{"id":"https://openalex.org/W4321782112","doi":"https://doi.org/10.1145/3582514.3582523","title":"Exploring OpenMP GPU Offloading for Implementing Convolutional Neural Networks","display_name":"Exploring OpenMP GPU Offloading for Implementing Convolutional Neural Networks","publication_year":2023,"publication_date":"2023-02-24","ids":{"openalex":"https://openalex.org/W4321782112","doi":"https://doi.org/10.1145/3582514.3582523"},"language":"en","primary_location":{"id":"doi:10.1145/3582514.3582523","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3582514.3582523","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3582514.3582523","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th International Workshop on Programming Models and Applications for Multicores and Manycores","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3582514.3582523","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088522033","display_name":"Kewei Yan","orcid":"https://orcid.org/0000-0003-0406-1276"},"institutions":[{"id":"https://openalex.org/I102149020","display_name":"University of North Carolina at Charlotte","ror":"https://ror.org/04dawnj30","country_code":"US","type":"education","lineage":["https://openalex.org/I102149020"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kewei Yan","raw_affiliation_strings":["University of North Carolina at Charlotte, Charlotte, USA"],"raw_orcid":"https://orcid.org/0000-0003-0406-1276","affiliations":[{"raw_affiliation_string":"University of North Carolina at Charlotte, Charlotte, USA","institution_ids":["https://openalex.org/I102149020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043940110","display_name":"Yaying Shi","orcid":"https://orcid.org/0000-0002-8721-8509"},"institutions":[{"id":"https://openalex.org/I102149020","display_name":"University of North Carolina at Charlotte","ror":"https://ror.org/04dawnj30","country_code":"US","type":"education","lineage":["https://openalex.org/I102149020"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yaying Shi","raw_affiliation_strings":["University of North Carolina at Charlotte, Charlotte, USA"],"raw_orcid":"https://orcid.org/0000-0002-8721-8509","affiliations":[{"raw_affiliation_string":"University of North Carolina at Charlotte, Charlotte, USA","institution_ids":["https://openalex.org/I102149020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102715061","display_name":"Yonghong Yan","orcid":"https://orcid.org/0000-0002-5274-8526"},"institutions":[{"id":"https://openalex.org/I102149020","display_name":"University of North Carolina at Charlotte","ror":"https://ror.org/04dawnj30","country_code":"US","type":"education","lineage":["https://openalex.org/I102149020"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yonghong Yan","raw_affiliation_strings":["University of North Carolina at Charlotte, Charlotte, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-5274-8526","affiliations":[{"raw_affiliation_string":"University of North Carolina at Charlotte, Charlotte, United States of America","institution_ids":["https://openalex.org/I102149020"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I102149020"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01193431,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"60","last_page":"69"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"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/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9887999892234802,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9878000020980835,"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":0.9043737649917603},{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.8847439289093018},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7020204067230225},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5712880492210388},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5173963308334351},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5041400194168091},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.4488150477409363},{"id":"https://openalex.org/keywords/host","display_name":"Host (biology)","score":0.4245879054069519},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.422626793384552},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.40061724185943604},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.37506961822509766},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.269817054271698},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.23131683468818665},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1586146056652069},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13326144218444824}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9043737649917603},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.8847439289093018},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7020204067230225},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5712880492210388},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5173963308334351},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5041400194168091},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.4488150477409363},{"id":"https://openalex.org/C126831891","wikidata":"https://www.wikidata.org/wiki/Q221673","display_name":"Host (biology)","level":2,"score":0.4245879054069519},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.422626793384552},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.40061724185943604},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.37506961822509766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.269817054271698},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.23131683468818665},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1586146056652069},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13326144218444824},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3582514.3582523","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3582514.3582523","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3582514.3582523","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th International Workshop on Programming Models and Applications for Multicores and Manycores","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3582514.3582523","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3582514.3582523","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3582514.3582523","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th International Workshop on Programming Models and Applications for Multicores and Manycores","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G706490860","display_name":"CAREER: Programming the Existing and Emerging Memory Systems for Extreme-scale Parallel Performance","funder_award_id":"1833332","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7566237621","display_name":"CAREER: Programming the Existing and Emerging Memory Systems for Extreme-scale Parallel Performance","funder_award_id":"2015254","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"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4321782112.pdf","grobid_xml":"https://content.openalex.org/works/W4321782112.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W2007339694","https://openalex.org/W2072462334","https://openalex.org/W2080592089","https://openalex.org/W2108598243","https://openalex.org/W2142427060","https://openalex.org/W2155893237","https://openalex.org/W2159139478","https://openalex.org/W2180288011","https://openalex.org/W2521614036","https://openalex.org/W2560960843","https://openalex.org/W2727576198","https://openalex.org/W2767028519","https://openalex.org/W2789876780","https://openalex.org/W2884700152","https://openalex.org/W2885571639","https://openalex.org/W2970909703","https://openalex.org/W3037205796","https://openalex.org/W3037847693","https://openalex.org/W4246945770","https://openalex.org/W6713134421","https://openalex.org/W6779860269"],"related_works":["https://openalex.org/W3102660566","https://openalex.org/W2983282793","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"],"abstract_inverted_index":{"Computing":[0],"on":[1,177,183],"heterogeneous":[2],"architecture":[3],"involving":[4],"CPUs":[5],"and":[6,25,36,85,91,102,115,123,151,163,176,190],"accelerators":[7],"is":[8,143],"now":[9],"a":[10,17,30],"popular":[11],"choice":[12],"of":[13,33,53,65,77,111,126,139],"parallel":[14,39],"computing.":[15],"As":[16],"directive-based":[18],"programming":[19],"model,":[20],"OpenMP":[21,55,79,161,173],"has":[22],"become":[23],"more":[24,26],"comprehensive":[27],"that":[28],"supports":[29],"large":[31],"variety":[32],"hardware":[34],"architectures":[35],"commonly":[37],"used":[38],"patterns":[40],"for":[41,58,70,81,97],"high":[42],"performance":[43,170,179],"computing":[44],"applications.":[45],"In":[46],"this":[47],"paper,":[48],"we":[49],"present":[50],"our":[51,95,108,158],"experience":[52],"using":[54,78,100],"offloading":[56],"model":[57],"computer":[59],"vision":[60],"tasks":[61],"with":[62,160,172,180],"the":[63,146,196],"implementation":[64,96,159],"Convolutional":[66],"Neural":[67],"Network":[68],"(CNN)":[69],"image":[71],"classification.":[72],"We":[73,93,155,166],"explore":[74],"different":[75],"approaches":[76],"directives":[80],"parallelizing":[82,112],"computational":[83,113],"loops":[84,114],"managing":[86],"data":[87,104,116,185],"copy":[88,117],"between":[89,148],"host":[90],"GPUs.":[92],"evaluate":[94],"CNN":[98],"training":[99],"MNIST":[101],"ImageNet":[103,184],"sets.":[105],"According":[106],"to":[107,119,121,136],"evaluation,":[109],"optimization":[110],"leads":[118],"up":[120,135],"3.1x":[122],"1.6x":[124],"improvements":[125],"overall":[127,140],"execution":[128,141],"time":[129,142],"among":[130],"single":[131,152],"GPU":[132,153],"cases.":[133,154],"Besides,":[134],"2.7x":[137],"improvement":[138],"observed":[144,167],"from":[145],"comparison":[147,191],"4-GPU":[149],"cases":[150],"also":[156,193],"compare":[157],"CPU":[162,174],"cuDNN":[164,181],"versions.":[165],"solid":[168],"better":[169],"comparing":[171],"version":[175,182],"par":[178],"set.":[186],"Detailed":[187],"breakdown":[188],"analysis":[189],"are":[192],"provided":[194],"in":[195],"paper.":[197]},"counts_by_year":[],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}