{"id":"https://openalex.org/W3036208378","doi":"https://doi.org/10.23919/date48585.2020.9116236","title":"PhoneBit: Efficient GPU-Accelerated Binary Neural Network Inference Engine for Mobile Phones","display_name":"PhoneBit: Efficient GPU-Accelerated Binary Neural Network Inference Engine for Mobile Phones","publication_year":2020,"publication_date":"2020-03-01","ids":{"openalex":"https://openalex.org/W3036208378","doi":"https://doi.org/10.23919/date48585.2020.9116236","mag":"3036208378"},"language":"en","primary_location":{"id":"doi:10.23919/date48585.2020.9116236","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date48585.2020.9116236","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 Design, Automation & Test in Europe Conference & Exhibition (DATE)","raw_type":"proceedings-article"},"type":"preprint","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/A5100389329","display_name":"Gang Chen","orcid":"https://orcid.org/0000-0003-4234-1359"},"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":true,"raw_author_name":"Gang Chen","raw_affiliation_strings":["Sun Yat-sen University, China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047761633","display_name":"Shengyu He","orcid":"https://orcid.org/0009-0006-7919-6908"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shengyu He","raw_affiliation_strings":["Notheastem University, China"],"affiliations":[{"raw_affiliation_string":"Notheastem University, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112876106","display_name":"Haitao Meng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haitao Meng","raw_affiliation_strings":["Notheastem University, China"],"affiliations":[{"raw_affiliation_string":"Notheastem University, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100768452","display_name":"Kai Huang","orcid":"https://orcid.org/0000-0003-0359-7810"},"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":"Kai Huang","raw_affiliation_strings":["Sun Yat-sen University, China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100389329"],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":1.2755,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.8255492,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"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":0.8619297742843628},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6353514790534973},{"id":"https://openalex.org/keywords/porting","display_name":"Porting","score":0.5781325697898865},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5719300508499146},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.5554559230804443},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.5417848229408264},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.4585781395435333},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4572112560272217},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4552054703235626},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.38520482182502747},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.32654571533203125},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19308629631996155},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.1353859007358551},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10073119401931763}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8619297742843628},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6353514790534973},{"id":"https://openalex.org/C106251023","wikidata":"https://www.wikidata.org/wiki/Q851989","display_name":"Porting","level":3,"score":0.5781325697898865},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5719300508499146},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.5554559230804443},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.5417848229408264},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.4585781395435333},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4572112560272217},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4552054703235626},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.38520482182502747},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.32654571533203125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19308629631996155},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.1353859007358551},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10073119401931763}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/date48585.2020.9116236","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date48585.2020.9116236","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 Design, Automation & Test in Europe Conference & Exhibition (DATE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.8999999761581421,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2039140951","https://openalex.org/W2300242332","https://openalex.org/W2319920447","https://openalex.org/W2525951180","https://openalex.org/W2591922920","https://openalex.org/W2604319603","https://openalex.org/W2618939455","https://openalex.org/W2724616073","https://openalex.org/W2786406308","https://openalex.org/W2790167166","https://openalex.org/W2801496955","https://openalex.org/W2895432151","https://openalex.org/W2962851801","https://openalex.org/W6698200048","https://openalex.org/W6700264148","https://openalex.org/W6748003292","https://openalex.org/W6755325935"],"related_works":["https://openalex.org/W2356602486","https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2351992668","https://openalex.org/W2324828474","https://openalex.org/W1662038552","https://openalex.org/W3021568819","https://openalex.org/W2103995555","https://openalex.org/W4376647684","https://openalex.org/W4221139464"],"abstract_inverted_index":{"Over":[0],"the":[1,117,161],"last":[2],"years,":[3],"a":[4,50,105,127,150],"great":[5],"success":[6],"of":[7,70,84,120,129,167],"deep":[8],"neural":[9,43],"networks":[10,44],"(DNNs)":[11],"has":[12],"been":[13,47],"witnessed":[14],"in":[15,96],"computer":[16],"vision":[17],"and":[18,23,140,153,164,177,193],"other":[19],"fields.":[20],"However,":[21],"performance":[22,92],"power":[24,119,166],"constraints":[25],"make":[26],"it":[27],"still":[28],"challenging":[29],"to":[30,37,53,61,79,87,158],"deploy":[31],"DNNs":[32],"on":[33,122],"mobile":[34,88,112,123,168,201],"devices":[35,89,113],"due":[36],"their":[38,180],"high":[39],"computational":[40],"complexity.":[41],"Binary":[42],"(BNNs)":[45],"have":[46],"demonstrated":[48],"as":[49],"promising":[51],"solution":[52],"achieve":[54,190],"this":[55,100],"goal":[56],"by":[57],"using":[58],"bit-wise":[59],"operations":[60],"replace":[62],"most":[63],"arithmetic":[64],"operations.":[65],"Currently,":[66],"existing":[67],"GPU-accelerated":[68,106],"implementations":[69,86],"BNNs":[71,121],"are":[72],"only":[73],"tailored":[74],"for":[75,110,143,156,200],"desktop":[76],"platforms.":[77],"Due":[78],"architecture":[80],"differences,":[81],"mere":[82],"porting":[83],"such":[85],"yields":[90],"suboptimal":[91],"or":[93],"is":[94],"impossible":[95],"some":[97],"cases.":[98],"In":[99],"paper,":[101],"we":[102],"propose":[103],"PhoneBit,":[104],"BNN":[107],"inference":[108],"engine":[109],"Android-based":[111],"that":[114,187],"fully":[115],"exploits":[116],"computing":[118,165],"GPUs.":[124,169],"PhoneBit":[125,157,172,188],"provides":[126],"set":[128],"operator-level":[130],"optimizations":[131],"including":[132],"locality-friendly":[133],"data":[134],"layout,":[135],"bit":[136],"packing":[137],"with":[138,173,179,197],"vectorization":[139],"layers":[141],"integration":[142],"efficient":[144],"binary":[145,181],"convolution.":[146],"We":[147,170],"also":[148],"provide":[149],"detailed":[151],"implementation":[152],"parallelization":[154],"optimization":[155],"optimally":[159],"utilize":[160],"memory":[162],"bandwidth":[163],"evaluate":[171],"AlexNet,":[174],"YOLOv2":[175],"Tiny":[176],"VGG16":[178],"version.":[182],"Our":[183],"experiment":[184],"results":[185],"show":[186],"can":[189],"significant":[191],"speedup":[192],"energy":[194],"efficiency":[195],"compared":[196],"state-of-the-art":[198],"frameworks":[199],"devices.":[202]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}