{"id":"https://openalex.org/W3203464687","doi":"https://doi.org/10.1145/3472456.3472493","title":"Accurate Matrix Multiplication on Binary128 Format Accelerated by Ozaki Scheme","display_name":"Accurate Matrix Multiplication on Binary128 Format Accelerated by Ozaki Scheme","publication_year":2021,"publication_date":"2021-08-09","ids":{"openalex":"https://openalex.org/W3203464687","doi":"https://doi.org/10.1145/3472456.3472493","mag":"3203464687"},"language":"en","primary_location":{"id":"doi:10.1145/3472456.3472493","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3472456.3472493","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":"50th International Conference on Parallel Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3472456.3472493","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035972892","display_name":"Daichi Mukunoki","orcid":"https://orcid.org/0000-0002-0051-6811"},"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":true,"raw_author_name":"Daichi Mukunoki","raw_affiliation_strings":["RIKEN Center for Computational Science, Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN Center for Computational Science, Japan","institution_ids":["https://openalex.org/I4210129730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042608261","display_name":"Katsuhisa Ozaki","orcid":"https://orcid.org/0000-0003-0431-6232"},"institutions":[{"id":"https://openalex.org/I171481255","display_name":"Shibaura Institute of Technology","ror":"https://ror.org/020wjcq07","country_code":"JP","type":"education","lineage":["https://openalex.org/I171481255"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Katsuhisa Ozaki","raw_affiliation_strings":["Shibaura Institute of Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Shibaura Institute of Technology, Japan","institution_ids":["https://openalex.org/I171481255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028381863","display_name":"Takeshi Ogita","orcid":"https://orcid.org/0000-0002-9346-2452"},"institutions":[{"id":"https://openalex.org/I20560788","display_name":"Tokyo Woman's Christian University","ror":"https://ror.org/03mb27p64","country_code":"JP","type":"education","lineage":["https://openalex.org/I20560788"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takeshi Ogita","raw_affiliation_strings":["Tokyo Woman''s Christian University, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Woman''s Christian University, Japan","institution_ids":["https://openalex.org/I20560788"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086152822","display_name":"Toshiyuki Imamura","orcid":"https://orcid.org/0000-0003-1601-9710"},"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":"Toshiyuki Imamura","raw_affiliation_strings":["RIKEN Center for Computational Science, Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN Center for Computational Science, Japan","institution_ids":["https://openalex.org/I4210129730"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5035972892"],"corresponding_institution_ids":["https://openalex.org/I4210129730"],"apc_list":null,"apc_paid":null,"fwci":0.4439,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.68000143,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11697","display_name":"Numerical Methods and Algorithms","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T11697","display_name":"Numerical Methods and Algorithms","score":0.9994999766349792,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T11693","display_name":"Cryptography and Residue Arithmetic","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7929055690765381},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.7521738409996033},{"id":"https://openalex.org/keywords/x86","display_name":"x86","score":0.7256459593772888},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.6968215107917786},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5766139030456543},{"id":"https://openalex.org/keywords/emulation","display_name":"Emulation","score":0.512012779712677},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4711174964904785},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.46068432927131653},{"id":"https://openalex.org/keywords/division","display_name":"Division (mathematics)","score":0.4183274507522583},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.27689749002456665},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.2695786654949188},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11371731758117676},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10558900237083435}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7929055690765381},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.7521738409996033},{"id":"https://openalex.org/C170723468","wikidata":"https://www.wikidata.org/wiki/Q182933","display_name":"x86","level":3,"score":0.7256459593772888},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.6968215107917786},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5766139030456543},{"id":"https://openalex.org/C149810388","wikidata":"https://www.wikidata.org/wiki/Q5374873","display_name":"Emulation","level":2,"score":0.512012779712677},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4711174964904785},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.46068432927131653},{"id":"https://openalex.org/C60798267","wikidata":"https://www.wikidata.org/wiki/Q1226939","display_name":"Division (mathematics)","level":2,"score":0.4183274507522583},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.27689749002456665},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.2695786654949188},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11371731758117676},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10558900237083435},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3472456.3472493","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3472456.3472493","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":"50th International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3472456.3472493","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3472456.3472493","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":"50th International Conference on Parallel Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W16036026","https://openalex.org/W1968165559","https://openalex.org/W1969213662","https://openalex.org/W2002257715","https://openalex.org/W2012407419","https://openalex.org/W2048517891","https://openalex.org/W2071148743","https://openalex.org/W2073327480","https://openalex.org/W2091275975","https://openalex.org/W2104281151","https://openalex.org/W2121848241","https://openalex.org/W2148979214","https://openalex.org/W2155673213","https://openalex.org/W2172382511","https://openalex.org/W2207050309","https://openalex.org/W2288982856","https://openalex.org/W2480266340","https://openalex.org/W2752061190","https://openalex.org/W2924160840","https://openalex.org/W2988926770","https://openalex.org/W2995828186","https://openalex.org/W3010988589","https://openalex.org/W3012028217","https://openalex.org/W3034986667","https://openalex.org/W3120677723","https://openalex.org/W4229666556"],"related_works":["https://openalex.org/W3099313426","https://openalex.org/W4287593139","https://openalex.org/W752783541","https://openalex.org/W1506547947","https://openalex.org/W2995605830","https://openalex.org/W4206811032","https://openalex.org/W2086123442","https://openalex.org/W2596457687","https://openalex.org/W3212757063","https://openalex.org/W2093666864"],"abstract_inverted_index":{"Although":[0,116],"IEEE":[1],"754-2008":[2],"binary128":[3,59,154],"(with":[4],"a":[5,48,186],"15-bit":[6],"exponent":[7],"and":[8,131,143,182],"113-bit":[9],"significand,":[10],"i.e.,":[11],"quadruple-precision)":[12],"is":[13,23,31,40,72],"not":[14],"currently":[15],"implemented":[16],"on":[17,25,54,61,121,166,173],"x86":[18,62],"in":[19,43,57,83,101,156],"hardware,":[20],"software":[21],"emulation":[22,155],"available":[24],"some":[26],"compilers.":[27],"However,":[28],"the":[29,36,58,68,94,110,117,122,128,132,136,152,183],"performance":[30,119,142,165],"significantly":[32],"slower":[33],"compared":[34,145],"to":[35,89,146,179],"binary64":[37,95],"operation,":[38],"which":[39,71],"supported":[41],"natively":[42],"hardware.":[44],"This":[45,85],"study":[46],"proposes":[47],"fast":[49],"implementation":[50,66,138,171],"of":[51,112,185],"matrix":[52,75,96,148,175],"multiplication":[53,76,97,149,176],"matrices":[55,124],"stored":[56],"format":[60],"CPUs.":[63],"The":[64],"proposed":[65,78,137],"utilizes":[67],"Ozaki":[69,80],"scheme,":[70],"an":[73,170],"accurate":[74],"algorithm":[77],"by":[79],"et":[81],"al.":[82],"2012.":[84],"scheme":[86],"enables":[87],"one":[88],"perform":[90],"most":[91],"computations":[92],"using":[93,151],"(the":[98,125],"DGEMM":[99],"routine":[100],"Basic":[102],"Linear":[103],"Algebra":[104],"Subprograms":[105],"(BLAS));":[106],"it":[107],"can":[108,139],"exploit":[109],"high-performance":[111],"highly-optimized":[113],"vendor":[114],"BLAS.":[115],"achievable":[118],"depends":[120],"input":[123],"inner-product":[126],"dimension,":[127],"absolute":[129],"range,":[130],"significand":[133],"bit":[134],"length),":[135],"achieve":[140],"better":[141],"accuracy":[144],"naive":[147],"performed":[150],"GCC\u2019s":[153],"many":[157],"cases.":[158],"In":[159],"addition,":[160],"we":[161],"discuss":[162],"GPU":[163],"acceleration,":[164],"reduced":[167],"precision":[168],"inputs,":[169],"based":[172],"binary32":[174],"(SGEMM),":[177],"application":[178],"memory-intensive":[180],"operations,":[181],"possibility":[184],"distributed":[187],"parallel":[188],"implementation.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}