{"id":"https://openalex.org/W2405076432","doi":"https://doi.org/10.3233/978-1-61499-041-3-429","title":"Exploiting Fine-Grain Parallelism in Recursive LU Factorization","display_name":"Exploiting Fine-Grain Parallelism in Recursive LU Factorization","publication_year":2012,"publication_date":"2012-01-01","ids":{"openalex":"https://openalex.org/W2405076432","doi":"https://doi.org/10.3233/978-1-61499-041-3-429","mag":"2405076432"},"language":"en","primary_location":{"id":"doi:10.3233/978-1-61499-041-3-429","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-61499-041-3-429","pdf_url":null,"source":{"id":"https://openalex.org/S4210175178","display_name":"Advances in parallel computing","issn_l":"0927-5452","issn":["0927-5452","1879-808X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Parallel Computing","raw_type":"book-chapter"},"type":"book-chapter","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/A5075517045","display_name":"Jack Dongarra","orcid":"https://orcid.org/0000-0003-3247-1782"},"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":"Dongarra Jack","raw_affiliation_strings":["ICL - Innovative Computing Laboratory [Knoxville] (Suite 203 Claxton\r\n1122 Volunteer Blvd\r\nKnoxville, TN 37996 - United States)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ICL - Innovative Computing Laboratory [Knoxville] (Suite 203 Claxton\r\n1122 Volunteer Blvd\r\nKnoxville, TN 37996 - United States)","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034603717","display_name":"Mathieu Faverge","orcid":"https://orcid.org/0000-0002-2128-1230"},"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":"Faverge Mathieu","raw_affiliation_strings":["ICL - Innovative Computing Laboratory [Knoxville] (Suite 203 Claxton\r\n1122 Volunteer Blvd\r\nKnoxville, TN 37996 - United States)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ICL - Innovative Computing Laboratory [Knoxville] (Suite 203 Claxton\r\n1122 Volunteer Blvd\r\nKnoxville, TN 37996 - United States)","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":"Ltaief Hatem","raw_affiliation_strings":["ICL - Innovative Computing Laboratory [Knoxville] (Suite 203 Claxton\r\n1122 Volunteer Blvd\r\nKnoxville, TN 37996 - United States)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ICL - Innovative Computing Laboratory [Knoxville] (Suite 203 Claxton\r\n1122 Volunteer Blvd\r\nKnoxville, TN 37996 - United States)","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073990539","display_name":"Piotr \u0141uszczek","orcid":"https://orcid.org/0000-0002-0089-6965"},"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":"Luszczek Piotr","raw_affiliation_strings":["ICL - Innovative Computing Laboratory [Knoxville] (Suite 203 Claxton\r\n1122 Volunteer Blvd\r\nKnoxville, TN 37996 - United States)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ICL - Innovative Computing Laboratory [Knoxville] (Suite 203 Claxton\r\n1122 Volunteer Blvd\r\nKnoxville, TN 37996 - United States)","institution_ids":["https://openalex.org/I75027704"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I75027704"],"apc_list":null,"apc_paid":null,"fwci":5.7225,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.96284585,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"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":0.9998000264167786,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.9998000264167786,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9987000226974487,"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/factorization","display_name":"Factorization","score":0.8790054321289062},{"id":"https://openalex.org/keywords/incomplete-lu-factorization","display_name":"Incomplete LU factorization","score":0.7681715488433838},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7158889770507812},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7077146768569946},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5963467955589294},{"id":"https://openalex.org/keywords/lu-decomposition","display_name":"LU decomposition","score":0.5222761631011963},{"id":"https://openalex.org/keywords/incomplete-cholesky-factorization","display_name":"Incomplete Cholesky factorization","score":0.45360079407691956},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.4066084027290344},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3444296717643738}],"concepts":[{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.8790054321289062},{"id":"https://openalex.org/C134978465","wikidata":"https://www.wikidata.org/wiki/Q1654069","display_name":"Incomplete LU