{"id":"https://openalex.org/W2517714857","doi":"https://doi.org/10.1145/2967938.2967944","title":"Bridging the Semantic Gaps of GPU Acceleration for Scale-out CNN-based Big Data Processing","display_name":"Bridging the Semantic Gaps of GPU Acceleration for Scale-out CNN-based Big Data Processing","publication_year":2016,"publication_date":"2016-08-31","ids":{"openalex":"https://openalex.org/W2517714857","doi":"https://doi.org/10.1145/2967938.2967944","mag":"2517714857"},"language":"en","primary_location":{"id":"doi:10.1145/2967938.2967944","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2967938.2967944","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2967938.2967944","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 International Conference on Parallel Architectures and Compilation","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/2967938.2967944","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000111354","display_name":"Mingcong Song","orcid":"https://orcid.org/0009-0002-5289-685X"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mingcong Song","raw_affiliation_strings":["University of Florida, Gainesville, FL, USA"],"affiliations":[{"raw_affiliation_string":"University of Florida, Gainesville, FL, USA","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066434078","display_name":"Yang Hu","orcid":"https://orcid.org/0000-0001-6942-4395"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang Hu","raw_affiliation_strings":["University of Florida, Gainesville, FL, USA"],"affiliations":[{"raw_affiliation_string":"University of Florida, Gainesville, FL, USA","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102900140","display_name":"Yunlong Xu","orcid":"https://orcid.org/0000-0003-4727-0676"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunlong Xu","raw_affiliation_strings":["Xi'an Jiaotong University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100323157","display_name":"Chao Li","orcid":"https://orcid.org/0000-0002-0734-0011"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Li","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062135968","display_name":"Huixiang Chen","orcid":"https://orcid.org/0000-0002-4260-9899"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huixiang Chen","raw_affiliation_strings":["University of Florida, Gainesville, FL, USA"],"affiliations":[{"raw_affiliation_string":"University of Florida, Gainesville, FL, USA","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062853168","display_name":"Jingling Yuan","orcid":"https://orcid.org/0000-0001-7924-8620"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingling Yuan","raw_affiliation_strings":["Wuhan University of Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology, Wuhan, China","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100455376","display_name":"Tao Li","orcid":"https://orcid.org/0000-0003-1697-8022"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tao Li","raw_affiliation_strings":["University of Florida, Gainesville, FL, USA"],"affiliations":[{"raw_affiliation_string":"University of Florida, Gainesville, FL, USA","institution_ids":["https://openalex.org/I33213144"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5000111354"],"corresponding_institution_ids":["https://openalex.org/I33213144"],"apc_list":null,"apc_paid":null,"fwci":2.0041,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.91172571,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"315","last_page":"326"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":1.0,"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":1.0,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9983000159263611,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9980000257492065,"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":0.885394811630249},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7427006363868713},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.6671252250671387},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5692541003227234},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.510263204574585},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.4855029582977295},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4819047749042511},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.47632867097854614},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4600704610347748},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.44394904375076294},{"id":"https://openalex.org/keywords/parallel-processing","display_name":"Parallel processing","score":0.42049920558929443},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4135338068008423},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3918004035949707},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3596076965332031},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.21574276685714722},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.18531358242034912},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.12210270762443542},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09362098574638367},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.08714315295219421}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.885394811630249},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7427006363868713},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.6671252250671387},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5692541003227234},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.510263204574585},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.4855029582977295},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4819047749042511},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.47632867097854614},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4600704610347748},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.44394904375076294},{"id":"https://openalex.org/C106515295","wikidata":"https://www.wikidata.org/wiki/Q26806595","display_name":"Parallel