{"id":"https://openalex.org/W3161212090","doi":"https://doi.org/10.1109/tpds.2021.3078153","title":"Architectural Adaptation and Performance-Energy Optimization for CFD Application on AMD EPYC Rome","display_name":"Architectural Adaptation and Performance-Energy Optimization for CFD Application on AMD EPYC Rome","publication_year":2021,"publication_date":"2021-05-07","ids":{"openalex":"https://openalex.org/W3161212090","doi":"https://doi.org/10.1109/tpds.2021.3078153","mag":"3161212090"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2021.3078153","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpds.2021.3078153","pdf_url":"https://ieeexplore.ieee.org/ielx7/71/9445716/09426456.pdf","source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/71/9445716/09426456.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033643387","display_name":"\u0141ukasz Szustak","orcid":"https://orcid.org/0000-0001-7429-6981"},"institutions":[{"id":"https://openalex.org/I130294970","display_name":"Cz\u0119stochowa University of Technology","ror":"https://ror.org/046awyn59","country_code":"PL","type":"education","lineage":["https://openalex.org/I130294970"]}],"countries":["PL"],"is_corresponding":true,"raw_author_name":"Lukasz Szustak","raw_affiliation_strings":["Department of Computer Science, Czestochowa University of Technology, Czestochowa, Poland"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Czestochowa University of Technology, Czestochowa, Poland","institution_ids":["https://openalex.org/I130294970"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001502834","display_name":"Roman Wyrzykowski","orcid":"https://orcid.org/0000-0003-0328-2034"},"institutions":[{"id":"https://openalex.org/I130294970","display_name":"Cz\u0119stochowa University of Technology","ror":"https://ror.org/046awyn59","country_code":"PL","type":"education","lineage":["https://openalex.org/I130294970"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Roman Wyrzykowski","raw_affiliation_strings":["Department of Computer Science, Czestochowa University of Technology, Czestochowa, Poland"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Czestochowa University of Technology, Czestochowa, Poland","institution_ids":["https://openalex.org/I130294970"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069171629","display_name":"\u0141ukasz Kuczy\u0144ski","orcid":"https://orcid.org/0000-0001-8113-7882"},"institutions":[{"id":"https://openalex.org/I130294970","display_name":"Cz\u0119stochowa University of Technology","ror":"https://ror.org/046awyn59","country_code":"PL","type":"education","lineage":["https://openalex.org/I130294970"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Lukasz Kuczynski","raw_affiliation_strings":["Department of Computer Science, Czestochowa University of Technology, Czestochowa, Poland"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Czestochowa University of Technology, Czestochowa, Poland","institution_ids":["https://openalex.org/I130294970"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091237703","display_name":"Tomasz Olas","orcid":"https://orcid.org/0000-0002-7286-8023"},"institutions":[{"id":"https://openalex.org/I130294970","display_name":"Cz\u0119stochowa University of Technology","ror":"https://ror.org/046awyn59","country_code":"PL","type":"education","lineage":["https://openalex.org/I130294970"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Tomasz Olas","raw_affiliation_strings":["Department of Computer Science, Czestochowa University of Technology, Czestochowa, Poland"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Czestochowa University of Technology, Czestochowa, Poland","institution_ids":["https://openalex.org/I130294970"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5033643387"],"corresponding_institution_ids":["https://openalex.org/I130294970"],"apc_list":null,"apc_paid":null,"fwci":1.6515,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.82495402,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"32","issue":"12","first_page":"2852","last_page":"2866"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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":0.9995999932289124,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9968000054359436,"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/computer-science","display_name":"Computer science","score":0.8506961464881897},{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.6939282417297363},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6114709973335266},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6110007762908936},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.5649600625038147},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.5040897130966187},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.49567711353302},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.472626656293869},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.46736499667167664},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.4568503797054291},{"id":"https://openalex.org/keywords/stencil","display_name":"Stencil","score":0.4540347754955292},{"id":"https://openalex.org/keywords/microarchitecture","display_name":"Microarchitecture","score":0.43547922372817993},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4347575008869171},{"id":"https://openalex.org/keywords/software-portability","display_name":"Software