{"id":"https://openalex.org/W4403839977","doi":"https://doi.org/10.1007/s11227-024-06523-w","title":"Mixed-precision pre-pivoting strategy for the LU factorization","display_name":"Mixed-precision pre-pivoting strategy for the LU factorization","publication_year":2024,"publication_date":"2024-10-28","ids":{"openalex":"https://openalex.org/W4403839977","doi":"https://doi.org/10.1007/s11227-024-06523-w"},"language":"en","primary_location":{"id":"doi:10.1007/s11227-024-06523-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11227-024-06523-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11227-024-06523-w.pdf","source":{"id":"https://openalex.org/S32326811","display_name":"The Journal of Supercomputing","issn_l":"0920-8542","issn":["0920-8542","1573-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of Supercomputing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11227-024-06523-w.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5099776640","display_name":"Nima Sahraneshinsamani","orcid":null},"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":"Nima Sahraneshinsamani","raw_affiliation_strings":["Departament d\u2019Enginyeria i Ci\u00e8ncia dels Computadors, Universitat Jaume I, Av/ Vicent Sos Baynat, Castell\u00f3 de la Plana, 12071, Comunitat Valenciana, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departament d\u2019Enginyeria i Ci\u00e8ncia dels Computadors, Universitat Jaume I, Av/ Vicent Sos Baynat, Castell\u00f3 de la Plana, 12071, Comunitat Valenciana, Spain","institution_ids":["https://openalex.org/I10902133"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005202822","display_name":"Sandra Catal\u00e1n","orcid":"https://orcid.org/0000-0002-9321-2728"},"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":"Sandra Catal\u00e1n","raw_affiliation_strings":["Departament d\u2019Enginyeria i Ci\u00e8ncia dels Computadors, Universitat Jaume I, Av/ Vicent Sos Baynat, Castell\u00f3 de la Plana, 12071, Comunitat Valenciana, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departament d\u2019Enginyeria i Ci\u00e8ncia dels Computadors, Universitat Jaume I, Av/ Vicent Sos Baynat, Castell\u00f3 de la Plana, 12071, Comunitat Valenciana, Spain","institution_ids":["https://openalex.org/I10902133"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010665955","display_name":"Jos\u00e9 R. Herrero","orcid":"https://orcid.org/0000-0002-4060-367X"},"institutions":[{"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":"Jos\u00e9 R. Herrero","raw_affiliation_strings":["Departament d\u2019Arquitectura de Computadors, Universitat Polit\u00e8cnica de Catalunya, C/ Jordi Girona 1-3, Barcelona, 08034, Catalunya, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departament d\u2019Arquitectura de Computadors, Universitat Polit\u00e8cnica de Catalunya, C/ Jordi Girona 1-3, Barcelona, 08034, Catalunya, Spain","institution_ids":["https://openalex.org/I9617848"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5099776640"],"corresponding_institution_ids":["https://openalex.org/I10902133"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":0.5127,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.68452728,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"81","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11697","display_name":"Numerical Methods 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"}},"topics":[{"id":"https://openalex.org/T11697","display_name":"Numerical Methods 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/T10792","display_name":"Matrix Theory and Algorithms","score":0.9958999752998352,"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/T11034","display_name":"Digital Filter Design and Implementation","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9066784977912903},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.5150108337402344},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4120682179927826},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3647475242614746}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9066784977912903},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.5150108337402344},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4120682179927826},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3647475242614746}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s11227-024-06523-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11227-024-06523-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11227-024-06523-w.pdf","source":{"id":"https://openalex.org/S32326811","display_name":"The Journal of Supercomputing","issn_l":"0920-8542","issn":["0920-8542","1573-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of Supercomputing","raw_type":"journal-article"},{"id":"pmh:oai:upcommons.upc.edu:2117/420256","is_oa":true,"landing_page_url":"https://hdl.handle.net/2117/420256","pdf_url":"https://upcommons.upc.edu/bitstreams/2becb236-72ec-4e64-94bd-6cdb8172dcdc/download","source":{"id":"https://openalex.org/S4377196262","display_name":"UPCommons institutional repository (Universitat Polit\u00e8cnica de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9617848","host_organization_name":"Universitat Polit\u00e8cnica de