{"id":"https://openalex.org/W2508010902","doi":"https://doi.org/10.1177/1094342016658109","title":"Designing a graphics processing unit accelerated petaflop capable lattice Boltzmann solver: Read aligned data layouts and asynchronous communication","display_name":"Designing a graphics processing unit accelerated petaflop capable lattice Boltzmann solver: Read aligned data layouts and asynchronous communication","publication_year":2016,"publication_date":"2016-08-24","ids":{"openalex":"https://openalex.org/W2508010902","doi":"https://doi.org/10.1177/1094342016658109","mag":"2508010902"},"language":"en","primary_location":{"id":"doi:10.1177/1094342016658109","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342016658109","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":true,"oa_status":"green","oa_url":"https://jyx.jyu.fi/bitstreams/7c69fffa-1c80-4743-94e4-de0763fb64c4/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076963210","display_name":"Fredrik Roberts\u00e9n","orcid":"https://orcid.org/0000-0001-8455-274X"},"institutions":[{"id":"https://openalex.org/I130217899","display_name":"\u00c5bo Akademi University","ror":"https://ror.org/029pk6x14","country_code":"FI","type":"education","lineage":["https://openalex.org/I130217899"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Fredrik Roberts\u00e9n","raw_affiliation_strings":["\u00c5bo Akademi University, Faculty of Science and Engineering, \u00c5bo, Finland"],"affiliations":[{"raw_affiliation_string":"\u00c5bo Akademi University, Faculty of Science and Engineering, \u00c5bo, Finland","institution_ids":["https://openalex.org/I130217899"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068418488","display_name":"Jan Westerholm","orcid":"https://orcid.org/0000-0001-9082-350X"},"institutions":[{"id":"https://openalex.org/I130217899","display_name":"\u00c5bo Akademi University","ror":"https://ror.org/029pk6x14","country_code":"FI","type":"education","lineage":["https://openalex.org/I130217899"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Jan Westerholm","raw_affiliation_strings":["\u00c5bo Akademi University, Faculty of Science and Engineering, \u00c5bo, Finland"],"affiliations":[{"raw_affiliation_string":"\u00c5bo Akademi University, Faculty of Science and Engineering, \u00c5bo, Finland","institution_ids":["https://openalex.org/I130217899"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028365524","display_name":"Keijo Mattila","orcid":"https://orcid.org/0000-0002-3307-8723"},"institutions":[{"id":"https://openalex.org/I94722563","display_name":"University of Jyv\u00e4skyl\u00e4","ror":"https://ror.org/05n3dz165","country_code":"FI","type":"education","lineage":["https://openalex.org/I94722563"]},{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]},{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Keijo Mattila","raw_affiliation_strings":["Department of Physics and Nanoscience Center, University of Jyv\u00e4skyl\u00e4, Jyv\u00e4skyl\u00e4, Finland","Department of Physics, Tampere University of Technology, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Physics and Nanoscience Center, University of Jyv\u00e4skyl\u00e4, Jyv\u00e4skyl\u00e4, Finland","institution_ids":["https://openalex.org/I94722563"]},{"raw_affiliation_string":"Department of Physics, Tampere University of Technology, Tampere, Finland","institution_ids":["https://openalex.org/I166825849","https://openalex.org/I4210133110"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5076963210"],"corresponding_institution_ids":["https://openalex.org/I130217899"],"apc_list":null,"apc_paid":null,"fwci":0.9119,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.73865451,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"31","issue":"3","first_page":"246","last_page":"255"},"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":0.9800999760627747,"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":0.916700005531311,"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":0.8287509083747864},{"id":"https://openalex.org/keywords/lattice-boltzmann-methods","display_name":"Lattice Boltzmann methods","score":0.7017274498939514},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.695263683795929},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.6789124608039856},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.6717453002929688},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6024686694145203},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.578031599521637},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.566421627998352},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.5099493265151978},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5066695809364319},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.47984573245048523},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.4395659863948822},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3290029764175415},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.28143298625946045},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10079529881477356}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8287509083747864},{"id":"https://openalex.org/C21821499","wikidata":"https://www.wikidata.org/wiki/Q1807064","display_name":"Lattice Boltzmann