{"id":"https://openalex.org/W2159998508","doi":"https://doi.org/10.1109/ipdps.2008.4536353","title":"Design of scalable dense linear algebra libraries for multithreaded architectures: the LU factorization","display_name":"Design of scalable dense linear algebra libraries for multithreaded architectures: the LU factorization","publication_year":2008,"publication_date":"2008-04-01","ids":{"openalex":"https://openalex.org/W2159998508","doi":"https://doi.org/10.1109/ipdps.2008.4536353","mag":"2159998508"},"language":"en","primary_location":{"id":"doi:10.1109/ipdps.2008.4536353","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2008.4536353","pdf_url":null,"source":{"id":"https://openalex.org/S4210174069","display_name":"Proceedings - IEEE International Parallel and Distributed Processing Symposium","issn_l":"1530-2075","issn":["1530-2075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Symposium on Parallel and Distributed Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5086284706","display_name":"Gregorio Quintana\u2010Ort\u00ed","orcid":"https://orcid.org/0000-0002-7912-7826"},"institutions":[{"id":"https://openalex.org/I10902133","display_name":"Universitat Jaume I","ror":"https://ror.org/02ws1xc11","country_code":"ES","type":"education","lineage":["https://openalex.org/I10902133"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Gregorio Quintana-Orti","raw_affiliation_strings":["Departmento de Ingenier\u00eda y Ciencia de Computadores, Universidad Jaume I, Castellon, Spain"],"affiliations":[{"raw_affiliation_string":"Departmento de Ingenier\u00eda y Ciencia de Computadores, Universidad Jaume I, Castellon, Spain","institution_ids":["https://openalex.org/I10902133"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012806004","display_name":"Enrique S. Quintana\u2013Ort\u0301\u0131","orcid":"https://orcid.org/0000-0002-5454-165X"},"institutions":[{"id":"https://openalex.org/I10902133","display_name":"Universitat Jaume I","ror":"https://ror.org/02ws1xc11","country_code":"ES","type":"education","lineage":["https://openalex.org/I10902133"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Enrique S. Quintana-Orti","raw_affiliation_strings":["Departmento de Ingenier\u00eda y Ciencia de Computadores, Universidad Jaume I, Castellon, Spain"],"affiliations":[{"raw_affiliation_string":"Departmento de Ingenier\u00eda y Ciencia de Computadores, Universidad Jaume I, Castellon, Spain","institution_ids":["https://openalex.org/I10902133"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051174937","display_name":"Ernie Chan","orcid":null},"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":"Ernie Chan","raw_affiliation_strings":["Department of Computer Sciences, University of Texas, Austin, Austin, TX, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Sciences, University of Texas, Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","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":["Department of Computer Sciences, University of Texas, Austin, Austin, TX, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Sciences, University of Texas, Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","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":["Department of Computer Sciences, University of Texas, Austin, Austin, TX, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Sciences, University of Texas, Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5086284706"],"corresponding_institution_ids":["https://openalex.org/I10902133"],"apc_list":null,"apc_paid":null,"fwci":2.7556,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.91498374,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9965999722480774,"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/T10126","display_name":"Logic, programming, and type systems","score":0.9948999881744385,"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":0.8134359121322632},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.8093744516372681},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7813645601272583},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.7247220873832703},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.5987672805786133},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5558729767799377},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.4799611568450928},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.4490368068218231},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4111921489238739},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1660381555557251},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12654051184654236},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12166222929954529},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10512411594390869}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8134359121322632},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8093744516372681},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7813645601272583},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.7247220873832703},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.5987672805786133},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5558729767799377},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.4799611568450928},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.4490368068218231},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4111921489238739},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1660381555557251},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12654051184654236},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12166222929954529},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10512411594390869},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ipdps.2008.4536353","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2008.4536353","pdf_url":null,"source":{"id":"https://openalex.org/S4210174069","display_name":"Proceedings - IEEE International Parallel and Distributed Processing Symposium","issn_l":"1530-2075","issn":["1530-2075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Symposium on Parallel and Distributed Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.140.1364","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.140.1364","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.utexas.edu/users/flame/pubs/LU_SuperMatrix.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332500","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1555915743","https://openalex.org/W1589630408","https://openalex.org/W1973305402","https://openalex.org/W1988425770","https://openalex.org/W2002257715","https://openalex.org/W2005900526","https://openalex.org/W2016358047","https://openalex.org/W2019592888","https://openalex.org/W2021525945","https://openalex.org/W2038469228","https://openalex.org/W2047656763","https://openalex.org/W2059807497","https://openalex.org/W2079658918","https://openalex.org/W2081114193","https://openalex.org/W2095597068","https://openalex.org/W2124480634","https://openalex.org/W2135622428","https://openalex.org/W2136570295","https://openalex.org/W2151994818","https://openalex.org/W2152786407","https://openalex.org/W2725179571","https://openalex.org/W2798909945","https://openalex.org/W2896073125","https://openalex.org/W2950745813"],"related_works":["https://openalex.org/W2120447654","https://openalex.org/W2977179488","https://openalex.org/W2144453115","https://openalex.org/W2128223750","https://openalex.org/W4238532390","https://openalex.org/W2188872161","https://openalex.org/W2961779879","https://openalex.org/W797688974","https://openalex.org/W2002978035","https://openalex.org/W2025467172"],"abstract_inverted_index":{"The":[0,43],"scalable":[1],"parallel":[2],"implementation,":[3],"targeting":[4],"SMP":[5],"and/or":[6],"multicore":[7],"architectures,":[8],"of":[9,34,45,58],"dense":[10],"linear":[11],"algebra":[12],"libraries":[13],"is":[14,25,53,61],"analyzed.":[15],"Using":[16],"the":[17,49,56,59],"LU":[18],"factorization":[19],"as":[20],"a":[21,31],"case":[22],"study,":[23],"it":[24],"shown":[26],"that":[27],"an":[28],"algorithm-by-blocks":[29],"exposes":[30],"higher":[32],"degree":[33],"parallelism":[35],"than":[36],"traditional":[37],"implementations":[38],"based":[39],"on":[40,63],"multithreaded":[41],"BIAS.":[42],"implementation":[44],"this":[46],"algorithm":[47],"using":[48],"SuperMatrix":[50],"runtime":[51],"system":[52],"discussed":[54],"and":[55],"scalability":[57],"solution":[60],"demonstrated":[62],"two":[64],"different":[65],"platforms":[66],"with":[67],"16":[68],"processors.":[69]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}