{"id":"https://openalex.org/W1503313641","doi":"https://doi.org/10.1109/hpcsim.2015.7237021","title":"Optimizing communications in multi-GPU Lattice Boltzmann simulations","display_name":"Optimizing communications in multi-GPU Lattice Boltzmann simulations","publication_year":2015,"publication_date":"2015-07-01","ids":{"openalex":"https://openalex.org/W1503313641","doi":"https://doi.org/10.1109/hpcsim.2015.7237021","mag":"1503313641"},"language":"en","primary_location":{"id":"doi:10.1109/hpcsim.2015.7237021","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcsim.2015.7237021","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 International Conference on High Performance Computing &amp; Simulation (HPCS)","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/A5067711003","display_name":"Enrico Calore","orcid":"https://orcid.org/0000-0002-2301-3838"},"institutions":[{"id":"https://openalex.org/I201324441","display_name":"University of Ferrara","ror":"https://ror.org/041zkgm14","country_code":"IT","type":"education","lineage":["https://openalex.org/I201324441"]},{"id":"https://openalex.org/I4210107105","display_name":"Istituto Nazionale di Fisica Nucleare, Sezione di Ferrara","ror":"https://ror.org/00zs3y046","country_code":"IT","type":"facility","lineage":["https://openalex.org/I160013858","https://openalex.org/I4210107105"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Enrico Calore","raw_affiliation_strings":["Dipartimento di Fisica e Scienze della Terra, Univ. di Ferrara and INFN, Ferrara, ITALY","Dipartimento di Fisica e Scienze della Terra, Univ. di Ferrara and INFN, I-44122, ITALY"],"affiliations":[{"raw_affiliation_string":"Dipartimento di Fisica e Scienze della Terra, Univ. di Ferrara and INFN, Ferrara, ITALY","institution_ids":["https://openalex.org/I4210107105","https://openalex.org/I201324441"]},{"raw_affiliation_string":"Dipartimento di Fisica e Scienze della Terra, Univ. di Ferrara and INFN, I-44122, ITALY","institution_ids":["https://openalex.org/I4210107105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078118467","display_name":"Davide Marchi","orcid":null},"institutions":[{"id":"https://openalex.org/I201324441","display_name":"University of Ferrara","ror":"https://ror.org/041zkgm14","country_code":"IT","type":"education","lineage":["https://openalex.org/I201324441"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Davide Marchi","raw_affiliation_strings":["Dipartimento di Matematica e Informatica, Univ. di Ferrara, Ferrara, ITALY","Dipartimento di Matematica e Informatica, Univ. di Ferrara, I-44122, ITALY"],"affiliations":[{"raw_affiliation_string":"Dipartimento di Matematica e Informatica, Univ. di Ferrara, Ferrara, ITALY","institution_ids":["https://openalex.org/I201324441"]},{"raw_affiliation_string":"Dipartimento di Matematica e Informatica, Univ. di Ferrara, I-44122, ITALY","institution_ids":["https://openalex.org/I201324441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071220084","display_name":"Sebastiano Fabio Schifano","orcid":"https://orcid.org/0000-0002-0132-9196"},"institutions":[{"id":"https://openalex.org/I4210107105","display_name":"Istituto Nazionale di Fisica Nucleare, Sezione di Ferrara","ror":"https://ror.org/00zs3y046","country_code":"IT","type":"facility","lineage":["https://openalex.org/I160013858","https://openalex.org/I4210107105"]},{"id":"https://openalex.org/I201324441","display_name":"University of Ferrara","ror":"https://ror.org/041zkgm14","country_code":"IT","type":"education","lineage":["https://openalex.org/I201324441"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Sebastiano Fabio Schifano","raw_affiliation_strings":["Dipartimento di Matematica e Informatica, Univ. di Ferrara and INFN, Ferrara, ITALY","Dipartimento di Matematica e Informatica, Univ. di Ferrara and INFN, I-44122, ITALY"],"affiliations":[{"raw_affiliation_string":"Dipartimento di Matematica e Informatica, Univ. di Ferrara and INFN, Ferrara, ITALY","institution_ids":["https://openalex.org/I201324441","https://openalex.org/I4210107105"]},{"raw_affiliation_string":"Dipartimento di Matematica e Informatica, Univ. di Ferrara and INFN, I-44122, ITALY","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042662251","display_name":"R. Tripiccione","orcid":"https://orcid.org/0000-0002-8516-2492"},"institutions":[{"id":"https://openalex.org/I201324441","display_name":"University of