{"id":"https://openalex.org/W7125409735","doi":"https://doi.org/10.1145/3784828.3785255","title":"Hybrid Inference Optimization for AI-Enhanced Turbulent Boundary Layer Simulation on Heterogeneous Systems","display_name":"Hybrid Inference Optimization for AI-Enhanced Turbulent Boundary Layer Simulation on Heterogeneous Systems","publication_year":2026,"publication_date":"2026-01-22","ids":{"openalex":"https://openalex.org/W7125409735","doi":"https://doi.org/10.1145/3784828.3785255"},"language":"en","primary_location":{"id":"doi:10.1145/3784828.3785255","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3784828.3785255","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Supercomputing Asia and International Conference on High Performance Computing in Asia Pacific Region Workshops","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3784828.3785255","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001414405","display_name":"Fabian Orland","orcid":"https://orcid.org/0000-0002-8681-2661"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Fabian Orland","raw_affiliation_strings":["High Performance Computing, RWTH Aachen University, Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"High Performance Computing, RWTH Aachen University, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5095780945","display_name":"Tom Hilgers","orcid":"https://orcid.org/0000-0002-7501-3936"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tom Hilgers","raw_affiliation_strings":["RWTH Aachen University, Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"RWTH Aachen University, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052891281","display_name":"Fabian H\u00fcbenthal","orcid":"https://orcid.org/0009-0000-7159-8220"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Fabian H\u00fcbenthal","raw_affiliation_strings":["Chair of Fluid Mechanics and Institute of Aerodynamics, RWTH Aachen University, Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"Chair of Fluid Mechanics and Institute of Aerodynamics, RWTH Aachen University, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018538293","display_name":"Rakesh Sarma","orcid":"https://orcid.org/0000-0002-7069-4082"},"institutions":[{"id":"https://openalex.org/I171892758","display_name":"Forschungszentrum J\u00fclich","ror":"https://ror.org/02nv7yv05","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I171892758"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Rakesh Sarma","raw_affiliation_strings":["J\u00fclich Supercomputing Centre, Forschungszentrum J\u00fclich, J\u00fclich, Germany"],"affiliations":[{"raw_affiliation_string":"J\u00fclich Supercomputing Centre, Forschungszentrum J\u00fclich, J\u00fclich, Germany","institution_ids":["https://openalex.org/I171892758"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Andreas Lintermann","orcid":"https://orcid.org/0000-0003-3321-6599"},"institutions":[{"id":"https://openalex.org/I171892758","display_name":"Forschungszentrum J\u00fclich","ror":"https://ror.org/02nv7yv05","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I171892758"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andreas Lintermann","raw_affiliation_strings":["J\u00fclich Supercomputing Centre, Forschungszentrum J\u00fclich, J\u00fclich, Germany"],"affiliations":[{"raw_affiliation_string":"J\u00fclich Supercomputing Centre, Forschungszentrum J\u00fclich, J\u00fclich, Germany","institution_ids":["https://openalex.org/I171892758"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023057979","display_name":"Christian Terboven","orcid":"https://orcid.org/0000-0003-2284-2957"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christian Terboven","raw_affiliation_strings":["High Performance Computing, RWTH Aachen University, Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"High Performance Computing, RWTH Aachen University, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5001414405"],"corresponding_institution_ids":["https://openalex.org/I887968799"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19297492,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"165","last_page":"176"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.3197000026702881,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.3197000026702881,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11751","display_name":"Lattice Boltzmann Simulation Studies","score":0.14720000326633453,"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/T12007","display_name":"Plasma and Flow Control in Aerodynamics","score":0.10140000283718109,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"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/solver","display_name":"Solver","score":0.8259999752044678},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5625},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5489000082015991},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.48330000042915344},{"id":"https://openalex.org/keywords/computational-fluid-dynamics","display_name":"Computational