{"id":"https://openalex.org/W1485294004","doi":"https://doi.org/10.1007/3-540-44520-x_138","title":"General Matrix-Matrix Multiplication Using SIMD Features of the PIII","display_name":"General Matrix-Matrix Multiplication Using SIMD Features of the PIII","publication_year":2000,"publication_date":"2000-01-01","ids":{"openalex":"https://openalex.org/W1485294004","doi":"https://doi.org/10.1007/3-540-44520-x_138","mag":"1485294004"},"language":"en","primary_location":{"id":"doi:10.1007/3-540-44520-x_138","is_oa":true,"landing_page_url":"https://doi.org/10.1007/3-540-44520-x_138","pdf_url":"https://link.springer.com/content/pdf/10.1007%2F3-540-44520-X_138.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007%2F3-540-44520-X_138.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Douglas Aberdeen","orcid":null},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Douglas Aberdeen","raw_affiliation_strings":["Research School of Information Sciences and Engineering, Australian National University, Australia"],"affiliations":[{"raw_affiliation_string":"Research School of Information Sciences and Engineering, Australian National University, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jonathan Baxter","orcid":null},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jonathan Baxter","raw_affiliation_strings":["Research School of Information Sciences and Engineering, Australian National University, Australia"],"affiliations":[{"raw_affiliation_string":"Research School of Information Sciences and Engineering, Australian National University, Australia","institution_ids":["https://openalex.org/I118347636"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I118347636"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392},"fwci":0.0,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.11429502,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"980","last_page":"983"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11697","display_name":"Numerical Methods and Algorithms","score":0.3061999976634979,"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":0.3061999976634979,"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":0.24250000715255737,"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/T12303","display_name":"Tensor decomposition and applications","score":0.11190000176429749,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.8652999997138977},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.7696999907493591},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.7055000066757202},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.66839998960495},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4465000033378601},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4332999885082245},{"id":"https://openalex.org/keywords/multiplication-algorithm","display_name":"Multiplication algorithm","score":0.40959998965263367},{"id":"https://openalex.org/keywords/floating-point","display_name":"Floating point","score":0.39969998598098755}],"concepts":[{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.8652999997138977},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8349999785423279},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.7696999907493591},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.7055000066757202},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.66839998960495},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6345000267028809},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.44850000739097595},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4465000033378601},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4332999885082245},{"id":"https://openalex.org/C201290732","wikidata":"https://www.wikidata.org/wiki/Q130762","display_name":"Multiplication algorithm","level":3,"score":0.40959998965263367},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.39969998598098755},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.3578000068664551},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.3248000144958496},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3203999996185303},{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C106515295","wikidata":"https://www.wikidata.org/wiki/Q26806595","display_name":"Parallel processing","level":2,"score":0.2849999964237213},{"id":"https://openalex.org/C16901944","wikidata":"https://www.wikidata.org/wiki/Q367183","display_name":"Addressing mode","level":4,"score":0.2815000116825104},{"id":"https://openalex.org/C120373497","wikidata":"https://www.wikidata.org/wiki/Q1087987","display_name":"Parallel algorithm","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.2759000062942505},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.2687999904155731},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.2612000107765198}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/3-540-44520-x_138","is_oa":true,"landing_page_url":"https://doi.org/10.1007/3-540-44520-x_138","pdf_url":"https://link.springer.com/content/pdf/10.1007%2F3-540-44520-X_138.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:arXiv.org:1912.04379","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1912.04379","pdf_url":"https://arxiv.org/pdf/1912.04379","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1007/3-540-44520-x_138","is_oa":true,"landing_page_url":"https://doi.org/10.1007/3-540-44520-x_138","pdf_url":"https://link.springer.com/content/pdf/10.1007%2F3-540-44520-X_138.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1485294004.pdf","grobid_xml":"https://content.openalex.org/works/W1485294004.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W1964031104","https://openalex.org/W2136811828","https://openalex.org/W3102635321","https://openalex.org/W3139307873"],"related_works":[],"abstract_inverted_index":{"Generalised":[0],"matrix-matrix":[1,12,74],"multiplication":[2,25],"forms":[3],"the":[4,30,43,56,70],"kernel":[5],"of":[6,42,55,65],"many":[7],"mathematical":[8],"algorithms.":[9,17],"A":[10,40],"faster":[11,68],"multiply":[13,75],"immediately":[14],"benefits":[15],"these":[16],"In":[18],"this":[19],"paper":[20],"we":[21],"implement":[22],"efficient":[23],"matrix":[24],"for":[26],"large":[27],"matrices":[28],"using":[29],"floating":[31],"point":[32],"Intel":[33],"SIMD":[34],"(Single":[35],"Instruction":[36],"Multiple":[37],"Data)":[38],"architecture.":[39],"description":[41],"issues":[44],"and":[45],"our":[46],"solution":[47],"is":[48],"presented,":[49],"paying":[50],"attention":[51],"to":[52],"all":[53],"levels":[54],"memory":[57],"hierarchy.":[58],"Our":[59],"results":[60],"demonstrate":[61],"an":[62],"average":[63],"performance":[64],"2.09":[66],"times":[67],"than":[69],"leading":[71],"public":[72],"domain":[73],"routines.":[76]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2016-06-24T00:00:00"}