{"id":"https://openalex.org/W1981534910","doi":"https://doi.org/10.1109/aiccsa.2011.6126599","title":"LU factorization for accelerator-based systems","display_name":"LU factorization for accelerator-based systems","publication_year":2011,"publication_date":"2011-12-01","ids":{"openalex":"https://openalex.org/W1981534910","doi":"https://doi.org/10.1109/aiccsa.2011.6126599","mag":"1981534910"},"language":"en","primary_location":{"id":"doi:10.1109/aiccsa.2011.6126599","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aiccsa.2011.6126599","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 9th IEEE/ACS International Conference on Computer Systems and Applications (AICCSA)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/hal-00654193","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074132178","display_name":"Emmanuel Agullo","orcid":"https://orcid.org/0000-0003-0655-6934"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I15057530","display_name":"Universit\u00e9 de Bordeaux","ror":"https://ror.org/057qpr032","country_code":"FR","type":"education","lineage":["https://openalex.org/I15057530"]},{"id":"https://openalex.org/I4210142254","display_name":"Laboratoire Bordelais de Recherche en Informatique","ror":"https://ror.org/03adqg323","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I15057530","https://openalex.org/I4210142254","https://openalex.org/I4210159245","https://openalex.org/I4210160189"]},{"id":"https://openalex.org/I4210160189","display_name":"Institut Polytechnique de Bordeaux","ror":"https://ror.org/054qv7y42","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210160189"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Emmanuel Agullo","raw_affiliation_strings":["INRIA, LaBRI, University of Bordeaux 1, France","INRIA, LaBRI, University of Bordeaux, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA, LaBRI, University of Bordeaux 1, France","institution_ids":["https://openalex.org/I4210142254","https://openalex.org/I1326498283","https://openalex.org/I15057530","https://openalex.org/I4210160189"]},{"raw_affiliation_string":"INRIA, LaBRI, University of Bordeaux, France","institution_ids":["https://openalex.org/I15057530","https://openalex.org/I4210142254"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037007015","display_name":"C\u00e9dric Augonnet","orcid":"https://orcid.org/0009-0006-3337-5863"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I15057530","display_name":"Universit\u00e9 de Bordeaux","ror":"https://ror.org/057qpr032","country_code":"FR","type":"education","lineage":["https://openalex.org/I15057530"]},{"id":"https://openalex.org/I4210142254","display_name":"Laboratoire Bordelais de Recherche en Informatique","ror":"https://ror.org/03adqg323","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I15057530","https://openalex.org/I4210142254","https://openalex.org/I4210159245","https://openalex.org/I4210160189"]},{"id":"https://openalex.org/I4210160189","display_name":"Institut Polytechnique de Bordeaux","ror":"https://ror.org/054qv7y42","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210160189"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Cedric Augonnet","raw_affiliation_strings":["INRIA, LaBRI, University of Bordeaux 1, France","INRIA, LaBRI, University of Bordeaux, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA, LaBRI, University of Bordeaux 1, France","institution_ids":["https://openalex.org/I4210142254","https://openalex.org/I1326498283","https://openalex.org/I15057530","https://openalex.org/I4210160189"]},{"raw_affiliation_string":"INRIA, LaBRI, University of Bordeaux, France","institution_ids":["https://openalex.org/I15057530","https://openalex.org/I4210142254"]}]},{"author_position":"middle","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":["Innovative Computing Laboratory, University of Tennessee, Knoxville, TN, USA","INNOVATIVE COMPUTING LABORATORY, UNIVERSITY OF TENNESSEE, KNOXVILLE TN 37996, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Innovative Computing Laboratory, University of Tennessee, Knoxville, TN, USA","institution_ids":["https://openalex.org/I75027704"]},{"raw_affiliation_string":"INNOVATIVE COMPUTING LABORATORY, UNIVERSITY OF TENNESSEE, KNOXVILLE TN 37996, USA#TAB#","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":"Mathieu Faverge","raw_affiliation_strings":["Innovative Computing Laboratory, University of Tennessee, Knoxville, TN, USA","INNOVATIVE COMPUTING LABORATORY, UNIVERSITY OF TENNESSEE, KNOXVILLE TN 37996, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Innovative Computing Laboratory, University of Tennessee, Knoxville, TN, USA","institution_ids":["https://openalex.org/I75027704"]},{"raw_affiliation_string":"INNOVATIVE COMPUTING LABORATORY, UNIVERSITY OF TENNESSEE, KNOXVILLE TN 37996, USA#TAB#","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020584809","display_name":"Julien Langou","orcid":"https://orcid.org/0000-0002-7803-1822"},"institutions":[{"id":"https://openalex.org/I921990950","display_name":"University