{"id":"https://openalex.org/W2154641788","doi":"https://doi.org/10.1109/ipdps.2010.5470443","title":"Tile QR factorization with parallel panel processing for multicore architectures","display_name":"Tile QR factorization with parallel panel processing for multicore architectures","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2154641788","doi":"https://doi.org/10.1109/ipdps.2010.5470443","mag":"2154641788"},"language":"en","primary_location":{"id":"doi:10.1109/ipdps.2010.5470443","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2010.5470443","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Symposium on Parallel & Distributed Processing (IPDPS)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/inria-00548899","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026042046","display_name":"Bilel Hadri","orcid":"https://orcid.org/0000-0002-8796-9791"},"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":"Bilel Hadri","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of Tennessee, Knoxville, TN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of Tennessee, Knoxville, TN, USA","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017526753","display_name":"Hatem Ltaief","orcid":"https://orcid.org/0000-0002-6897-1095"},"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, Knoxville, TN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of Tennessee, Knoxville, TN, USA","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074132178","display_name":"Emmanuel Agullo","orcid":"https://orcid.org/0000-0003-0655-6934"},"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":"Emmanuel Agullo","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of Tennessee, Knoxville, TN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of Tennessee, Knoxville, TN, USA","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075517045","display_name":"Jack Dongarra","orcid":"https://orcid.org/0000-0003-3247-1782"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]},{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]},{"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":["GB","US"],"is_corresponding":false,"raw_author_name":"Jack Dongarra","raw_affiliation_strings":["Computer Science and Mathematics Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA","Department of Electrical Engineering and Computer Science, University of Tennessee, Knoxville, TN, USA","School of Mathematics & School of Computer Science, University of Manchester, Institute of Science and Technology, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Mathematics Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]},{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of Tennessee, Knoxville, TN, USA","institution_ids":["https://openalex.org/I75027704"]},{"raw_affiliation_string":"School of Mathematics & School of Computer Science, University of Manchester, Institute of Science and Technology, UK","institution_ids":["https://openalex.org/I28407311"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.996999979019165,"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":0.996999979019165,"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/T12029","display_name":"DNA and Biological Computing","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12162","display_name":"Cellular Automata and Applications","score":0.9965000152587891,"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/computer-science","display_name":"Computer science","score":0.8040021061897278},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7328826189041138},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.6755505800247192},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.6476821899414062},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5540435314178467},{"id":"https://openalex.org/keywords/qr-decomposition","display_name":"QR decomposition","score":0.5351384878158569},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.48527857661247253},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.47937729954719543},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.44948846101760864},{"id":"https://openalex.org/keywords/tile","display_name":"Tile","score":0.43010926246643066},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3819007873535156},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24922075867652893},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12270766496658325},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.0950784683227539}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8040021061897278},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7328826189041138},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.6755505800247192},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.6476821899414062},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5540435314178467},{"id":"https://openalex.org/C188060507","wikidata":"https://www.wikidata.org/wiki/Q653242","display_name":"QR