Ferrara","ror":"https://ror.org/041zkgm14","country_code":"IT","type":"education","lineage":["https://openalex.org/I201324441"]},{"id":"https://openalex.org/I4210107105","display_name":"Istituto Nazionale di Fisica Nucleare, Sezione di Ferrara","ror":"https://ror.org/00zs3y046","country_code":"IT","type":"facility","lineage":["https://openalex.org/I160013858","https://openalex.org/I4210107105"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Raffaele Tripiccione","raw_affiliation_strings":["Dipartimento di Fisica e Scienze della Terra, Univ. di Ferrara and INFN, Ferrara, ITALY","Dipartimento di Fisica e Scienze della Terra, Univ. di Ferrara and INFN, I-44122, ITALY"],"affiliations":[{"raw_affiliation_string":"Dipartimento di Fisica e Scienze della Terra, Univ. di Ferrara and INFN, Ferrara, ITALY","institution_ids":["https://openalex.org/I4210107105","https://openalex.org/I201324441"]},{"raw_affiliation_string":"Dipartimento di Fisica e Scienze della Terra, Univ. di Ferrara and INFN, I-44122, ITALY","institution_ids":["https://openalex.org/I4210107105"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5067711003"],"corresponding_institution_ids":["https://openalex.org/I201324441","https://openalex.org/I4210107105"],"apc_list":null,"apc_paid":null,"fwci":2.2742,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.86050725,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"1","issue":null,"first_page":"55","last_page":"62"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11751","display_name":"Lattice Boltzmann Simulation Studies","score":1.0,"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":1.0,"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":0.9685999751091003,"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":0.9671000242233276,"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":0.855404794216156},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7494295835494995},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6772860288619995},{"id":"https://openalex.org/keywords/gpu-cluster","display_name":"GPU cluster","score":0.6102799773216248},{"id":"https://openalex.org/keywords/stencil","display_name":"Stencil","score":0.5907160043716431},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5507925748825073},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5428310632705688},{"id":"https://openalex.org/keywords/lattice-boltzmann-methods","display_name":"Lattice Boltzmann methods","score":0.5249738097190857},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.521934986114502},{"id":"https://openalex.org/keywords/data-parallelism","display_name":"Data parallelism","score":0.5123761892318726},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4703165590763092},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.4366828203201294},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.38889768719673157},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.34936755895614624},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.19971054792404175}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.855404794216156},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7494295835494995},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6772860288619995},{"id":"https://openalex.org/C2781335571","wikidata":"https://www.wikidata.org/wiki/Q2633544","display_name":"GPU cluster","level":3,"score":0.6102799773216248},{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.5907160043716431},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5507925748825073},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5428310632705688},{"id":"https://openalex.org/C21821499","wikidata":"https://www.wikidata.org/wiki/Q1807064","display_name":"Lattice Boltzmann methods","level":2,"score":0.5249738097190857},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.521934986114502},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.5123761892318726},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4703165590763092},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.4366828203201294},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.38889768719673157},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.34936755895614624},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.19971054792404175},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/hpcsim.2015.7237021","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcsim.2015.7237021","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 International Conference on High Performance Computing &amp; Simulation (HPCS)","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.unife.it:11392/2352805","is_oa":false,"landing_page_url":"http://hdl.handle.net/11392/2352805","pdf_url":null,"source":{"id":"https://openalex.org/S4306400369","display_name":"Institutional Research Information System University of Ferrara (University of Ferrara)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I201324441","host_organization_name":"University of Ferrara","host_organization_lineage":["https://openalex.org/I201324441"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"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":28,"referenced_works":["https://openalex.org/W8849792","https://openalex.org/W1664235680","https://openalex.org/W1963911172","https://openalex.org/W1992299697","https://openalex.org/W1994531540","https://openalex.org/W1997147891","https://openalex.org/W2003661150","https://openalex.org/W2015067420","https://openalex.org/W2077575837","https://openalex.org/W2090407558","https://openalex.org/W2105324170","https://openalex.org/W2106648293","https://openalex.org/W2111523137","https://openalex.org/W2120900954","https://openalex.org/W2147078405","https://openalex.org/W2154078685","https://openalex.org/W2156416954","https://openalex.org/W2159749532","https://openalex.org/W2169562125","https://openalex.org/W2170704964","https://openalex.org/W2949165561","https://openalex.org/W3102241748","https://openalex.org/W4243388494","https://openalex.org/W4249931713","https://openalex.org/W4388316717","https://openalex.org/W6632862924","https://openalex.org/W6650994893","https://openalex.org/W6858326409"],"related_works":["https://openalex.org/W2056717482","https://openalex.org/W2017587301","https://openalex.org/W2030707850","https://openalex.org/W2170611190","https://openalex.org/W2566934642","https://openalex.org/W4200595202","https://openalex.org/W4236300446","https://openalex.org/W2092007952","https://openalex.org/W2548246577","https://openalex.org/W2096672917"],"abstract_inverted_index":{"An":[0],"increasingly":[1],"large":[2,9,19,109,120,210],"number":[3],"of":[4,22,71,83,98,111,116,126,159,165,185,193,212],"scientific":[5],"applications":[6,24,84,118],"run":[7,207],"on":[8,12,59,119,208],"clusters":[10,121],"based":[11],"GPU":[13],"systems.":[14],"In":[15],"most":[16],"cases":[17],"the":[18,23,30,45,49,55,157,163,173],"scale":[20],"parallelism":[21,46,112],"uses":[25],"MPI,":[26],"widely":[27],"recognized":[28],"as":[29,145],"de-facto":[31],"standard":[32],"for":[33,104,202],"building":[34],"parallel":[35,56],"applications,":[36,73],"while":[37],"several":[38],"programming":[39],"languages":[40],"are":[41,66,85],"used":[42,67,90],"to":[43,76,133],"express":[44],"available":[47,58],"in":[48,68,91,171],"application":[50],"and":[51,63,136,178,183,187,197],"map":[52],"it":[53],"onto":[54],"resources":[57],"GPUs.":[60,114,213],"Regular":[61],"grids":[62],"stencil":[64],"codes":[65,204],"a":[69,108,123,146,149,160,166,209],"subset":[70],"these":[72,117,142],"often":[74],"corresponding":[75],"computational":[77,92],"\u201cGrand":[78],"Challenges\u201d.":[79],"One":[80],"such":[81],"class":[82],"Lattice":[86],"Boltzmann":[87],"Methods":[88],"(LB)":[89],"fluid":[93],"dynamics.":[94],"The":[95],"regular":[96],"structure":[97],"LB":[99,152],"algorithms":[100],"makes":[101],"them":[102],"suitable":[103],"processor":[105],"architectures":[106],"with":[107,199],"degree":[110],"like":[113],"Scalability":[115],"requires":[122],"careful":[124],"design":[125],"processor-to-processor":[127],"data":[128,176,179],"communications,":[129],"exploiting":[130],"all":[131],"possibilities":[132],"overlap":[134],"communication":[135,186],"computation.":[137,188],"This":[138],"paper":[139],"looks":[140],"at":[141],"issues,":[143],"considering":[144],"use":[147],"case":[148],"state-of-the-art":[150],"two-dimensional":[151],"model,":[153],"that":[154,205],"accurately":[155],"reproduces":[156],"thermo-hydrodynamics":[158],"2D-fluid":[161],"obeying":[162],"equation-of-state":[164],"perfect":[167],"gas.":[168],"We":[169,189],"study":[170],"details":[172],"interplay":[174],"between":[175],"organization":[177],"layout,":[180],"data-communication":[181],"options":[182],"overlapping":[184],"derive":[190],"partial":[191],"models":[192],"some":[194],"performance":[195],"features":[196],"compare":[198],"experimental":[200],"results":[201],"production-grade":[203],"we":[206],"cluster":[211]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}
