{"id":"https://openalex.org/W2537159990","doi":"https://doi.org/10.1109/hpec.2012.6408659","title":"High locality and increased intra-node parallelism for solving finite element models on GPUs by novel element-by-element implementation","display_name":"High locality and increased intra-node parallelism for solving finite element models on GPUs by novel element-by-element implementation","publication_year":2012,"publication_date":"2012-09-01","ids":{"openalex":"https://openalex.org/W2537159990","doi":"https://doi.org/10.1109/hpec.2012.6408659","mag":"2537159990"},"language":"en","primary_location":{"id":"doi:10.1109/hpec.2012.6408659","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec.2012.6408659","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE Conference on High Performance Extreme Computing","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/A5040670032","display_name":"Imre Kiss","orcid":"https://orcid.org/0000-0001-5373-7485"},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Imre Kiss","raw_affiliation_strings":["Budapest University of Technology and Economics, Budapest, Hungary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Budapest University of Technology and Economics, Budapest, Hungary","institution_ids":["https://openalex.org/I29770179"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073001863","display_name":"Zsolt Badics","orcid":"https://orcid.org/0000-0001-6176-3675"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zsolt Badics","raw_affiliation_strings":["Tensor Research, LLC, Andover, MA, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tensor Research, LLC, Andover, MA, U.S.A","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036535695","display_name":"Szabolcs Gyim\u00f3thy","orcid":"https://orcid.org/0000-0002-5650-7906"},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Szabolcs Gyimothy","raw_affiliation_strings":["Budapest University of Technology and Economics, Budapest, Hungary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Budapest University of Technology and Economics, Budapest, Hungary","institution_ids":["https://openalex.org/I29770179"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069086142","display_name":"J\u00f3zsef P\u00e1v\u00f3","orcid":"https://orcid.org/0000-0002-9501-7176"},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Jozsef Pavo","raw_affiliation_strings":["Budapest University of Technology and Economics, Budapest, Hungary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Budapest University of Technology and Economics, Budapest, Hungary","institution_ids":["https://openalex.org/I29770179"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1052,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.79769001,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"31","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10339","display_name":"Advanced Numerical Methods in Computational Mathematics","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10339","display_name":"Advanced Numerical Methods in Computational Mathematics","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"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":0.9977999925613403,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7724936008453369},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7485252022743225},{"id":"https://openalex.org/keywords/conjugate-gradient-method","display_name":"Conjugate gradient method","score":0.7318464517593384},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.6960716843605042},{"id":"https://openalex.org/keywords/finite-element-method","display_name":"Finite element method","score":0.6921727657318115},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.6757919788360596},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6344617009162903},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.5323605537414551},{"id":"https://openalex.org/keywords/element","display_name":"Element (criminal law)","score":0.5123056173324585},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.43176132440567017},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2782721221446991}],"concepts":[{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7724936008453369},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7485252022743225},{"id":"https://openalex.org/C81184566","wikidata":"https://www.wikidata.org/wiki/Q1191895","display_name":"Conjugate gradient method","level":2,"score":0.7318464517593384},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.6960716843605042},{"id":"https://openalex.org/C135628077","wikidata":"https://www.wikidata.org/wiki/Q220184","display_name":"Finite element method","level":2,"score":0.6921727657318115},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.6757919788360596},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6344617009162903},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.5323605537414551},{"id":"https://openalex.org/C200288055","wikidata":"https://www.wikidata.org/wiki/Q2621792","display_name":"Element (criminal law)","level":2,"score":0.5123056173324585},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.43176132440567017},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2782721221446991},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec.2012.6408659","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec.2012.6408659","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE Conference on High Performance Extreme Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.9100000262260437,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1555620806","https://openalex.org/W1570126984","https://openalex.org/W1575701986","https://openalex.org/W1762731526","https://openalex.org/W1965268863","https://openalex.org/W1974948496","https://openalex.org/W1979553104","https://openalex.org/W1980562919","https://openalex.org/W1987091525","https://openalex.org/W2001088168","https://openalex.org/W2026714155","https://openalex.org/W2030884284","https://openalex.org/W2032576830","https://openalex.org/W2104215969","https://openalex.org/W2154118576","https://openalex.org/W2398736067","https://openalex.org/W2540997694","https://openalex.org/W2997945685","https://openalex.org/W4301459988","https://openalex.org/W6633320338","https://openalex.org/W6645304955"],"related_works":["https://openalex.org/W3062287","https://openalex.org/W2380390332","https://openalex.org/W2742145873","https://openalex.org/W4245975140","https://openalex.org/W3189307731","https://openalex.org/W2949962288","https://openalex.org/W2364686214","https://openalex.org/W1428699136","https://openalex.org/W1998560227","https://openalex.org/W2022772718"],"abstract_inverted_index":{"The":[0],"utilization":[1],"of":[2,109,115,127],"Graphical":[3],"Processing":[4],"Units":[5],"(GPUs)":[6],"for":[7,101],"the":[8,41,47,58,68,81,106,116],"element-by-element":[9],"(EbE)":[10],"finite":[11],"element":[12,42,75],"method":[13],"(FEM)":[14],"is":[15,19,64,90,98],"demonstrated.":[16],"EbE":[17],"FEM":[18],"a":[20,26,121],"long":[21],"known":[22],"technique,":[23],"by":[24],"which":[25,130],"conjugate":[27],"gradient":[28],"(CG)":[29],"type":[30],"iterative":[31],"solution":[32],"scheme":[33],"can":[34,84],"be":[35,79,85],"entirely":[36],"decomposed":[37],"into":[38],"computations":[39,71],"on":[40],"level,":[43],"i.e.,":[44],"without":[45],"assembling":[46],"global":[48],"system":[49],"matrix.":[50],"In":[51],"our":[52],"implementation,":[53],"NVIDIA's":[54],"parallel":[55,118],"computing":[56],"solution,":[57],"Compute":[59],"Unified":[60],"Device":[61],"Architecture":[62],"(CUDA),":[63],"used":[65],"to":[66],"perform":[67],"required":[69],"element-wise":[70],"in":[72,137],"parallel.":[73],"Since":[74],"matrices":[76],"need":[77],"not":[78],"stored,":[80],"memory":[82],"requirement":[83],"kept":[86],"extremely":[87],"low.":[88],"It":[89],"shown":[91],"that":[92],"this":[93],"low-storage":[94],"but":[95],"computation-intensive":[96],"technique":[97],"better":[99],"suited":[100],"GPUs":[102],"than":[103],"those":[104],"requiring":[105],"massive":[107],"manipulation":[108],"large":[110],"data":[111,128],"sets.":[112],"This":[113],"study":[114],"proposed":[117],"model":[119],"illustrates":[120],"highly":[122],"improved":[123],"locality":[124],"and":[125],"minimization":[126],"movement,":[129],"could":[131],"also":[132],"significantly":[133],"reduce":[134],"energy":[135],"consumption":[136],"other":[138],"heterogeneous":[139],"HPC":[140],"architectures.":[141]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
