{"id":"https://openalex.org/W2737067755","doi":"https://doi.org/10.1145/3086466","title":"Implementing High-performance Complex Matrix Multiplication via the 3m and 4m Methods","display_name":"Implementing High-performance Complex Matrix Multiplication via the 3m and 4m Methods","publication_year":2017,"publication_date":"2017-07-24","ids":{"openalex":"https://openalex.org/W2737067755","doi":"https://doi.org/10.1145/3086466","mag":"2737067755"},"language":"en","primary_location":{"id":"doi:10.1145/3086466","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3086466","pdf_url":null,"source":{"id":"https://openalex.org/S163326656","display_name":"ACM Transactions on Mathematical Software","issn_l":"0098-3500","issn":["0098-3500","1557-7295"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Mathematical Software","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035211620","display_name":"Field G. Zee","orcid":"https://orcid.org/0009-0007-2498-9430"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Field G. Van Zee","raw_affiliation_strings":["The University of Texas at Austin, Austin, TX"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, Austin, TX","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111393098","display_name":"Tyler Smith","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tyler M. Smith","raw_affiliation_strings":["The University of Texas at Austin, Austin, TX"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, Austin, TX","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":1.7896,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.86415594,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"44","issue":"1","first_page":"1","last_page":"36"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9977999925613403,"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"}},{"id":"https://openalex.org/T11697","display_name":"Numerical Methods and Algorithms","score":0.9846000075340271,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.7787301540374756},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.777774453163147},{"id":"https://openalex.org/keywords/software-portability","display_name":"Software portability","score":0.7501951456069946},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.6963887810707092},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6328194737434387},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5705402493476868},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.5085865259170532},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.49700143933296204},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.48366889357566833},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.47517532110214233},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4607011675834656},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.450038343667984},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4418787956237793},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.4200412333011627},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3767731785774231},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3645963966846466},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.3480744957923889},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17577242851257324},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.11640569567680359}],"concepts":[{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.7787301540374756},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.777774453163147},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.7501951456069946},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.6963887810707092},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6328194737434387},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5705402493476868},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.5085865259170532},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.49700143933296204},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48366889357566833},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.47517532110214233},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4607011675834656},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.450038343667984},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4418787956237793},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.4200412333011627},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3767731785774231},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3645963966846466},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.3480744957923889},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17577242851257324},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.11640569567680359},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3086466","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3086466","pdf_url":null,"source":{"id":"https://openalex.org/S163326656","display_name":"ACM Transactions on Mathematical Software","issn_l":"0098-3500","issn":["0098-3500","1557-7295"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Mathematical Software","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G11231614","display_name":null,"funder_award_id":"CCF-1320112, ACI-1148125/1340293, and ACI-1550493","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W133977063","https://openalex.org/W1947869163","https://openalex.org/W1981663184","https://openalex.org/W1983157164","https://openalex.org/W2002257715","https://openalex.org/W2016279572","https://openalex.org/W2035476608","https://openalex.org/W2043275593","https://openalex.org/W2050090934","https://openalex.org/W2061397794","https://openalex.org/W2073061372","https://openalex.org/W2084379367","https://openalex.org/W2093529653","https://openalex.org/W2125457238","https://openalex.org/W2135653967","https://openalex.org/W2146406121","https://openalex.org/W2169631286","https://openalex.org/W2252007067","https://openalex.org/W2289632204","https://openalex.org/W2412152731","https://openalex.org/W2516525699","https://openalex.org/W2953065450","https://openalex.org/W3136479147","https://openalex.org/W4229666556"],"related_works":["https://openalex.org/W2148952300","https://openalex.org/W3099313426","https://openalex.org/W4287593139","https://openalex.org/W752783541","https://openalex.org/W1506547947","https://openalex.org/W3138063244","https://openalex.org/W2995605830","https://openalex.org/W4206811032","https://openalex.org/W2086123442","https://openalex.org/W2596457687"],"abstract_inverted_index":{"In":[0],"this":[1],"article,":[2],"we":[3],"explore":[4],"the":[5,20,35,56,103,111,131,141,147,158,169,177,180],"implementation":[6,196],"of":[7,50,120,134,151],"complex":[8,32,51,59],"matrix":[9,52,126],"multiplication.":[10],"We":[11,42,96,129],"begin":[12],"by":[13],"briefly":[14],"identifying":[15],"various":[16],"challenges":[17,197],"associated":[18],"with":[19,116],"conventional":[21],"approach,":[22],"which":[23,121],"calls":[24],"for":[25,58],"a":[26,48],"carefully":[27],"written":[28],"kernel":[29,85],"that":[30,54,109,140,167,198],"implements":[31],"arithmetic":[33],"at":[34],"lowest":[36],"possible":[37],"level":[38],"(i.e.,":[39],"assembly":[40],"language).":[41],"then":[43],"set":[44],"out":[45],"to":[46,87,195],"develop":[47,97],"method":[49,106,143,175],"multiplication":[53,127],"avoids":[55],"need":[57],"kernels":[60],"altogether.":[61],"This":[62],"constraint":[63],"promotes":[64],"code":[65],"reuse":[66],"and":[67,77,83,93,107,138,161],"portability":[68],"within":[69,157],"libraries":[70],"such":[71],"as":[72],"Basic":[73],"Linear":[74],"Algebra":[75],"Subprograms":[76],"BLAS-Like":[78],"Library":[79],"Instantiation":[80],"Software":[81],"(BLIS)":[82],"allows":[84],"developers":[86],"focus":[88],"their":[89],"efforts":[90],"on":[91,102,124,163],"fewer":[92],"simpler":[94],"kernels.":[95,128],"two":[98],"alternative":[99],"approaches\u2014one":[100],"based":[101],"3":[104,173],"m":[105,114,149,174,188],"one":[108],"reflects":[110],"classic":[112],"4":[113,148,187],"formulation\u2014each":[115],"multiple":[117],"variants,":[118],"all":[119],"rely":[122],"only":[123],"real":[125],"discuss":[130],"performance":[132,190],"characteristics":[133],"these":[135],"\u201cinduced\u201d":[136],"methods":[137],"observe":[139],"assembly-level":[142],"actually":[144],"resides":[145],"along":[146],"spectrum":[150],"algorithmic":[152],"variants.":[153],"Implementations":[154],"are":[155],"developed":[156],"BLIS":[159],"framework,":[160],"testing":[162],"modern":[164],"hardware":[165],"confirms":[166],"while":[168],"less":[170],"numerically":[171],"stable":[172,182],"yields":[176],"fastest":[178],"runtimes,":[179],"more":[181],"(and":[183],"thus":[184],"widely":[185],"applicable)":[186],"method\u2019s":[189],"is":[191],"somewhat":[192],"limited":[193],"due":[194],"appear":[199],"inherent":[200],"in":[201],"nature.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