processing","level":2,"score":0.42049920558929443},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4135338068008423},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3918004035949707},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3596076965332031},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.21574276685714722},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.18531358242034912},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.12210270762443542},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09362098574638367},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.08714315295219421},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2967938.2967944","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2967938.2967944","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2967938.2967944","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 International Conference on Parallel Architectures and Compilation","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/2967938.2967944","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2967938.2967944","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2967938.2967944","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 International Conference on Parallel Architectures and Compilation","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7099999785423279}],"awards":[{"id":"https://openalex.org/G4008716106","display_name":null,"funder_award_id":"61303029","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5258214010","display_name":null,"funder_award_id":"1527535, 1423090, 1320100,1117261, 0937869, 0916384, 0845721(CAREER), 0834288, 0811611, 0720476","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5531126461","display_name":null,"funder_award_id":"2008-HJ-1798, 2007-RJ-1651G","funder_id":"https://openalex.org/F4320306087","funder_display_name":"Semiconductor Research Corporation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306087","display_name":"Semiconductor Research Corporation","ror":"https://ror.org/047z4n946"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2517714857.pdf","grobid_xml":"https://content.openalex.org/works/W2517714857.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W1538245821","https://openalex.org/W1598064945","https://openalex.org/W1667652561","https://openalex.org/W1832693441","https://openalex.org/W1905882502","https://openalex.org/W1954873805","https://openalex.org/W1958236864","https://openalex.org/W1984993578","https://openalex.org/W1985353575","https://openalex.org/W1986327994","https://openalex.org/W1995562189","https://openalex.org/W2000967104","https://openalex.org/W2016053056","https://openalex.org/W2048266589","https://openalex.org/W2067523571","https://openalex.org/W2072034469","https://openalex.org/W2094756095","https://openalex.org/W2097117768","https://openalex.org/W2099517310","https://openalex.org/W2102605133","https://openalex.org/W2108598243","https://openalex.org/W2117539524","https://openalex.org/W2124237318","https://openalex.org/W2131975293","https://openalex.org/W2134670479","https://openalex.org/W2142801765","https://openalex.org/W2144867138","https://openalex.org/W2152839228","https://openalex.org/W2155893237","https://openalex.org/W2162741153","https://openalex.org/W2163605009","https://openalex.org/W2173213060","https://openalex.org/W2410158158","https://openalex.org/W2412152175","https://openalex.org/W2565334518","https://openalex.org/W2912516925","https://openalex.org/W2962835968"],"related_works":["https://openalex.org/W3062287","https://openalex.org/W2380390332","https://openalex.org/W2742145873","https://openalex.org/W2023572661","https://openalex.org/W4245975140","https://openalex.org/W2532592438","https://openalex.org/W1977763331","https://openalex.org/W2062253548","https://openalex.org/W4225414539","https://openalex.org/W4289522463"],"abstract_inverted_index":{"Convolutional":[0],"Neural":[1],"Networks":[2],"(CNNs)":[3],"have":[4],"substantially":[5],"advanced":[6],"the":[7,15,53,66],"state-of-the-art":[8],"accuracies":[9],"of":[10,18,21,45,71],"object":[11],"recognition,":[12,31],"which":[13],"is":[14],"core":[16],"function":[17],"a":[19,42],"myriad":[20],"modern":[22],"multimedia":[23],"processing":[24],"techniques":[25],"such":[26],"as":[27],"image/video":[28],"processing,":[29],"speech":[30],"and":[32,69],"natural":[33],"language":[34],"processing.":[35,81],"GPU-based":[36],"accelerators":[37],"gained":[38],"increasing":[39],"attention":[40],"because":[41],"large":[43],"amount":[44],"highly":[46],"parallel":[47],"neurons":[48],"in":[49],"CNN":[50],"naturally":[51],"matches":[52],"GPU":[54,73],"computation":[55],"pattern.":[56],"In":[57],"this":[58],"work,":[59],"we":[60],"perform":[61],"comprehensive":[62],"experiments":[63],"to":[64],"investigate":[65],"performance":[67],"bottlenecks":[68],"overheads":[70],"current":[72],"acceleration":[74],"platform":[75],"for":[76],"scale-out":[77],"CNN-based":[78],"big":[79],"data":[80]},"counts_by_year":[{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}