{"id":"https://openalex.org/W4388581158","doi":"https://doi.org/10.1145/3624062.3624247","title":"GPU-based LU Factorization and Solve on Batches of Matrices with Band Structure","display_name":"GPU-based LU Factorization and Solve on Batches of Matrices with Band Structure","publication_year":2023,"publication_date":"2023-11-10","ids":{"openalex":"https://openalex.org/W4388581158","doi":"https://doi.org/10.1145/3624062.3624247"},"language":"en","primary_location":{"id":"doi:10.1145/3624062.3624247","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3624062.3624247","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis","raw_type":"proceedings-article"},"type":"conference-paper","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/A5077268543","display_name":"Ahmad Abdelfattah","orcid":"https://orcid.org/0000-0001-5054-4784"},"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":"Ahmad Abdelfattah","raw_affiliation_strings":["University of Tennessee, United States of America"],"raw_orcid":"https://orcid.org/0000-0001-5054-4784","affiliations":[{"raw_affiliation_string":"University of Tennessee, United States of America","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083604741","display_name":"Stanimire Tomov","orcid":"https://orcid.org/0000-0002-5937-7959"},"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":"Stanimire Tomov","raw_affiliation_strings":["University of Tennessee, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-5937-7959","affiliations":[{"raw_affiliation_string":"University of Tennessee, United States of America","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","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":"Piotr Luszczek","raw_affiliation_strings":["University of Tennessee, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-0089-6965","affiliations":[{"raw_affiliation_string":"University of Tennessee, United States of America","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012133869","display_name":"Hartwig Anzt","orcid":"https://orcid.org/0000-0003-2177-952X"},"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":"Hartwig Anzt","raw_affiliation_strings":["University of Tennessee, United States of America"],"raw_orcid":"https://orcid.org/0000-0003-2177-952X","affiliations":[{"raw_affiliation_string":"University of Tennessee, United States of America","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"last","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":"Jack Dongarra","raw_affiliation_strings":["University of Tennessee, United States of America"],"raw_orcid":"https://orcid.org/0000-0003-3247-1782","affiliations":[{"raw_affiliation_string":"University of Tennessee, United States of America","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":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1672","last_page":"1679"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.9988999962806702,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.9988999962806702,"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/T10739","display_name":"Electromagnetic Scattering and Analysis","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13126","display_name":"Scientific Research and Discoveries","score":0.9663000106811523,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6993993520736694},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.5872354507446289},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.5243520736694336},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4999525547027588},{"id":"https://openalex.org/keywords/lu-decomposition","display_name":"LU decomposition","score":0.43660610914230347},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3205302357673645},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.26562124490737915},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09978443384170532}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6993993520736694},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.5872354507446289},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.5243520736694336},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4999525547027588},{"id":"https://openalex.org/C123213974","wikidata":"https://www.wikidata.org/wiki/Q833089","display_name":"LU decomposition","level":4,"score":0.43660610914230347},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3205302357673645},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26562124490737915},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09978443384170532},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3624062.3624247","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3624062.3624247","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1973889046","https://openalex.org/W2047111386","https://openalex.org/W2062515718","https://openalex.org/W2124847994","https://openalex.org/W2138215414","https://openalex.org/W2499931820","https://openalex.org/W2531348778","https://openalex.org/W2621991888","https://openalex.org/W2736056409","https://openalex.org/W2767890311","https://openalex.org/W2793489890","https://openalex.org/W2944412207","https://openalex.org/W3145384893","https://openalex.org/W3176376637","https://openalex.org/W3195156891","https://openalex.org/W4285259669","https://openalex.org/W4294771628","https://openalex.org/W4308206517","https://openalex.org/W4313060083","https://openalex.org/W4321636545"],"related_works":["https://openalex.org/W2766762530","https://openalex.org/W119752240","https://openalex.org/W2602301532","https://openalex.org/W2099322959","https://openalex.org/W1988437637","https://openalex.org/W1998894100","https://openalex.org/W1977700955","https://openalex.org/W4388311419","https://openalex.org/W2130886743","https://openalex.org/W1973739845"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,10,27,33,83,106,138],"portable":[4],"and":[5,104,133],"performance-efficient":[6],"approach":[7],"to":[8,60,137],"solve":[9],"batch":[11],"of":[12,15,30,74,102],"linear":[13],"systems":[14],"equations":[16],"using":[17,26,45],"Graphics":[18],"Processing":[19],"Units":[20],"(GPUs).":[21],"Each":[22,41],"system":[23],"is":[24,43,77,117],"represented":[25],"special":[28],"type":[29,101],"matrices":[31],"with":[32,49],"band":[34,76],"structure":[35],"above":[36],"and/or":[37],"below":[38],"the":[39,56,62,75,94,121],"diagonal.":[40],"matrix":[42],"factorized":[44],"an":[46],"LU":[47,86],"factorization":[48,87],"partial":[50],"pivoting":[51],"for":[52,64,98,144],"numerical":[53],"stability.":[54],"Subsequently,":[55],"factors":[57],"are":[58,128],"used":[59],"find":[61],"solution":[63,141],"as":[65,70],"many":[66],"right":[67],"hand":[68],"sides":[69],"needed.":[71],"The":[72],"width":[73],"often":[78],"small":[79],"enough":[80],"that":[81,109],"performing":[82],"fully":[84],"dense":[85],"results":[88,127],"in":[89,120],"poor":[90],"performance.":[91],"We":[92],"follow":[93],"standard":[95],"LAPACK":[96],"specifications":[97],"addressing":[99],"this":[100],"problems":[103],"develop":[105],"dedicated":[107],"solver":[108,116],"runs":[110],"efficiently":[111],"on":[112,130],"GPUs.":[113],"No":[114],"similar":[115],"currently":[118],"available":[119],"vendor\u2019s":[122],"software":[123],"stack,":[124],"so":[125],"performance":[126],"shown":[129],"both":[131],"NVIDIA":[132],"AMD":[134],"GPUs":[135],"relative":[136],"parallel":[139],"CPU":[140],"utilizing":[142],"OpenMP":[143],"thread-level":[145],"parallelization.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}