decomposition","level":3,"score":0.5351384878158569},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.48527857661247253},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.47937729954719543},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.44948846101760864},{"id":"https://openalex.org/C2780728851","wikidata":"https://www.wikidata.org/wiki/Q468402","display_name":"Tile","level":2,"score":0.43010926246643066},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3819007873535156},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24922075867652893},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12270766496658325},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0950784683227539},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/ipdps.2010.5470443","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2010.5470443","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Symposium on Parallel & Distributed Processing (IPDPS)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.161.5428","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.161.5428","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://icl.cs.utk.edu/news_pub/submissions/tile-caqr-ipdps.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.986.3629","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.986.3629","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://hal.archives-ouvertes.fr/file/index/docid/548899/filename/tile-caqr-ipdps.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:inria-00548899v1","is_oa":true,"landing_page_url":"https://inria.hal.science/inria-00548899","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"24th IEEE International Parallel and Distributed Processing Symposium (IPDPS 2010), Apr 2010, Atlanta, United States","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:inria-00548899v1","is_oa":true,"landing_page_url":"https://inria.hal.science/inria-00548899","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"24th IEEE International Parallel and Distributed Processing Symposium (IPDPS 2010), Apr 2010, Atlanta, United States","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W94439627","https://openalex.org/W171963546","https://openalex.org/W1480928214","https://openalex.org/W2014116693","https://openalex.org/W2018338919","https://openalex.org/W2039778940","https://openalex.org/W2040425799","https://openalex.org/W2042025615","https://openalex.org/W2064744742","https://openalex.org/W2095041371","https://openalex.org/W2095597068","https://openalex.org/W2124480634","https://openalex.org/W2145960411","https://openalex.org/W2157237396","https://openalex.org/W2798909945","https://openalex.org/W2950745813","https://openalex.org/W2951500637","https://openalex.org/W4210861204","https://openalex.org/W4231150350","https://openalex.org/W6682839433"],"related_works":["https://openalex.org/W2114959296","https://openalex.org/W38346124","https://openalex.org/W2502442966","https://openalex.org/W2138666621","https://openalex.org/W2383936314","https://openalex.org/W160834089","https://openalex.org/W2112488134","https://openalex.org/W2021525945","https://openalex.org/W3007255846","https://openalex.org/W1985693271"],"abstract_inverted_index":{"To":[0],"exploit":[1],"the":[2,129,161],"potential":[3],"of":[4,25,27,39,63,131],"multicore":[5,97],"architectures,":[6],"recent":[7],"dense":[8],"linear":[9],"algebra":[10],"libraries":[11],"have":[12],"used":[13],"tile":[14,132],"algorithms,":[15],"which":[16],"consist":[17],"in":[18,67,116],"scheduling":[19],"a":[20,40,65,85,92,113],"Directed":[21],"Acyclic":[22],"Graph":[23],"(DAG)":[24],"tasks":[26],"fine":[28],"granularity":[29],"where":[30],"nodes":[31],"represent":[32,44],"tasks,":[33],"either":[34],"panel":[35,66,114],"factorization":[36,94,115],"or":[37,79],"update":[38],"block-column,":[41],"and":[42,57,76,122],"edges":[43],"dependencies":[45],"among":[46],"them.":[47],"Although":[48],"past":[49],"approaches":[50],"already":[51],"achieve":[52],"high":[53],"performance":[54,72],"on":[55,95],"moderate":[56],"large":[58],"square":[59,81],"matrices,":[60],"their":[61],"way":[62],"processing":[64],"sequence":[68],"leads":[69],"to":[70,106,128,144,150,155],"limited":[71],"when":[73],"factorizing":[74],"tall":[75],"skinny":[77],"matrices":[78],"small":[80],"matrices.":[82],"We":[83,153],"present":[84],"new":[86],"fully":[87],"asynchronous":[88,135],"method":[89],"for":[90,125,165],"computing":[91],"QR":[93,121],"shared-memory":[96],"architectures":[98],"that":[99,111],"overcomes":[100],"this":[101,158],"bottleneck.":[102],"Our":[103],"contribution":[104],"is":[105],"adapt":[107],"an":[108],"existing":[109],"algorithm":[110],"performs":[112],"parallel":[117],"(named":[118],"Communication-A":[119],"voiding":[120],"initially":[123],"designed":[124],"distributed-memory":[126],"machines),":[127],"context":[130],"algorithms":[133],"using":[134],"computations.":[136],"An":[137],"experimental":[138],"study":[139],"shows":[140],"significant":[141],"improvement":[142],"(up":[143],"almost":[145],"10":[146],"times":[147],"faster)":[148],"compared":[149],"state-of-the-art":[151],"approaches.":[152],"aim":[154],"eventually":[156],"incorporate":[157],"work":[159],"into":[160],"Parallel":[162],"Linear":[163],"Algebra":[164],"Scalable":[166],"Multi-core":[167],"Architectures":[168],"(PLASMA)":[169],"library.":[170]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}