{"id":"https://openalex.org/W3134030220","doi":"https://doi.org/10.1109/tpds.2021.3061895","title":"Analysis of GPU Data Access Patterns on Complex Geometries for the D3Q19 Lattice Boltzmann Algorithm","display_name":"Analysis of GPU Data Access Patterns on Complex Geometries for the D3Q19 Lattice Boltzmann Algorithm","publication_year":2021,"publication_date":"2021-03-09","ids":{"openalex":"https://openalex.org/W3134030220","doi":"https://doi.org/10.1109/tpds.2021.3061895","mag":"3134030220"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2021.3061895","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2021.3061895","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/biblio/1807241","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039335591","display_name":"Gregory Herschlag","orcid":"https://orcid.org/0000-0001-5443-6449"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gregory Herschlag","raw_affiliation_strings":["Duke University, Durham, NC, USA"],"raw_orcid":"https://orcid.org/0000-0001-5443-6449","affiliations":[{"raw_affiliation_string":"Duke University, Durham, NC, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090962911","display_name":"Seyong Lee","orcid":"https://orcid.org/0000-0001-8872-4932"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Seyong Lee","raw_affiliation_strings":["Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"raw_orcid":"https://orcid.org/0000-0001-8872-4932","affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061838490","display_name":"Jeffrey S. Vetter","orcid":"https://orcid.org/0000-0002-2449-6720"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeffrey S. Vetter","raw_affiliation_strings":["Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056497188","display_name":"Amanda Randles","orcid":"https://orcid.org/0000-0001-6318-3885"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amanda Randles","raw_affiliation_strings":["Duke University, Durham, NC, USA"],"raw_orcid":"https://orcid.org/0000-0001-6318-3885","affiliations":[{"raw_affiliation_string":"Duke University, Durham, NC, USA","institution_ids":["https://openalex.org/I170897317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7253,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.81662451,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"32","issue":"10","first_page":"2400","last_page":"2414"},"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":0.9577999711036682,"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":0.9569000005722046,"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":0.8672780990600586},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6736950278282166},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.6444506645202637},{"id":"https://openalex.org/keywords/lattice-boltzmann-methods","display_name":"Lattice Boltzmann methods","score":0.5982179641723633},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4738900065422058},{"id":"https://openalex.org/keywords/data-access","display_name":"Data access","score":0.47010961174964905},{"id":"https://openalex.org/keywords/lexicographical-order","display_name":"Lexicographical order","score":0.4490068554878235},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.42691880464553833},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.42363640666007996},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4224252998828888},{"id":"https://openalex.org/keywords/lattice","display_name":"Lattice (music)","score":0.41228240728378296},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3541994094848633},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.0964195728302002}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8672780990600586},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6736950278282166},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.6444506645202637},{"id":"https://openalex.org/C21821499","wikidata":"https://www.wikidata.org/wiki/Q1807064","display_name":"Lattice Boltzmann methods","level":2,"score":0.5982179641723633},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4738900065422058},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.47010961174964905},{"id":"https://openalex.org/C159254197","wikidata":"https://www.wikidata.org/wiki/Q1144915","display_name":"Lexicographical order","level":2,"score":0.4490068554878235},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.42691880464553833},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.42363640666007996},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4224252998828888},{"id":"https://openalex.org/C2781204021","wikidata":"https://www.wikidata.org/wiki/Q6497091","display_name":"Lattice (music)","level":2,"score":0.41228240728378296},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3541994094848633},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0964195728302002},{"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/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpds.2021.3061895","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2021.3061895","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},{"id":"pmh:oai:osti.gov:1807241","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1807241","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"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":null}],"best_oa_location":{"id":"pmh:oai:osti.gov:1807241","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1807241","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"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":null},"sustainable_development_goals":[{"score":0.6000000238418579,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G1645119126","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G2890516381","display_name":null,"funder_award_id":"DP5OD019876","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G4423657506","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320338287","funder_display_name":"Oak