{"id":"https://openalex.org/W6889796878","doi":"https://doi.org/10.3233/spr-2010-0297","title":"Scheduling Two-Sided Transformations Using Tile Algorithms on Multicore Architectures","display_name":"Scheduling Two-Sided Transformations Using Tile Algorithms on Multicore Architectures","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W6889796878","doi":"https://doi.org/10.3233/spr-2010-0297"},"language":"en","primary_location":{"id":"pmh:oai:doaj.org/article:f4b4c835892842a8861bf3de6589d004","is_oa":true,"landing_page_url":"https://doaj.org/article/f4b4c835892842a8861bf3de6589d004","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scientific Programming, Vol 18, Iss 1, Pp 35-50 (2010)","raw_type":"article"},"type":"article","indexed_in":["doaj"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doaj.org/article/f4b4c835892842a8861bf3de6589d004","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Hatem Ltaief","orcid":null},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hatem Ltaief","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of Tennessee, TN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of Tennessee, TN, USA","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jakub Kurzak","orcid":null},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jakub Kurzak","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of Tennessee, TN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of Tennessee, TN, USA","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jack Dongarra","orcid":null},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jack Dongarra","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of Tennessee, TN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of Tennessee, TN, USA","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"last","author":{"id":null,"display_name":"Rosa M. Badia","orcid":null},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Rosa M. Badia","raw_affiliation_strings":["Barcelona Supercomputing Center \u2013 Centro Nacional de Supercomputaci\u00f3n, Consejo Nacional de Investigaciones Cientificas, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center \u2013 Centro Nacional de Supercomputaci\u00f3n, Consejo Nacional de Investigaciones Cientificas, Barcelona, Spain","institution_ids":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]}]}],"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":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.46785975,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.7523000240325928,"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":0.7523000240325928,"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":0.09860000014305115,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.06390000134706497,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.7534000277519226},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.6355000138282776},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6288999915122986},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.5691999793052673},{"id":"https://openalex.org/keywords/tile","display_name":"Tile","score":0.48249998688697815},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4251999855041504},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.38260000944137573},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.3619000017642975},{"id":"https://openalex.org/keywords/numerical-linear-algebra","display_name":"Numerical linear algebra","score":0.35519999265670776}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7786999940872192},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.7534000277519226},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7038000226020813},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.6355000138282776},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6288999915122986},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.5691999793052673},{"id":"https://openalex.org/C2780728851","wikidata":"https://www.wikidata.org/wiki/Q468402","display_name":"Tile","level":2,"score":0.48249998688697815},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4251999855041504},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42329999804496765},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.38260000944137573},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.3619000017642975},{"id":"https://openalex.org/C163834973","wikidata":"https://www.wikidata.org/wiki/Q2004891","display_name":"Numerical linear algebra","level":3,"score":0.35519999265670776},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.3529999852180481},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.33169999718666077},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.3305000066757202},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.3303999900817871},{"id":"https://openalex.org/C193702766","wikidata":"https://www.wikidata.org/wiki/Q1414548","display_name":"Concurrency","level":2,"score":0.3125},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C9395851","wikidata":"https://www.wikidata.org/wiki/Q177929","display_name":"Stack (abstract data type)","level":2,"score":0.3005000054836273},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.26829999685287476},{"id":"https://openalex.org/C96147967","wikidata":"https://www.wikidata.org/wiki/Q190686","display_name":"Subroutine","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C53833338","wikidata":"https://www.wikidata.org/wiki/Q1061424","display_name":"Context switch","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:doaj.org/article:f4b4c835892842a8861bf3de6589d004","is_oa":true,"landing_page_url":"https://doaj.org/article/f4b4c835892842a8861bf3de6589d004","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scientific Programming, Vol 18, Iss 1, Pp 35-50 (2010)","raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:doaj.org/article:f4b4c835892842a8861bf3de6589d004","is_oa":true,"landing_page_url":"https://doaj.org/article/f4b4c835892842a8861bf3de6589d004","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scientific Programming, Vol 18, Iss 1, Pp 35-50 (2010)","raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,166],"objective":[1],"of":[2,11,104,151,169],"this":[3],"paper":[4],"is":[5,110,120,177],"to":[6,66,69,122,125,149,191,194,200],"describe,":[7],"in":[8,24,107,185],"the":[9,19,26,33,37,42,54,75,78,102,123,152,170,179,197,201],"context":[10],"multicore":[12,63,89],"architectures,":[13],"three":[14],"different":[15],"scheduler":[16],"implementations":[17],"for":[18,36,87,135,174],"two-sided":[20,140,175],"linear":[21,49],"algebra":[22,50],"transformations,":[23],"particular":[25],"Hessenberg":[27],"and":[28,41,56],"Bidiagonal":[29],"reductions":[30,141],"which":[31,108],"are":[32],"first":[34],"steps":[35],"standard":[38],"eigenvalue":[39],"problems":[40],"singular":[43],"value":[44],"decompositions":[45],"respectively.":[46],"State-of-the-art":[47],"dense":[48],"softwares,":[51],"such":[52],"as":[53,84],"LAPACK":[55],"ScaLAPACK":[57],"libraries,":[58],"suffer":[59],"performance":[60,144],"losses":[61],"on":[62,155],"processors":[64],"due":[65],"their":[67],"inability":[68],"fully":[70],"exploit":[71],"thread-level":[72],"parallelism.":[73],"At":[74],"same":[76],"time":[77],"fine-grain":[79],"dataflow":[80],"model":[81],"gains":[82],"popularity":[83],"a":[85,156],"paradigm":[86],"programming":[88],"architectures.":[90],"Buttari":[91],"et":[92],"al.":[93],"(Parellel":[94],"Comput.":[95],"Syst.":[96],"Appl.":[97],"35":[98],"(2009),":[99],"38\u201353)":[100],"introduced":[101],"concept":[103],"tile":[105,139,171],"algorithms":[106,172],"parallelism":[109],"no":[111],"longer":[112],"hidden":[113],"inside":[114],"Basic":[115],"Linear":[116],"Algebra":[117],"Subprograms":[118],"but":[119],"brought":[121],"fore":[124],"yield":[126],"much":[127],"better":[128],"performance.":[129],"Along":[130],"with":[131,159],"efficient":[132],"scheduling":[133],"mechanisms":[134],"data-driven":[136],"execution,":[137],"these":[138],"achieve":[142],"high":[143],"computing":[145],"by":[146],"reaching":[147],"up":[148],"75%":[150],"DGEMM":[153],"peak":[154],"12000\u00d712000":[157],"matrix":[158],"16":[160],"Intel":[161],"Tigerton":[162],"2.4":[163],"GHz":[164],"processors.":[165],"main":[167],"drawback":[168],"approach":[173],"transformations":[176],"that":[178],"full":[180],"reduction":[181],"cannot":[182],"be":[183,192],"obtained":[184],"one":[186],"stage.":[187],"Other":[188],"methods":[189],"have":[190],"considered":[193],"further":[195],"reduce":[196],"band":[198],"matrices":[199],"required":[202],"forms.":[203]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}