fluid dynamics","score":0.426800012588501},{"id":"https://openalex.org/keywords/hybrid-system","display_name":"Hybrid system","score":0.41929998993873596},{"id":"https://openalex.org/keywords/drag","display_name":"Drag","score":0.385699987411499},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.36340001225471497},{"id":"https://openalex.org/keywords/multiphase-flow","display_name":"Multiphase flow","score":0.3546000123023987}],"concepts":[{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.8259999752044678},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7213000059127808},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5625},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5489000082015991},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.48330000042915344},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4790000021457672},{"id":"https://openalex.org/C1633027","wikidata":"https://www.wikidata.org/wiki/Q815820","display_name":"Computational fluid dynamics","level":2,"score":0.426800012588501},{"id":"https://openalex.org/C50897621","wikidata":"https://www.wikidata.org/wiki/Q2665508","display_name":"Hybrid system","level":2,"score":0.41929998993873596},{"id":"https://openalex.org/C72921944","wikidata":"https://www.wikidata.org/wiki/Q206621","display_name":"Drag","level":2,"score":0.385699987411499},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3749000132083893},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.36340001225471497},{"id":"https://openalex.org/C2779379648","wikidata":"https://www.wikidata.org/wiki/Q1559665","display_name":"Multiphase flow","level":2,"score":0.3546000123023987},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.34779998660087585},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.34769999980926514},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.32519999146461487},{"id":"https://openalex.org/C62469222","wikidata":"https://www.wikidata.org/wiki/Q17092103","display_name":"Hybrid algorithm (constraint satisfaction)","level":5,"score":0.3197999894618988},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.3188000023365021},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.3172999918460846},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3133000135421753},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3068999946117401},{"id":"https://openalex.org/C111603439","wikidata":"https://www.wikidata.org/wiki/Q752193","display_name":"Boundary layer","level":2,"score":0.3057999908924103},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.30239999294281006},{"id":"https://openalex.org/C46743427","wikidata":"https://www.wikidata.org/wiki/Q1341685","display_name":"Inference engine","level":3,"score":0.2865000069141388},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2711000144481659},{"id":"https://openalex.org/C131675550","wikidata":"https://www.wikidata.org/wiki/Q7646884","display_name":"Surrogate model","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C90278072","wikidata":"https://www.wikidata.org/wiki/Q216320","display_name":"Fluid dynamics","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.2612000107765198},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.2603999972343445},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.2581000030040741},{"id":"https://openalex.org/C50478463","wikidata":"https://www.wikidata.org/wiki/Q1401936","display_name":"Finite volume method","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.2524999976158142}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3784828.3785255","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3784828.3785255","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Supercomputing Asia and International Conference on High Performance Computing in Asia Pacific Region Workshops","raw_type":"proceedings-article"},{"id":"pmh:oai:publications.rwth-aachen.de:1028455","is_oa":true,"landing_page_url":"https://publications.rwth-aachen.de/record/1028455","pdf_url":null,"source":{"id":"https://openalex.org/S4306401033","display_name":"RWTH Publications (RWTH Aachen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887968799","host_organization_name":"RWTH Aachen University","host_organization_lineage":["https://openalex.org/I887968799"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Supercomputing Asia and International Conference on High Performance Computing in Asia Pacific Region Workshops<br/>SCA/HPCAsia 2026 Workshops: Supercomputing Asia and International Conference on High Performance Computing in Asia Pacific Region Workshops, SCA/HPCAsiaWS 2026, Osaka, Japan, 2026-01-26 - 2026-01-29","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:doi:10.18154/rwth-2026-01646","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Book