{"id":"https://openalex.org/W2801656560","doi":"https://doi.org/10.1109/tpds.2018.2826533","title":"Optimizations of Unstructured Aerodynamics Computations for Many-core Architectures","display_name":"Optimizations of Unstructured Aerodynamics Computations for Many-core Architectures","publication_year":2018,"publication_date":"2018-04-13","ids":{"openalex":"https://openalex.org/W2801656560","doi":"https://doi.org/10.1109/tpds.2018.2826533","mag":"2801656560"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2018.2826533","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2018.2826533","pdf_url":null,"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":null,"license_id":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045148446","display_name":"Mohammed Al Farhan","orcid":"https://orcid.org/0000-0002-4988-4674"},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Mohammed A. Al Farhan","raw_affiliation_strings":["Extreme Computing Research Center, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia","Extreme Comput-ing Research Center, King Abdullah University of Science and Technology, Thuwal 23955-6900, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0002-4988-4674","affiliations":[{"raw_affiliation_string":"Extreme Computing Research Center, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]},{"raw_affiliation_string":"Extreme Comput-ing Research Center, King Abdullah University of Science and Technology, Thuwal 23955-6900, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021283893","display_name":"David E. Keyes","orcid":"https://orcid.org/0000-0002-4052-7224"},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"David E. Keyes","raw_affiliation_strings":["Extreme Computing Research Center, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia","Extreme Comput-ing Research Center, King Abdullah University of Science and Technology, Thuwal 23955-6900, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0002-4052-7224","affiliations":[{"raw_affiliation_string":"Extreme Computing Research Center, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]},{"raw_affiliation_string":"Extreme Comput-ing Research Center, King Abdullah University of Science and Technology, Thuwal 23955-6900, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6129,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.90978311,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"29","issue":"10","first_page":"2317","last_page":"2332"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9894999861717224,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.9843999743461609,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.8807240724563599},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8449221849441528},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.8188644051551819},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.708967387676239},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6315082311630249},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.585328221321106},{"id":"https://openalex.org/keywords/multithreading","display_name":"Multithreading","score":0.5427958369255066},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.4984419345855713},{"id":"https://openalex.org/keywords/microarchitecture","display_name":"Microarchitecture","score":0.49829554557800293},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.49582991003990173},{"id":"https://openalex.org/keywords/single-core","display_name":"Single-core","score":0.46810078620910645},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4167778789997101},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3527311682701111},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1311737596988678}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8807240724563599},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8449221849441528},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8188644051551819},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.708967387676239},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6315082311630249},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.585328221321106},{"id":"https://openalex.org/C201410400","wikidata":"https://www.wikidata.org/wiki/Q1064412","display_name":"Multithreading","level":3,"score":0.5427958369255066},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.4984419345855713},{"id":"https://openalex.org/C107598950","wikidata":"https://www.wikidata.org/wiki/Q259864","display_name":"Microarchitecture","level":2,"score":0.49829554557800293},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.49582991003990173},{"id":"https://openalex.org/C2780365336","wikidata":"https://www.wikidata.org/wiki/Q25047934","display_name":"Single-core","level":2,"score":0.46810078620910645},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4167778789997101},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3527311682701111},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1311737596988678}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpds.2018.2826533","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2018.2826533","pdf_url":null,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},{"id":"pmh:oai:repository.kaust.edu.sa:10754/627692","is_oa":false,"landing_page_url":"http://hdl.handle.net/10754/627692","pdf_url":null,"source":{"id":"https://openalex.org/S4306401596","display_name":"King Abdullah University of Science and Technology Repository (King Abdullah University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I71920554","host_organization_name":"King Abdullah University of Science and