{"id":"https://openalex.org/W7125379529","doi":"https://doi.org/10.1145/3784828.3785398","title":"Mixed precision solvers with half-precision floating point numbers for Lattice QCD on A64FX processor","display_name":"Mixed precision solvers with half-precision floating point numbers for Lattice QCD on A64FX processor","publication_year":2026,"publication_date":"2026-01-22","ids":{"openalex":"https://openalex.org/W7125379529","doi":"https://doi.org/10.1145/3784828.3785398"},"language":null,"primary_location":{"id":"doi:10.1145/3784828.3785398","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3784828.3785398","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Supercomputing Asia and International Conference on High Performance Computing in Asia Pacific Region Workshops","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3784828.3785398","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123547310","display_name":"Issaku Kanamori","orcid":null},"institutions":[{"id":"https://openalex.org/I4210129730","display_name":"RIKEN Center for Computational Science","ror":"https://ror.org/03r519674","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210129730"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Issaku Kanamori","raw_affiliation_strings":["Center for Computational Science, RIKEN, Kobe, Japan"],"raw_orcid":"https://orcid.org/0000-0003-4467-1052","affiliations":[{"raw_affiliation_string":"Center for Computational Science, RIKEN, Kobe, Japan","institution_ids":["https://openalex.org/I4210129730"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hideo Matsufuru","orcid":"https://orcid.org/0000-0003-1056-3969"},"institutions":[{"id":"https://openalex.org/I138728355","display_name":"High Energy Accelerator Research Organization","ror":"https://ror.org/01g5y5k24","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I138728355"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hideo Matsufuru","raw_affiliation_strings":["Computing Research Center, High Energy Accelerator Research Organization (KEK), Tsukuba, Japan and Accelerator Science Program, Graduate Institute for Advanced Studies, SOKENDAI, Tsukuba, Japan"],"raw_orcid":"https://orcid.org/0000-0003-1056-3969","affiliations":[{"raw_affiliation_string":"Computing Research Center, High Energy Accelerator Research Organization (KEK), Tsukuba, Japan and Accelerator Science Program, Graduate Institute for Advanced Studies, SOKENDAI, Tsukuba, Japan","institution_ids":["https://openalex.org/I138728355"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012073213","display_name":"Tatsumi Aoyama","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsumi Aoyama","raw_affiliation_strings":["The Institute for Solid State Physics, The University of Tokyo, Kashiwa, Japan"],"raw_orcid":"https://orcid.org/0009-0009-0491-1024","affiliations":[{"raw_affiliation_string":"The Institute for Solid State Physics, The University of Tokyo, Kashiwa, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019609864","display_name":"K. Kanaya","orcid":"https://orcid.org/0000-0002-5608-6347"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuyuki Kanaya","raw_affiliation_strings":["Tomonaga Center for the History of the Universe, University of Tsukuba, Tsukuba, Japan"],"raw_orcid":"https://orcid.org/0000-0002-5608-6347","affiliations":[{"raw_affiliation_string":"Tomonaga Center for the History of the Universe, University of Tsukuba, Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032016726","display_name":"Yusuke Namekawa","orcid":"https://orcid.org/0000-0002-3578-5085"},"institutions":[{"id":"https://openalex.org/I41661162","display_name":"Fukuyama University","ror":"https://ror.org/00mrjbj15","country_code":"JP","type":"education","lineage":["https://openalex.org/I41661162"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yusuke Namekawa","raw_affiliation_strings":["Department of Computer Science, Fukuyama University, Fukuyama, Japan"],"raw_orcid":"https://orcid.org/0000-0002-3578-5085","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Fukuyama University, Fukuyama, Japan","institution_ids":["https://openalex.org/I41661162"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004154860","display_name":"Hidekatsu Nemura","orcid":null},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hidekatsu Nemura","raw_affiliation_strings":["Research Center for Nuclear Physics, Osaka University, Ibaraki, Japan"],"raw_orcid":"https://orcid.org/0009-0004-8203-4569","affiliations":[{"raw_affiliation_string":"Research Center for Nuclear Physics, Osaka University, Ibaraki, Japan","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022962037","display_name":"Keigo