{"id":"https://openalex.org/W2899997033","doi":"https://doi.org/10.14529/jsfi180203","title":"On the Inversion of Multiple Matrices on GPU in Batched Mode","display_name":"On the Inversion of Multiple Matrices on GPU in Batched Mode","publication_year":2018,"publication_date":"2018-06-01","ids":{"openalex":"https://openalex.org/W2899997033","doi":"https://doi.org/10.14529/jsfi180203","mag":"2899997033"},"language":"en","primary_location":{"id":"doi:10.14529/jsfi180203","is_oa":true,"landing_page_url":"https://doi.org/10.14529/jsfi180203","pdf_url":null,"source":{"id":"https://openalex.org/S4210177204","display_name":"Supercomputing Frontiers and Innovations","issn_l":"2313-8734","issn":["2313-8734","2409-6008"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310312680","host_organization_name":"Publishing center of the South Ural State University","host_organization_lineage":["https://openalex.org/P4310312680"],"host_organization_lineage_names":["Publishing center of the South Ural State University"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Supercomputing Frontiers and Innovations","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.14529/jsfi180203","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028516024","display_name":"Nikolay M. Evstigneev","orcid":"https://orcid.org/0000-0002-8785-6762"},"institutions":[{"id":"https://openalex.org/I4210115688","display_name":"Institute for Systems Analysis","ror":"https://ror.org/02kmet255","country_code":"RU","type":"facility","lineage":["https://openalex.org/I4210115688"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Nikolay M. Evstigneev","raw_affiliation_strings":["Federal Research Center ''Informatics and Control'', Institute for System Analysis, Russian Academy of Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Federal Research Center ''Informatics and Control'', Institute for System Analysis, Russian Academy of Science","institution_ids":["https://openalex.org/I4210115688"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062010793","display_name":"O. I. Ryabkov","orcid":null},"institutions":[{"id":"https://openalex.org/I4210115688","display_name":"Institute for Systems Analysis","ror":"https://ror.org/02kmet255","country_code":"RU","type":"facility","lineage":["https://openalex.org/I4210115688"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Oleg I. Ryabkov","raw_affiliation_strings":["Federal Research Center ''Informatics and Control'', Institute for System Analysis, Russian Academy of Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Federal Research Center ''Informatics and Control'', Institute for System Analysis, Russian Academy of Science","institution_ids":["https://openalex.org/I4210115688"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104609534","display_name":"Eugene A. Tsatsorin","orcid":null},"institutions":[{"id":"https://openalex.org/I19880235","display_name":"Lomonosov Moscow State University","ror":"https://ror.org/010pmpe69","country_code":"RU","type":"education","lineage":["https://openalex.org/I19880235"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Eugene A. Tsatsorin","raw_affiliation_strings":["The faculty of Computational Mathematics and Cybernetics of Lomonosov Moscow State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The faculty of Computational Mathematics and Cybernetics of Lomonosov Moscow State University","institution_ids":["https://openalex.org/I19880235"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1898,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.56401271,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"5","issue":"2","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.9972000122070312,"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":0.9972000122070312,"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":0.9909999966621399,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9879000186920166,"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/inversion","display_name":"Inversion (geology)","score":0.8175491690635681},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6891182661056519},{"id":"https://openalex.org/keywords/gaussian-elimination","display_name":"Gaussian elimination","score":0.667761504650116},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5951899886131287},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5514859557151794},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.5129448771476746},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.49627310037612915},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4941730797290802},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.45948562026023865},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.44490742683410645},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.15984320640563965},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.12000569701194763},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.11986896395683289},{"id":"https://openalex.org/keywords/computational-chemistry","display_name":"Computational