portability","score":0.4301181435585022},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.35136717557907104},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.18541944026947021},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.18031799793243408}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8506961464881897},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.6939282417297363},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6114709973335266},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6110007762908936},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.5649600625038147},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.5040897130966187},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.49567711353302},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.472626656293869},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.46736499667167664},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.4568503797054291},{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.4540347754955292},{"id":"https://openalex.org/C107598950","wikidata":"https://www.wikidata.org/wiki/Q259864","display_name":"Microarchitecture","level":2,"score":0.43547922372817993},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4347575008869171},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.4301181435585022},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.35136717557907104},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.18541944026947021},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.18031799793243408},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2021.3078153","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpds.2021.3078153","pdf_url":"https://ieeexplore.ieee.org/ielx7/71/9445716/09426456.pdf","source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/tpds.2021.3078153","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpds.2021.3078153","pdf_url":"https://ieeexplore.ieee.org/ielx7/71/9445716/09426456.pdf","source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8999999761581421,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3161212090.pdf","grobid_xml":"https://content.openalex.org/works/W3161212090.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1559264847","https://openalex.org/W1972922682","https://openalex.org/W1975539849","https://openalex.org/W1997147891","https://openalex.org/W2002555321","https://openalex.org/W2035430533","https://openalex.org/W2055722407","https://openalex.org/W2070961300","https://openalex.org/W2075022716","https://openalex.org/W2154078685","https://openalex.org/W2170886848","https://openalex.org/W2508492666","https://openalex.org/W2598460206","https://openalex.org/W2615550444","https://openalex.org/W2725179571","https://openalex.org/W2748740248","https://openalex.org/W2772612468","https://openalex.org/W2777139487","https://openalex.org/W2782482897","https://openalex.org/W2795684256","https://openalex.org/W2810140736","https://openalex.org/W2916280107","https://openalex.org/W2948541941","https://openalex.org/W2963242393","https://openalex.org/W3029586207","https://openalex.org/W3101880650","https://openalex.org/W4205292626","https://openalex.org/W4248486648","https://openalex.org/W4252315406","https://openalex.org/W4255560897","https://openalex.org/W6737749052","https://openalex.org/W6746694394","https://openalex.org/W6805133334"],"related_works":["https://openalex.org/W2475524688","https://openalex.org/W2739740241","https://openalex.org/W2085105049","https://openalex.org/W2592417500","https://openalex.org/W2522739246","https://openalex.org/W1974923383","https://openalex.org/W2105221648","https://openalex.org/W2279642117","https://openalex.org/W4300190729","https://openalex.org/W2953056293"],"abstract_inverted_index":{"The":[0,92,130],"advantages":[1],"of":[2,50,83,94,105,120,166,188],"the":[3,14,19,48,51,68,80,84,88,95,99,112,121,134,137,156,174,186],"second-generation":[4],"AMD":[5,89,151,189],"EPYC":[6,90],"Rome":[7,39,113,152,190],"processors":[8,165,191],"can":[9,74],"be":[10,75],"successfully":[11],"used":[12],"in":[13,196],"race":[15],"to":[16,26,36,60,78,172],"Exascale.":[17],"However,":[18],"novel":[20,100],"architecture's":[21],"complexity":[22],"makes":[23],"it":[24],"challenging":[25],"adapt":[27],"demanding":[28],"scientific":[29,197],"codes":[30],"-":[31,35,118],"like":[32],"stencil":[33],"ones":[34],"platforms":[37],"with":[38,161],"CPUs.":[40],"This":[41],"article":[42,131],"tackles":[43],"this":[44],"challenge":[45],"by":[46,148],"exploring":[47],"adaptation":[49,72,97],"stencil-based":[52],"CFD":[53],"(computational":[54],"fluid":[55],"dynamics)":[56],"application":[57],"called":[58],"MPDATA":[59,86],"these":[61],"processors'":[62],"influential":[63],"features.":[64],"We":[65],"show":[66],"that":[67,109],"previously":[69],"proposed":[70],"parametric":[71,96],"methodology":[73],"profitably":[76],"applied":[77],"extend":[79],"performance":[81,138,176],"portability":[82],"memory-bound":[85],"on":[87,98],"architecture.":[91],"extension":[93],"architecture":[101,114],"requires":[102],"careful":[103],"consideration":[104],"two":[106,159],"relevant":[107],"aspects":[108],"reflect":[110],"splitting":[111],"into":[115,127],"multiple":[116],"dies":[117],"features":[119],"cache":[122],"hierarchy":[123],"and":[124,140,177],"partitioning":[125],"cores":[126],"work":[128],"teams.":[129],"also":[132],"investigates":[133],"correlation":[135],"between":[136],"optimizations":[139],"energy":[141,178],"efficiency":[142,179],"for":[143],"a":[144,182],"ccNUMA":[145],"platform":[146],"powered":[147],"top-of-the-line":[149],"64-core":[150],"7742":[153],"CPUs,":[154],"comparing":[155],"results":[157,180],"against":[158,192],"servers":[160],"Intel":[162,193],"Xeon":[163,194],"Scalable":[164],"different":[167],"generations.":[168],"Even":[169],"without":[170],"appealing":[171],"prices,":[173],"achieved":[175],"are":[181],"solid":[183],"argument":[184],"confirming":[185],"competitiveness":[187],"CPUs":[195],"applications.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}