Nitadori","orcid":"https://orcid.org/0000-0001-7374-4236"},"institutions":[{"id":"https://openalex.org/I4210129730","display_name":"RIKEN Center for Computational Science","ror":"https://ror.org/03r519674","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210129730"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keigo Nitadori","raw_affiliation_strings":["Center for Computational Science, RIKEN, Kobe, Japan"],"raw_orcid":"https://orcid.org/0000-0001-7374-4236","affiliations":[{"raw_affiliation_string":"Center for Computational Science, RIKEN, Kobe, Japan","institution_ids":["https://openalex.org/I4210129730"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14048162,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"145","last_page":"155"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10048","display_name":"Particle physics theoretical and experimental studies","score":0.11649999767541885,"subfield":{"id":"https://openalex.org/subfields/3106","display_name":"Nuclear and High Energy Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10048","display_name":"Particle physics theoretical and experimental studies","score":0.11649999767541885,"subfield":{"id":"https://openalex.org/subfields/3106","display_name":"Nuclear and High Energy Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.11240000277757645,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10224","display_name":"Quantum Chromodynamics and Particle Interactions","score":0.10920000076293945,"subfield":{"id":"https://openalex.org/subfields/3106","display_name":"Nuclear and High Energy Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/biconjugate-gradient-stabilized-method","display_name":"Biconjugate gradient stabilized method","score":0.8787999749183655},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.7749000191688538},{"id":"https://openalex.org/keywords/double-precision-floating-point-format","display_name":"Double-precision floating-point format","score":0.5637999773025513},{"id":"https://openalex.org/keywords/floating-point","display_name":"Floating point","score":0.5526999831199646},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.46160000562667847},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.44679999351501465},{"id":"https://openalex.org/keywords/lattice","display_name":"Lattice (music)","score":0.43059998750686646},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.4296000003814697},{"id":"https://openalex.org/keywords/single-precision-floating-point-format","display_name":"Single-precision floating-point format","score":0.41130000352859497}],"concepts":[{"id":"https://openalex.org/C120553275","wikidata":"https://www.wikidata.org/wiki/Q4903720","display_name":"Biconjugate gradient stabilized method","level":3,"score":0.8787999749183655},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.7749000191688538},{"id":"https://openalex.org/C35912277","wikidata":"https://www.wikidata.org/wiki/Q1243369","display_name":"Double-precision floating-point format","level":3,"score":0.5637999773025513},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.5526999831199646},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5224999785423279},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.47350001335144043},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.46160000562667847},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.44679999351501465},{"id":"https://openalex.org/C2781204021","wikidata":"https://www.wikidata.org/wiki/Q6497091","display_name":"Lattice (music)","level":2,"score":0.43059998750686646},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.4296000003814697},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4251999855041504},{"id":"https://openalex.org/C133095886","wikidata":"https://www.wikidata.org/wiki/Q1307173","display_name":"Single-precision floating-point format","level":3,"score":0.41130000352859497},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.4041999876499176},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3937000036239624},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.38679999113082886},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.351500004529953},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.34769999980926514},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.3456999957561493},{"id":"https://openalex.org/C203739276","wikidata":"https://www.wikidata.org/wiki/Q1780355","display_name":"Machine epsilon","level":2,"score":0.3244999945163727},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C83581934","wikidata":"https://www.wikidata.org/wiki/Q527381","display_name":"Arbitrary-precision