{"id":"https://openalex.org/W3196629340","doi":"https://doi.org/10.1145/3468267.3470615","title":"Accelerating parallel CFD codes on modern vector processors using blockettes","display_name":"Accelerating parallel CFD codes on modern vector processors using blockettes","publication_year":2021,"publication_date":"2021-07-05","ids":{"openalex":"https://openalex.org/W3196629340","doi":"https://doi.org/10.1145/3468267.3470615","mag":"3196629340"},"language":"en","primary_location":{"id":"doi:10.1145/3468267.3470615","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3468267.3470615","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Platform for Advanced Scientific Computing Conference","raw_type":"proceedings-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/A5046045686","display_name":"An\u0131l Y\u0131ld\u0131r\u0131m","orcid":"https://orcid.org/0000-0002-1814-9191"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Anil Yildirim","raw_affiliation_strings":["University of Michigan"],"affiliations":[{"raw_affiliation_string":"University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037507826","display_name":"Charles A. Mader","orcid":"https://orcid.org/0000-0002-2744-1151"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charles A. Mader","raw_affiliation_strings":["University of Michigan"],"affiliations":[{"raw_affiliation_string":"University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002602051","display_name":"Joaquim R. R. A. Martins","orcid":"https://orcid.org/0000-0003-2143-1478"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joaquim R. R. A. Martins","raw_affiliation_strings":["University of Michigan"],"affiliations":[{"raw_affiliation_string":"University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5046045686"],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":0.6908,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.66756074,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9973999857902527,"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":0.9973999857902527,"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/T10173","display_name":"Computational Fluid Dynamics and Aerodynamics","score":0.9883000254631042,"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/T10339","display_name":"Advanced Numerical Methods in Computational Mathematics","score":0.9824000000953674,"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":0.8312727212905884},{"id":"https://openalex.org/keywords/computational-fluid-dynamics","display_name":"Computational fluid dynamics","score":0.8242404460906982},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7616775035858154},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7523661255836487},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.7213208675384521},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6803810596466064},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.5319621562957764},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.4852571487426758},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.46171000599861145},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.45626023411750793},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.35505762696266174},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16123434901237488},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.12735995650291443},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07401719689369202}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8312727212905884},{"id":"https://openalex.org/C1633027","wikidata":"https://www.wikidata.org/wiki/Q815820","display_name":"Computational fluid dynamics","level":2,"score":0.8242404460906982},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7616775035858154},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7523661255836487},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.7213208675384521},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6803810596466064},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.5319621562957764},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4852571487426758},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.46171000599861145},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.45626023411750793},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.35505762696266174},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16123434901237488},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.12735995650291443},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07401719689369202},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace 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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3468267.3470615","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3468267.3470615","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Platform for Advanced Scientific Computing Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1517282106","https://openalex.org/W1531802798","https://openalex.org/W1569090332","https://openalex.org/W1973919608","https://openalex.org/W2002555321","https://openalex.org/W2006382715","https://openalex.org/W2021012767","https://openalex.org/W2074976694","https://openalex.org/W2091836560","https://openalex.org/W2095154945","https://openalex.org/W2108266785","https://openalex.org/W2115215129","https://openalex.org/W2154865023","https://openalex.org/W2171303908","https://openalex.org/W2175831267","https://openalex.org/W2195884801","https://openalex.org/W2253091535","https://openalex.org/W2313852289","https://openalex.org/W2329921027","https://openalex.org/W2417194949","https://openalex.org/W2567781558","https://openalex.org/W2586670930","https://openalex.org/W2609466678","https://openalex.org/W2731415668","https://openalex.org/W2782154358","https://openalex.org/W2884969009","https://openalex.org/W2946650127","https://openalex.org/W2950298599","https://openalex.org/W2952865777","https://openalex.org/W2963153849","https://openalex.org/W3036238768","https://openalex.org/W3118701516","https://openalex.org/W3178266934","https://openalex.org/W4390173575"],"related_works":["https://openalex.org/W3012895752","https://openalex.org/W1582436825","https://openalex.org/W1604758548","https://openalex.org/W2804126825","https://openalex.org/W1996803181","https://openalex.org/W1549048322","https://openalex.org/W4367553810","https://openalex.org/W2104142636","https://openalex.org/W2979588510","https://openalex.org/W2015141752"],"abstract_inverted_index":{"The":[0,75],"performance":[1,40],"and":[2,31,119],"scalability":[3],"of":[4,22,111,143],"computational":[5,81],"fluid":[6],"dynamics":[7],"(CFD)":[8],"solvers":[9],"are":[10,50,88],"essential":[11],"for":[12,99],"many":[13],"applications,":[14],"including":[15],"multidisciplinary":[16],"design":[17],"optimization.":[18],"With":[19],"the":[20,35,47,54,95,140,144],"evolution":[21],"highperformance":[23],"computing":[24],"resources":[25],"such":[26,116],"as":[27,117],"Intel's":[28],"Knights":[29],"Landing":[30],"Skylake":[32],"architectures":[33,124],"in":[34,139],"Stampede2":[36],"cluster,":[37],"CFD":[38,69,146],"solver":[39],"can":[41,107],"be":[42],"improved":[43],"by":[44],"modifying":[45],"how":[46],"core":[48,101,141],"computations":[49],"performed":[51],"while":[52],"keeping":[53],"mathematical":[55],"formulation":[56],"unchanged.":[57],"In":[58],"this":[59,126,129],"work,":[60],"we":[61,131],"introduce":[62],"a":[63,103],"cache-blocking":[64],"method":[65],"to":[66,79,91,135],"improve":[67],"memory-bound":[68],"codes":[70],"that":[71,87],"use":[72],"structured":[73],"grids.":[74],"overall":[76],"idea":[77],"is":[78],"split":[80],"blocks":[82],"into":[83,94],"smaller,":[84],"fixed-sized":[85],"blockettes":[86],"sufficiently":[89],"small":[90],"completely":[92],"fit":[93],"available":[96],"cache":[97],"size":[98],"each":[100],"on":[102,121],"given":[104],"architecture.":[105],"We":[106],"fully":[108],"take":[109],"advantage":[110],"modern":[112,123],"vector":[113],"instruction":[114],"sets":[115],"AVX2":[118],"AVX512":[120],"these":[122],"with":[125],"approach.":[127],"Using":[128],"method,":[130],"have":[132],"achieved":[133],"up":[134],"3.27":[136],"times":[137],"speedup":[138],"routines":[142],"open-source":[145],"solver,":[147],"ADflow.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}