methods","level":2,"score":0.7017274498939514},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.695263683795929},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.6789124608039856},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.6717453002929688},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6024686694145203},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.578031599521637},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.566421627998352},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.5099493265151978},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5066695809364319},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.47984573245048523},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.4395659863948822},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3290029764175415},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.28143298625946045},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10079529881477356},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1177/1094342016658109","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342016658109","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"},{"id":"pmh:oai:jyx.jyu.fi:123456789/54958","is_oa":true,"landing_page_url":"http://urn.fi/URN:NBN:fi:jyu-201707193327","pdf_url":"https://jyx.jyu.fi/bitstreams/7c69fffa-1c80-4743-94e4-de0763fb64c4/download","source":{"id":"https://openalex.org/S4306400563","display_name":"Jyv\u00e4skyl\u00e4 University Digital Archive (University of Jyv\u00e4skyl\u00e4)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I94722563","host_organization_name":"University of Jyv\u00e4skyl\u00e4","host_organization_lineage":["https://openalex.org/I94722563"],"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":"A1"},{"id":"pmh:oai:pure.atira.dk:publications/714e1910-0537-4195-858b-0b0a9a37bd50","is_oa":false,"landing_page_url":"https://research.abo.fi/en/publications/714e1910-0537-4195-858b-0b0a9a37bd50","pdf_url":null,"source":{"id":"https://openalex.org/S4406923060","display_name":"\u00c5bo Akademi University Research Portal","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":"Roberts\u00e9n, F, Westerholm, J & Mattila, K 2016, 'Designing a graphics processing unit accelerated petaflop capable lattice Boltzmann solver: Read aligned data layouts and asynchronous communication', International Journal of High Performance Computing Applications, pp. \u2013. https://doi.org/10.1177/1094342016658109","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:jyx.jyu.fi:123456789/54958","is_oa":true,"landing_page_url":"http://urn.fi/URN:NBN:fi:jyu-201707193327","pdf_url":"https://jyx.jyu.fi/bitstreams/7c69fffa-1c80-4743-94e4-de0763fb64c4/download","source":{"id":"https://openalex.org/S4306400563","display_name":"Jyv\u00e4skyl\u00e4 University Digital Archive (University of Jyv\u00e4skyl\u00e4)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I94722563","host_organization_name":"University of Jyv\u00e4skyl\u00e4","host_organization_lineage":["https://openalex.org/I94722563"],"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":"A1"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2508010902.pdf"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W235498264","https://openalex.org/W1970172627","https://openalex.org/W1971418186","https://openalex.org/W1971876223","https://openalex.org/W1982933896","https://openalex.org/W1992773065","https://openalex.org/W2016656166","https://openalex.org/W2037561415","https://openalex.org/W2073875590","https://openalex.org/W2081233300","https://openalex.org/W2097495737","https://openalex.org/W2112053550","https://openalex.org/W2113754927","https://openalex.org/W2114079704","https://openalex.org/W2120900954","https://openalex.org/W2195479374","https://openalex.org/W2470003930","https://openalex.org/W2598048660","https://openalex.org/W4205258316"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2080146221","https://openalex.org/W2370314112","https://openalex.org/W2153506571","https://openalex.org/W3104348697"],"abstract_inverted_index":{"The":[0],"lattice":[1,37],"Boltzmann":[2,38],"method":[3],"is":[4],"a":[5,36,57,106],"well-established":[6],"numerical":[7],"approach":[8],"for":[9,40],"complex":[10],"fluid":[11],"flow":[12,111],"simulations.":[13],"Recently,":[14],"general-purpose":[15],"graphics":[16],"processing":[17,94],"units":[18],"(GPUs)":[19],"have":[20],"become":[21],"available":[22],"as":[23],"high-performance":[24],"computing":[25,101],"resources":[26],"at":[27],"large":[28],"scale.":[29],"We":[30],"report":[31],"on":[32,48,102,127],"designing":[33],"and":[34,67,96,115,119],"implementing":[35],"solver":[39],"multi-GPU":[41],"systems":[42],"that":[43],"achieves":[44],"1.79":[45],"PFLOPS":[46],"performance":[47,122],"16,384":[49],"GPUs.":[50],"To":[51],"achieve":[52],"this":[53],"performance,":[54],"we":[55,80,109],"introduce":[56],"GPU":[58,99],"compatible":[59],"version":[60],"of":[61,83],"the":[62,69,84,91,97,103,124],"so-called":[63],"bundle":[64],"data":[65,76,88],"layout":[66],"eliminate":[68],"halo":[70],"sites":[71],"in":[72,112],"order":[73],"to":[74,86],"improve":[75],"access":[77],"alignment.":[78],"Furthermore,":[79],"make":[81],"use":[82],"possibility":[85],"overlap":[87],"transfer":[89],"between":[90],"host":[92],"central":[93],"unit":[95],"device":[98],"with":[100,123],"GPU.":[104],"As":[105],"benchmark":[107],"case,":[108],"simulate":[110],"porous":[113],"media":[114],"measure":[116],"both":[117],"strong":[118],"weak":[120],"scaling":[121],"emphasis":[125],"being":[126],"large-scale":[128],"simulations":[129],"using":[130],"realistic":[131],"input":[132],"data.":[133]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