chemistry","score":0.09825900197029114}],"concepts":[{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.8175491690635681},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6891182661056519},{"id":"https://openalex.org/C126312332","wikidata":"https://www.wikidata.org/wiki/Q2658","display_name":"Gaussian elimination","level":3,"score":0.667761504650116},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5951899886131287},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5514859557151794},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.5129448771476746},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.49627310037612915},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4941730797290802},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.45948562026023865},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.44490742683410645},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.15984320640563965},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.12000569701194763},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.11986896395683289},{"id":"https://openalex.org/C147597530","wikidata":"https://www.wikidata.org/wiki/Q369472","display_name":"Computational chemistry","level":1,"score":0.09825900197029114},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C109007969","wikidata":"https://www.wikidata.org/wiki/Q749565","display_name":"Structural basin","level":2,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14529/jsfi180203","is_oa":true,"landing_page_url":"https://doi.org/10.14529/jsfi180203","pdf_url":null,"source":{"id":"https://openalex.org/S4210177204","display_name":"Supercomputing Frontiers and Innovations","issn_l":"2313-8734","issn":["2313-8734","2409-6008"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310312680","host_organization_name":"Publishing center of the South Ural State University","host_organization_lineage":["https://openalex.org/P4310312680"],"host_organization_lineage_names":["Publishing center of the South Ural State University"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Supercomputing Frontiers and Innovations","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.14529/jsfi180203","is_oa":true,"landing_page_url":"https://doi.org/10.14529/jsfi180203","pdf_url":null,"source":{"id":"https://openalex.org/S4210177204","display_name":"Supercomputing Frontiers and Innovations","issn_l":"2313-8734","issn":["2313-8734","2409-6008"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310312680","host_organization_name":"Publishing center of the South Ural State University","host_organization_lineage":["https://openalex.org/P4310312680"],"host_organization_lineage_names":["Publishing center of the South Ural State University"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Supercomputing Frontiers and Innovations","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W211231959","https://openalex.org/W341880711","https://openalex.org/W2006682733","https://openalex.org/W2098168282","https://openalex.org/W2141909384","https://openalex.org/W2483424394","https://openalex.org/W2499931820","https://openalex.org/W2531348778","https://openalex.org/W2580907809"],"related_works":["https://openalex.org/W1990474090","https://openalex.org/W2034934546","https://openalex.org/W4229056291","https://openalex.org/W2471791783","https://openalex.org/W68665637","https://openalex.org/W2040458802","https://openalex.org/W2089495050","https://openalex.org/W2001342884","https://openalex.org/W4321636545","https://openalex.org/W138787272"],"abstract_inverted_index":{"In":[0,38],"this":[1,39],"research":[2],"we":[3],"are":[4],"considering":[5],"the":[6,24,41,53,61,81,104,108,120,139,145],"benchmarking":[7],"of":[8,14,19,33,57,141],"batched":[9],"matrix":[10,21,63,82,110],"inversion":[11,22,111],"and":[12,45,72,75],"solution":[13],"linear":[15],"systems.":[16],"The":[17,55],"problem":[18],"multiple":[20,62],"with":[23,36],"same":[25],"fill":[26],"sparsity":[27],"is":[28,43,49,60,101,107],"usually":[29],"considered":[30],"in":[31,144],"problems":[32],"fluid":[34],"mechanics":[35],"chemistry.":[37],"case":[40],"system":[42],"stiff,":[44],"an":[46],"implicit":[47],"method":[48,59,106,124],"required":[50],"to":[51],"solve":[52],"problem.":[54,149],"core":[56],"such":[58],"inversion.":[64],"We":[65,84,116,136],"benchmark":[66],"different":[67],"methods":[68],"based":[69],"on":[70,80,95],"cuSPARSE":[71,133],"MAGMA":[73],"libraries":[74],"CPU":[76],"LAPACK":[77],"version":[78],"depending":[79],"filling.":[83],"also":[85,117,137],"provide":[86],"our":[87],"own":[88],"experimental":[89],"code":[90],"that":[91,103,119],"implements":[92],"GaussJordan":[93],"elimination":[94,123],"GPU":[96],"using":[97],"register":[98],"shuffle.":[99],"It":[100],"shown":[102],"fastest":[105],"QR":[109,134],"for":[112],"single":[113],"precision":[114],"calculations.":[115],"show":[118],"suggested":[121],"Gauss\u2013Jordan":[122],"looks":[125],"promising":[126],"being":[127],"about":[128],"8\u201310":[129],"times":[130],"faster":[131],"than":[132],"method.":[135],"demonstrate":[138],"application":[140],"batch":[142],"solvers":[143],"coupled":[146],"reactive":[147],"flow":[148]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2018-11-16T00:00:00"}
