{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T12:02:34Z","timestamp":1767960154128,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":31,"publisher":"ACM","funder":[{"name":"Japan Society for the Promotion of Science KAKENHI","award":["JP25K15134"],"award-info":[{"award-number":["JP25K15134"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,1,26]]},"DOI":"10.1145\/3773656.3773673","type":"proceedings-article","created":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T10:22:11Z","timestamp":1767954131000},"page":"142-152","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Improved Implementation of Number Theoretic Transform on NVIDIA GPU with Tensor Cores"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7349-1491","authenticated-orcid":false,"given":"Yukimasa","family":"Sugizaki","sequence":"first","affiliation":[{"name":"Graduate School of Science and Technology, University of Tsukuba, Tsukuba, Ibaraki, Japan and Secure System Platform Research Laboratories, NEC Corporation, Minato, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1357-5770","authenticated-orcid":false,"given":"Daisuke","family":"Takahashi","sequence":"additional","affiliation":[{"name":"Center for Computational Sciences, University of Tsukuba, Tsukuba, Ibaraki, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,1,25]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"Amazon Web Services. [n. d.]. Trainium\/Inferentia2 Architecture Guide for NKI. https:\/\/github.com\/aws-neuron\/aws-neuron-sdk\/blob\/master\/general\/nki\/arch\/trainium_inferentia2_arch.rst Accessed: September 19 2025."},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"crossref","unstructured":"D.\u00a0H. Bailey. 1990. FFTs in External or Hierarchical Memory. J. Supercomput. 4 (1990) 23\u201335. doi:10.1007\/BF00162341","DOI":"10.1007\/BF00162341"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"crossref","unstructured":"J.\u00a0C. Bajard and S. Duquesne. 2021. Montgomery-friendly primes and applications to cryptography. J. Cryptogr. Eng. 11 (2021) 399\u2013415. doi:10.1007\/s13389-021-00260-z","DOI":"10.1007\/s13389-021-00260-z"},{"key":"e_1_3_3_2_5_2","series-title":"Lect. Notes Comput. Sci.","first-page":"311","volume-title":"Adv. Cryptol. (CRYPTO 1986)","author":"Barrett P.","year":"1987","unstructured":"P. Barrett. 1987. Implementing the Rivest Shamir and Adleman Public Key Encryption Algorithm on a Standard Digital Signal Processor. In Adv. Cryptol. (CRYPTO 1986)(Lect. Notes Comput. Sci., Vol.\u00a0263), A.\u00a0M. Odlyzko (Ed.). Springer, Berlin, Heidelberg, 311\u2013323. doi:10.1007\/3-540-47721-7_24"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-43414-7_24"},{"key":"e_1_3_3_2_7_2","volume-title":"Prime Numbers: A Computational Perspective (second ed.)","author":"Crandall R.","year":"2005","unstructured":"R. Crandall and C. Pomerance. 2005. Prime Numbers: A Computational Perspective (second ed.). Springer. doi:10.1007\/0-387-28979-8"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"crossref","unstructured":"B. Curless and M. Gowanlock. 2025. Fast and Scalable Mixed Precision Euclidean Distance Calculations Using GPU Tensor Cores. (2025). https:\/\/arxiv.org\/abs\/2508.21230","DOI":"10.1145\/3754598.3754636"},{"key":"e_1_3_3_2_9_2","unstructured":"K. Dinel. [n. d.]. Nvidia SM90a Instruction Set Architecture. https:\/\/kuterdinel.com\/nv_isa\/ Accessed: September 19 2025."},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/PACT52795.2021.00032"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA61900.2025.00091"},{"key":"e_1_3_3_2_12_2","unstructured":"Google Cloud. [n. d.]. TPU architecture. https:\/\/cloud.google.com\/tpu\/docs\/system-architecture-tpu-vm Accessed: September 19 2025."},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"crossref","unstructured":"D. Harvey. 2014. Faster arithmetic for number-theoretic transforms. J. Symb. Comput. 60 (2014) 113\u2013119. doi:10.1016\/j.jsc.2013.09.002","DOI":"10.1016\/j.jsc.2013.09.002"},{"key":"e_1_3_3_2_14_2","unstructured":"Intel Corporation. [n. d.]. Intel 64 and IA-32 Architectures Software Developer Manuals. https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/articles\/technical\/intel-sdm.html Accessed: September 19 2025."},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"crossref","unstructured":"R. Jesus T.\u00a0O. Silva and M. Weiland. 2023. Vectorizing and distributing number-theoretic transform to count Goldbach partitions on Arm-based supercomputers. Concurr. Comput.: Pract. Exp. 35 28 (2023). doi:10.1002\/cpe.7882","DOI":"10.1002\/cpe.7882"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3695053.3731408"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"crossref","unstructured":"\u00c7.