{"id":"https://openalex.org/W2769126660","doi":"https://doi.org/10.3390/computation5040048","title":"A Holistic Scalable Implementation Approach of the Lattice Boltzmann Method for CPU/GPU Heterogeneous Clusters","display_name":"A Holistic Scalable Implementation Approach of the Lattice Boltzmann Method for CPU/GPU Heterogeneous Clusters","publication_year":2017,"publication_date":"2017-11-30","ids":{"openalex":"https://openalex.org/W2769126660","doi":"https://doi.org/10.3390/computation5040048","mag":"2769126660"},"language":"en","primary_location":{"id":"doi:10.3390/computation5040048","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computation5040048","pdf_url":"https://www.mdpi.com/2079-3197/5/4/48/pdf?version=1512441312","source":{"id":"https://openalex.org/S2738402919","display_name":"Computation","issn_l":"2079-3197","issn":["2079-3197"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computation","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2079-3197/5/4/48/pdf?version=1512441312","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Christoph Riesinger","orcid":null},"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":"Christoph Riesinger","raw_affiliation_strings":["Department of Informatics, Technical University of Munich, 85748 Garching, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, Technical University of Munich, 85748 Garching, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113698804","display_name":"Arash Bakhtiari","orcid":null},"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":"Arash Bakhtiari","raw_affiliation_strings":["Department of Informatics, Technical University of Munich, 85748 Garching, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, Technical University of Munich, 85748 Garching, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103223211","display_name":"Martin Schreiber","orcid":"https://orcid.org/0000-0002-2390-6716"},"institutions":[{"id":"https://openalex.org/I23923803","display_name":"University of Exeter","ror":"https://ror.org/03yghzc09","country_code":"GB","type":"education","lineage":["https://openalex.org/I23923803"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Martin Schreiber","raw_affiliation_strings":["Department of Computer Science/Mathematics, University of Exeter, Exeter EX4 4QF, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science/Mathematics, University of Exeter, Exeter EX4 4QF, UK","institution_ids":["https://openalex.org/I23923803"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083022537","display_name":"Philipp Neumann","orcid":"https://orcid.org/0000-0001-8604-8846"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Philipp Neumann","raw_affiliation_strings":["Scientific Computing, University of Hamburg, 20146 Hamburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Scientific Computing, University of Hamburg, 20146 Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068403289","display_name":"Hans\u2010Joachim Bungartz","orcid":"https://orcid.org/0000-0002-0171-0712"},"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":"Hans-Joachim Bungartz","raw_affiliation_strings":["Department of Informatics, Technical University of Munich, 85748 Garching, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, Technical University of Munich, 85748 Garching, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":2.963,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.9096697,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"5","issue":"4","first_page":"48","last_page":"48"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11751","display_name":"Lattice Boltzmann Simulation Studies","score":0.9998999834060669,"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":0.9998999834060669,"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/T12163","display_name":"Aerosol Filtration and Electrostatic Precipitation","score":0.9708999991416931,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9442999958992004,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.845609188079834},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7952344417572021},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7673318386077881},{"id":"https://openalex.org/keywords/gpu-cluster","display_name":"GPU cluster","score":0.6814007759094238},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.540834367275238},{"id":"https://openalex.org/keywords/symmetric-multiprocessor-system","display_name":"Symmetric multiprocessor system","score":0.5227951407432556},{"id":"https://openalex.org/keywords/lattice-boltzmann-methods","display_name":"Lattice Boltzmann methods","score":0.52186119556427},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.5092481374740601},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5079217553138733},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4967120289802551},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.4690708816051483},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4615798592567444},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.41221609711647034},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.37103068828582764},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11424615979194641},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11393368244171143}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.845609188079834},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7952344417572021},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7673318386077881},{"id":"https://openalex.org/C2781335571","wikidata":"https://www.wikidata.org/wiki/Q2633544","display_name":"GPU cluster","level":3,"score":0.6814007759094238},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.540834367275238},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.5227951407432556},{"id":"https://openalex.org/C21821499","wikidata":"https://www.wikidata.org/wiki/Q1807064","display_name":"Lattice Boltzmann