arithmetic","level":2,"score":0.29760000109672546},{"id":"https://openalex.org/C3909970","wikidata":"https://www.wikidata.org/wiki/Q6166044","display_name":"Lattice QCD","level":3,"score":0.2971999943256378},{"id":"https://openalex.org/C157449380","wikidata":"https://www.wikidata.org/wiki/Q1030759","display_name":"Fixed-point iteration","level":3,"score":0.2847999930381775},{"id":"https://openalex.org/C89408827","wikidata":"https://www.wikidata.org/wiki/Q855169","display_name":"Biconjugate gradient method","level":5,"score":0.2648000121116638},{"id":"https://openalex.org/C44274781","wikidata":"https://www.wikidata.org/wiki/Q6497132","display_name":"Lattice reduction","level":4,"score":0.25859999656677246},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.25589999556541443},{"id":"https://openalex.org/C48753275","wikidata":"https://www.wikidata.org/wiki/Q11216","display_name":"Numerical analysis","level":2,"score":0.2540999948978424}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3784828.3785398","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3784828.3785398","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Supercomputing Asia and International Conference on High Performance Computing in Asia Pacific Region Workshops","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2602.14450","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.14450","pdf_url":"https://arxiv.org/pdf/2602.14450","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:doi:10.48550/arxiv.2602.14450","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1145/3784828.3785398","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3784828.3785398","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Supercomputing Asia and International Conference on High Performance Computing in Asia Pacific Region Workshops","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2465208202","display_name":null,"funder_award_id":"JP25H01109","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G5258345551","display_name":null,"funder_award_id":"P22H01224","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320323954","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320335125","display_name":"RIKEN","ror":"https://ror.org/01sjwvz98"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W575488288","https://openalex.org/W1966448113","https://openalex.org/W1987779630","https://openalex.org/W2074846139","https://openalex.org/W2111987198","https://openalex.org/W2122297947","https://openalex.org/W2155216327","https://openalex.org/W2155967869","https://openalex.org/W2172949211","https://openalex.org/W2490842274","https://openalex.org/W3132840842","https://openalex.org/W3176827258","https://openalex.org/W3199250535","https://openalex.org/W3211509455","https://openalex.org/W4231440689","https://openalex.org/W4281657881","https://openalex.org/W4313491888","https://openalex.org/W4313827511","https://openalex.org/W4318473671","https://openalex.org/W4319067173","https://openalex.org/W4401211033","https://openalex.org/W4413240155"],"related_works":[],"abstract_inverted_index":{"We":[0,115],"investigate":[1],"the":[2,18,52,66,72,88,94,100,108,118],"use":[3],"of":[4,20,54],"half-precision":[5],"floating-point":[6],"numbers":[7],"(FP16)":[8],"in":[9,38,64,129],"mixed-precision":[10,24],"linear":[11],"solvers":[12],"for":[13,22,113],"lattice":[14],"QCD":[15],"simulations.":[16],"Since":[17],"emergence":[19],"GPUs":[21],"general-purpose,":[23],"algorithms":[25],"that":[26,107,117],"combine":[27],"single-precision":[28],"(FP32)":[29],"with":[30,83],"double-precision":[31],"(FP64)":[32],"arithmetics":[33],"have":[34],"become":[35],"widely":[36],"used":[37],"this":[39,58],"field":[40],"and":[41,71,93],"others.":[42],"While":[43],"FP32-based":[44],"methods":[45,121],"are":[46],"now":[47],"well":[48],"established,":[49],"we":[50,60],"examine":[51],"practicality":[53],"using":[55],"FP16.":[56],"In":[57,80],"work,":[59],"introduce":[61],"rescaling":[62,120],"steps":[63],"both":[65],"outer":[67],"iterative":[68],"refinement":[69],"step":[70],"inner":[73],"BiCGStab":[74],"solver":[75,89],"to":[76,99],"avoid":[77],"numerical":[78],"instability.":[79],"our":[81],"experiments":[82],"a":[84],"simple":[85],"Wilson":[86],"kernel,":[87],"shows":[90],"improved":[91],"stability,":[92],"additional":[95],"iteration":[96],"count":[97],"compared":[98],"FP64":[101],"version":[102,110],"remains":[103],"within":[104],"20%,":[105],"indicating":[106],"FP16":[109],"is":[111],"practical":[112],"use.":[114],"believe":[116],"proposed":[119],"can":[122],"also":[123],"benefit":[124],"other":[125],"mixed":[126],"precision":[127],"preconditioners":[128],"avoiding":[130],"underflows.":[131]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-01-23T00:00:00"}
