{"id":"https://openalex.org/W2102248047","doi":"https://doi.org/10.1109/ipdps.2010.5470348","title":"Adapting communication-avoiding LU and QR factorizations to multicore architectures","display_name":"Adapting communication-avoiding LU and QR factorizations to multicore architectures","publication_year":2010,"publication_date":"2010-04-01","ids":{"openalex":"https://openalex.org/W2102248047","doi":"https://doi.org/10.1109/ipdps.2010.5470348","mag":"2102248047"},"language":"en","primary_location":{"id":"doi:10.1109/ipdps.2010.5470348","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2010.5470348","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":"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/A5022982824","display_name":"Simplice Donfack","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126360","display_name":"Inria Saclay - \u00cele de France","ror":"https://ror.org/0315e5x55","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210126360"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en informatique et en automatique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I102197404","display_name":"Universit\u00e9 Paris-Sud","ror":"https://ror.org/028rypz17","country_code":"FR","type":"education","lineage":["https://openalex.org/I102197404"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Simplice Donfack","raw_affiliation_strings":["INRIA Saclay-Ile de France, Universite Paris-Sud 11, Orsay, France","INRIA Saclay-Ile de France, Bat 490, Universite Paris-Sud 11, 91405, Orsay, France"],"affiliations":[{"raw_affiliation_string":"INRIA Saclay-Ile de France, Universite Paris-Sud 11, Orsay, France","institution_ids":["https://openalex.org/I4210126360","https://openalex.org/I102197404","https://openalex.org/I1326498283"]},{"raw_affiliation_string":"INRIA Saclay-Ile de France, Bat 490, Universite Paris-Sud 11, 91405, Orsay, France","institution_ids":["https://openalex.org/I4210126360","https://openalex.org/I102197404","https://openalex.org/I1326498283"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040521001","display_name":"Laura Grigori","orcid":"https://orcid.org/0000-0002-5880-1076"},"institutions":[{"id":"https://openalex.org/I4210126360","display_name":"Inria Saclay - \u00cele de France","ror":"https://ror.org/0315e5x55","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210126360"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en informatique et en automatique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I102197404","display_name":"Universit\u00e9 Paris-Sud","ror":"https://ror.org/028rypz17","country_code":"FR","type":"education","lineage":["https://openalex.org/I102197404"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Laura Grigori","raw_affiliation_strings":["INRIA Saclay-Ile de France, Universite Paris-Sud 11, Orsay, France","INRIA Saclay-Ile de France, Bat 490, Universite Paris-Sud 11, 91405, Orsay, France"],"affiliations":[{"raw_affiliation_string":"INRIA Saclay-Ile de France, Universite Paris-Sud 11, Orsay, France","institution_ids":["https://openalex.org/I4210126360","https://openalex.org/I102197404","https://openalex.org/I1326498283"]},{"raw_affiliation_string":"INRIA Saclay-Ile de France, Bat 490, Universite Paris-Sud 11, 91405, Orsay, France","institution_ids":["https://openalex.org/I4210126360","https://openalex.org/I102197404","https://openalex.org/I1326498283"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101688318","display_name":"Alok Kumar Gupta","orcid":"https://orcid.org/0000-0002-2562-1335"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alok Kumar Gupta","raw_affiliation_strings":["BCCS, Bergen, Norway","BCCS, Bergen Norway-5075"],"affiliations":[{"raw_affiliation_string":"BCCS, Bergen, Norway","institution_ids":[]},{"raw_affiliation_string":"BCCS, Bergen Norway-5075","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5022982824"],"corresponding_institution_ids":["https://openalex.org/I102197404","https://openalex.org/I1326498283","https://openalex.org/I4210126360"],"apc_list":null,"apc_paid":null,"fwci":2.2472,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.89129806,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"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":0.9998000264167786,"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":0.9998000264167786,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.843567967414856},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.7880365252494812},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.7071568965911865},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6476994156837463},{"id":"https://openalex.org/keywords/factor","display_name":"Factor (programming language)","score":0.4909253418445587},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.4773162305355072},{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.43688786029815674},{"id":"https://openalex.org/keywords/qr-decomposition","display_name":"QR