chapter"}],"best_oa_location":{"id":"doi:10.1145/3784828.3785255","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3784828.3785255","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Supercomputing Asia and International Conference on High Performance Computing in Asia Pacific Region Workshops","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.9022535085678101,"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":26,"referenced_works":["https://openalex.org/W2046899724","https://openalex.org/W2150476673","https://openalex.org/W2150871235","https://openalex.org/W3002709689","https://openalex.org/W3005054771","https://openalex.org/W3161200675","https://openalex.org/W3193663588","https://openalex.org/W3199810640","https://openalex.org/W4236395669","https://openalex.org/W4280589740","https://openalex.org/W4282970339","https://openalex.org/W4285082282","https://openalex.org/W4290944486","https://openalex.org/W4319287664","https://openalex.org/W4319763984","https://openalex.org/W4382302122","https://openalex.org/W4389624813","https://openalex.org/W4396978967","https://openalex.org/W4399324447","https://openalex.org/W4400224437","https://openalex.org/W4402855489","https://openalex.org/W4408864961","https://openalex.org/W4409591484","https://openalex.org/W4414931310","https://openalex.org/W6948527093","https://openalex.org/W6949250267"],"related_works":[],"abstract_inverted_index":{"Active":[0],"drag":[1,15],"reduction":[2],"(ADR)":[3],"using":[4],"spanwise":[5],"traveling":[6],"surface":[7,57],"waves":[8,58],"is":[9,47],"a":[10,74,82,99,114,182,188,203,233,253],"promising":[11,75],"approach":[12,155],"to":[13,49,125,146,151,206,265],"reduce":[14],"of":[16,37,55,85,106,129,138,220,261,284],"airplanes":[17],"by":[18,167,276],"manipulating":[19],"the":[20,41,51,103,119,127,134,139,141,148,158,163,168,197,208,215,225,259,273,281,285,293],"turbulent":[21,107],"boundary":[22],"layer":[23],"(TBL)":[24],"around":[25],"an":[26],"airfoil,":[27],"which":[28],"directly":[29],"translates":[30],"into":[31,196],"power":[32],"savings":[33],"and":[34,110,193,218,242],"lower":[35],"emission":[36],"greenhouse":[38],"gases":[39],"harming":[40],"environment.":[42],"However,":[43],"no":[44],"analytical":[45],"solution":[46],"known":[48],"determine":[50],"optimal":[52,209,305],"actuation":[53],"parameters":[54],"these":[56],"based":[59,186],"on":[60,187,232],"given":[61],"flow":[62,108],"conditions.":[63],"Data-driven":[64],"deep":[65],"learning":[66],"(DL)":[67],"techniques":[68],"from":[69,88,118,229,299],"artificial":[70],"intelligence":[71],"(AI)":[72],"are":[73],"alternative":[76],"approach,":[77],"but":[78],"their":[79],"training":[80],"requires":[81],"huge":[83],"amount":[84],"high-fidelity":[86],"data":[87],"computationally":[89,135],"expensive":[90,104,136],"computational":[91,216],"fluid":[92],"dynamics":[93],"(CFD)":[94],"simulations.":[95],"Previous":[96],"works":[97],"proposed":[98],"TBL-Transformer":[100],"architecture":[101],"for":[102],"time-marching":[105],"fields":[109],"coupled":[111,226,286],"it":[112,161,195],"with":[113],"finite":[115],"volume":[116],"solver":[117,122,169,228,287],"multi-physics":[120],"PDE":[121],"framework":[123],"m-AIA":[124,227],"accelerate":[126,133],"generation":[128],"TBL":[130],"data.":[131],"To":[132,173,213],"inference":[137,149,159,184,251,278],"TBL-Transformer,":[140],"AIxeleratorService":[142,198],"library":[143],"was":[144],"used":[145],"offload":[147],"task":[150],"GPUs.":[152,245],"While":[153],"this":[154],"significantly":[156],"accelerates":[157],"task,":[160],"leaves":[162],"CPU":[164,263],"resources":[165],"allocated":[166,262],"unutilized":[170],"during":[171],"inference.":[172],"fully":[174],"exploit":[175],"modern":[176],"heterogeneous":[177,234],"computer":[178],"systems,":[179],"we":[180,201,223,290],"introduce":[181],"hybrid":[183,189,210,221,250,277,295],"method":[185],"work":[190,211,231,296],"distribution":[191,297],"model":[192,205,302],"implement":[194],"library.":[199],"Moreover,":[200],"present":[202],"formal":[204,301],"derive":[207],"distribution.":[212],"evaluate":[214],"performance":[217,254],"scalability":[219],"inference,":[222],"benchmark":[224],"previous":[230],"HPC":[235],"system":[236],"comprising":[237],"Intel":[238],"Sapphire":[239],"Rapids":[240],"CPUs":[241],"NVIDIA":[243],"H100":[244],"Our":[246],"results":[247,306],"show":[248],"that":[249,256,272,292],"achieves":[252],"speedup,":[255],"grows":[257],"as":[258],"ratio":[260],"cores":[264],"GPU":[266],"devices":[267],"increases.":[268],"We":[269],"further":[270],"demonstrate":[271],"runtime":[274],"improvement":[275],"also":[279],"increases":[280],"energy":[282],"efficiency":[283],"application.":[288],"Finally,":[289],"highlight":[291],"theoretical":[294],"derived":[298],"our":[300],"yields":[303],"near":[304],"in":[307],"practice.":[308]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2026-01-23T00:00:00"}