{"id":"https://openalex.org/W2799990610","doi":"https://doi.org/10.1177/1094342018774126","title":"Practical applicability of optimizations and performance models to complex stencil-based loop kernels in CFD","display_name":"Practical applicability of optimizations and performance models to complex stencil-based loop kernels in CFD","publication_year":2018,"publication_date":"2018-05-10","ids":{"openalex":"https://openalex.org/W2799990610","doi":"https://doi.org/10.1177/1094342018774126","mag":"2799990610"},"language":"en","primary_location":{"id":"doi:10.1177/1094342018774126","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342018774126","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":true,"oa_status":"green","oa_url":"http://mediatum.ub.tum.de/node?id=1367496","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086437222","display_name":"Karl-Robert Wichmann","orcid":"https://orcid.org/0009-0002-2879-6613"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Karl-Robert Wichmann","raw_affiliation_strings":["Institute for Computational Mechanics, Technical University of Munich, Garching b. M\u00fcnchen, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Computational Mechanics, Technical University of Munich, Garching b. M\u00fcnchen, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048891988","display_name":"Martin Kronbichler","orcid":"https://orcid.org/0000-0001-8406-835X"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Martin Kronbichler","raw_affiliation_strings":["Institute for Computational Mechanics, Technical University of Munich, Garching b. M\u00fcnchen, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Computational Mechanics, Technical University of Munich, Garching b. M\u00fcnchen, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030435894","display_name":"Rainald L\u00f6hner","orcid":"https://orcid.org/0000-0003-0083-5131"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rainald L\u00f6hner","raw_affiliation_strings":["Center for Computational Fluid Dynamics, George Mason University, Fairfax, VA, USA"],"affiliations":[{"raw_affiliation_string":"Center for Computational Fluid Dynamics, George Mason University, Fairfax, VA, USA","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053323760","display_name":"Wolfgang A. Wall","orcid":"https://orcid.org/0000-0001-7419-3384"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Wolfgang A Wall","raw_affiliation_strings":["Institute for Computational Mechanics, Technical University of Munich, Garching b. M\u00fcnchen, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Computational Mechanics, Technical University of Munich, Garching b. M\u00fcnchen, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5048891988"],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":0.832,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.6944793,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"33","issue":"4","first_page":"602","last_page":"618"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11751","display_name":"Lattice Boltzmann Simulation Studies","score":0.9940999746322632,"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/T11751","display_name":"Lattice Boltzmann Simulation Studies","score":0.9940999746322632,"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/T10173","display_name":"Computational Fluid Dynamics and Aerodynamics","score":0.9940000176429749,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9937000274658203,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/stencil","display_name":"Stencil","score":0.9601811170578003},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.7959624528884888},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7077762484550476},{"id":"https://openalex.org/keywords/computational-fluid-dynamics","display_name":"Computational fluid dynamics","score":0.6719927191734314},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5674371719360352},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5010495185852051},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.46444064378738403},{"id":"https://openalex.org/keywords/compressibility","display_name":"Compressibility","score":0.4583228826522827},{"id":"https://openalex.org/keywords/scalar","display_name":"Scalar (mathematics)","score":0.432010293006897},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.42821985483169556},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14799439907073975},{"id":"https://openalex.org/keywords/mechanics","display_name":"Mechanics","score":0.12483751773834229},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09521496295928955}],"concepts":[{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.9601811170578003},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.7959624528884888},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7077762484550476},{"id":"https://openalex.org/C1633027","wikidata":"https://www.wikidata.org/wiki/Q815820","display_name":"Computational fluid dynamics","level":2,"score":0.6719927191734314},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5674371719360352},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5010495185852051},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.46444064378738403},{"id":"https://openalex.org/C84655787","wikidata":"https://www.wikidata.org/wiki/Q8067817","display_name":"Compressibility","level":2,"score":0.4583228826522827},{"id":"https://openalex.org/C57691317","wikidata":"https://www.wikidata.org/wiki/Q1289248","display_name":"Scalar (mathematics)","level":2,"score":0.432010293006897},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.42821985483169556},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14799439907073975},{"id":"https://openalex.org/C57879066","wikidata":"https://www.wikidata.org/wiki/Q41217","display_name":"Mechanics","level":1,"score":0.12483751773834229},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09521496295928955},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1177/1094342018774126","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342018774126","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"},{"id":"pmh:oai:mediatum.ub.tum.de:node/1367496","is_oa":true,"landing_page_url":"http://mediatum.ub.tum.de/node?id=1367496","pdf_url":null,"source":{"id":"https://openalex.org/S4306400453","display_name":"mediaTUM \u2013 the media and publications repository of the Technical University Munich (Technical University Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"},{"id":"pmh:oai:mediatum.ub.tum.de:node/1536324","is_oa":true,"landing_page_url":"http://mediatum.ub.tum.de/node?id=1536324","pdf_url":null,"source":{"id":"https://openalex.org/S4377196330","display_name":"mediaTUM  (Technical University of Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"},{"id":"pmh:oai:uni-augsburg.opus-bayern.de:98195","is_oa":false,"landing_page_url":"https://opus.bibliothek.uni-augsburg.de/opus4/frontdoor/index/index/docId/98195","pdf_url":null,"source":{"id":"https://openalex.org/S4306400930","display_name":"OPUS (Augsburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119916105","host_organization_name":"Augsburg University","host_organization_lineage":["https://openalex.org/I119916105"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"},{"id":"pmh:oai:uni-augsburg.opus-bayern.de:98197","is_oa":false,"landing_page_url":"https://opus.bibliothek.uni-augsburg.de/opus4/frontdoor/index/index/docId/98197","pdf_url":null,"source":{"id":"https://openalex.org/S4306400930","display_name":"OPUS (Augsburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119916105","host_organization_name":"Augsburg University","host_organization_lineage":["https://openalex.org/I119916105"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:mediatum.ub.tum.de:node/1367496","is_oa":true,"landing_page_url":"http://mediatum.ub.tum.de/node?id=1367496","pdf_url":null,"source":{"id":"https://openalex.org/S4306400453","display_name":"mediaTUM \u2013 the media and publications repository of the Technical University Munich (Technical University Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1961751213","https://openalex.org/W1971876223","https://openalex.org/W1978197409","https://openalex.org/W1986328299","https://openalex.org/W1997147891","https://openalex.org/W2008005532","https://openalex.org/W2057577013","https://openalex.org/W2063249715","https://openalex.org/W2073875590","https://openalex.org/W2078636996","https://openalex.org/W2092388465","https://openalex.org/W2096642134","https://openalex.org/W2113754927","https://openalex.org/W2116493917","https://openalex.org/W2120934608","https://openalex.org/W2128544095","https://openalex.org/W2135682468","https://openalex.org/W2138007781","https://openalex.org/W2173545083","https://openalex.org/W2257508639","https://openalex.org/W2314366485","https://openalex.org/W2593836394","https://openalex.org/W2963799023","https://openalex.org/W3103104567","https://openalex.org/W3106055984","https://openalex.org/W3125983777","https://openalex.org/W3178266934","https://openalex.org/W4213211643","https://openalex.org/W4249930535","https://openalex.org/W4249968602","https://openalex.org/W4253068647","https://openalex.org/W4376596376"],"related_works":["https://openalex.org/W2177020196","https://openalex.org/W1429949169","https://openalex.org/W1604758548","https://openalex.org/W2804126825","https://openalex.org/W4367553810","https://openalex.org/W2104142636","https://openalex.org/W1549048322","https://openalex.org/W2011940952","https://openalex.org/W2731831065","https://openalex.org/W3139770841"],"abstract_inverted_index":{"This":[0],"work":[1],"investigates":[2],"the":[3,31,67,90,99,115,122,137,150,158,168,173,191],"application":[4],"and":[5,10,43,89,124],"interaction":[6],"of":[7,190],"optimization":[8],"techniques":[9],"performance":[11,62,72,161,175,193],"models":[12,63,73,100,162],"in":[13,51,136,145],"a":[14,36,48,76,143],"computational":[15],"fluid":[16],"dynamics":[17],"(CFD)":[18],"approach":[19],"employing":[20],"an":[21],"OpenMP":[22],"parallelized,":[23],"explicit,":[24],"weakly":[25],"compressible,":[26],"finite":[27],"difference\u2013based":[28],"solver":[29],"for":[30,104,111,121,181],"incompressible":[32],"Navier\u2013Stokes":[33],"equations":[34],"using":[35],"five-point":[37],"wide":[38],"stencil.":[39,126],"The":[40],"presented":[41],"loop":[42],"stencil":[44],"optimizations":[45],"lead":[46],"to":[47,57,66,131,142,165],"6.8\u00d7":[49],"increase":[50],"per":[52],"core":[53],"throughput.":[54],"In":[55],"order":[56],"verify":[58],"optimal":[59],"CPU":[60],"utilization,":[61],"are":[64,74,163],"applied":[65,159],"tuned":[68,125,183],"code.":[69,184],"Three":[70],"different":[71],"considered:":[75],"roofline-based":[77],"model,":[78,138],"utilizing":[79],"purely":[80,148],"theoretical":[81],"figures,":[82],"one":[83],"which":[84,146,153],"is":[85,96,118,129],"enhanced":[86],"by":[87,176],"measurements,":[88],"execution":[91],"cache":[92],"memory":[93],"model.":[94],"It":[95],"shown":[97],"that":[98],"provide":[101],"reliable":[102],"estimates":[103],"simple":[105],"benchmarks,":[106],"such":[107],"as":[108],"seven-point":[109],"stencils":[110],"scalar":[112],"Laplacians,":[113],"but":[114],"estimate":[116],"quality":[117],"significantly":[119],"worse":[120],"complex":[123],"While":[127],"it":[128,139,147,154],"possible":[130],"include":[132],"even":[133],"more":[134,177],"details":[135],"eventually":[140],"leads":[141],"state":[144],"reproduces":[149],"benchmarks":[151],"from":[152],"was":[155],"derived.":[156],"Thus,":[157],"general-purpose":[160],"found":[164],"inaccurately":[166],"predict":[167],"actual":[169],"performance.":[170],"They":[171],"overestimate":[172],"achievable":[174],"than":[178],"about":[179],"97%":[180],"highly":[182],"Through":[185],"further":[186],"code":[187],"tuning,":[188],"66%":[189],"predicted":[192],"could":[194],"be":[195],"achieved.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2018-05-17T00:00:00"}
