{"id":"https://openalex.org/W2886991855","doi":"https://doi.org/10.1109/ipdps.2018.00034","title":"BitFlow: Exploiting Vector Parallelism for Binary Neural Networks on CPU","display_name":"BitFlow: Exploiting Vector Parallelism for Binary Neural Networks on CPU","publication_year":2018,"publication_date":"2018-05-01","ids":{"openalex":"https://openalex.org/W2886991855","doi":"https://doi.org/10.1109/ipdps.2018.00034","mag":"2886991855"},"language":"en","primary_location":{"id":"doi:10.1109/ipdps.2018.00034","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2018.00034","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Parallel and Distributed Processing Symposium (IPDPS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101586926","display_name":"Yuwei Hu","orcid":"https://orcid.org/0000-0002-2698-6811"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuwei Hu","raw_affiliation_strings":["TuSimple Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TuSimple Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071200777","display_name":"Jidong Zhai","orcid":"https://orcid.org/0000-0002-7656-6428"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jidong Zhai","raw_affiliation_strings":["Department of Computer Science, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076464969","display_name":"Dinghua Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dinghua Li","raw_affiliation_strings":["TuSimple Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TuSimple Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077401426","display_name":"Yifan Gong","orcid":"https://orcid.org/0000-0001-8786-3391"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yifan Gong","raw_affiliation_strings":["TuSimple Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TuSimple Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023684582","display_name":"Yuhao Zhu","orcid":"https://orcid.org/0000-0002-2802-0578"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuhao Zhu","raw_affiliation_strings":["Department of Computer Science, University of Rochester"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Rochester","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100641708","display_name":"Wei Liu","orcid":"https://orcid.org/0000-0002-2237-3655"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Liu","raw_affiliation_strings":["TuSimple Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TuSimple Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062117879","display_name":"Lei Su","orcid":"https://orcid.org/0000-0003-1190-5916"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Su","raw_affiliation_strings":["TuSimple Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TuSimple Inc","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031914716","display_name":"Jiangming Jin","orcid":"https://orcid.org/0000-0001-7552-6937"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiangming Jin","raw_affiliation_strings":["TuSimple Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TuSimple Inc","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"244","last_page":"253"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8356035947799683},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.8335916996002197},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7526172399520874},{"id":"https://openalex.org/keywords/bitwise-operation","display_name":"Bitwise operation","score":0.6720433235168457},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.5794185400009155},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.5349510908126831},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.489869087934494},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.4830482602119446},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.4816909730434418},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.4776969254016876},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46810007095336914},{"id":"https://openalex.org/keywords/coprocessor","display_name":"Coprocessor","score":0.42697176337242126},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3063310384750366},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25258582830429077},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.13750463724136353},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09154358506202698}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8356035947799683},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8335916996002197},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7526172399520874},{"id":"https://openalex.org/C134765980","wikidata":"https://www.wikidata.org/wiki/Q879126","display_name":"Bitwise