{"id":"https://openalex.org/W4381327473","doi":"https://doi.org/10.1145/3577193.3593707","title":"Towards a Unified Implementation of GEMM in BLIS","display_name":"Towards a Unified Implementation of GEMM in BLIS","publication_year":2023,"publication_date":"2023-06-20","ids":{"openalex":"https://openalex.org/W4381327473","doi":"https://doi.org/10.1145/3577193.3593707"},"language":"en","primary_location":{"id":"doi:10.1145/3577193.3593707","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1145/3577193.3593707","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3577193.3593707?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th International Conference on Supercomputing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3577193.3593707?download=true","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018163531","display_name":"RuQing G. Xu","orcid":"https://orcid.org/0000-0002-5782-716X"},"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":"RuQing G. Xu","raw_affiliation_strings":["The University of Tokyo, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-5782-716X","affiliations":[{"raw_affiliation_string":"The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","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, USA"],"raw_orcid":"https://orcid.org/0009-0007-2498-9430","affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061722569","display_name":"Robert A. Geijn","orcid":"https://orcid.org/0009-0004-6434-8492"},"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":"Robert A. van de Geijn","raw_affiliation_strings":["The University of Texas at Austin, Austin, United States"],"raw_orcid":"https://orcid.org/0009-0004-6434-8492","affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, Austin, United States","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"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":0.07163498,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"111","last_page":"121"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9983000159263611,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.7845393419265747},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.613754153251648},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.5871111154556274},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.5755528211593628},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5721243023872375},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5005476474761963},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4886963665485382},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.45040470361709595},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4108957052230835},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3883529603481293},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.15337029099464417}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7845393419265747},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.613754153251648},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.5871111154556274},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.5755528211593628},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5721243023872375},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5005476474761963},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4886963665485382},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.45040470361709595},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4108957052230835},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3883529603481293},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.15337029099464417},{"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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3577193.3593707","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1145/3577193.3593707","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3577193.3593707?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th International Conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3577193.3593707","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1145/3577193.3593707","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3577193.3593707?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th International Conference on Supercomputing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2794193206","display_name":null,"funder_award_id":"CSSI-2003921","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5931240580","display_name":"Collaborative Research: Frameworks: Beyond the BLAS: A framework for accelerating computational and data science","funder_award_id":"2003921","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"},{"id":"https://openalex.org/F4320308696","display_name":"Georgia Space Grant Consortium","ror":"https://ror.org/013b2jw60"},{"id":"https://openalex.org/F4320310620","display_name":"University of Texas at Austin","ror":"https://ror.org/00hj54h04"},{"id":"https://openalex.org/F4320322832","display_name":"University of Tokyo","ror":"https://ror.org/057zh3y96"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4381327473.pdf"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1975244539","https://openalex.org/W1988425770","https://openalex.org/W2002257715","https://openalex.org/W2038469228","https://openalex.org/W2073061372","https://openalex.org/W2084379367","https://openalex.org/W2087158689","https://openalex.org/W2252007067","https://openalex.org/W2412152731","https://openalex.org/W2516525699","https://openalex.org/W2588061952","https://openalex.org/W2737067755","https://openalex.org/W2949953997","https://openalex.org/W2954698171","https://openalex.org/W3084619881","https://openalex.org/W3099506637","https://openalex.org/W4241904697","https://openalex.org/W4244254628","https://openalex.org/W4251235123","https://openalex.org/W4281707342","https://openalex.org/W4284689293","https://openalex.org/W6647710255"],"related_works":["https://openalex.org/W3000097931","https://openalex.org/W2354322770","https://openalex.org/W2384867379","https://openalex.org/W1599154403","https://openalex.org/W1925544630","https://openalex.org/W110174833","https://openalex.org/W2004686618","https://openalex.org/W2883805925","https://openalex.org/W4200572757","https://openalex.org/W4285148873"],"abstract_inverted_index":{"Matrix":[0],"libraries":[1,103],"often":[2],"focus":[3],"on":[4,148],"achieving":[5],"high":[6,46],"performance":[7,47,80,92,147],"for":[8,34,48,77],"problems":[9],"considered":[10],"to":[11,22,25,58,67,111],"be":[12],"either":[13],"\"small\"":[14],"or":[15],"\"large\",":[16],"as":[17],"these":[18],"two":[19],"scenarios":[20],"tend":[21],"respond":[23],"best":[24],"different":[26],"optimization":[27],"strategies.":[28],"We":[29],"propose":[30],"a":[31,68,99,120,125,149],"unified":[32],"technique":[33,134],"implementing":[35],"matrix":[36,40,79],"operations":[37],"like":[38],"general":[39],"multiplication":[41],"(gemm)":[42],"that":[43,64,88,117],"can":[44],"achieve":[45],"both":[49],"small":[50],"and":[51,73,114,124,146],"large":[52,78],"problem":[53,95],"sizes.":[54],"The":[55],"key":[56],"is":[57,75,144,153],"fuse":[59],"packing":[60],"-":[61,81],"an":[62],"operation":[63],"copies":[65],"data":[66],"contiguous":[69],"layout":[70],"in":[71],"memory":[72],"which":[74],"critical":[76],"with":[82,136],"the":[83,94,109,133,137],"first":[84],"computational":[85],"\"pass\"":[86],"over":[87],"data.":[89],"This":[90],"boosts":[91],"across":[93],"size":[96],"spectrum.":[97],"As":[98],"result,":[100],"tuning":[101],"general-purpose":[102],"becomes":[104],"simpler":[105],"since":[106],"it":[107],"obviates":[108],"need":[110],"carefully":[112],"express":[113],"parameterize":[115],"logic":[116],"chooses":[118],"between":[119],"\"small":[121],"matrix\"":[122,127],"strategy":[123],"\"large":[126],"strategy.":[128],"A":[129],"prototype":[130],"implementation":[131],"of":[132,151],"built":[135],"BLAS-like":[138],"Library":[139],"Instantiation":[140],"Software":[141],"(BLIS)":[142],"framework":[143],"described":[145],"range":[150],"architectures":[152],"reported.":[154]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
