{"id":"https://openalex.org/W2109241917","doi":"https://doi.org/10.1177/1094342015576846","title":"OpenACC acceleration of the Nek5000 spectral element code","display_name":"OpenACC acceleration of the Nek5000 spectral element code","publication_year":2015,"publication_date":"2015-03-30","ids":{"openalex":"https://openalex.org/W2109241917","doi":"https://doi.org/10.1177/1094342015576846","mag":"2109241917"},"language":"en","primary_location":{"id":"doi:10.1177/1094342015576846","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342015576846","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},"type":"article","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/A5085178088","display_name":"Stefano Markidis","orcid":"https://orcid.org/0000-0003-0639-0639"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Stefano Markidis","raw_affiliation_strings":["HPCViz Department, KTH Royal Institute of Technology, Sweden","1HPCViz Department, KTH Royal Institute of Technology, Sweden"],"affiliations":[{"raw_affiliation_string":"HPCViz Department, KTH Royal Institute of Technology, Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"1HPCViz Department, KTH Royal Institute of Technology, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100684212","display_name":"Jing Gong","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Jing Gong","raw_affiliation_strings":["HPCViz Department, KTH Royal Institute of Technology, Sweden","1HPCViz Department, KTH Royal Institute of Technology, Sweden"],"affiliations":[{"raw_affiliation_string":"HPCViz Department, KTH Royal Institute of Technology, Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"1HPCViz Department, KTH Royal Institute of Technology, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090283734","display_name":"Michael Schliephake","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Michael Schliephake","raw_affiliation_strings":["HPCViz Department, KTH Royal Institute of Technology, Sweden","1HPCViz Department, KTH Royal Institute of Technology, Sweden"],"affiliations":[{"raw_affiliation_string":"HPCViz Department, KTH Royal Institute of Technology, Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"1HPCViz Department, KTH Royal Institute of Technology, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011376663","display_name":"Erwin Laure","orcid":"https://orcid.org/0000-0002-9901-9857"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Erwin Laure","raw_affiliation_strings":["HPCViz Department, KTH Royal Institute of Technology, Sweden","1HPCViz Department, KTH Royal Institute of Technology, Sweden"],"affiliations":[{"raw_affiliation_string":"HPCViz Department, KTH Royal Institute of Technology, Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"1HPCViz Department, KTH Royal Institute of Technology, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103584438","display_name":"Alistair Hart","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123032","display_name":"Exascale (United Kingdom)","ror":"https://ror.org/032khhz22","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210123032"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alistair Hart","raw_affiliation_strings":["Cray Exascale Research Initiative Europe, UK"],"affiliations":[{"raw_affiliation_string":"Cray Exascale Research Initiative Europe, UK","institution_ids":["https://openalex.org/I4210123032"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060481619","display_name":"David Henty","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"David Henty","raw_affiliation_strings":["Edinburgh Parallel Computing Centre, Edinburgh University, UK","3Edinburgh Parallel Computing Centre, Edinburgh University, UK"],"affiliations":[{"raw_affiliation_string":"Edinburgh Parallel Computing Centre, Edinburgh University, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"3Edinburgh Parallel Computing Centre, Edinburgh University, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037600451","display_name":"Katherine Heisey","orcid":null},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Katherine Heisey","raw_affiliation_strings":["Argonne National Laboratory, USA","argonne national laboratory"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, USA","institution_ids":["https://openalex.org/I1282105669"]},{"raw_affiliation_string":"argonne national laboratory","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081088881","display_name":"Paul Fischer","orcid":"https://orcid.org/0000-0002-6506-4502"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paul Fischer","raw_affiliation_strings":["Argonne National Laboratory, USA","argonne national laboratory"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, USA","institution_ids":["https://openalex.org/I1282105669"]},{"raw_affiliation_string":"argonne national