decomposition","score":0.43148452043533325},{"id":"https://openalex.org/keywords/row","display_name":"Row","score":0.4217190444469452},{"id":"https://openalex.org/keywords/vendor","display_name":"Vendor","score":0.4159852862358093},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3941980004310608},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.32508477568626404},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14048010110855103},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09226709604263306}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.843567967414856},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.7880365252494812},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.7071568965911865},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6476994156837463},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.4909253418445587},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.4773162305355072},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.43688786029815674},{"id":"https://openalex.org/C188060507","wikidata":"https://www.wikidata.org/wiki/Q653242","display_name":"QR decomposition","level":3,"score":0.43148452043533325},{"id":"https://openalex.org/C135598885","wikidata":"https://www.wikidata.org/wiki/Q1366302","display_name":"Row","level":2,"score":0.4217190444469452},{"id":"https://openalex.org/C2777338717","wikidata":"https://www.wikidata.org/wiki/Q1762621","display_name":"Vendor","level":2,"score":0.4159852862358093},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3941980004310608},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.32508477568626404},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14048010110855103},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09226709604263306},{"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/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"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/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipdps.2010.5470348","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2010.5470348","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W43375082","https://openalex.org/W94439627","https://openalex.org/W98110951","https://openalex.org/W1502919101","https://openalex.org/W1525880654","https://openalex.org/W1606525066","https://openalex.org/W2007768252","https://openalex.org/W2018338919","https://openalex.org/W2026237859","https://openalex.org/W2030167104","https://openalex.org/W2042025615","https://openalex.org/W2115780241","https://openalex.org/W2124480634","https://openalex.org/W2157237396","https://openalex.org/W2951500637","https://openalex.org/W4210861204","https://openalex.org/W4231150350","https://openalex.org/W6601798773","https://openalex.org/W6631582148","https://openalex.org/W6635988513","https://openalex.org/W6682839433"],"related_works":["https://openalex.org/W1974923383","https://openalex.org/W2475524688","https://openalex.org/W2739740241","https://openalex.org/W2085105049","https://openalex.org/W2592417500","https://openalex.org/W2526069705","https://openalex.org/W2024016913","https://openalex.org/W2019153376","https://openalex.org/W2981664121","https://openalex.org/W2022666014"],"abstract_inverted_index":{"In":[0,36],"this":[1,37],"paper":[2,38],"we":[3,39],"study":[4],"algorithms":[5,20,42,63,88,92],"for":[6,24],"performing":[7],"the":[8,86,90,126,141,163],"LU":[9],"and":[10,34,46,66,75,109,140],"QR":[11],"factorizations":[12],"of":[13,138,152,161],"dense":[14],"matrices.":[15],"Recently,":[16],"two":[17,41,87],"communication":[18,31,59,61],"optimal":[19],"have":[21,80],"been":[22],"introduced":[23],"distributed":[25],"memory":[26],"architectures,":[27],"referred":[28],"to":[29,51,57,135,149],"as":[30],"avoiding":[32,62],"CALU":[33,47,124],"CAQR.":[35],"discuss":[40],"based":[43,103,115],"on":[44,98,104,110,116],"CAQR":[45,156],"that":[48,72,77],"are":[49,73],"adapted":[50],"multicore":[52],"architectures.":[53],"They":[54],"combine":[55],"ideas":[56],"reduce":[58],"from":[60,93,130,145,167],"with":[64],"asynchronism":[65],"dynamic":[67],"task":[68],"scheduling.":[69],"For":[70,120],"matrices":[71],"tall":[74],"skinny,":[76],"is,":[78],"they":[79],"many":[81],"more":[82],"rows":[83],"than":[84],"columns,":[85],"outperform":[89],"corresponding":[91,127,142,164],"Intel":[94,105,131],"MKL":[95,132,168],"vendor":[96],"library":[97,133,147],"a":[99,111,136,150,159],"dual-socket,":[100],"quad-core":[101,113],"machine":[102,114],"Xeon":[106],"EMT64":[107],"processor":[108],"four-socket,":[112],"AMD":[117],"Opteron":[118],"processor.":[119],"these":[121],"matrices,":[122],"multithreaded":[123,155],"outperforms":[125,157],"routine":[128,143,166],"dgetrf":[129,144],"up":[134,148],"factor":[137,151,160],"2.3":[139],"ACML":[146],"5,":[153],"while":[154],"by":[158],"5.3":[162],"dgeqrf":[165],"library.":[169]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":3}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}