{"id":"https://openalex.org/W7125433442","doi":"https://doi.org/10.1145/3784828.3785017","title":"DGEMM using FP64 Arithmetic Emulation and FP8 Tensor Cores with Ozaki Scheme","display_name":"DGEMM using FP64 Arithmetic Emulation and FP8 Tensor Cores with Ozaki Scheme","publication_year":2026,"publication_date":"2026-01-22","ids":{"openalex":"https://openalex.org/W7125433442","doi":"https://doi.org/10.1145/3784828.3785017"},"language":null,"primary_location":{"id":"doi:10.1145/3784828.3785017","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3784828.3785017","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3784828.3785017","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/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Daichi Mukunoki","raw_affiliation_strings":["Information Technology Center, Nagoya University, Nagoya, Japan"],"raw_orcid":"https://orcid.org/0000-0002-0051-6811","affiliations":[{"raw_affiliation_string":"Information Technology Center, Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5035972892"],"corresponding_institution_ids":["https://openalex.org/I60134161"],"apc_list":null,"apc_paid":null,"fwci":18.0163,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.95665914,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"303","last_page":"311"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.6976000070571899,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.6976000070571899,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.10589999705553055,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.0674000009894371,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/emulation","display_name":"Emulation","score":0.8123000264167786},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.7257999777793884},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6496999859809875},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.6114000082015991},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5979999899864197},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.5493999719619751},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.46939998865127563}],"concepts":[{"id":"https://openalex.org/C149810388","wikidata":"https://www.wikidata.org/wiki/Q5374873","display_name":"Emulation","level":2,"score":0.8123000264167786},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.7257999777793884},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6938999891281128},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6496999859809875},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.6114000082015991},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5979999899864197},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.5493999719619751},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.46939998865127563},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4611999988555908},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.43650001287460327},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3978999853134155},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3912000060081482},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.38920000195503235},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.37880000472068787},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.27869999408721924},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C97137487","wikidata":"https://www.wikidata.org/wiki/Q729138","display_name":"Integer (computer science)","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C44074806","wikidata":"https://www.wikidata.org/wiki/Q1066790","display_name":"Inscribed figure","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.25429999828338623},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2531000077724457}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3784828.3785017","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3784828.3785017","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"}],"best_oa_location":{"id":"doi:10.1145/3784828.3785017","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3784828.3785017","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":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1969213662","https://openalex.org/W2002257715","https://openalex.org/W2012407419","https://openalex.org/W2073327480","https://openalex.org/W2079450792","https://openalex.org/W2104380208","https://openalex.org/W2606722458","https://openalex.org/W2791673912","https://openalex.org/W2889796855","https://openalex.org/W2981849318","https://openalex.org/W2981980078","https://openalex.org/W3012028217","https://openalex.org/W3034986667","https://openalex.org/W3120677723","https://openalex.org/W3175644086","https://openalex.org/W3203464687","https://openalex.org/W3207730444","https://openalex.org/W4221160294","https://openalex.org/W4283812690","https://openalex.org/W4367294087","https://openalex.org/W4382702310","https://openalex.org/W4392884779","https://openalex.org/W4393137758","https://openalex.org/W4400409880","https://openalex.org/W4405129106","https://openalex.org/W4405741266","https://openalex.org/W4406214914"],"related_works":[],"abstract_inverted_index":{"The":[0,99],"rapid":[1],"growth":[2],"of":[3,10,61,164,200,230],"AI":[4,22,56,232],"workloads":[5,57],"has":[6,72],"driven":[7],"the":[8,15,59,116,162,170,194,201,218],"development":[9],"specialized":[11],"accelerators":[12,67,233],"optimized":[13],"for":[14,30,49,68,95,234],"low-precision":[16,110,145,153,165],"matrix":[17,90,167],"multiplication":[18,91],"required":[19,197],"by":[20,86,156],"modern":[21,96],"models.":[23],"These":[24],"devices":[25],"are":[26],"generally":[27],"not":[28],"designed":[29],"scientific":[31,51,70,236],"applications":[32],"and":[33,127],"often":[34],"lack":[35],"FP64":[36,42,62,89,190,195,205],"capability":[37],"or":[38],"provide":[39],"only":[40],"limited":[41],"performance.":[43,63],"Even":[44],"general-purpose":[45],"GPUs,":[46,126],"originally":[47],"adopted":[48],"heterogeneous":[50,79],"computing,":[52],"have":[53],"increasingly":[54,143],"prioritized":[55],"at":[58],"expense":[60],"Consequently,":[64],"leveraging":[65],"such":[66,148],"FP64-based":[69,235],"computing":[71],"emerged":[73],"as":[74,149],"a":[75,224],"new":[76],"challenge":[77,85],"in":[78,169,198],"systems.":[80],"This":[81,221],"study":[82,160,222],"addresses":[83],"this":[84,157,159],"improving":[87],"an":[88],"(DGEMM)":[92],"emulation":[93],"method":[94],"AI-oriented":[97,141],"processors.":[98],"Ozaki":[100,171],"scheme":[101,117,202],"(Ozaki":[102],"et":[103],"al.,":[104],"2012)":[105],"enables":[106],"DGEMM":[107],"computation":[108],"using":[109,132],"GEMM.":[111],"Earlier":[112],"work":[113],"demonstrated":[114],"that":[115],"could":[118],"exploit":[119],"FP16":[120],"matrix-multiplication":[121],"units":[122,168],"(Tensor":[123],"Cores)":[124],"on":[125,175,180],"later":[128],"achieved":[129],"substantial":[130],"speedups":[131],"newly":[133],"introduced":[134],"8-bit":[135],"integer":[136],"Tensor":[137,177],"Cores.":[138],"However,":[139],"recent":[140],"hardware":[142],"emphasizes":[144],"floating-point":[146,166],"operations":[147],"FP8":[150,176],"rather":[151],"than":[152],"integers.":[154],"Motivated":[155],"trend,":[158],"revisits":[161],"use":[163,229],"scheme,":[172],"focusing":[173],"specifically":[174],"Cores":[178],"available":[179],"NVIDIA":[181],"Blackwell":[182],"GPUs.":[183],"Additionally,":[184],"to":[185,209],"support":[186],"processors":[187],"without":[188],"native":[189],"units,":[191],"we":[192,214],"replace":[193],"arithmetic":[196,206],"portions":[199],"with":[203],"integer-based":[204],"emulation.":[207],"Furthermore,":[208],"accelerate":[210],"existing":[211],"FP16-based":[212],"implementations,":[213],"explore":[215],"blocking":[216],"along":[217],"inner-product":[219],"dimension.":[220],"provides":[223],"step":[225],"toward":[226],"enabling":[227],"effective":[228],"emerging":[231],"computing.":[237]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-01-23T00:00:00"}