{"id":"https://openalex.org/W2585086512","doi":"https://doi.org/10.1109/hipcw.2016.020","title":"An Efficient GPU Parallelization for Arbitrary Collocated Polyhedral Finite Volume Grids and Its Application to Incompressible Fluid Flows","display_name":"An Efficient GPU Parallelization for Arbitrary Collocated Polyhedral Finite Volume Grids and Its Application to Incompressible Fluid Flows","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2585086512","doi":"https://doi.org/10.1109/hipcw.2016.020","mag":"2585086512"},"language":"en","primary_location":{"id":"doi:10.1109/hipcw.2016.020","doi":"https://doi.org/10.1109/hipcw.2016.020","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hipcw.2016.020","pdf_url":null,"source":{"id":"https://openalex.org/S7407087828","display_name":"IEEE International Conference on High Performance Computing Workshops (HiPCW)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 23rd International Conference on High Performance Computing Workshops (HiPCW)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5011739402","display_name":"Shashank Jaiswal","orcid":"https://orcid.org/0000-0003-4678-1511","observed_orcids":["https://orcid.org/0000-0003-4678-1511","https://orcid.org/0009-0002-4160-2043"]},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shashank Jaiswal","raw_affiliation_strings":["Dept. of Mechanical and Aerospace Engineering, Indian Institute of Technology Hyderabad, Hyderabad, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Mechanical and Aerospace Engineering, Indian Institute of Technology Hyderabad, Hyderabad, India","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009116542","display_name":"Rajesh Reddy","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rajesh Reddy","raw_affiliation_strings":["Dept. of Mechanical and Aerospace Engineering, Indian Institute of Technology Hyderabad, Hyderabad, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Mechanical and Aerospace Engineering, Indian Institute of Technology Hyderabad, Hyderabad, India","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054274180","display_name":"Raja Banerjee","orcid":"https://orcid.org/0000-0002-7163-1470","observed_orcids":["https://orcid.org/0000-0002-7163-1470"]},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Raja Banerjee","raw_affiliation_strings":["Indian Institute of Technology Hyderabad, Hyderabad, Telangana, IN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Hyderabad, Hyderabad, Telangana, IN","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101648448","display_name":"Shingo Sato","orcid":"https://orcid.org/0000-0002-3175-9672","observed_orcids":["https://orcid.org/0000-0002-3175-9672"]},"institutions":[{"id":"https://openalex.org/I4405275791","display_name":"JFE Steel Corporation (Japan)","ror":"https://ror.org/049nfwr75","country_code":"JP","type":"company","lineage":["https://openalex.org/I4405275791"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shingo Sato","raw_affiliation_strings":["Numerical Simulation Research Dept., Steel Research Laboratory JFE Steel Corporation, Kawasaki, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Numerical Simulation Research Dept., Steel Research Laboratory JFE Steel Corporation, Kawasaki, Japan","institution_ids":["https://openalex.org/I4405275791"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039907394","display_name":"Daisuke Komagata","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405275791","display_name":"JFE Steel Corporation (Japan)","ror":"https://ror.org/049nfwr75","country_code":"JP","type":"company","lineage":["https://openalex.org/I4405275791"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Daisuke Komagata","raw_affiliation_strings":["Numerical Simulation Research Dept., Steel Research Laboratory JFE Steel Corporation, Kawasaki, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Numerical Simulation Research Dept., Steel Research Laboratory JFE Steel Corporation, Kawasaki, Japan","institution_ids":["https://openalex.org/I4405275791"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Makoto Ando","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405275791","display_name":"JFE Steel Corporation (Japan)","ror":"https://ror.org/049nfwr75","country_code":"JP","type":"company","lineage":["https://openalex.org/I4405275791"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Makoto Ando","raw_affiliation_strings":["Numerical Simulation Research Dept., Steel Research Laboratory JFE Steel Corporation, Kawasaki, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Numerical Simulation Research Dept., Steel Research Laboratory JFE