\u00a0K. Ko\u00e7 T. Acar and B.\u00a0S. Kaliski Jr.1996. Analyzing and comparing Montgomery multiplication algorithms. IEEE Micro 16 3 (1996) 26\u201333. doi:10.1109\/40.502403","DOI":"10.1109\/40.502403"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/Cluster48925.2021.00035"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"crossref","unstructured":"W. Luo R. Fan Z. Li D. Du Q. Wang and X. Chu. 2024. Benchmarking and Dissecting the Nvidia Hopper GPU Architecture. (2024). https:\/\/arxiv.org\/abs\/2402.13499","DOI":"10.1109\/IPDPS57955.2024.00064"},{"key":"e_1_3_3_2_20_2","unstructured":"E.\u00a0W. Mayer. 2016. Efficient long division via Montgomery multiply. (2016). https:\/\/arxiv.org\/abs\/1303.0328"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.5555\/548089"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"crossref","unstructured":"P.\u00a0L. Montgomery. 1985. Modular Multiplication Without Trial Division. Math. Comput. 44 (1985) 519\u2013521. doi:10.1090\/S0025-5718-1985-0777282-X","DOI":"10.1090\/S0025-5718-1985-0777282-X"},{"key":"e_1_3_3_2_23_2","unstructured":"NVIDIA Corporation. [n. d.]. CUDA C++ Programming Guide. https:\/\/docs.nvidia.com\/cuda\/cuda-c-programming-guide\/ Accessed: September 19 2025."},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"crossref","unstructured":"H. Ootomo K. Ozaki and R. Yokota. 2024. DGEMM on integer matrix multiplication unit. Int. J. High Perform. Comput. Appl. 38 4 (2024) 297\u2013313. doi:10.1177\/10943420241239588","DOI":"10.1177\/10943420241239588"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"crossref","unstructured":"H. Ootomo and R. Yokota. 2022. Recovering single precision accuracy from Tensor Cores while surpassing the FP32 theoretical peak performance. Int. J. High Perform. Comput. Appl. 36 4 (2022) 475\u2013491. doi:10.1177\/10943420221090256","DOI":"10.1177\/10943420221090256"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"crossref","unstructured":"A. Ozcan A. Javeed and E. Savas. 2025. High-Performance Number Theoretic Transform on GPU Through radix2-CT and 4-Step Algorithms. IEEE Access 13 (2025) 87862\u201387883. doi:10.1109\/ACCESS.2025.3570024","DOI":"10.1109\/ACCESS.2025.3570024"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"crossref","unstructured":"J.\u00a0M. Pollard. 1971. The Fast Fourier Transform in a Finite Field. Math. Comput. 25 (1971) 365\u2013374. doi:10.1090\/S0025-5718-1971-0301966-0","DOI":"10.1090\/S0025-5718-1971-0301966-0"},{"key":"e_1_3_3_2_28_2","unstructured":"A. Samajdar Y. Zhu P. Whatmough M. Mattina and T. Krishna. 2019. SCALE-Sim: Systolic CNN Accelerator Simulator. (2019). https:\/\/arxiv.org\/abs\/1811.02883"},{"key":"e_1_3_3_2_29_2","volume-title":"Adv. Neural Inf. Process. Syst. (NeurIPS 2024)","author":"Shah J.","year":"2024","unstructured":"J. Shah, G. Bikshandi, Y. Zhang, V. Thakkar, P. Ramani, and T. Dao. 2024. FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision. In Adv. Neural Inf. Process. Syst. (NeurIPS 2024)."},{"key":"e_1_3_3_2_30_2","volume-title":"IEEE Int. Symp. Parallel Distrib. Comput. (ISPDC 2025)","author":"Sugizaki Y.","year":"2025","unstructured":"Y. Sugizaki and D. Takahashi. 2025. An Improved Implementation of Multi-Threaded Number Theoretic Transform Using Arm Scalable Vector Extension Instruction Set. In IEEE Int. Symp. Parallel Distrib. Comput. (ISPDC 2025)."},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-14788-3_18"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-17143-7_25"}],"event":{"name":"SCA\/HPCAsia 2026: Supercomputing Asia and International Conference on High Performance Computing in Asia Pacific Region","location":"Osaka Japan","acronym":"SCA\/HPCAsia 2026"},"container-title":["Proceedings of the Supercomputing Asia and International Conference on High Performance Computing in Asia Pacific Region"],"original-title":[],"deposited":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T10:23:29Z","timestamp":1767954209000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3773656.3773673"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,25]]},"references-count":31,"alternative-id":["10.1145\/3773656.3773673","10.1145\/3773656"],"URL":"https:\/\/doi.org\/10.1145\/3773656.3773673","relation":{},"subject":[],"published":{"date-parts":[[2026,1,25]]},"assertion":[{"value":"2026-01-25","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}