{"id":"https://openalex.org/W2921987484","doi":"https://doi.org/10.1177/1094342019832968","title":"Hierarchical approach for deriving a reproducible unblocked LU factorization","display_name":"Hierarchical approach for deriving a reproducible unblocked LU factorization","publication_year":2019,"publication_date":"2019-03-17","ids":{"openalex":"https://openalex.org/W2921987484","doi":"https://doi.org/10.1177/1094342019832968","mag":"2921987484"},"language":"en","primary_location":{"id":"doi:10.1177/1094342019832968","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342019832968","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-01419813","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018682944","display_name":"Roman Iakymchuk","orcid":"https://orcid.org/0000-0003-2414-700X"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Roman Iakymchuk","raw_affiliation_strings":["KTH Royal Institute of Technology, Stockholm, Sweden","KTH - KTH Royal Institute of Technology [Stockholm] (SE-100 44, Stockholm, Sweden - Sweden)"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"KTH - KTH Royal Institute of Technology [Stockholm] (SE-100 44, Stockholm, Sweden - Sweden)","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020384391","display_name":"Stef Graillat","orcid":"https://orcid.org/0000-0001-8954-2276"},"institutions":[{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Stef Graillat","raw_affiliation_strings":["Sorbonne Universit\u00e9s, Paris, France"],"affiliations":[{"raw_affiliation_string":"Sorbonne Universit\u00e9s, Paris, France","institution_ids":["https://openalex.org/I39804081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103080181","display_name":"David Defour","orcid":"https://orcid.org/0000-0001-9923-2394"},"institutions":[{"id":"https://openalex.org/I151295451","display_name":"Universit\u00e9 de Perpignan","ror":"https://ror.org/03am2jy38","country_code":"FR","type":"education","lineage":["https://openalex.org/I151295451"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"David Defour","raw_affiliation_strings":["Universit\u00e9 de Perpignan, Perpignan, France"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Perpignan, Perpignan, France","institution_ids":["https://openalex.org/I151295451"]}]},{"author_position":"last","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-Ort\u00ed","raw_affiliation_strings":["Universidad Jaime I, Castell\u00f3n, Spain"],"affiliations":[{"raw_affiliation_string":"Universidad Jaime I, Castell\u00f3n, Spain","institution_ids":["https://openalex.org/I10902133"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5018682944"],"corresponding_institution_ids":["https://openalex.org/I86987016"],"apc_list":null,"apc_paid":null,"fwci":0.3992,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.62585059,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"33","issue":"5","first_page":"791","last_page":"803"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11697","display_name":"Numerical Methods and Algorithms","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9986000061035156,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9983000159263611,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.7901610136032104},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.703568696975708},{"id":"https://openalex.org/keywords/lu-decomposition","display_name":"LU decomposition","score":0.6970853805541992},{"id":"https://openalex.org/keywords/incomplete-lu-factorization","display_name":"Incomplete LU factorization","score":0.6427034139633179},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5387606620788574},{"id":"https://openalex.org/keywords/dot-product","display_name":"Dot product","score":0.5257193446159363},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.48271939158439636},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.47251707315444946},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.4296644628047943},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.4159892201423645},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.41464489698410034},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3494889736175537},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1931973397731781},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.13111186027526855},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.05581939220428467}],"concepts":[{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.7901610136032104},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.703568696975708},{"id":"https://openalex.org/C123213974","wikidata":"https://www.wikidata.org/wiki/Q833089","display_name":"LU decomposition","level":4,"score":0.6970853805541992},{"id":"https://openalex.org/C134978465","wikidata":"https://www.wikidata.org/wiki/Q1654069","display_name":"Incomplete LU factorization","level":4,"score":0.6427034139633179},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5387606620788574},{"id":"https://openalex.org/C32900221","wikidata":"https://www.wikidata.org/wiki/Q181365","display_name":"Dot