{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T04:48:03Z","timestamp":1769143683910,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":27,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["P22H01224"],"award-info":[{"award-number":["P22H01224"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["JP25H01109"],"award-info":[{"award-number":["JP25H01109"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,1,26]]},"DOI":"10.1145\/3784828.3785398","type":"proceedings-article","created":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T13:19:17Z","timestamp":1769087957000},"page":"145-155","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Mixed precision solvers with half-precision floating point numbers for Lattice QCD on A64FX processor"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4467-1052","authenticated-orcid":false,"given":"Issaku","family":"Kanamori","sequence":"first","affiliation":[{"name":"Center for Computational Science, RIKEN, Kobe, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1056-3969","authenticated-orcid":false,"given":"Hideo","family":"Matsufuru","sequence":"additional","affiliation":[{"name":"Computing Research Center, High Energy Accelerator Research Organization (KEK), Tsukuba, Japan and Accelerator Science Program, Graduate Institute for Advanced Studies, SOKENDAI, Tsukuba, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0491-1024","authenticated-orcid":false,"given":"Tatsumi","family":"Aoyama","sequence":"additional","affiliation":[{"name":"The Institute for Solid State Physics, The University of Tokyo, Kashiwa, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5608-6347","authenticated-orcid":false,"given":"Kazuyuki","family":"Kanaya","sequence":"additional","affiliation":[{"name":"Tomonaga Center for the History of the Universe, University of Tsukuba, Tsukuba, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3578-5085","authenticated-orcid":false,"given":"Yusuke","family":"Namekawa","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Fukuyama University, Fukuyama, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8203-4569","authenticated-orcid":false,"given":"Hidekatsu","family":"Nemura","sequence":"additional","affiliation":[{"name":"Research Center for Nuclear Physics, Osaka University, Ibaraki, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7374-4236","authenticated-orcid":false,"given":"Keigo","family":"Nitadori","sequence":"additional","affiliation":[{"name":"Center for Computational Science, RIKEN, Kobe, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,1,25]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"publisher","unstructured":"Yutaro Akahoshi Sinya Aoki Tatsumi Aoyama Issaku Kanamori Kazuyuki Kanaya Hideo Matsufuru Yusuke Namekawa Hidekatsu Nemura and Yusuke Taniguchi. 2022. General purpose lattice QCD code set Bridge++ 2.0 for high performance computing. J. Phys. Conf. Ser. 2207 1 (2022) 012053. 10.1088\/1742-6596\/2207\/1\/012053 arxiv:https:\/\/arXiv.org\/abs\/2111.04457\u00a0[hep-lat]","DOI":"10.1088\/1742-6596\/2207\/1\/012053"},{"key":"e_1_3_3_2_3_2","unstructured":"Ani Anciaux-Sedrakian Hugo Dorfsman Thomas Guignon Fabienne J\u00e9z\u00e9quel and Theo Mary. 2025. Mixed Precision Strategies for Solving Sparse Linear Systems with BiCGStab. (Oct. 2025). https:\/\/hal.science\/hal-05326901 working paper or preprint."},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","unstructured":"Tatsumi Aoyama Issaku Kanamori Kazuyuki Kanaya Hideo Matsufuru and Yusuke Namekawa. 2023. Bridge++ 2.0: Benchmark results on supercomputer Fugaku. PoS LATTICE2022 (2023) 284. 10.22323\/1.430.0284 arxiv:https:\/\/arXiv.org\/abs\/2303.05883\u00a0[hep-lat]","DOI":"10.22323\/1.430.0284"},{"key":"e_1_3_3_2_5_2","unstructured":"Bridge++ project. 2012-. Lattice QCD code Bridge++. https:\/\/bridge.kek.jp\/Lattice-code\/."},{"key":"e_1_3_3_2_6_2","unstructured":"Alfredo Buttari Xin Liu Theo Mary and Bastien Vieubl\u00e9. 2025. Mixed precision strategies for preconditioned GMRES: a comprehensive analysis. (May 2025). https:\/\/hal.science\/hal-05071696 working paper or preprint."},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","unstructured":"M.A. Clark R. Babich K. Barros R.C. Brower and C. Rebbi. 2010. Solving lattice QCD systems of equations using mixed precision solvers on GPUs. Computer Physics Communications 181 9 (2010) 1517\u20131528. 10.1016\/j.cpc.2010.05.002","DOI":"10.1016\/j.cpc.2010.05.002"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","unstructured":"M.\u00a0A. Clark Dean Howarth Jiqun Tu Mathias Wagner and Evan Weinberg. 2023. Maximizing the Bang Per Bit. PoS LATTICE2022 (2023) 338. 10.22323\/1.430.0338 arxiv:https:\/\/arXiv.org\/abs\/2302.09224\u00a0[hep-lat]","DOI":"10.22323\/1.430.0338"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1142\/6065"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","unstructured":"Gyozo\u00a0I. Egri Zoltan Fodor Christian Hoelbling Sandor\u00a0D. Katz Daniel Nogradi and Kalman\u00a0K. Szabo. 