Technology","host_organization_lineage":["https://openalex.org/I71920554"],"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":null,"sustainable_development_goals":[{"score":0.5,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322320","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":86,"referenced_works":["https://openalex.org/W53560269","https://openalex.org/W196824805","https://openalex.org/W348433680","https://openalex.org/W1506424797","https://openalex.org/W1517282106","https://openalex.org/W1569090332","https://openalex.org/W1596846800","https://openalex.org/W1901281515","https://openalex.org/W1977294541","https://openalex.org/W1999329795","https://openalex.org/W2000882268","https://openalex.org/W2016488637","https://openalex.org/W2020215844","https://openalex.org/W2023432267","https://openalex.org/W2056609352","https://openalex.org/W2064735574","https://openalex.org/W2067635581","https://openalex.org/W2070232376","https://openalex.org/W2074976694","https://openalex.org/W2076804553","https://openalex.org/W2095258827","https://openalex.org/W2095420020","https://openalex.org/W2115215129","https://openalex.org/W2139205226","https://openalex.org/W2143257021","https://openalex.org/W2147076738","https://openalex.org/W2150342712","https://openalex.org/W2150871235","https://openalex.org/W2161351786","https://openalex.org/W2171303908","https://openalex.org/W2216523920","https://openalex.org/W2340076492","https://openalex.org/W2344628725","https://openalex.org/W2417194949","https://openalex.org/W2473693139","https://openalex.org/W2476946651","https://openalex.org/W2505067803","https://openalex.org/W2529487057","https://openalex.org/W2551238896","https://openalex.org/W2551656647","https://openalex.org/W2559660259","https://openalex.org/W2581090187","https://openalex.org/W2581189719","https://openalex.org/W2594229401","https://openalex.org/W2606413522","https://openalex.org/W2609137082","https://openalex.org/W2617189289","https://openalex.org/W2618868084","https://openalex.org/W2724545582","https://openalex.org/W2729169124","https://openalex.org/W2740116753","https://openalex.org/W2741421049","https://openalex.org/W2745269232","https://openalex.org/W2767926324","https://openalex.org/W2768065515","https://openalex.org/W2786544209","https://openalex.org/W2789228469","https://openalex.org/W2962978274","https://openalex.org/W2963242393","https://openalex.org/W3021837324","https://openalex.org/W3099448935","https://openalex.org/W3101140947","https://openalex.org/W3145241477","https://openalex.org/W3188799945","https://openalex.org/W4232055594","https://openalex.org/W4242286475","https://openalex.org/W6602196487","https://openalex.org/W6630988189","https://openalex.org/W6635603319","https://openalex.org/W6677416967","https://openalex.org/W6680844048","https://openalex.org/W6680930741","https://openalex.org/W6681958216","https://openalex.org/W6687222882","https://openalex.org/W6720990514","https://openalex.org/W6728321799","https://openalex.org/W6729819855","https://openalex.org/W6729926270","https://openalex.org/W6736973013","https://openalex.org/W6737976357","https://openalex.org/W6738122305","https://openalex.org/W6740000624","https://openalex.org/W6740567796","https://openalex.org/W6741914247","https://openalex.org/W6742690309","https://openalex.org/W6745595149"],"related_works":["https://openalex.org/W2014711461","https://openalex.org/W2998169068","https://openalex.org/W1996932109","https://openalex.org/W1563877120","https://openalex.org/W3092250248","https://openalex.org/W3036939780","https://openalex.org/W1993711049","https://openalex.org/W4302771143","https://openalex.org/W2801656560","https://openalex.org/W2170960709"],"abstract_inverted_index":{"We":[0,21,54],"investigate":[1],"several":[2],"state-of-the-practice":[3],"shared-memory":[4],"optimization":[5],"techniques":[6],"applied":[7],"to":[8,108,118,134,138,153,166],"key":[9],"routines":[10,106],"of":[11,32,50,76,103,141,144,156,168],"an":[12],"unstructured":[13,173],"computational":[14],"aerodynamics":[15],"application":[16],"with":[17,125],"irregular":[18],"memory":[19],"accesses.":[20],"illustrate":[22],"for":[23,170],"the":[24,33,46,51,82,85,104,109,139],"Intel":[25],"Knights":[26,95],"Landing":[27,96],"processor,":[28],"as":[29,178],"a":[30,72,93,145,157],"representative":[31],"processors":[34],"in":[35],"contemporary":[36],"leading":[37],"supercomputers,":[38],"identifying":[39],"and":[40,57,64,78,84,121,149,180],"addressing":[41],"performance":[42,140,152],"challenges":[43],"without":[44],"compromising":[45],"floating":[47],"point":[48],"numerics":[49],"original":[52],"code.":[53],"employ":[55],"low":[56],"high-level":[58],"architecture-specific":[59],"code":[60],"optimizations":[61,163],"involving":[62],"thread":[63],"data-level":[65],"parallelism.":[66],"Our":[67],"approach":[68],"is":[69],"based":[70],"upon":[71],"multi-level":[73],"hierarchical":[74],"distribution":[75],"work":[77],"data":[79],"across":[80],"both":[81],"threads":[83,143,155],"SIMD":[86],"units":[87],"within":[88],"every":[89],"hardware":[90],"core.":[91],"On":[92],"64-core":[94],"chip,":[97],"we":[98,131],"achieve":[99,132],"nearly":[100],"2.9\u00d7":[101],"speedup":[102,136],"dominant":[105],"relative":[107,137],"baseline.":[110],"These":[111,162],"exhibit":[112],"almost":[113],"linear":[114],"strong":[115],"scalability":[116],"up":[117,133],"64":[119],"threads,":[120],"thereafter":[122],"some":[123],"improvement":[124],"hyperthreading.":[126],"At":[127],"substantially":[128],"fewer":[129],"Watts,":[130],"1.7\u00d7":[135],"72":[142],"36-core":[146],"Haswell":[147],"CPU":[148],"roughly":[150],"equivalent":[151],"112":[154],"56-core":[158],"Skylake":[159],"scalable":[160],"processor.":[161],"are":[164],"expected":[165],"be":[167],"value":[169],"many":[171],"other":[172],"mesh":[174],"PDE-based":[175],"scientific":[176],"applications":[177],"multi":[179],"many-core":[181],"architecture":[182],"evolves.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}