product","level":2,"score":0.5257193446159363},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.48271939158439636},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.47251707315444946},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.4296644628047943},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.4159892201423645},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.41464489698410034},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3494889736175537},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1931973397731781},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.13111186027526855},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.05581939220428467},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1177/1094342019832968","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342019832968","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},{"id":"pmh:oai:repositori.uji.es:10234/184835","is_oa":false,"landing_page_url":"http://hdl.handle.net/10234/184835","pdf_url":null,"source":{"id":"https://openalex.org/S4306400303","display_name":"Repositori UJI (Universitat Jaume I)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I10902133","host_organization_name":"Universitat Jaume I","host_organization_lineage":["https://openalex.org/I10902133"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:HAL:hal-01419813v4","is_oa":true,"landing_page_url":"https://hal.science/hal-01419813","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":"International Journal of High Performance Computing Applications, 2019, pp.#1094342019832968. &#x27E8;10.1177/1094342019832968&#x27E9;","raw_type":"Journal articles"},{"id":"pmh:oai:riunet.upv.es:10251/150674","is_oa":true,"landing_page_url":"http://hdl.handle.net/10251/150674","pdf_url":null,"source":{"id":"https://openalex.org/S4306401500","display_name":"RiuNet (Politechnical University of Valencia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I60053951","host_organization_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","host_organization_lineage":["https://openalex.org/I60053951"],"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":"","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-01419813v4","is_oa":true,"landing_page_url":"https://hal.science/hal-01419813","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":"International Journal of High Performance Computing Applications, 2019, pp.#1094342019832968. &#x27E8;10.1177/1094342019832968&#x27E9;","raw_type":"Journal articles"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W605824955","https://openalex.org/W1591365734","https://openalex.org/W1953299766","https://openalex.org/W1968165559","https://openalex.org/W1969213662","https://openalex.org/W1977343658","https://openalex.org/W2002257715","https://openalex.org/W2019592888","https://openalex.org/W2020804487","https://openalex.org/W2030638350","https://openalex.org/W2041844083","https://openalex.org/W2044610542","https://openalex.org/W2052942864","https://openalex.org/W2057176337","https://openalex.org/W2069000895","https://openalex.org/W2104281151","https://openalex.org/W2104380208","https://openalex.org/W2132161525","https://openalex.org/W2138215414","https://openalex.org/W2280592497","https://openalex.org/W2412538644","https://openalex.org/W2500063960","https://openalex.org/W2556862623","https://openalex.org/W3021014091","https://openalex.org/W4297727662"],"related_works":["https://openalex.org/W3172485183","https://openalex.org/W2039715635","https://openalex.org/W4367460660","https://openalex.org/W4235971573","https://openalex.org/W2156095889","https://openalex.org/W2562747818","https://openalex.org/W2544917149","https://openalex.org/W2921987484","https://openalex.org/W1973739845","https://openalex.org/W210173153"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,45,59,65,87],"reproducible":[3,28,66],"variant":[4],"of":[5,51,69],"the":[6,31,38,49,52,70,94],"unblocked":[7,67],"LU":[8,71,96],"factorization":[9,72],"for":[10,30,73,79,93],"graphics":[11],"processor":[12],"units":[13],"(GPUs).":[14],"For":[15],"this":[16],"purpose,":[17],"we":[18,43,62],"build":[19],"upon":[20],"Level-1/2":[21],"BLAS":[22],"kernels":[23],"that":[24],"deliver":[25],"correctly-rounded":[26],"and":[27,37,81,90],"results":[29],"dot":[32],"(inner)":[33],"product,":[34],"vector":[35],"scaling,":[36],"matrix-vector":[39],"product.":[40],"In":[41],"addition,":[42],"draw":[44],"strategy":[46],"to":[47],"enhance":[48],"accuracy":[50],"triangular":[53],"solve":[54],"via":[55],"iterative":[56],"refinement.":[57],"Following":[58],"bottom-up":[60],"approach,":[61],"finally":[63],"construct":[64],"implementation":[68],"GPUs,":[74],"which":[75],"accommodates":[76],"partial":[77],"pivoting":[78],"stability":[80],"can":[82],"be":[83],"eventually":[84],"integrated":[85],"in":[86],"high":[88],"performance":[89],"stable":[91],"algorithm":[92],"(blocked)":[95],"factorization.":[97]},"counts_by_year":[{"year":2020,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
