{"id":"https://openalex.org/W2052283284","doi":"https://doi.org/10.1109/asap.2013.6567597","title":"GPU acceleration of Data Assembly in Finite Element Methods and its energy implications","display_name":"GPU acceleration of Data Assembly in Finite Element Methods and its energy implications","publication_year":2013,"publication_date":"2013-06-01","ids":{"openalex":"https://openalex.org/W2052283284","doi":"https://doi.org/10.1109/asap.2013.6567597","mag":"2052283284"},"language":"en","primary_location":{"id":"doi:10.1109/asap.2013.6567597","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asap.2013.6567597","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE 24th International Conference on Application-Specific Systems, Architectures and Processors","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/biblio/1078756","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008622930","display_name":"Li Tang","orcid":"https://orcid.org/0000-0002-7636-0876"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li Tang","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, IN, USA","Department of Computer Science and Engineering University of Notre Dame Notre Dame IN USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, IN, USA","institution_ids":["https://openalex.org/I107639228"]},{"raw_affiliation_string":"Department of Computer Science and Engineering University of Notre Dame Notre Dame IN USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100600905","display_name":"Xiaobo Sharon Hu","orcid":"https://orcid.org/0000-0002-6636-9738"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"X. Sharon Hu","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, IN, USA","Department of Computer Science and Engineering University of Notre Dame Notre Dame IN USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, IN, USA","institution_ids":["https://openalex.org/I107639228"]},{"raw_affiliation_string":"Department of Computer Science and Engineering University of Notre Dame Notre Dame IN USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060901632","display_name":"Danny Z. Chen","orcid":"https://orcid.org/0000-0001-6565-2884"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Danny Z. Chen","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, IN, USA","Department of Computer Science and Engineering University of Notre Dame Notre Dame IN USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, IN, USA","institution_ids":["https://openalex.org/I107639228"]},{"raw_affiliation_string":"Department of Computer Science and Engineering University of Notre Dame Notre Dame IN USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003032564","display_name":"Michael Niemier","orcid":"https://orcid.org/0000-0001-7776-4306"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Niemier","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, IN, USA","Department of Computer Science and Engineering University of Notre Dame Notre Dame IN USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, IN, USA","institution_ids":["https://openalex.org/I107639228"]},{"raw_affiliation_string":"Department of Computer Science and Engineering University of Notre Dame Notre Dame IN USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018947758","display_name":"Richard Frederick Barrett","orcid":null},"institutions":[{"id":"https://openalex.org/I192454743","display_name":"Sandia National Laboratories California","ror":"https://ror.org/058m7ey48","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1330989302","https://openalex.org/I192454743","https://openalex.org/I198811213","https://openalex.org/I198811213","https://openalex.org/I4210104735"]},{"id":"https://openalex.org/I4210104735","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richard F. Barrett","raw_affiliation_strings":["Center for Computing Research, Sandia National Laboratories, Albuquerque, NM, USA","Center for Comput. Res., Sandia Nat. Labs., Albuquerque, NM, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Computing Research, Sandia National Laboratories, Albuquerque, NM, USA","institution_ids":["https://openalex.org/I4210104735"]},{"raw_affiliation_string":"Center for Comput. Res., Sandia Nat. Labs., Albuquerque, NM, USA","institution_ids":["https://openalex.org/I192454743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110468921","display_name":"Simon David Hammond","orcid":null},"institutions":[{"id":"https://openalex.org/I192454743","display_name":"Sandia National Laboratories California","ror":"https://ror.org/058m7ey48","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1330989302","https://openalex.org/I192454743","https://openalex.org/I198811213","https://openalex.org/I198811213","https://openalex.org/I4210104735"]},{"id":"https://openalex.org/I4210104735","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Simon D. Hammond","raw_affiliation_strings":["Center for Computing Research, Sandia National Laboratories, Albuquerque, NM, USA","Center for Comput. Res., Sandia Nat. Labs., Albuquerque, NM, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Computing Research, Sandia National Laboratories, Albuquerque, NM, USA","institution_ids":["https://openalex.org/I4210104735"]},{"raw_affiliation_string":"Center for Comput. Res., Sandia Nat. Labs., Albuquerque, NM, USA","institution_ids":["https://openalex.org/I192454743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037206391","display_name":"Genie Hsieh","orcid":null},"institutions":[{"id":"https://openalex.org/I192454743","display_name":"Sandia National Laboratories California","ror":"https://ror.org/058m7ey48","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1330989302","https://openalex.org/I192454743","https://openalex.org/I198811213","https://openalex.org/I198811213","https://openalex.org/I4210104735"]},{"id":"https://openalex.org/I4210104735","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Genie Hsieh","raw_affiliation_strings":["Center for Computing Research, Sandia National Laboratories, Albuquerque, NM, USA","Center for Comput. Res., Sandia Nat. Labs., Albuquerque, NM, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Computing Research, Sandia National Laboratories, Albuquerque, NM, USA","institution_ids":["https://openalex.org/I4210104735"]},{"raw_affiliation_string":"Center for Comput. Res., Sandia