of Colorado Denver","ror":"https://ror.org/02hh7en24","country_code":"US","type":"education","lineage":["https://openalex.org/I921990950"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julien Langou","raw_affiliation_strings":["University of Colorado, Denver, CO, USA","University of Colorado Denver, CO 80202, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Colorado, Denver, CO, USA","institution_ids":["https://openalex.org/I921990950"]},{"raw_affiliation_string":"University of Colorado Denver, CO 80202, USA","institution_ids":["https://openalex.org/I921990950"]}]},{"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/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Hatem Ltaief","raw_affiliation_strings":["KAUST Supercomputing Laboratory, Thuwal, Saudi Arabia","[KAUST Supercomputing Laboratory, Thuwal, Saudi Arabia]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAUST Supercomputing Laboratory, Thuwal, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]},{"raw_affiliation_string":"[KAUST Supercomputing Laboratory, Thuwal, Saudi Arabia]","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"last","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":["Innovative Computing Laboratory, University of Tennessee, Knoxville, TN, USA","INNOVATIVE COMPUTING LABORATORY, UNIVERSITY OF TENNESSEE, KNOXVILLE TN 37996, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Innovative Computing Laboratory, University of Tennessee, Knoxville, TN, USA","institution_ids":["https://openalex.org/I75027704"]},{"raw_affiliation_string":"INNOVATIVE COMPUTING LABORATORY, UNIVERSITY OF TENNESSEE, KNOXVILLE TN 37996, USA#TAB#","institution_ids":["https://openalex.org/I75027704"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":58,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"217","last_page":"224"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9995999932289124,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994999766349792,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.725640058517456},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.71616530418396},{"id":"https://openalex.org/keywords/double-precision-floating-point-format","display_name":"Double-precision floating-point format","score":0.6030696630477905},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.5714392066001892},{"id":"https://openalex.org/keywords/cholesky-decomposition","display_name":"Cholesky decomposition","score":0.5246368050575256},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5130223631858826},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4474928379058838},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4174790382385254},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4114159047603607},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.39371824264526367},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.26760363578796387},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1410697102546692},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08830425143241882},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.0643928050994873}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.725640058517456},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.71616530418396},{"id":"https://openalex.org/C35912277","wikidata":"https://www.wikidata.org/wiki/Q1243369","display_name":"Double-precision floating-point format","level":3,"score":0.6030696630477905},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.5714392066001892},{"id":"https://openalex.org/C34727166","wikidata":"https://www.wikidata.org/wiki/Q515375","display_name":"Cholesky decomposition","level":3,"score":0.5246368050575256},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5130223631858826},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4474928379058838},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4174790382385254},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4114159047603607},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.39371824264526367},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26760363578796387},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1410697102546692},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08830425143241882},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0643928050994873},{"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/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/aiccsa.2011.6126599","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aiccsa.2011.6126599","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 9th IEEE/ACS International Conference on Computer Systems and Applications (AICCSA)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.186.3358","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.186.3358","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://icl.cs.utk.edu/news_pub/submissions/plagma_lu.