{"id":"https://openalex.org/W3154127707","doi":"https://doi.org/10.1109/access.2021.3073667","title":"GPU Acceleration of the HemeLB Code for Lattice Boltzmann Simulations in Sparse Complex Geometries","display_name":"GPU Acceleration of the HemeLB Code for Lattice Boltzmann Simulations in Sparse Complex Geometries","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3154127707","doi":"https://doi.org/10.1109/access.2021.3073667","mag":"3154127707"},"language":"en","primary_location":{"id":"doi:10.1109/access.2021.3073667","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3073667","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09405635.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09405635.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083665803","display_name":"Benjamin T. Shealy","orcid":"https://orcid.org/0000-0002-2230-7404"},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Benjamin T. Shealy","raw_affiliation_strings":["Clemson University, Clemson, SC, USA"],"raw_orcid":"https://orcid.org/0000-0002-2230-7404","affiliations":[{"raw_affiliation_string":"Clemson University, Clemson, SC, USA","institution_ids":["https://openalex.org/I8078737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058426398","display_name":"Mehrdad Yousefi","orcid":"https://orcid.org/0000-0002-6497-7166"},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mehrdad Yousefi","raw_affiliation_strings":["Clemson University, Clemson, SC, USA"],"raw_orcid":"https://orcid.org/0000-0002-6497-7166","affiliations":[{"raw_affiliation_string":"Clemson University, Clemson, SC, USA","institution_ids":["https://openalex.org/I8078737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078753236","display_name":"Ashwin Trikuta Srinath","orcid":null},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashwin T. Srinath","raw_affiliation_strings":["Cyberinfrastructure Technology Integration Team, Clemson University, Clemson, SC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cyberinfrastructure Technology Integration Team, Clemson University, Clemson, SC, USA","institution_ids":["https://openalex.org/I8078737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043923029","display_name":"Melissa C. Smith","orcid":"https://orcid.org/0000-0003-0798-8536"},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Melissa C. Smith","raw_affiliation_strings":["Clemson University, Clemson, SC, USA"],"raw_orcid":"https://orcid.org/0000-0003-0798-8536","affiliations":[{"raw_affiliation_string":"Clemson University, Clemson, SC, USA","institution_ids":["https://openalex.org/I8078737"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063715857","display_name":"Ulf Schiller","orcid":"https://orcid.org/0000-0001-8941-1284"},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ulf D. Schiller","raw_affiliation_strings":["Clemson University, Clemson, SC, USA"],"raw_orcid":"https://orcid.org/0000-0001-8941-1284","affiliations":[{"raw_affiliation_string":"Clemson University, Clemson, SC, USA","institution_ids":["https://openalex.org/I8078737"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I8078737"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.6904,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.63525085,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"9","issue":null,"first_page":"61224","last_page":"61236"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11751","display_name":"Lattice Boltzmann Simulation Studies","score":0.9993000030517578,"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":0.9993000030517578,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9966999888420105,"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"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9851999878883362,"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":0.8101261854171753},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.748079776763916},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.7431115508079529},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7417110800743103},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5796127915382385},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.5363560914993286},{"id":"https://openalex.org/keywords/lattice-boltzmann-methods","display_name":"Lattice Boltzmann methods","score":0.49123281240463257},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.44329914450645447},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1142849326133728},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09106487035751343},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08272731304168701},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.0819610059261322}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8101261854171753},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.748079776763916},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.7431115508079529},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7417110800743103},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5796127915382385},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.5363560914993286},{"id":"https://openalex.org/C21821499","wikidata":"https://www.wikidata.org/wiki/Q1807064","display_name":"Lattice Boltzmann methods","level":2,"score":0.49123281240463257},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.44329914450645447},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1142849326133728},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09106487035751343},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08272731304168701},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0819610059261322},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/access.2021.3073667","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3073667","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09405635.