Joris van\u00a0der Hoeven and Gr\u00e9goire Lecerf. 2024. Implementing number theoretic transforms. (2024)."},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-17143-7_25"},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD57390.2023.10323744"},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"publisher","unstructured":"Zhiwei Wang Peinan Li Rui Hou Zhihao Li Jiangfeng Cao XiaoFeng Wang and Dan Meng. 2023. HE-Booster: an efficient polynomial arithmetic acceleration on GPUs for fully homomorphic encryption. IEEE Transactions on Parallel and Distributed Systems 34 4 (2023) 1067\u20131081. 10.1109\/TPDS.2022.3228628","DOI":"10.1109\/TPDS.2022.3228628"},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD58817.2023.00061"},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"crossref","unstructured":"Samuel Williams Andrew Waterman and David Patterson. 2009. Roofline: an insightful visual performance model for multicore architectures. Commun. ACM 52 4 (2009) 65\u201376.","DOI":"10.1145\/1498765.1498785"},{"key":"e_1_3_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC58863.2023.10363559"},{"key":"e_1_3_3_2_51_2","volume-title":"2023 IEEE\/ACM International Symposium on Code Generation and Optimization (CGO)","author":"Zhang Naifeng","year":"2023","unstructured":"Naifeng Zhang and Franz Franchetti. 2023. Generating number theoretic transforms for multi-word integer data types. In 2023 IEEE\/ACM International Symposium on Code Generation and Optimization (CGO)."},{"key":"e_1_3_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1145\/3696443.3708948"},{"key":"e_1_3_3_2_53_2","unstructured":"Sean Zhang. 2022. Extending gem5 to Support AVX Instructions. https:\/\/seanzw.github.io\/posts\/gem5-avx\/."},{"key":"e_1_3_3_2_54_2","doi-asserted-by":"publisher","unstructured":"Hao Zhou Changxu Liu Lan Yang Li Shang and Fan Yang. 2024. A Fully Pipelined Reconfigurable Montgomery Modular Multiplier Supporting Variable Bit-Widths. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (2024). 10.1109\/TCAD.2024.3410847","DOI":"10.1109\/TCAD.2024.3410847"}],"event":{"name":"MICRO 2025: 58th IEEE\/ACM International Symposium on Microarchitecture","location":"Seoul Korea","acronym":"MICRO 2025","sponsor":["SIGMICRO ACM Special Interest Group on Microarchitectural Research and Processing"]},"container-title":["Proceedings of the 58th IEEE\/ACM International Symposium on Microarchitecture"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3725843.3756120","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3725843.3756120","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T21:46:42Z","timestamp":1769464002000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3725843.3756120"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,17]]},"references-count":53,"alternative-id":["10.1145\/3725843.3756120","10.1145\/3725843"],"URL":"https:\/\/doi.org\/10.1145\/3725843.3756120","relation":{},"subject":[],"published":{"date-parts":[[2025,10,17]]},"assertion":[{"value":"2025-10-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}