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:hal-00654193v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-00654193","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":"9th ACS/IEEE International Conference on Computer Systems and Applications (AICCSA 11), Jun 2011, Sharm El-Sheikh, Egypt","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:oskar-bordeaux.fr:20.500.12278/197966","is_oa":false,"landing_page_url":"https://oskar-bordeaux.fr/handle/20.500.12278/197966","pdf_url":null,"source":{"id":"https://openalex.org/S4306402569","display_name":"Oskar-Bordeaux (Universite de Bordeaux)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Communication dans un congr\u00e8s"},{"id":"pmh:oai:repository.kaust.edu.sa:10754/575804","is_oa":false,"landing_page_url":"http://hdl.handle.net/10754/575804","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":"Conference Paper"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-00654193v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-00654193","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":"9th ACS/IEEE International Conference on Computer Systems and Applications (AICCSA 11), Jun 2011, Sharm El-Sheikh, Egypt","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W840690709","https://openalex.org/W1004371317","https://openalex.org/W1483880184","https://openalex.org/W1574785859","https://openalex.org/W1890479029","https://openalex.org/W1966592804","https://openalex.org/W2014116693","https://openalex.org/W2016358047","https://openalex.org/W2047614366","https://openalex.org/W2050612421","https://openalex.org/W2064744742","https://openalex.org/W2081114193","https://openalex.org/W2085118703","https://openalex.org/W2112340065","https://openalex.org/W2115780241","https://openalex.org/W2124480634","https://openalex.org/W2139116943","https://openalex.org/W2145960411","https://openalex.org/W2187691968","https://openalex.org/W2725973130","https://openalex.org/W2731838583","https://openalex.org/W3145506805","https://openalex.org/W4234740575","https://openalex.org/W6623644678","https://openalex.org/W6639443654","https://openalex.org/W6662378236","https://openalex.org/W6687000134","https://openalex.org/W6740207907","https://openalex.org/W6740657393","https://openalex.org/W6817185352"],"related_works":["https://openalex.org/W2403987929","https://openalex.org/W2039814159","https://openalex.org/W2374847384","https://openalex.org/W2063512590","https://openalex.org/W2107649022","https://openalex.org/W2356488190","https://openalex.org/W2020279179","https://openalex.org/W3087399931","https://openalex.org/W1493347376","https://openalex.org/W2279423721"],"abstract_inverted_index":{"Multicore":[0],"architectures":[1],"enhanced":[2],"with":[3],"multiple":[4,102],"GPUs":[5,108,113,115],"are":[6,192],"likely":[7],"to":[8],"become":[9],"mainstream":[10],"High":[11],"Performance":[12],"Computing":[13],"(HPC)":[14],"platforms":[15,44],"in":[16,45,89,126,134,194],"a":[17,52],"near":[18],"future.":[19],"In":[20],"this":[21],"paper,":[22],"we":[23],"present":[24],"the":[25,40,75,80,86,94,142,148,158,161,166,172,176,190],"design":[26],"and":[27,60,110],"implementation":[28],"of":[29,42,47,67,79,91,101,152,160,163,175],"an":[30],"LU":[31,72,121,178],"factorization":[32,179],"using":[33],"tile":[34,120,177],"algorithm":[35],"that":[36,171],"can":[37],"fully":[38],"exploit":[39],"potential":[41],"such":[43],"spite":[46],"their":[48],"complexity.":[49],"We":[50,155,169],"use":[51],"methodology":[53],"derived":[54],"from":[55],"previous":[56],"work":[57],"on":[58,77,129,141,165],"Cholesky":[59],"QR":[61],"factorizations.":[62],"Our":[63],"contributions":[64],"essentially":[65],"consist":[66],"providing":[68],"new":[69],"CPU/GPU":[70],"hybrid":[71,119],"kernels,":[73],"studying":[74],"impact":[76,159],"performance":[78,133],"looking":[81],"variants":[82],"as":[83,85,187,189],"well":[84],"storage":[87],"layout":[88],"presence":[90],"pivoting,":[92],"tuning":[93],"kernels":[95],"for":[96,184],"two":[97],"different":[98],"machines":[99],"composed":[100],"recent":[103],"NVIDIA":[104],"Tesla":[105,153],"S1070":[106],"(four":[107],"total)":[109],"Fermi-based":[111,143],"S2050":[112],"(three":[114],"total),":[116],"respectively.":[117],"The":[118,132],"asymptotically":[122],"achieves":[123],"1":[124],"Tflop/s":[125],"single":[127],"precision":[128,136,196],"both":[130],"hardwares.":[131],"double":[135,195],"arithmetic":[137],"reaches":[138],"500":[139],"Gflop/s":[140],"system,":[144],"twice":[145],"faster":[146],"than":[147],"old":[149],"GPU":[150],"generation":[151],"S1070.":[154],"also":[156],"discuss":[157],"number":[162],"tiles":[164],"numerical":[167,173],"stability.":[168],"show":[170],"results":[174],"will":[180],"be":[181],"accurate":[182],"enough":[183],"most":[185],"applications":[186],"long":[188],"computations":[191],"performed":[193],"arithmetic.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":12},{"year":2013,"cited_by_count":16},{"year":2012,"cited_by_count":10}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