Steel Corporation, Kawasaki, Japan","institution_ids":["https://openalex.org/I4405275791"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103283074","display_name":"Jun Okada","orcid":"https://orcid.org/0000-0002-9895-0762","observed_orcids":["https://orcid.org/0000-0002-9895-0762"]},"institutions":[{"id":"https://openalex.org/I4405275791","display_name":"JFE Steel Corporation (Japan)","ror":"https://ror.org/049nfwr75","country_code":"JP","type":"company","lineage":["https://openalex.org/I4405275791"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jun Okada","raw_affiliation_strings":["Numerical Simulation Research Dept., Steel Research Laboratory JFE Steel Corporation, Kawasaki, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Numerical Simulation Research Dept., Steel Research Laboratory JFE Steel Corporation, Kawasaki, Japan","institution_ids":["https://openalex.org/I4405275791"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2178,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.40314698,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"81","last_page":"89"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9648000001907349,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9648000001907349,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10173","display_name":"Computational Fluid Dynamics and Aerodynamics","score":0.01860000006854534,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.007799999788403511,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/gpu-parallelization","display_name":"GPU parallelization","score":0.9829999804496765},{"id":"https://openalex.org/keywords/collocated-grid","display_name":"collocated grid","score":0.8159999847412109},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.6240000128746033},{"id":"https://openalex.org/keywords/openfoam","display_name":"OpenFOAM","score":0.9440000057220459},{"id":"https://openalex.org/keywords/incompressible-flow","display_name":"incompressible flow","score":0.949999988079071},{"id":"https://openalex.org/keywords/pressure-poisson-equation","display_name":"pressure Poisson equation","score":0.996999979019165},{"id":"https://openalex.org/keywords/conjugate-gradient-method","display_name":"conjugate gradient method","score":0.9190000295639038},{"id":"https://openalex.org/keywords/lid-driven-cavity-flow","display_name":"lid-driven cavity flow","score":0.9169999957084656},{"id":"https://openalex.org/keywords/speedup","display_name":"speedup","score":0.5419999957084656}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7658380270004272},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7480950355529785},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.7234947681427002},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.7124385237693787},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.6808215975761414},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.5953572392463684},{"id":"https://openalex.org/C137119250","wikidata":"https://www.wikidata.org/wiki/Q1413101","display_name":"Multigrid method","level":3,"score":0.5575689077377319},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5575418472290039},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.50426185131073},{"id":"https://openalex.org/C1633027","wikidata":"https://www.wikidata.org/wiki/Q815820","display_name":"Computational fluid dynamics","level":2,"score":0.5018656253814697},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.49411728978157043},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.457973450422287},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4462425410747528},{"id":"https://openalex.org/C84655787","wikidata":"https://www.wikidata.org/wiki/Q8067817","display_name":"Compressibility","level":2,"score":0.4356966018676758},{"id":"https://openalex.org/C50478463","wikidata":"https://www.wikidata.org/wiki/Q1401936","display_name":"Finite volume method","level":2,"score":0.4335865378379822},{"id":"https://openalex.org/C93779851","wikidata":"https://www.wikidata.org/wiki/Q271977","display_name":"Partial differential equation","level":2,"score":0.15096592903137207},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14445790648460388},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.13482174277305603},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.11706352233886719},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.111838698387146},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.10257342457771301},{"id":"https://openalex.org/C57879066","wikidata":"https://www.wikidata.org/wiki/Q41217","display_name":"Mechanics","level":1,"score":0.0930439829826355},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical 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},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hipcw.2016.020","doi":"https://doi.org/10.1109/hipcw.2016.020","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hipcw.2016.020","pdf_url":null,"source":{"id":"https://openalex.org/S7407087828","display_name":"IEEE International Conference on High Performance Computing Workshops (HiPCW)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 23rd International Conference on High Performance Computing Workshops (HiPCW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W70668290","https://openalex.org/W83699269","https://openalex.org/W1536590744","https://openalex.org/W1593385775","https://openalex.org/W1603142303","https://openalex.org/W1862644536","https://openalex.org/W1927238317","https://openalex.org/W1961194538","https://openalex.org/W2004152688","https://openalex.org/W2019432579","https://openalex.org/W2020385488","https://openalex.org/W2023567863","https://openalex.org/W2079026062","https://openalex.org/W2098841537","https://openalex.org/W2110187357","https://openalex.org/W2120919211","https://openalex.org/W2124192278","https://openalex.org/W2132540527","https://openalex.org/W2133755209","https://openalex.org/W2142202027","https://openalex.org/W2146353930","https://openalex.org/W2154118576","https://openalex.org/W2154441000","https://openalex.org/W2167795988","https://openalex.org/W2168575889","https://openalex.org/W2573097811","https://openalex.org/W2607771244","https://openalex.org/W2744008313","https://openalex.org/W2964108306","https://openalex.org/W2997945685","https://openalex.org/W2999104210","https://openalex.org/W3172349748","https://openalex.org/W6670089613"],"related_works":["https://openalex.org/W4387502312","https://openalex.org/W1536590744","https://openalex.org/W2496831976","https://openalex.org/W2622598072","https://openalex.org/W2340961326","https://openalex.org/W2953267338","https://openalex.org/W4410005150","https://openalex.org/W2317160655","https://openalex.org/W2110874417","https://openalex.org/W4362727199"],"abstract_inverted_index":{"This":[0,123],"paper":[1],"presents":[2],"GPU":[3,135,159,182],"parallelization":[4,39],"for":[5,176,211],"a":[6,14,68,166,187,212],"computational":[7],"fluid":[8],"dynamics":[9],"solver":[10,127,138,160,184],"which":[11,76],"works":[12],"on":[13,56],"mesh":[15],"consisting":[16],"of":[17,27,36,79,125,189,215],"polyhedral":[18,88],"cells,":[19],"where":[20,98],"each":[21,30],"cell":[22],"has":[23,32,63,185],"an":[24,33],"arbitrary":[25,34,81],"number":[26,35],"faces":[28],"and":[29,151,198],"face":[31],"vertices.":[37],"The":[38,49,61,91,109,134,158,180],"is":[40,77,103,112,128,140],"achieved":[41],"using":[42,114,207],"NVIDIAs":[43],"compute":[44],"unified":[45],"device":[46],"architecture":[47],"(CUDA).":[48],"developed":[50],"code":[51],"specifically":[52],"targets":[53],"performance":[54],"improvement":[55],"NVIDIA":[57],"Tesla":[58],"accelerator":[59],"GPUs.":[60],"implementation":[62],"been":[64],"carried":[65],"out":[66],"in":[67],"general":[69],"purpose":[70],"open-source":[71],"CFD":[72],"framework":[73],"namely":[74],"OpenFOAM":[75,131,145,204],"capable":[78],"solving":[80,99],"flow":[82,96,175],"problems":[83],"involving":[84],"complex":[85],"geometries":[86],"with":[87,142],"unstructured":[89],"grids.":[90],"present":[92],"work":[93],"considers":[94],"incompressible":[95],"simulations,":[97],"pressure":[100,136],"Poisson":[101,110,137],"equation":[102,111],"the":[104,126],"most":[105],"computationally":[106],"expensive":[107],"step.":[108],"solved":[113],"conjugate":[115],"gradient":[116],"method":[117],"preconditioned":[118],"by":[119,130,164],"algebraic":[120],"multigrid":[121],"method.":[122],"part":[124],"outsourced":[129],"to":[132,144,194,203],"GPU.":[133],"acceleration":[139,161],"determined":[141],"respect":[143],"serial":[146],"version":[147,154,206],"(single":[148],"cpu":[149,156,196,209],"core)":[150],"MPI":[152,205],"parallelized":[153],"(8":[155],"cores).":[157],"was":[162],"tested":[163],"simulating":[165],"standard":[167],"benchmark":[168],"test":[169],"case":[170],"called":[171],"lid":[172],"driven":[173],"cavity":[174],"different":[177],"grid":[178,213],"sizes.":[179],"current":[181],"based":[183],"shown":[186],"speedup":[188],"approximately":[190],"16\u00d7":[191],"when":[192,201],"compared":[193,202],"single":[195],"core":[197],"3.3":[199],"\u00d7":[200],"8":[208],"cores,":[210],"size":[214],"5":[216],"million":[217],"cells.":[218]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2017-02-10T00:00:00"}