Ridge National Laboratory"},{"id":"https://openalex.org/G8813984943","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320316892","funder_display_name":"UT-Battelle"},{"id":"https://openalex.org/G8906985441","display_name":null,"funder_award_id":"00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8943143067","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320316892","funder_display_name":"UT-Battelle"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320306250","display_name":"Battelle","ror":"https://ror.org/01h5tnr73"},{"id":"https://openalex.org/F4320316892","display_name":"UT-Battelle","ror":"https://ror.org/04nza6677"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320338287","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W235498264","https://openalex.org/W1599770531","https://openalex.org/W1664235680","https://openalex.org/W1925088345","https://openalex.org/W1964428959","https://openalex.org/W1966277182","https://openalex.org/W1968244180","https://openalex.org/W1976346389","https://openalex.org/W1982008063","https://openalex.org/W1986967511","https://openalex.org/W1996820070","https://openalex.org/W2000691406","https://openalex.org/W2010386705","https://openalex.org/W2012250964","https://openalex.org/W2020395610","https://openalex.org/W2023972518","https://openalex.org/W2037561415","https://openalex.org/W2043616378","https://openalex.org/W2049800247","https://openalex.org/W2058916022","https://openalex.org/W2059088502","https://openalex.org/W2064744742","https://openalex.org/W2070487325","https://openalex.org/W2071296827","https://openalex.org/W2071642149","https://openalex.org/W2073875590","https://openalex.org/W2074573067","https://openalex.org/W2075460388","https://openalex.org/W2076361081","https://openalex.org/W2081233300","https://openalex.org/W2089096153","https://openalex.org/W2092687851","https://openalex.org/W2099916305","https://openalex.org/W2106821446","https://openalex.org/W2108266785","https://openalex.org/W2109907633","https://openalex.org/W2112053550","https://openalex.org/W2113754927","https://openalex.org/W2117242079","https://openalex.org/W2118784321","https://openalex.org/W2132147136","https://openalex.org/W2141579716","https://openalex.org/W2147468445","https://openalex.org/W2153730006","https://openalex.org/W2195479374","https://openalex.org/W2272866099","https://openalex.org/W2278920287","https://openalex.org/W2291499491","https://openalex.org/W2604510839","https://openalex.org/W2887331837","https://openalex.org/W2918924644","https://openalex.org/W3034399266","https://openalex.org/W3099053820","https://openalex.org/W4240916550","https://openalex.org/W4251386884","https://openalex.org/W4388316717","https://openalex.org/W6679559547","https://openalex.org/W6735580177"],"related_works":["https://openalex.org/W4399354997","https://openalex.org/W1993634787","https://openalex.org/W3125614403","https://openalex.org/W4400317913","https://openalex.org/W2476923378","https://openalex.org/W3100240142","https://openalex.org/W3062287","https://openalex.org/W2380390332","https://openalex.org/W4285014488","https://openalex.org/W2066011280"],"abstract_inverted_index":{"GPU":[0],"performance":[1,63,151],"of":[2,38,55,98,108,139],"the":[3,45,76,90,95,105,121,158,161,179],"lattice":[4,28],"Boltzmann":[5],"method":[6],"(LBM)":[7],"depends":[8],"heavily":[9],"on":[10,18,111,126,172,190],"memory":[11,56,87,144],"access":[12,57],"patterns.":[13],"When":[14,129],"implemented":[15],"with":[16,186],"GPUs":[17,171],"complex":[19],"domains,":[20],"typically,":[21],"geometric":[22],"data":[23,29],"is":[24,30,71,123],"accessed":[25,31],"indirectly":[26],"and":[27,62,85,101,113,142,153,177],"lexicographically.":[32],"Although":[33],"there":[34],"are":[35],"a":[36,53],"variety":[37],"other":[39],"options,":[40],"no":[41],"study":[42],"has":[43],"examined":[44],"relative":[46],"efficacy":[47],"between":[48],"them.":[49],"Here,":[50],"we":[51,92,156],"examine":[52],"suite":[54],"schemes":[58],"via":[59],"empirical":[60],"testing":[61],"modeling.":[64],"We":[65,163],"find":[66,93],"strong":[67,182],"evidence":[68],"that":[69,94,165],"semi-direct":[70],"often":[72],"better":[73],"suited":[74],"than":[75],"more":[77,124],"common":[78,106],"indirect":[79],"addressing,":[80],"providing":[81],"increased":[82],"computational":[83,154],"speed":[84],"reducing":[86],"consumption.":[88],"For":[89],"layout,":[91],"Collected":[96],"Structure":[97,107],"Arrays":[99],"(CSoA)":[100],"bundling":[102],"layouts":[103],"outperform":[104],"Array":[109],"layout;":[110],"V100":[112],"P100":[114],"devices,":[115],"CSoA":[116],"consistently":[117],"outperforms":[118],"bundling,":[119],"however":[120],"relationship":[122],"complicated":[125],"K40":[127],"devices.":[128],"compared":[130],"to":[131,137,147],"state-of-the-art":[132],"practices,":[133],"our":[134,166],"recommendations":[135],"lead":[136],"speedups":[138],"10-40":[140],"percent":[141],"reduce":[143],"consumption":[145],"up":[146],"17":[148],"percent.":[149],"Using":[150],"modeling":[152],"experimentation,":[155],"determine":[157],"mechanisms":[159],"behind":[160],"accelerations.":[162],"demonstrate":[164],"results":[167,183],"hold":[168],"across":[169],"multiple":[170],"two":[173],"leadership":[174],"class":[175],"systems,":[176],"present":[178],"first":[180],"near-optimal":[181],"for":[184],"LBM":[185],"arterial":[187],"geometries":[188],"run":[189],"GPUs.":[191]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-09T07:52:08.696243","created_date":"2025-10-10T00:00:00"}
