{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T03:48:52Z","timestamp":1782964132787,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":32,"publisher":"ACM","funder":[{"name":"Japan Society for the Promotion of Science","award":["25K24387"],"award-info":[{"award-number":["25K24387"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,1,26]]},"DOI":"10.1145\/3784828.3785017","type":"proceedings-article","created":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T13:19:17Z","timestamp":1769087957000},"page":"303-311","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["DGEMM using FP64 Arithmetic Emulation and FP8 Tensor Cores with Ozaki Scheme"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0051-6811","authenticated-orcid":false,"given":"Daichi","family":"Mukunoki","sequence":"first","affiliation":[{"name":"Information Technology Center, Nagoya University, Nagoya, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,1,25]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"Ahmad Abdelfattah Jack Dongarra Massimiliano Fasi Mantas Mikaitis and Fran\u00e7oise Tisseur. 2025. Analysis of Floating-Point Matrix Multiplication Computed via Integer Arithmetic. arxiv:https:\/\/arXiv.org\/abs\/2506.11277\u00a0[math.NA] https:\/\/arxiv.org\/abs\/2506.11277"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/ARITH.2019.00022"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","unstructured":"William Dawson Katsuhisa Ozaki Jens Domke and Takahito Nakajima. 2024. Reducing Numerical Precision Requirements in Quantum Chemistry Calculations. Journal of Chemical Theory and Computation 20 24 (2024) 10826\u201310837. 10.1021\/acs.jctc.4c00938PMID: 39644230.","DOI":"10.1021\/acs.jctc.4c00938"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"crossref","unstructured":"T.\u00a0J. Dekker. 1971. A Floating-Point Technique for Extending the Available Precision. Numer. Math. 18 (1971) 224\u2013242.","DOI":"10.1007\/BF01397083"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS49936.2021.00114"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"crossref","unstructured":"J.\u00a0J. Dongarra C.\u00a0J. Du S. Hammarling and I.\u00a0S. Duff. 1990. A Set of Level 3 Basic Linear Algebra Subprograms. ACM Trans. Math. Softw. 16 1 (March 1990) 1\u201317.","DOI":"10.1145\/77626.79170"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","unstructured":"Nicolas Fabiano Jean-Michel Muller and Joris Picot. 2019. Algorithms for Triple-Word Arithmetic. IEEE Trans. Comput. 68 11 (Nov. 2019) 1573\u20131583. 10.1109\/TC.2019.2918451","DOI":"10.1109\/TC.2019.2918451"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","unstructured":"Massimiliano Fasi Nicholas\u00a0J. Higham Florent Lopez Theo Mary and Mantas Mikaitis. 2023. Matrix Multiplication in Multiword Arithmetic: Error Analysis and Application to GPU Tensor Cores. SIAM Journal on Scientific Computing 45 1 (2023) C1\u2013C19. 10.1137\/21M1465032","DOI":"10.1137\/21M1465032"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"crossref","unstructured":"L. Fousse G. Hanrot V. Lef\u00e8vre P. P\u00e9lissier and P. Zimmermann. 2007. MPFR: A Multiple-precision Binary Floating-point Library with Correct Rounding. ACM Trans. Math. Software 33 2 (2007) 13:1\u201313:15.","DOI":"10.1145\/1236463.1236468"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-69583-4_2"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.5555\/2911024"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/ARITH.2019.00019"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/ARITH.2001.930115"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-37108-0_34"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/Cluster48925.2021.00035"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS57955.2024.00064"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2018.00091"},{"key":"e_1_3_3_2_20_2","unstructured":"Paulius Micikevicius Dusan Stosic Neil Burgess Marius Cornea Pradeep Dubey Richard Grisenthwaite Sangwon Ha Alexander Heinecke Patrick Judd John Kamalu Naveen Mellempudi Stuart Oberman Mohammad Shoeybi Michael Siu and Hao Wu. 2022. FP8 Formats for Deep Learning. arxiv:https:\/\/arXiv.org\/abs\/2209.05433\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2209.05433"},{"key":"e_1_3_3_2_21_2","volume-title":"The 35th JSST Annual Conference International Conference on Simulation Technology","author":"Minamihata A.","year":"2016","unstructured":"A. Minamihata, K. Ozaki, T. Ogita, and S. Oishi. 2016. Improved extraction scheme for accurate floating-point summation. In The 35th JSST Annual Conference International Conference on Simulation Technology."},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-43229-4_44"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3432261.3432270"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-50743-5_12"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3472456.3472493"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-30442-2_4"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","unstructured":"Hiroyuki Ootomo Katsuhisa Ozaki and Rio Yokota. 2024. DGEMM on integer matrix multiplication unit. The International Journal of High Performance Computing Applications (2024). 10.1177\/10943420241239588","DOI":"10.1177\/10943420241239588"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","unstructured":"Hiroyuki Ootomo and Rio Yokota. 2022. Recovering single precision accuracy from Tensor Cores while surpassing the FP32 theoretical peak performance. The International Journal of High Performance Computing Applications 36 4 (2022) 475\u2013491. 10.1177\/10943420221090256","DOI":"10.1177\/10943420221090256"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"crossref","unstructured":"K. Ozaki T. Ogita S. Oishi and S.\u00a0M. Rump. 2012. Error-free transformations of matrix multiplication by using fast routines of matrix multiplication and its applications. Numer. Algorithms 59 1 (2012) 95\u2013118.","DOI":"10.1007\/s11075-011-9478-1"},{"key":"e_1_3_3_2_30_2","unstructured":"Katsuhisa Ozaki Yuki Uchino and Toshiyuki Imamura. 2025. Ozaki Scheme II: A GEMM-oriented emulation of floating-point matrix multiplication using an integer modular technique. arxiv:https:\/\/arXiv.org\/abs\/2504.08009\u00a0[cs.MS] https:\/\/arxiv.org\/abs\/2504.08009"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/1179622.1179682"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","unstructured":"Yuki Uchino Katsuhisa Ozaki and Toshiyuki Imamura. 2025. Performance enhancement of the Ozaki Scheme on integer matrix multiplication unit. The International Journal of High Performance Computing Applications 39 3 (2025) 462\u2013476. 10.1177\/10943420241313064","DOI":"10.1177\/10943420241313064"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00064"}],"event":{"name":"SCA\/HPCAsiaWS 2026: SCA\/HPCAsia 2026 Workshops: Supercomputing Asia and International Conference on High Performance Computing in Asia Pacific Region Workshops","location":"Osaka , Japan","acronym":"SCA\/HPCAsiaWS 2026"},"container-title":["Proceedings of the Supercomputing Asia and International Conference on High Performance Computing in Asia Pacific Region Workshops"],"original-title":[],"deposited":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T13:37:46Z","timestamp":1769089066000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3784828.3785017"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,25]]},"references-count":32,"alternative-id":["10.1145\/3784828.3785017","10.1145\/3784828"],"URL":"https:\/\/doi.org\/10.1145\/3784828.3785017","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"}}]}}