{"id":"https://openalex.org/W3103789084","doi":null,"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/W3103789084","mag":"3103789084"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.24.7358","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.24.7358","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://csl.anu.edu.au/~daa/files/europar2000.ps.gz","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5015132137","display_name":"Douglas Aberdeen","orcid":null,"observed_orcids":[]},"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":"Douglas Aberdeen","raw_affiliation_strings":["Research School of Information Sciences and Engineering, Australian National University, Australia"],"raw_orcid":null,"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":"https://openalex.org/A5108191771","display_name":"Jonathan Baxter","orcid":null,"observed_orcids":[]},"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"],"raw_orcid":null,"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":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I118347636"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":93},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9603999853134155,"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":0.9603999853134155,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.03720000013709068,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.00139999995008111,"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-matrix-multiplication","display_name":"matrix-matrix multiplication","score":0.9959999918937683},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.9409999847412109},{"id":"https://openalex.org/keywords/floating-point-arithmetic","display_name":"floating-point arithmetic","score":0.9169999957084656},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"memory hierarchy","score":0.925000011920929},{"id":"https://openalex.org/keywords/parallel-algorithms","display_name":"parallel algorithms","score":0.44200000166893005},{"id":"https://openalex.org/keywords/performance-optimization","display_name":"performance optimization","score":0.43799999356269836}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7304898500442505},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.7202816009521484},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.677716076374054},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.6223788261413574},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.5275818109512329},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5203694701194763},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.4474829435348511},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.43487679958343506},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37892627716064453},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.3589822053909302},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20391041040420532},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.15026938915252686},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.08708015084266663},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.24.7358","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.24.7358","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://csl.anu.edu.au/~daa/files/europar2000.ps.gz","raw_type":"text"},{"id":"pmh:oai:openresearch-repository.anu.edu.au:1885/27679","doi":null,"is_oa":false,"landing_page_url":"http://hdl.handle.net/1885/27679","pdf_url":null,"source":{"id":"https://openalex.org/S4306402539","display_name":"ANU Open Research (Australian National University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I118347636","host_organization_name":"Australian National University","host_organization_lineage":["https://openalex.org/I118347636"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EuroPar-2000","raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W1964031104","https://openalex.org/W2136811828","https://openalex.org/W3102635321","https://openalex.org/W3139307873"],"related_works":["https://openalex.org/W1493501700","https://openalex.org/W2116431830","https://openalex.org/W7100716479","https://openalex.org/W1502634912","https://openalex.org/W2056999868","https://openalex.org/W2808588760","https://openalex.org/W1595041639","https://openalex.org/W7056535043","https://openalex.org/W7095704764","https://openalex.org/W7097991001"],"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],"benets":[15],"these":[16],"In":[18],"this":[19],"paper":[20],"we":[21],"implement":[22],"ecient":[23],"matrix":[24],"for":[26],"large":[27],"matrices":[28],"using":[29],"oating":[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":2022,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2020-11-23T00:00:00"}
