{"id":"https://openalex.org/W2899879734","doi":"https://doi.org/10.1109/access.2018.2879877","title":"SingleCaffe: An Efficient Framework for Deep Learning on a Single Node","display_name":"SingleCaffe: An Efficient Framework for Deep Learning on a Single Node","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2899879734","doi":"https://doi.org/10.1109/access.2018.2879877","mag":"2899879734"},"language":"en","primary_location":{"id":"doi:10.1109/access.2018.2879877","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2018.2879877","pdf_url":null,"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":null,"license_id":null,"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://doi.org/10.1109/access.2018.2879877","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100455049","display_name":"Chenxu Wang","orcid":"https://orcid.org/0000-0003-1276-5759"},"institutions":[{"id":"https://openalex.org/I4210112812","display_name":"National Supercomputing Center in Shenzhen","ror":"https://ror.org/02291hh73","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210112812"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenxu Wang","raw_affiliation_strings":["National Supercomputer Center in Guangzhou, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1276-5759","affiliations":[{"raw_affiliation_string":"National Supercomputer Center in Guangzhou, Guangzhou, China","institution_ids":["https://openalex.org/I4210112812"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021445324","display_name":"Yixian Shen","orcid":"https://orcid.org/0000-0001-8447-872X"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixian Shen","raw_affiliation_strings":["School of Data and Computer Science, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Data and Computer Science, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100405577","display_name":"Jia Jia","orcid":"https://orcid.org/0000-0003-3164-8988"},"institutions":[{"id":"https://openalex.org/I4210144889","display_name":"Beijing Municipal Engineering Design and Research Institute (China)","ror":"https://ror.org/03x92hw77","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210144889"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Jia","raw_affiliation_strings":["Beijing Special Engineering and Design Institute, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Special Engineering and Design Institute, Beijing, China","institution_ids":["https://openalex.org/I4210144889"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101633465","display_name":"Yutong Lu","orcid":"https://orcid.org/0000-0001-5315-3375"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yutong Lu","raw_affiliation_strings":["School of Data and Computer Science, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Data and Computer Science, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108648345","display_name":"Zhiguang Chen","orcid":"https://orcid.org/0000-0002-5427-1266"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiguang Chen","raw_affiliation_strings":["School of Data and Computer Science, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Data and Computer Science, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100408109","display_name":"Bo Wang","orcid":"https://orcid.org/0000-0002-5596-1795"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bo Wang","raw_affiliation_strings":["State Key Laboratory of Mathematical Engineering and Advanced Computing, Zhengzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Mathematical Engineering and Advanced Computing, Zhengzhou, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.2081,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.56339715,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":"6","issue":null,"first_page":"69660","last_page":"69671"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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":0.9998000264167786,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9977999925613403,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.993399977684021,"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":0.8815485239028931},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.8071801662445068},{"id":"https://openalex.org/keywords/multithreading","display_name":"Multithreading","score":0.6575978994369507},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4800751805305481},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.47990497946739197},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.47603726387023926},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4671558439731598},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.46673616766929626},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4511720538139343},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.40480726957321167},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.34922295808792114},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32928451895713806},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2613837718963623}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8815485239028931},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.8071801662445068},{"id":"https://openalex.org/C201410400","wikidata":"https://www.wikidata.org/wiki/Q1064412","display_name":"Multithreading","level":3,"score":0.6575978994369507},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4800751805305481},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.47990497946739197},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.47603726387023926},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4671558439731598},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.46673616766929626},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4511720538139343},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.40480726957321167},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.34922295808792114},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32928451895713806},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2613837718963623}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2018.2879877","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2018.2879877","pdf_url":null,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:04a53bc050574beea7e4843436a43605","is_oa":true,"landing_page_url":"https://doaj.org/article/04a53bc050574beea7e4843436a43605","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 