methods","level":2,"score":0.52186119556427},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.5092481374740601},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5079217553138733},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4967120289802551},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.4690708816051483},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4615798592567444},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.41221609711647034},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.37103068828582764},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11424615979194641},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11393368244171143},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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:10.3390/computation5040048","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computation5040048","pdf_url":"https://www.mdpi.com/2079-3197/5/4/48/pdf?version=1512441312","source":{"id":"https://openalex.org/S2738402919","display_name":"Computation","issn_l":"2079-3197","issn":["2079-3197"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computation","raw_type":"journal-article"},{"id":"pmh:oai:ore.exeter.ac.uk:10871/30463","is_oa":true,"landing_page_url":"http://hdl.handle.net/10871/30463","pdf_url":null,"source":{"id":"https://openalex.org/S4306401998","display_name":"Open Research Exeter (University of Exeter)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I23923803","host_organization_name":"University of Exeter","host_organization_lineage":["https://openalex.org/I23923803"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"pmh:oai:doaj.org/article:4192d61ebea245719bf8865b4da455cc","is_oa":true,"landing_page_url":"https://doaj.org/article/4192d61ebea245719bf8865b4da455cc","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computation, Vol 5, Iss 4, p 48 (2017)","raw_type":"article"},{"id":"pmh:oai:figshare.com:article/29737580","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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":"Journal contribution"},{"id":"pmh:oai:mdpi.com:/2079-3197/5/4/48/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/computation5040048","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computation; Volume 5; Issue 4; Pages: 48","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/computation5040048","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computation5040048","pdf_url":"https://www.mdpi.com/2079-3197/5/4/48/pdf?version=1512441312","source":{"id":"https://openalex.org/S2738402919","display_name":"Computation","issn_l":"2079-3197","issn":["2079-3197"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computation","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4000000059604645,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1216276171","https://openalex.org/W1503313641","https://openalex.org/W1599770531","https://openalex.org/W1603142303","https://openalex.org/W1956179468","https://openalex.org/W1971876223","https://openalex.org/W1982068804","https://openalex.org/W1990604500","https://openalex.org/W2000882268","https://openalex.org/W2002589306","https://openalex.org/W2021041911","https://openalex.org/W2034544018","https://openalex.org/W2043616378","https://openalex.org/W2050365444","https://openalex.org/W2056295840","https://openalex.org/W2062900651","https://openalex.org/W2066060292","https://openalex.org/W2071296827","https://openalex.org/W2071530432","https://openalex.org/W2073875590","https://openalex.org/W2074129693","https://openalex.org/W2074573067","https://openalex.org/W2076361081","https://openalex.org/W2092687851","https://openalex.org/W2093090081","https://openalex.org/W2095283463","https://openalex.org/W2098220211","https://openalex.org/W2100647442","https://openalex.org/W2108238461","https://openalex.org/W2113754927","https://openalex.org/W2117242079","https://openalex.org/W2120900954","https://openalex.org/W2138782497","https://openalex.org/W2141579716","https://openalex.org/W2144826131","https://openalex.org/W2153795246","https://openalex.org/W2254696047","https://openalex.org/W2479591515","https://openalex.org/W2497980095","https://openalex.org/W2508453970","https://openalex.org/W2513293834","https://openalex.org/W2554811052","https://openalex.org/W2597626149","https://openalex.org/W2604510839","https://openalex.org/W2635379961","https://openalex.org/W2747643491","https://openalex.org/W2758320287","https://openalex.org/W2791769657","https://openalex.org/W3098206122","https://openalex.org/W3106440809","https://openalex.org/W4239647010","https://openalex.org/W4376597500"],"related_works":["https://openalex.org/W2056717482","https://openalex.org/W2017587301","https://openalex.org/W2030707850","https://openalex.org/W2170611190","https://openalex.org/W2890054038","https://openalex.org/W2566934642","https://openalex.org/W4236300446","https://openalex.org/W2092007952","https://openalex.org/W2546451654","https://openalex.org/W2001170981"],"abstract_inverted_index":{"Heterogeneous":[0],"clusters":[1,156],"are":[2,172],"a":[3,22,29,76,79,85,97],"widely":[4],"utilized":[5],"class":[6],"of":[7,13,50,54,62,78,99,115,117,119,124,157,167,185],"supercomputers":[8],"assembled":[9],"from":[10,105],"different":[11,43,55],"types":[12],"computing":[14,44,81,110,193],"devices,":[15,45],"for":[16,42,72,88,107,139,154],"instance":[17],"CPUs":[18],"and":[19,60,83,95,102,122,182,192],"GPUs,":[20],"providing":[21],"huge":[23],"computational":[24,137],"potential.":[25],"Programming":[26],"them":[27],"in":[28],"scalable":[30],"way":[31],"exploiting":[32],"the":[33,52,68,108,113,135,140,158,162,186],"maximal":[34],"performance":[35],"introduces":[36],"numerous":[37],"challenges":[38],"such":[39],"as":[40,75],"optimizations":[41,106],"dealing":[46],"with":[47,64,130],"multiple":[48],"levels":[49],"parallelism,":[51],"application":[53,82],"programming":[56],"models,":[57],"work":[58],"distribution,":[59],"hiding":[61],"communication":[63],"computation.":[65],"We":[66,93],"utilize":[67],"lattice":[69,141,200],"Boltzmann":[70,142],"method":[71,143],"fluid":[73],"flow":[74],"representative":[77],"scientific":[80],"develop":[84],"holistic":[86],"implementation":[87,132],"large-scale":[89],"CPU/GPU":[90,187],"heterogeneous":[91,155,188],"clusters.":[92],"review":[94],"combine":[96],"set":[98],"best":[100],"practices":[101],"techniques":[103],"ranging":[104],"particular":[109],"devices":[111],"to":[112,175],"orchestration":[114],"tens":[116],"thousands":[118,123],"CPU":[120,180],"cores":[121,181],"GPUs.":[125],"Eventually,":[126],"we":[127],"come":[128],"up":[129],"an":[131],"using":[133],"all":[134],"available":[136],"resources":[138],"operators.":[144],"Our":[145],"approach":[146],"shows":[147],"excellent":[148],"scalability":[149],"behavior":[150],"making":[151],"it":[152],"future-proof":[153],"upcoming":[159],"architectures":[160],"on":[161],"exaFLOPS":[163],"scale.":[164],"Parallel":[165],"efficiencies":[166],"more":[168,194],"than":[169,195],"90":[170],"%":[171],"achieved":[173],"leading":[174],"2604.72":[176],"GLUPS":[177],"utilizing":[178],"24,576":[179],"2048":[183],"GPUs":[184],"cluster":[189],"Piz":[190],"Daint":[191],"6.8":[196],"\u00d7":[197],"10":[198],"9":[199],"cells.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2017-12-04T00:00:00"}
