{"id":"https://openalex.org/W2676592635","doi":"https://doi.org/10.1145/3093172.3093229","title":"Evaluation of a Directive-Based GPU Programming Approach for High-Order Unstructured Mesh Computational Fluid Dynamics","display_name":"Evaluation of a Directive-Based GPU Programming Approach for High-Order Unstructured Mesh Computational Fluid Dynamics","publication_year":2017,"publication_date":"2017-06-23","ids":{"openalex":"https://openalex.org/W2676592635","doi":"https://doi.org/10.1145/3093172.3093229","mag":"2676592635"},"language":"en","primary_location":{"id":"doi:10.1145/3093172.3093229","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3093172.3093229","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Platform for Advanced Scientific Computing Conference","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/A5108778969","display_name":"Kunal Puri","orcid":null},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Kunal Puri","raw_affiliation_strings":["Technion, Israel Institute of Technology, Haifa, Haifa, Israel"],"affiliations":[{"raw_affiliation_string":"Technion, Israel Institute of Technology, Haifa, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101579941","display_name":"Vikram Singh","orcid":"https://orcid.org/0000-0001-5881-681X"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Vikram Singh","raw_affiliation_strings":["Technion, Israel Institute of Technology, Haifa, Haifa, Israel"],"affiliations":[{"raw_affiliation_string":"Technion, Israel Institute of Technology, Haifa, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076401038","display_name":"Steven H. Frankel","orcid":null},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Steven Frankel","raw_affiliation_strings":["Technion, Israel Institute of Technology, Haifa, Haifa, Israel"],"affiliations":[{"raw_affiliation_string":"Technion, Israel Institute of Technology, Haifa, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5108778969"],"corresponding_institution_ids":["https://openalex.org/I174306211"],"apc_list":null,"apc_paid":null,"fwci":0.4802,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.61777392,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11751","display_name":"Lattice Boltzmann Simulation Studies","score":0.9994000196456909,"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":0.9994000196456909,"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/T11382","display_name":"Fluid Dynamics and Heat Transfer","score":0.9969000220298767,"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/T10173","display_name":"Computational Fluid Dynamics and Aerodynamics","score":0.996399998664856,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7640166282653809},{"id":"https://openalex.org/keywords/directive","display_name":"Directive","score":0.6260455846786499},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.5938186049461365},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5708105564117432},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5308141708374023},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5170655846595764},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.44478166103363037},{"id":"https://openalex.org/keywords/computational-fluid-dynamics","display_name":"Computational fluid dynamics","score":0.4412088394165039},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3289785385131836},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.17905566096305847},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.11086452007293701},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07213139533996582},{"id":"https://openalex.org/keywords/aerospace-engineering","display_name":"Aerospace engineering","score":0.06760284304618835}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7640166282653809},{"id":"https://openalex.org/C2779547435","wikidata":"https://www.wikidata.org/wiki/Q1121492","display_name":"Directive","level":2,"score":0.6260455846786499},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.5938186049461365},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5708105564117432},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5308141708374023},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5170655846595764},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.44478166103363037},{"id":"https://openalex.org/C1633027","wikidata":"https://www.wikidata.org/wiki/Q815820","display_name":"Computational fluid dynamics","level":2,"score":0.4412088394165039},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3289785385131836},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.17905566096305847},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.11086452007293701},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07213139533996582},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.06760284304618835},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3093172.3093229","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3093172.3093229","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Platform for Advanced Scientific Computing Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W312001194","https://openalex.org/W822192266","https://openalex.org/W1038848389","https://openalex.org/W1813184150","https://openalex.org/W1935002285","https://openalex.org/W1965742121","https://openalex.org/W1971949097","https://openalex.org/W1976346389","https://openalex.org/W1983220757","https://openalex.org/W1985462363","https://openalex.org/W1996409055","https://openalex.org/W2088266489","https://openalex.org/W2092345168","https://openalex.org/W2112311198","https://openalex.org/W2124192278","https://openalex.org/W2152340913","https://openalex.org/W2162322364","https://openalex.org/W2173732377","https://openalex.org/W2263920657","https://openalex.org/W2273809747","https://openalex.org/W2294903947","https://openalex.org/W2327267590","https://openalex.org/W2332227794","https://openalex.org/W2403662085","https://openalex.org/W2511114288","https://openalex.org/W2513293834","https://openalex.org/W2518564289","https://openalex.org/W2564856016","https://openalex.org/W3105115110","https://openalex.org/W3105460217","https://openalex.org/W3106440809","https://openalex.org/W3121525383"],"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/W1912958759","https://openalex.org/W2792081825"],"abstract_inverted_index":{"In":[0],"this":[1],"work":[2],"we":[3,52,145],"evaluate":[4],"the":[5,14,38,54,62,72,84,100,104,148],"effectiveness":[6],"of":[7,16,31,56],"using":[8,57,123,138],"OpenACC":[9,124,154],"as":[10],"a":[11,17,157],"paradigm":[12],"for":[13,37,59,90],"auto-parallelization":[15],"high-order":[18],"unstructured":[19],"CFD":[20],"code":[21,36,69,89,137],"on":[22,71,103],"Graphics":[23],"Processing":[24],"Units":[25],"(GPUs).":[26],"This":[27],"is":[28,93,120,129,165,169],"in":[29,130,156],"lieu":[30],"hand-written":[32],"CUDA":[33],"or":[34],"OpenCL":[35,68,119,139],"algorithms":[39],"that":[40,83,113,142,147,164],"have":[41],"to":[42,48,133,167],"be":[43],"separately":[44],"maintained":[45],"and":[46,67,160,172],"tuned":[47],"available":[49],"hardware.":[50],"Specifically,":[51],"compare":[53],"performance":[55],"OpenACC-2.5":[58],"Fortran":[60],"with":[61,107,118,125],"commercial":[63],"PGI":[64],"compiler":[65],"suite":[66],"running":[70],"Nvidia":[73],"Kepler":[74],"series":[75],"(K20,":[76],"K40)":[77],"GPU":[78,87],"accelerators.":[79],"Our":[80],"results":[81,155],"show":[82],"(double":[85],"precision)":[86],"accelerated":[88],"both":[91],"approaches":[92],"2":[94],"~":[95],"3":[96],"times":[97],"faster":[98,121],"than":[99,122],"optimized":[101,136],"counterpart":[102],"CPU":[105],"(running":[106],"an":[108,135],"OpenMP":[109],"model).":[110],"We":[111],"find":[112,146],"sparse":[114],"matrix":[115],"vector":[116],"multiplication":[117],"CuBLAS.":[126],"While":[127],"it":[128],"general":[131],"possible":[132],"write":[134],"(or":[140],"CUDA)":[141],"outperforms":[143],"OpenACC,":[144],"directive":[149],"based":[150],"approach":[151],"offered":[152],"by":[153],"flexible,":[158],"unified":[159],"hence":[161],"smaller":[162],"code-base":[163],"easier":[166],"maintain,":[168],"readily":[170],"portable":[171],"promotes":[173],"algorithm":[174],"development.":[175]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
