{"id":"https://openalex.org/W4410517024","doi":"https://doi.org/10.1177/10943420251341179","title":"Julia versus C++ Kokkos for performance portable Cartesian CFD solvers on heterogeneous architectures","display_name":"Julia versus C++ Kokkos for performance portable Cartesian CFD solvers on heterogeneous architectures","publication_year":2025,"publication_date":"2025-05-20","ids":{"openalex":"https://openalex.org/W4410517024","doi":"https://doi.org/10.1177/10943420251341179"},"language":"en","primary_location":{"id":"doi:10.1177/10943420251341179","is_oa":false,"landing_page_url":"https://doi.org/10.1177/10943420251341179","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/A5117605654","display_name":"Luc Briand","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125654","display_name":"Maison de la Simulation","ror":"https://ror.org/03jv6w209","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I195731000","https://openalex.org/I2738703131","https://openalex.org/I2738703131","https://openalex.org/I277688954","https://openalex.org/I277688954","https://openalex.org/I4210113668","https://openalex.org/I4210125654","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I2738703131","display_name":"Commissariat \u00e0 l'\u00c9nergie Atomique et aux \u00c9nergies Alternatives","ror":"https://ror.org/00jjx8s55","country_code":"FR","type":"government","lineage":["https://openalex.org/I2738703131"]},{"id":"https://openalex.org/I4210101455","display_name":"CEA DAM \u00cele-de-France","ror":"https://ror.org/00kn4eb29","country_code":"FR","type":"government","lineage":["https://openalex.org/I4210101455"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Luc Briand","raw_affiliation_strings":["CEA, DAM, DIF, DSSI, Arpajon, France","Laboratoire en Informatique Haute Performance pour le Calcul et La Simulation, Universit\u00e9 Paris-Saclay, CEA DAM DIF, Arpajon, France"],"affiliations":[{"raw_affiliation_string":"CEA, DAM, DIF, DSSI, Arpajon, France","institution_ids":["https://openalex.org/I2738703131","https://openalex.org/I4210101455"]},{"raw_affiliation_string":"Laboratoire en Informatique Haute Performance pour le Calcul et La Simulation, Universit\u00e9 Paris-Saclay, CEA DAM DIF, Arpajon, France","institution_ids":["https://openalex.org/I277688954","https://openalex.org/I2738703131","https://openalex.org/I4210125654","https://openalex.org/I4210101455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064577997","display_name":"Herv\u00e9 Jourdren","orcid":null},"institutions":[{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I4210125654","display_name":"Maison de la Simulation","ror":"https://ror.org/03jv6w209","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I195731000","https://openalex.org/I2738703131","https://openalex.org/I2738703131","https://openalex.org/I277688954","https://openalex.org/I277688954","https://openalex.org/I4210113668","https://openalex.org/I4210125654","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I4210101455","display_name":"CEA DAM \u00cele-de-France","ror":"https://ror.org/00kn4eb29","country_code":"FR","type":"government","lineage":["https://openalex.org/I4210101455"]},{"id":"https://openalex.org/I2738703131","display_name":"Commissariat \u00e0 l'\u00c9nergie Atomique et aux \u00c9nergies Alternatives","ror":"https://ror.org/00jjx8s55","country_code":"FR","type":"government","lineage":["https://openalex.org/I2738703131"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Herv\u00e9 Jourdren","raw_affiliation_strings":["CEA, DAM, DIF, DSSI, Arpajon, France","Laboratoire en Informatique Haute Performance pour le Calcul et La Simulation, Universit\u00e9 Paris-Saclay, CEA DAM DIF, Arpajon, France"],"affiliations":[{"raw_affiliation_string":"CEA, DAM, DIF, DSSI, Arpajon, France","institution_ids":["https://openalex.org/I2738703131","https://openalex.org/I4210101455"]},{"raw_affiliation_string":"Laboratoire en Informatique Haute Performance pour le Calcul et La Simulation, Universit\u00e9 Paris-Saclay, CEA DAM DIF, Arpajon, France","institution_ids":["https://openalex.org/I277688954","https://openalex.org/I2738703131","https://openalex.org/I4210125654","https://openalex.org/I4210101455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015641898","display_name":"Marc P\u00e9rache","orcid":"https://orcid.org/0000-0003-1615-2749"},"institutions":[{"id":"https://openalex.org/I2738703131","display_name":"Commissariat \u00e0 l'\u00c9nergie Atomique et aux \u00c9nergies Alternatives","ror":"https://ror.org/00jjx8s55","country_code":"FR","type":"government","lineage":["https://openalex.org/I2738703131"]},{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I4210101455","display_name":"CEA DAM \u00cele-de-France","ror":"https://ror.org/00kn4eb29","country_code":"FR","type":"government","lineage":["https://openalex.org/I4210101455"]},{"id":"https://openalex.org/I4210125654","display_name":"Maison de la Simulation","ror":"https://ror.org/03jv6w209","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I195731000","https://openalex.org/I2738703131","https://openalex.org/I2738703131","https://openalex.org/I277688954","https://openalex.org/I277688954","https://openalex.org/I4210113668","https://openalex.org/I4210125654","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Marc P\u00e9rache","raw_affiliation_strings":["CEA, DAM, DIF, DSSI, Arpajon, France","Laboratoire en Informatique Haute Performance pour le Calcul et La Simulation, Universit\u00e9 Paris-Saclay, CEA DAM DIF, Arpajon, France"],"affiliations":[{"raw_affiliation_string":"CEA, DAM, DIF, DSSI, Arpajon, France","institution_ids":["https://openalex.org/I2738703131","https://openalex.org/I4210101455"]},{"raw_affiliation_string":"Laboratoire en Informatique Haute Performance pour le Calcul et La Simulation, Universit\u00e9 Paris-Saclay, CEA DAM DIF, Arpajon, France","institution_ids":["https://openalex.org/I277688954","https://openalex.org/I2738703131","https://openalex.org/I4210125654","https://openalex.org/I4210101455"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5117605654"],"corresponding_institution_ids":["https://openalex.org/I2738703131","https://openalex.org/I277688954","https://openalex.org/I4210101455","https://openalex.org/I4210125654"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13196713,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"39","issue":"4","first_page":"481","last_page":"501"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9915000200271606,"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"}},"topics":[{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9915000200271606,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9909999966621399,"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":0.9894999861717224,"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":0.7616904973983765},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7586365342140198},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.5759896039962769},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5206258296966553},{"id":"https://openalex.org/keywords/cartesian-coordinate-system","display_name":"Cartesian coordinate system","score":0.44891130924224854},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.44497150182724},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.39464446902275085},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14117825031280518},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1204623281955719},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.08274117112159729}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7616904973983765},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7586365342140198},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.5759896039962769},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5206258296966553},{"id":"https://openalex.org/C16038011","wikidata":"https://www.wikidata.org/wiki/Q62912","display_name":"Cartesian coordinate system","level":2,"score":0.44891130924224854},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.44497150182724},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.39464446902275085},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14117825031280518},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1204623281955719},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.08274117112159729}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/10943420251341179","is_oa":false,"landing_page_url":"https://doi.org/10.1177/10943420251341179","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":[{"score":0.9100000262260437,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W7882702","https://openalex.org/W1602359794","https://openalex.org/W1982403793","https://openalex.org/W1999399767","https://openalex.org/W2064983687","https://openalex.org/W2078794610","https://openalex.org/W2120575449","https://openalex.org/W2157871138","https://openalex.org/W2275070774","https://openalex.org/W2607112060","https://openalex.org/W2774096293","https://openalex.org/W2944412207","https://openalex.org/W2996807164","https://openalex.org/W3088889034","https://openalex.org/W3125160487","https://openalex.org/W3174986514","https://openalex.org/W3182781792","https://openalex.org/W3195293013","https://openalex.org/W4200478241","https://openalex.org/W4232262529","https://openalex.org/W4233549502","https://openalex.org/W4386907353","https://openalex.org/W6968978714","https://openalex.org/W7006015045"],"related_works":["https://openalex.org/W1604758548","https://openalex.org/W2804126825","https://openalex.org/W1549048322","https://openalex.org/W4367553810","https://openalex.org/W2104142636","https://openalex.org/W2731831065","https://openalex.org/W4283162424","https://openalex.org/W3032230396","https://openalex.org/W2011940952","https://openalex.org/W2144429051"],"abstract_inverted_index":{"Looking":[0],"for":[1,43,52,134,228,247,396],"high":[2,248],"performance":[3,12,249,274,318,332],"hydrocode":[4],"simulations":[5,252],"on":[6,48,55,83,199,303,308],"heterogeneous":[7,400],"architectures,":[8],"we":[9],"detail":[10],"a":[11,16,32,91,96,124,173,291,327,334,348,371,378,390],"portable":[13,275,319],"implementation":[14,145,151,277],"of":[15,137,176,215,278,315,329,336,355,370,377],"second-order":[17],"accurate":[18],"2-D":[19],"Cartesian":[20,184],"explicit":[21],"CFD":[22,190,280],"solver":[23,281],"using":[24,290],"Julia\u2019s":[25],"Just-in-Time":[26],"(JIT)":[27],"compilation.":[28],"In":[29,204],"this":[30,205,309],"work,":[31,349],"custom":[33],"abstraction":[34],"layer":[35],"is":[36,116,146,169],"used":[37,66],"targeting":[38],"two":[39],"Julia":[40,109,150,276,317,357],"packages,":[41],"Polyester.jl":[42],"efficient":[44],"shared":[45],"memory":[46,166,196,224,238,325],"multithreading":[47],"CPUs":[49,85,201],"and":[50,61,80,86,181,202,231,242,263,287,333,360,381],"KernelAbstractions.jl":[51],"appropriate":[53],"backends":[54],"GPUs.":[56,203],"Using":[57,90,139],"very":[58,125],"same":[59,126,155],"optimizations":[60],"data":[62],"structures":[63],"than":[64],"those":[65],"with":[67,95,123,221,271,300,393],"Julia,":[68],"comparisons":[69],"to":[70,100,118,153,268,343,389,398],"static":[71,292],"C++":[72,120,143],"Kokkos":[73,121,144],"compilation":[74,391],"are":[75,186,266],"then":[76],"provided,":[77],"including":[78],"speedups":[79],"energy":[81,340],"consumptions":[82],"high-end":[84],"GPUs":[87,302],"available":[88,225],"mid-2022.":[89],"single":[92],"64-core":[93],"CPU":[94,345],"few":[97],"million":[98],"cells":[99],"benefit":[101],"from":[102,296],"cache":[103],"effects":[104],"in":[105,188,331,338],"multithread":[106],"mode,":[107],"the":[108,142,149,154,164,189,208,212,216,279,312,316,344,353,356,368,375],"code":[110,320],"(\u22480.5":[111],"\u00d7":[112,130,159],"10":[113,131,160],"9":[114,132,161],"cell-cycles/s)":[115,133,162],"superior":[117],"its":[119,361],"counterpart,":[122],"lower":[127],"limit":[128,157],"(\u22480.16":[129],"higher":[135,243],"numbers":[136],"cells.":[138],"one":[140],"GPU,":[141],"slightly":[147],"superior,":[148],"tending":[152],"upper":[156],"(\u22481.5":[158],"when":[163],"GPU":[165,313],"(40":[167],"GiB)":[168],"entirely":[170],"used.":[171],"With":[172],"small":[174],"number":[175],"floating-point":[177,244],"operations":[178],"per":[179,226],"cell":[180,227],"time":[182],"step,":[183],"solvers":[185,193],"singular":[187],"landscape,":[191],"such":[192],"being":[194],"essentially":[195],"bandwidth":[197],"bound":[198],"both":[200],"context,":[206],"at":[207,322],"compute":[209,213,259],"node":[210],"level,":[211],"capability":[214],"CPU(s)":[217],"cannot":[218],"be":[219],"underestimated,":[220],"(much)":[222],"more":[223,384],"multi-physics":[229],"variables":[230],"-":[232,236],"year":[233,235],"over":[234],"improved":[237],"bandwidths,":[239],"larger":[240],"caches":[241],"capabilities.":[245],"Indeed,":[246],"computing":[250,401],"(HPC)":[251],"involving":[253],"many":[254],"MPI":[255],"processes,":[256],"communications":[257,270,298],"between":[258],"nodes":[260],"become":[261],"significant":[262],"best":[264],"efforts":[265],"requested":[267],"overlap":[269],"computations.":[272],"The":[273],"presented":[282],"here":[283],"combines":[284],"domain":[285],"decomposition":[286],"directional":[288],"splitting":[289],"scheduling":[293],"approach.":[294],"Benefits":[295],"asynchronous":[297],"appear":[299],"16":[301],"4":[304],"nodes.":[305],"At":[306],"best,":[307],"small-size":[310],"configuration,":[311],"mode":[314],"brings":[321],"full":[323],"GPUs\u2019":[324],"capacity":[326],"factor":[328,335],"14\u00d7":[330],"8\u00d7":[337],"device":[339],"efficiency":[341],"compared":[342],"mode.":[346],"Such":[347],"among":[350],"others,":[351],"confirms":[352],"potential":[354],"programming":[358],"language":[359],"emerging":[362],"HPC":[363],"software":[364],"stack,":[365],"offering":[366],"(i)":[367],"power":[369],"scripting":[372],"language,":[373,380],"(ii)":[374],"performances":[376],"compiled":[379],"perhaps":[382],"even":[383],"importantly":[385],"(iii)":[386],"an":[387],"access":[388],"toolchain":[392],"new":[394],"opportunities":[395],"developers":[397],"tackle":[399],"architectures.":[402]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