laboratory","institution_ids":["https://openalex.org/I1282105669"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5085178088"],"corresponding_institution_ids":["https://openalex.org/I86987016"],"apc_list":null,"apc_paid":null,"fwci":5.6076,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.96301429,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"29","issue":"3","first_page":"311","last_page":"319"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9993000030517578,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9950000047683716,"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/porting","display_name":"Porting","score":0.8391593098640442},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7786322832107544},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.715553879737854},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.635075032711029},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5481756329536438},{"id":"https://openalex.org/keywords/fortran","display_name":"Fortran","score":0.5036446452140808},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.41316959261894226},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3589041233062744},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.23155581951141357},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.13812968134880066},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.1277831792831421},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1083468496799469}],"concepts":[{"id":"https://openalex.org/C106251023","wikidata":"https://www.wikidata.org/wiki/Q851989","display_name":"Porting","level":3,"score":0.8391593098640442},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7786322832107544},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.715553879737854},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.635075032711029},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5481756329536438},{"id":"https://openalex.org/C2778241615","wikidata":"https://www.wikidata.org/wiki/Q83303","display_name":"Fortran","level":2,"score":0.5036446452140808},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.41316959261894226},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3589041233062744},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.23155581951141357},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.13812968134880066},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.1277831792831421},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1083468496799469}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/1094342015576846","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342015576846","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1981812667","https://openalex.org/W2047352485","https://openalex.org/W2104736438","https://openalex.org/W2117667603","https://openalex.org/W2598048660"],"related_works":["https://openalex.org/W2356602486","https://openalex.org/W1855765675","https://openalex.org/W3046859795","https://openalex.org/W1505902692","https://openalex.org/W111037196","https://openalex.org/W1582436825","https://openalex.org/W2357128959","https://openalex.org/W2886331427","https://openalex.org/W1996803181","https://openalex.org/W2979588510"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,8,16,22,88,116,143,148,163],"case":[3],"study":[4],"of":[5,11,37,59,64,67,91,94,103,166,171],"porting":[6],"NekBone,":[7],"skeleton":[9],"version":[10,125,140],"the":[12,29,35,50,65,68,124,133,172,177],"Nek5000":[13,20],"code,":[14],"to":[15,81,111,142,158],"parallel":[17,159,164],"GPU-accelerated":[18],"system.":[19],"is":[21],"computational":[23],"fluid":[24],"dynamics":[25],"code":[26,45,69,95],"based":[27],"on":[28,115,147,168],"spectral":[30],"element":[31],"method":[32],"used":[33,48],"for":[34,70],"simulation":[36],"incompressible":[38],"flow.":[39],"The":[40,57,105],"original":[41],"NekBone":[42,60,80,139,157],"Fortran":[43],"source":[44],"has":[46],"been":[47],"as":[49],"base":[51],"and":[52,73,87,155],"enhanced":[53],"by":[54],"OpenACC":[55,98,109,135],"directives.":[56],"profiling":[58],"provided":[61],"an":[62],"assessment":[63],"suitability":[66],"GPU":[71,82,160],"systems,":[72,161],"indicated":[74],"possible":[75],"kernel":[76],"optimizations.":[77],"To":[78],"port":[79],"systems":[83],"required":[84],"little":[85,112],"effort":[86],"small":[89],"number":[90],"additional":[92],"lines":[93,102],"(approximately":[96],"one":[97],"directive":[99],"per":[100],"1000":[101],"code).":[104],"na\u00efve":[106,134],"implementation":[107],"using":[108],"leads":[110,141],"performance":[113,146],"improvement:":[114],"single":[117,149],"node,":[118],"from":[119],"16":[120],"Gflops":[121,131],"obtained":[122],"with":[123,132],"without":[126],"OpenACC,":[127],"we":[128,153],"reached":[129],"20":[130],"implementation.":[136],"An":[137],"optimized":[138,156],"43":[144],"Gflop":[145],"node.":[150],"In":[151],"addition,":[152],"ported":[154],"reaching":[162],"efficiency":[165],"79.9%":[167],"1024":[169],"GPUs":[170],"Titan":[173],"XK7":[174],"supercomputer":[175],"at":[176],"Oak":[178],"Ridge":[179],"National":[180],"Laboratory.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":4}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}