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:22b095eb1a0341378c446e7d5d36289f","is_oa":true,"landing_page_url":"https://doaj.org/article/22b095eb1a0341378c446e7d5d36289f","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":"IEEE Access, Vol 9, Pp 61224-61236 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2021.3073667","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3073667","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09405635.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.6200000047683716}],"awards":[{"id":"https://openalex.org/G2629593585","display_name":null,"funder_award_id":"CNS-1725573","funder_id":"https://openalex.org/F4320337388","funder_display_name":"Division of Computer and Network Systems"},{"id":"https://openalex.org/G3328667828","display_name":"MRI: Acquisition of a Cyberinstrument for Interdisciplinary Computational Science and Engineering","funder_award_id":"1725573","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309106","display_name":"Clemson University","ror":"https://ror.org/037s24f05"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320337388","display_name":"Division of Computer and Network Systems","ror":"https://ror.org/02rdzmk74"},{"id":"https://openalex.org/F4320338287","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3154127707.pdf","grobid_xml":"https://content.openalex.org/works/W3154127707.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W1664235680","https://openalex.org/W1779734685","https://openalex.org/W1869349964","https://openalex.org/W1966277182","https://openalex.org/W1971876223","https://openalex.org/W1988271670","https://openalex.org/W2002555321","https://openalex.org/W2008456266","https://openalex.org/W2012250964","https://openalex.org/W2049800247","https://openalex.org/W2055213676","https://openalex.org/W2063597636","https://openalex.org/W2064744742","https://openalex.org/W2071296827","https://openalex.org/W2071642149","https://openalex.org/W2072260627","https://openalex.org/W2073875590","https://openalex.org/W2075460388","https://openalex.org/W2078794610","https://openalex.org/W2078961060","https://openalex.org/W2080435752","https://openalex.org/W2092687851","https://openalex.org/W2122017745","https://openalex.org/W2140441019","https://openalex.org/W2153730006","https://openalex.org/W2155609373","https://openalex.org/W2294453430","https://openalex.org/W2508453970","https://openalex.org/W2513293834","https://openalex.org/W2604510839","https://openalex.org/W2803094507","https://openalex.org/W2803941047","https://openalex.org/W2887331837","https://openalex.org/W2890095579","https://openalex.org/W2897332680","https://openalex.org/W2918924644","https://openalex.org/W2950704923","https://openalex.org/W2964159310","https://openalex.org/W3026448763","https://openalex.org/W3034966030","https://openalex.org/W3082181200","https://openalex.org/W3099053820","https://openalex.org/W3106440809","https://openalex.org/W3111964610","https://openalex.org/W3124939032","https://openalex.org/W4251386884","https://openalex.org/W4297669665","https://openalex.org/W4388316717","https://openalex.org/W6696797841","https://openalex.org/W6777924051"],"related_works":["https://openalex.org/W2076165488","https://openalex.org/W2183370537","https://openalex.org/W3189307731","https://openalex.org/W2949962288","https://openalex.org/W2364686214","https://openalex.org/W1428699136","https://openalex.org/W1998560227","https://openalex.org/W2415174576","https://openalex.org/W2062364940","https://openalex.org/W2614306844"],"abstract_inverted_index":{"We":[0,22,50,91,127],"present":[1,67],"an":[2],"implementation":[3,29,152,194],"and":[4,30,45,58,65,81,83,106,162,164,171,184],"scaling":[5],"analysis":[6,70],"of":[7,26,35,54,71,86,98,142,148,198,206],"a":[8,13,38,68,84,116,145],"GPU-accelerated":[9],"kernel":[10,135],"for":[11,18,160,181,211],"HemeLB,":[12],"high-performance":[14,208],"Lattice":[15],"Boltzmann":[16,214],"code":[17,201],"sparse":[19],"complex":[20],"geometries.":[21,90],"describe":[23],"the":[24,27,33,52,62,134,140,154,176,192,199],"structure":[25],"GPU":[28,39,59,151,193],"we":[31,66],"study":[32],"scalability":[34,122,141],"HemeLB":[36,180,200],"on":[37,61],"cluster":[40],"under":[41],"normal":[42],"operating":[43],"conditions":[44,159],"with":[46,120,175],"real-world":[47],"application":[48],"cases.":[49],"investigate":[51],"effect":[53],"CUDA":[55],"block":[56],"size":[57],"over-subscription":[60],"single-GPU":[63,96],"performance,":[64],"strong-scaling":[69],"multi-GPU":[72],"parallel":[73],"simulations":[74],"using":[75],"two":[76],"different":[77],"hardware":[78],"models":[79],"(P100":[80],"V100)":[82],"variety":[85],"large":[87],"cerebral":[88],"aneurysm":[89],"find":[92],"that":[93,191],"HemeLB-GPU":[94,143],"achieves":[95],"speedups":[97],"<inline-formula":[99,107],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[100,108],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[101,109],"<tex-math":[102,110],"notation=\"LaTeX\">$50\\times$":[103],"</tex-math></inline-formula>":[104,112],"(P100)":[105],"notation=\"LaTeX\">$100\\times$":[111],"(V100)":[113],"compared":[114],"to":[115,124,131,144,202],"single":[117],"CPU":[118],"core,":[119],"good":[121],"up":[123],"32":[125],"GPUs.":[126,149],"also":[128],"discuss":[129],"strategies":[130],"improve":[132],"both":[133],"performance":[136],"as":[137,139],"well":[138],"larger":[146],"number":[147],"The":[150],"supports":[153],"LBGK":[155],"collision":[156],"kernel,":[157],"boundary":[158],"walls":[161],"inlets/outlets,":[163],"several":[165],"lattice":[166,213],"types":[167],"(D3Q15,":[168],"D3Q19,":[169],"D3Q27),":[170],"it":[172],"integrates":[173],"seamlessly":[174],"existing":[177],"infrastructure":[178],"in":[179],"graph":[182],"partitioning":[183],"parallelization":[185],"via":[186],"MPI.":[187],"It":[188],"is":[189],"expected":[190],"will":[195],"enable":[196],"users":[197],"make":[203],"better":[204],"utilization":[205],"heterogeneous":[207],"computing":[209],"systems":[210],"large-scale":[212],"simulations.":[215]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}