2007. Lattice QCD as a video game. Comput. Phys. Commun. 177 (2007) 631\u2013639. 10.1016\/j.cpc.2007.06.005 arxiv:https:\/\/arXiv.org\/abs\/hep-lat\/0611022","DOI":"10.1016\/j.cpc.2007.06.005"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","unstructured":"S.\u00a0Navas et.\u00a0al (Particle Data Group\u00a0collaboration). 2024. Review of Particle Physics. Phys. Rev. D 110 (Aug 2024) 030001. Issue 3. 10.1103\/PhysRevD.110.030001","DOI":"10.1103\/PhysRevD.110.030001"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","unstructured":"Jacob Finkenrath. 2023. Review on Algorithms for dynamical fermions. PoS LATTICE2022 (2023) 227. 10.22323\/1.430.0227 arxiv:https:\/\/arXiv.org\/abs\/2402.11704\u00a0[hep-lat]","DOI":"10.22323\/1.430.0227"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-01850-3"},{"key":"e_1_3_3_2_14_2","unstructured":"Grid Developers. 2015-. Grid. https:\/\/github.com\/paboyle\/Grid."},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","unstructured":"Nicholas\u00a0J. Higham and Theo Mary. 2022. Mixed precision algorithms in numerical linear algebra. Acta Numerica 31 (2022) 347\u2013414. 10.1017\/S0962492922000022","DOI":"10.1017\/S0962492922000022"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","unstructured":"Ken-Ichi Ishikawa Issaku Kanamori Hideo Matsufuru Ikuo Miyoshi Yuta Mukai Yoshifumi Nakamura Keigo Nitadori and Miwako Tsuji. 2023. 102 PFLOPS lattice QCD quark solver on Fugaku. Comput. Phys. Commun. 282 (2023) 108510. 10.1016\/j.cpc.2022.108510 arxiv:https:\/\/arXiv.org\/abs\/2109.10687\u00a0[hep-lat]","DOI":"10.1016\/j.cpc.2022.108510"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581576.3581610"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780199691609.001.0001"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","unstructured":"Neil Lindquist Piotr Luszczek and Jack Dongarra. 2022. Accelerating Restarted GMRES With Mixed Precision Arithmetic. IEEE Transactions on Parallel and Distributed Systems 33 4 (2022) 1027\u20131037. 10.1109\/TPDS.2021.3090757","DOI":"10.1109\/TPDS.2021.3090757"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","unstructured":"Martin Luscher. 2004. Solution of the Dirac equation in lattice QCD using a domain decomposition method. Comput. Phys. Commun. 156 (2004) 209\u2013220. 10.1016\/S0010-4655(03)00486-7 arxiv:https:\/\/arXiv.org\/abs\/hep-lat\/0310048","DOI":"10.1016\/S0010-4655(03)00486-7"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","unstructured":"Giuseppe Magnifico Giovanni Cataldi Marco Rigobello Peter Majcen Daniel Jaschke Pietro Silvi and Simone Montangero. 2025. Tensor networks for lattice gauge theories beyond one dimension. Commun. Phys. 8 1 (2025) 322. 10.1038\/s42005-025-02125-x arxiv:https:\/\/arXiv.org\/abs\/2407.03058\u00a0[hep-lat]","DOI":"10.1038\/s42005-025-02125-x"},{"key":"e_1_3_3_2_22_2","unstructured":"QUDA Developers. 2009-. QUDA. https:\/\/github.com\/lattice\/quda."},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00051"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","unstructured":"Gerard L.\u00a0G. Sleijpen and Henk\u00a0A. van\u00a0der Vorst. 1995. Maintaining convergence properties of BiCGstab methods in finite precision arithmetic. Numerical Algorithms 10 (1995) 203\u2013223. 10.1007\/BF02140769","DOI":"10.1007\/BF02140769"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","unstructured":"S. Ueda S. Aoki T. Aoyama K. Kanaya H. Matsufuru S. Motoki Y. Namekawa H. Nemura Y. Taniguchi and N. Ukita. 2014. Development of an object oriented lattice QCD code \u2018Bridge++\u2019. J. Phys. Conf. Ser. 523 (2014) 012046. 10.1088\/1742-6596\/523\/1\/012046","DOI":"10.1088\/1742-6596\/523\/1\/012046"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","unstructured":"H.\u00a0A. van\u00a0der Vorst. 1992. Bi-CGSTAB: A Fast and Smoothly Converging Variant of Bi-CG for the Solution of Nonsymmetric Linear Systems. SIAM J. Sci. Stat. Comput. 13 2 (March 1992) 631\u2013644. 10.1137\/0913035","DOI":"10.1137\/0913035"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","unstructured":"Judith\u00a0A. Vogel. 2007. Flexible BiCG and flexible Bi-CGSTAB for nonsymmetric linear systems. Appl. Math. Comput. 188 1 (2007) 226\u2013233. 10.1016\/j.amc.2006.09.116","DOI":"10.1016\/j.amc.2006.09.116"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","unstructured":"Kenneth\u00a0G. Wilson. 1974. Confinement of quarks. Phys. Rev. D 10 (Oct 1974) 2445\u20132459. Issue 8. 10.1103\/PhysRevD.10.2445","DOI":"10.1103\/PhysRevD.10.2445"}],"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":"2026-01-22T13:38:20Z","timestamp":1769089100000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3784828.3785398"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,25]]},"references-count":27,"alternative-id":["10.1145\/3784828.3785398","10.1145\/3784828"],"URL":"https:\/\/doi.org\/10.1145\/3784828.3785398","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"}}]}}