factorization","level":4,"score":0.7681715488433838},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7158889770507812},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7077146768569946},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5963467955589294},{"id":"https://openalex.org/C123213974","wikidata":"https://www.wikidata.org/wiki/Q833089","display_name":"LU decomposition","level":4,"score":0.5222761631011963},{"id":"https://openalex.org/C44363057","wikidata":"https://www.wikidata.org/wiki/Q6015160","display_name":"Incomplete Cholesky factorization","level":4,"score":0.45360079407691956},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.4066084027290344},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3444296717643738},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3233/978-1-61499-041-3-429","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-61499-041-3-429","pdf_url":null,"source":{"id":"https://openalex.org/S4210175178","display_name":"Advances in parallel computing","issn_l":"0927-5452","issn":["0927-5452","1879-808X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Parallel Computing","raw_type":"book-chapter"},{"id":"pmh:oai:HAL:hal-00809755v1","is_oa":false,"landing_page_url":"https://inria.hal.science/hal-00809755","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of ParCo 2011, Aug 2011, Ghent, Belgium","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:repository.kaust.edu.sa:10754/575786","is_oa":false,"landing_page_url":"http://hdl.handle.net/10754/575786","pdf_url":null,"source":{"id":"https://openalex.org/S4306401596","display_name":"King Abdullah University of Science and Technology Repository (King Abdullah University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I71920554","host_organization_name":"King Abdullah University of Science and Technology","host_organization_lineage":["https://openalex.org/I71920554"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Book Chapter"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5299999713897705}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1979566015","https://openalex.org/W2016279572","https://openalex.org/W2026237859","https://openalex.org/W2110147698","https://openalex.org/W2145960411","https://openalex.org/W2150871235"],"related_works":["https://openalex.org/W2164374667","https://openalex.org/W1881162179","https://openalex.org/W2375608986","https://openalex.org/W2095258827","https://openalex.org/W2009574932","https://openalex.org/W2766762530","https://openalex.org/W2602301532","https://openalex.org/W2808680104","https://openalex.org/W2060455298","https://openalex.org/W1973739845"],"abstract_inverted_index":{"The":[0,178],"LU":[1,23,44,68,95,153],"factorization":[2,24,45,69,73,96,140,154],"is":[3,56,70,114,173],"an":[4],"important":[5],"numerical":[6,39],"algorithm":[7],"for":[8,20,146],"solving":[9],"system":[10],"of":[11,41,52,66,82,97,110,119,151,155,181],"linear":[12],"equations.":[13],"This":[14],"paper":[15],"proposes":[16],"a":[17,105],"novel":[18],"approach":[19,93],"computing":[21],"the":[22,32,38,42,50,53,62,67,71,80,84,111,120,129,142,147,152],"in":[25,90,163],"parallel":[26,106],"on":[27,116],"multicore":[28],"architectures.":[29],"It":[30,113],"improves":[31],"overall":[33,130],"performance":[34,144,179],"and":[35,59,79,99,122,187],"also":[36],"achieves":[37],"quality":[40],"standard":[43],"with":[46,134,175,194],"partial":[47],"pivoting.":[48],"While":[49],"update":[51],"trailing":[54],"submatrix":[55],"computationally":[57],"intensive":[58],"highly":[60],"parallel,":[61],"inherently":[63,148],"problematic":[64,149],"portion":[65,150],"panel":[72,101,139,160],"due":[74],"to":[75,94],"its":[76],"memory-bound":[77],"characteristic":[78],"atomicity":[81],"selecting":[83],"appropriate":[85],"pivots.":[86],"We":[87,103],"remedy":[88],"this":[89],"our":[91,168,182],"new":[92],"(narrow":[98],"tall)":[100],"submatrices.":[102],"use":[104],"fine-grained":[107],"recursive":[108,138],"formulation":[109],"factorization.":[112],"based":[115],"conflict-free":[117],"partitioning":[118],"data":[121],"lock-less":[123],"synchronization":[124],"mechanisms.":[125],"Our":[126,137],"implementation":[127,183],"lets":[128],"computation":[131],"naturally":[132],"flow":[133],"limited":[135],"contention.":[136],"provides":[141],"necessary":[143],"increase":[145],"square":[156],"matrices.":[157],"A":[158],"large":[159],"width":[161],"results":[162,180],"larger":[164],"Amdahl's":[165],"fraction":[166],"as":[167],"experiments":[169],"have":[170],"revealed":[171],"which":[172],"consistent":[174],"related":[176],"efforts.":[177],"reveal":[184],"superlinear":[185],"speedup":[186],"far":[188],"exceed":[189],"what":[190],"can":[191],"be":[192],"achieved":[193],"equivalent":[195],"MKL":[196],"and/or":[197],"LAPACK":[198],"routines.":[199]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