Nat. Labs., Albuquerque, NM, USA","institution_ids":["https://openalex.org/I192454743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"321","last_page":"328"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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"}},{"id":"https://openalex.org/T10998","display_name":"Heat Transfer and Optimization","score":0.979200005531311,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical Engineering"},"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/T10339","display_name":"Advanced Numerical Methods in Computational Mathematics","score":0.9627000093460083,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7984064817428589},{"id":"https://openalex.org/keywords/finite-element-method","display_name":"Finite element method","score":0.7892663478851318},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.7280735969543457},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6412692666053772},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.6321519613265991},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.6278074979782104},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6163464784622192},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.5876623392105103},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.5734948515892029},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.5030528903007507},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.5025901794433594},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.41967442631721497},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.4179350733757019},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.15231731534004211},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08474498987197876}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7984064817428589},{"id":"https://openalex.org/C135628077","wikidata":"https://www.wikidata.org/wiki/Q220184","display_name":"Finite element method","level":2,"score":0.7892663478851318},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.7280735969543457},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6412692666053772},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.6321519613265991},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.6278074979782104},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6163464784622192},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.5876623392105103},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.5734948515892029},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.5030528903007507},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.5025901794433594},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.41967442631721497},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.4179350733757019},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.15231731534004211},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08474498987197876},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/asap.2013.6567597","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asap.2013.6567597","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE 24th International Conference on Application-Specific Systems, Architectures and Processors","raw_type":"proceedings-article"},{"id":"pmh:oai:osti.gov:1078756","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1078756","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:osti.gov:1078756","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1078756","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"sustainable_development_goals":[{"score":0.9100000262260437,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1946796247","https://openalex.org/W1965034778","https://openalex.org/W2008060144","https://openalex.org/W2010580757","https://openalex.org/W2019793962","https://openalex.org/W2021261510","https://openalex.org/W2030846082","https://openalex.org/W2077368913","https://openalex.org/W2086515738","https://openalex.org/W2095954861","https://openalex.org/W2119785041","https://openalex.org/W2126256127","https://openalex.org/W2164575697","https://openalex.org/W2167722230","https://openalex.org/W2555583559","https://openalex.org/W3122718397","https://openalex.org/W4231684867","https://openalex.org/W6672293987","https://openalex.org/W6677973695"],"related_works":["https://openalex.org/W2120447654","https://openalex.org/W2977179488","https://openalex.org/W2144453115","https://openalex.org/W2128223750","https://openalex.org/W4238532390","https://openalex.org/W2188872161","https://openalex.org/W2961779879","https://openalex.org/W2331916929","https://openalex.org/W2897504747","https://openalex.org/W2402775763"],"abstract_inverted_index":{"The":[0,21,100],"Finite":[1],"Element":[2],"Method":[3],"(FEM)":[4],"is":[5,143],"a":[6,59],"numerical":[7],"technique":[8],"widely":[9],"used":[10],"in":[11,26],"finding":[12],"approximate":[13],"solutions":[14],"for":[15,109,145],"many":[16],"scientific":[17],"and":[18,53,77,83,87,95,107,122,128,133],"engineering":[19],"problems.":[20],"Data":[22],"Assembly":[23],"(DA)":[24],"stage":[25],"FEM":[27,36],"can":[28,116],"take":[29],"up":[30],"to":[31,49,64],"50%":[32],"of":[33,147],"the":[34,105,113,120,126,140,148],"total":[35],"execution":[37],"time.":[38],"Accelerating":[39],"DA":[40,66],"with":[41],"Graphics":[42],"Processing":[43],"Units":[44],"(GPUs)":[45],"presents":[46],"challenges":[47],"due":[48],"DA's":[50],"mixed":[51],"compute-intensive":[52],"memory-intensive":[54],"workloads.":[55],"This":[56],"paper":[57],"uses":[58],"representative":[60],"finite":[61],"element":[62],"mini-application":[63],"explore":[65],"acceleration":[67],"on":[68,73,92,112],"CPU+GPU":[69,94],"platforms.":[70,99,149],"Implementations":[71],"based":[72],"different":[74,110],"thread,":[75],"kernel":[76],"task":[78],"design":[79],"approaches":[80],"are":[81,90,125],"developed":[82],"compared.":[84],"Their":[85],"performance":[86,106,121,132],"energy":[88,108,123,134],"consumption":[89],"measured":[91],"four":[93],"two":[96],"CPU":[97],"only":[98],"results":[101],"show":[102],"that":[103],"(i)":[104],"implementations":[111],"same":[114],"platform":[115],"vary":[117],"significantly":[118],"but":[119],"trends":[124],"same,":[127],"(ii)":[129],"there":[130],"exist":[131],"tradeoffs":[135],"across":[136],"some":[137],"platforms":[138],"if":[139],"best":[141],"implementation":[142],"chosen":[144],"each":[146]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