operation","level":2,"score":0.6720433235168457},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.5794185400009155},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.5349510908126831},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.489869087934494},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.4830482602119446},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.4816909730434418},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.4776969254016876},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46810007095336914},{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.42697176337242126},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3063310384750366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25258582830429077},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.13750463724136353},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09154358506202698},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipdps.2018.00034","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2018.00034","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Parallel and Distributed Processing Symposium (IPDPS)","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":38,"referenced_works":["https://openalex.org/W1481935768","https://openalex.org/W1597968260","https://openalex.org/W1686810756","https://openalex.org/W1825532946","https://openalex.org/W1902934009","https://openalex.org/W1939907483","https://openalex.org/W2010128395","https://openalex.org/W2013305145","https://openalex.org/W2107307723","https://openalex.org/W2114508814","https://openalex.org/W2120385681","https://openalex.org/W2148461049","https://openalex.org/W2155893237","https://openalex.org/W2156163116","https://openalex.org/W2186615578","https://openalex.org/W2208150243","https://openalex.org/W2252007067","https://openalex.org/W2260663238","https://openalex.org/W2300242332","https://openalex.org/W2469490737","https://openalex.org/W2565125333","https://openalex.org/W2585560244","https://openalex.org/W2591066391","https://openalex.org/W2591922920","https://openalex.org/W2618591429","https://openalex.org/W2753301142","https://openalex.org/W2756779681","https://openalex.org/W2951978180","https://openalex.org/W2952750617","https://openalex.org/W2962835968","https://openalex.org/W2963114950","https://openalex.org/W2963309490","https://openalex.org/W2963619462","https://openalex.org/W2963674932","https://openalex.org/W3102169921","https://openalex.org/W4293867778","https://openalex.org/W6640546891","https://openalex.org/W6764512221"],"related_works":["https://openalex.org/W2137567370","https://openalex.org/W1988690899","https://openalex.org/W2282045800","https://openalex.org/W2085105049","https://openalex.org/W3203561460","https://openalex.org/W4251138667","https://openalex.org/W3009624197","https://openalex.org/W1969709731","https://openalex.org/W2682544458","https://openalex.org/W2943610686"],"abstract_inverted_index":{"Deep":[0,21],"learning":[1],"has":[2],"revolutionized":[3],"computer":[4],"vision":[5],"and":[6,61,79,119,145],"other":[7],"fields":[8],"since":[9],"its":[10],"big":[11],"bang":[12],"in":[13],"2012.":[14],"However,":[15],"it":[16],"is":[17],"challenging":[18],"to":[19,29,75,158],"deploy":[20],"Neural":[22,35],"Networks":[23,36],"(DNNs)":[24],"into":[25],"real-world":[26],"applications":[27],"due":[28,74],"their":[30],"high":[31],"computational":[32,40],"complexity.":[33],"Binary":[34],"(BNNs)":[37],"dramatically":[38],"reduce":[39],"complexity":[41],"by":[42],"replacing":[43],"most":[44],"arithmetic":[45,77],"operations":[46],"with":[47,125],"bitwise":[48,83],"operations.":[49,84],"Existing":[50],"implementations":[51],"of":[52,99,108,133],"BNNs":[53,100,157],"have":[54],"been":[55],"focusing":[56],"on":[57,101,166],"GPU":[58,167],"or":[59],"FPGA,":[60],"using":[62,116],"the":[63,96,126],"conventional":[64],"image-to-column":[65],"method":[66],"that":[67],"doesn't":[68],"perform":[69],"well":[70],"for":[71,82,93,112],"binary":[72,114],"convolution":[73,115],"low":[76],"intensity":[78],"unfriendly":[80],"pattern":[81],"We":[85,122],"propose":[86],"BitFlow,":[87],"a":[88,105,130],"gemm-operator-network":[89],"three-level":[90],"optimization":[91],"framework":[92],"fully":[94],"exploiting":[95],"computing":[97],"power":[98],"CPU.":[102],"BitFlow":[103,124,137,155],"features":[104],"new":[106],"class":[107],"algorithm":[109],"named":[110],"PressedConv":[111],"efficient":[113],"locality-aware":[117],"layout":[118],"vector":[120],"parallelism.":[121],"evaluate":[123],"VGG":[127],"network.":[128],"On":[129],"single":[131],"core":[132],"Intel":[134],"Xeon":[135],"Phi,":[136],"obtains":[138],"1.8x":[139],"speedup":[140,147],"over":[141,148],"unoptimized":[142],"BNN":[143],"implementations,":[144],"11.5x":[146],"counterpart":[149,163],"full-precision":[150,164],"DNNs.":[151],"Over":[152],"64":[153],"cores,":[154],"enables":[156],"run":[159],"1.1x":[160],"faster":[161],"than":[162],"DNNs":[165],"(GTX":[168],"1080).":[169]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}