Catalunya","host_organization_lineage":["https://openalex.org/I9617848"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1007/s11227-024-06523-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11227-024-06523-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11227-024-06523-w.pdf","source":{"id":"https://openalex.org/S32326811","display_name":"The Journal of Supercomputing","issn_l":"0920-8542","issn":["0920-8542","1573-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of Supercomputing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1590840659","display_name":null,"funder_award_id":"PID2019-107255GB","funder_id":"https://openalex.org/F4320321837","funder_display_name":"Ministerio de Econom\u00eda y Competitividad"},{"id":"https://openalex.org/G2247491333","display_name":null,"funder_award_id":"UJI-2023-04","funder_id":"https://openalex.org/F4320322926","funder_display_name":"Universitat Jaume I"},{"id":"https://openalex.org/G2469237109","display_name":null,"funder_award_id":"2021-SGR-01007","funder_id":"https://openalex.org/F4320321505","funder_display_name":"Generalitat de Catalunya"},{"id":"https://openalex.org/G3480869486","display_name":null,"funder_award_id":"13039","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G5368869175","display_name":null,"funder_award_id":"RYC2021-033973-I","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G5471711990","display_name":null,"funder_award_id":"UJI-2023-04","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G6833763678","display_name":null,"funder_award_id":"PID2019-107255GB","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G7084143925","display_name":null,"funder_award_id":"AEI/10","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G7425137858","display_name":null,"funder_award_id":"PID2019","funder_id":"https://openalex.org/F4320321505","funder_display_name":"Generalitat de Catalunya"},{"id":"https://openalex.org/G8684520763","display_name":null,"funder_award_id":"PID2019","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321505","display_name":"Generalitat de Catalunya","ror":"https://ror.org/01bg62x04"},{"id":"https://openalex.org/F4320321837","display_name":"Ministerio de Econom\u00eda y Competitividad","ror":"https://ror.org/034900433"},{"id":"https://openalex.org/F4320322926","display_name":"Universitat Jaume I","ror":"https://ror.org/02ws1xc11"},{"id":"https://openalex.org/F4320335598","display_name":"Agencia Estatal de Investigaci\u00f3n","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403839977.pdf","grobid_xml":"https://content.openalex.org/works/W4403839977.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1969213662","https://openalex.org/W1981031390","https://openalex.org/W2020804487","https://openalex.org/W2041364558","https://openalex.org/W2088160222","https://openalex.org/W2207050309","https://openalex.org/W2752588380","https://openalex.org/W2805454465","https://openalex.org/W2895305554","https://openalex.org/W2910374893","https://openalex.org/W2944067258","https://openalex.org/W2971946864","https://openalex.org/W2995792110","https://openalex.org/W2997728548","https://openalex.org/W2997929922","https://openalex.org/W3022136271","https://openalex.org/W3035977869","https://openalex.org/W3084211317","https://openalex.org/W3166178281","https://openalex.org/W4205976485","https://openalex.org/W4229666556","https://openalex.org/W4233996382","https://openalex.org/W4312608710","https://openalex.org/W4381327231","https://openalex.org/W4395000858"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2051487156","https://openalex.org/W2073681303","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109"],"abstract_inverted_index":{"Abstract":[0],"This":[1],"paper":[2],"investigates":[3],"the":[4,23,134],"efficient":[5],"application":[6],"of":[7,79,91,138],"half-precision":[8,96],"floating-point":[9],"(FP16)":[10],"arithmetic":[11],"on":[12,117],"GPUs":[13],"for":[14,112,133],"boosting":[15],"LU":[16,35,57,73,106],"decompositions":[17],"in":[18,43,60,68,88,94],"double":[19],"(FP64)":[20],"precision.":[21,100],"Addressing":[22],"motivation":[24],"to":[25],"enhance":[26],"computational":[27],"efficiency,":[28],"we":[29],"introduce":[30],"two":[31],"novel":[32],"algorithms:":[33],"Pre-Pivoted":[34],"(PRP)":[36],"and":[37,48,63,83,141],"Mixed-precision":[38],"Panel":[39],"Factorization":[40],"(MPF).":[41],"Deployed":[42],"both":[44],"hybrid":[45],"CPU-GPU":[46],"setups":[47],"native":[49,135],"GPU-only":[50],"configurations,":[51],"PRP":[52,139],"identifies":[53],"pivot":[54,92],"lists":[55,93],"through":[56],"decomposition":[58,74],"computed":[59],"reduced":[61],"precision":[62,70],"subsequently":[64],"reorders":[65],"matrix":[66],"rows":[67],"FP64":[69,105],"before":[71],"executing":[72],"without":[75],"pivoting.":[76],"Two":[77],"variants":[78,140],"PRP,":[80],"namely":[81],"hPRP":[82,111],"xPRP,":[84],"are":[85],"introduced,":[86],"differing":[87],"their":[89],"computation":[90],"full":[95],"or":[97],"mixed":[98],"half-single":[99],"The":[101,126],"MPF":[102],"algorithm":[103],"generates":[104],"factorization":[107],"while":[108],"internally":[109],"utilizing":[110],"panel":[113],"factorization,":[114],"showcasing":[115],"accuracy":[116],"par":[118],"with":[119,123],"standard":[120],"DGETRF":[121],"but":[122],"superior":[124],"speed.":[125],"study":[127],"further":[128],"explores":[129],"auxiliary":[130],"functions":[131],"required":[132],"mode":[136],"implementation":[137],"MPF.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