6, Pp 69660-69671 (2018)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2018.2879877","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2018.2879877","pdf_url":null,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2056914533","display_name":null,"funder_award_id":"U161126","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3136173457","display_name":"\u57fa\u4e8e\u8d85\u7ea7\u8ba1\u7b97\u673a\u7684\u5927\u6570\u636e\u5904\u7406\u652f\u6491\u5e73\u53f0\u7814\u7a76","funder_award_id":"61872392","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1442374986","https://openalex.org/W1563686443","https://openalex.org/W1606347560","https://openalex.org/W1641327695","https://openalex.org/W1686810756","https://openalex.org/W1799366690","https://openalex.org/W2060393849","https://openalex.org/W2081612620","https://openalex.org/W2097117768","https://openalex.org/W2102017903","https://openalex.org/W2112796928","https://openalex.org/W2117130368","https://openalex.org/W2118858186","https://openalex.org/W2132424367","https://openalex.org/W2132737349","https://openalex.org/W2147768505","https://openalex.org/W2154579312","https://openalex.org/W2155893237","https://openalex.org/W2160815625","https://openalex.org/W2163605009","https://openalex.org/W2168231600","https://openalex.org/W2186615578","https://openalex.org/W2271840356","https://openalex.org/W2294581108","https://openalex.org/W2339765813","https://openalex.org/W2474421929","https://openalex.org/W2579247884","https://openalex.org/W2580688187","https://openalex.org/W2613634265","https://openalex.org/W2622263826","https://openalex.org/W2757910899","https://openalex.org/W2783487361","https://openalex.org/W2885836230","https://openalex.org/W2962747323","https://openalex.org/W2962911728","https://openalex.org/W2963410977","https://openalex.org/W2998704965","https://openalex.org/W3118608800","https://openalex.org/W4285719527","https://openalex.org/W4301021472","https://openalex.org/W6628377381","https://openalex.org/W6665801690","https://openalex.org/W6677919164","https://openalex.org/W6679393576","https://openalex.org/W6680532216","https://openalex.org/W6682751323","https://openalex.org/W6684191040","https://openalex.org/W6684859321","https://openalex.org/W6712502102","https://openalex.org/W6737658843","https://openalex.org/W6743955621","https://openalex.org/W6753801579","https://openalex.org/W6787972765"],"related_works":["https://openalex.org/W3089117407","https://openalex.org/W2115561485","https://openalex.org/W2023373638","https://openalex.org/W1985089255","https://openalex.org/W2010970156","https://openalex.org/W2153202644","https://openalex.org/W2105895556","https://openalex.org/W2733115356","https://openalex.org/W2377593213","https://openalex.org/W4235861380"],"abstract_inverted_index":{"Deep":[0],"learning":[1],"(DL)":[2],"is":[3,94],"currently":[4],"the":[5,64,115,119,130,145,158,174,178,191,206,215],"most":[6,80],"promising":[7],"approach":[8],"in":[9,36,70],"complicated":[10],"applications":[11],"such":[12,59,68,73,111],"as":[13,60,74,152,161],"computer":[14],"vision":[15],"and":[16,26,32,43,49,77,91,113,137,157,166,205],"natural":[17],"language":[18],"processing.":[19],"It":[20],"thrives":[21],"with":[22,55],"large":[23,27],"neural":[24],"networks":[25],"datasets.":[28],"However,":[29,79],"larger":[30,33],"models":[31],"datasets":[34],"result":[35],"longer":[37],"training":[38,120,131,146,202,217],"times":[39],"that":[40,105,198],"impede":[41],"research":[42],"development":[44],"progress.":[45],"The":[46,182,194],"modern":[47],"high-performance":[48,89],"data-parallel":[50],"nature":[51],"of":[52,67,87,110,118,218],"hardware":[53,69,112],"equipped":[54],"high":[56],"computing":[57],"power,":[58],"GPUs,":[61],"has":[62],"triggered":[63],"widespread":[65],"adoption":[66],"DL":[71,81,103],"frameworks,":[72],"Caffe,":[75],"Torch,":[76],"TensorFlow.":[78],"frameworks":[82],"cannot":[83],"make":[84,107],"full":[85,108],"use":[86,109],"this":[88,97],"hardware,":[90],"computational":[92,116],"efficiency":[93,117,203],"low.":[95],"In":[96],"paper,":[98],"we":[99],"present":[100],"SingleCaffe1,":[101],"a":[102,134,150,153,209,219],"framework":[104,183],"can":[106,200,212],"improve":[114,201],"process.":[121],"SingleCaffe":[122,148,199],"opens":[123],"up":[124,129],"multiple":[125,142],"threads":[126,160],"to":[127,189],"speed":[128],"process":[132],"within":[133],"single":[135,210],"node":[136,211],"adopts":[138],"data":[139,165],"parallelism":[140],"on":[141,208],"threads.":[143,163],"During":[144],"process,":[147],"selects":[149],"thread":[151,156,176],"parameter":[154],"server":[155,175],"other":[159],"worker":[162,171],"Both":[164],"workloads":[167],"are":[168],"distributed":[169,216],"across":[170],"threads,":[172],"while":[173],"maintains":[177],"globally":[179],"shared":[180],"parameters.":[181],"also":[184],"manages":[185],"memory":[186,192],"allocation":[187],"carefully":[188],"reduce":[190],"overhead.":[193],"experimental":[195],"results":[196],"show":[197],"well,":[204],"performance":[207],"even":[213],"achieve":[214],"dozen":[220],"nodes.":[221]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}