{"id":"https://openalex.org/W2885661469","doi":"https://doi.org/10.1109/tpds.2018.2864299","title":"HyConv: Accelerating Multi-Phase CNN Computation by Fine-Grained Policy Selection","display_name":"HyConv: Accelerating Multi-Phase CNN Computation by Fine-Grained Policy Selection","publication_year":2018,"publication_date":"2018-08-07","ids":{"openalex":"https://openalex.org/W2885661469","doi":"https://doi.org/10.1109/tpds.2018.2864299","mag":"2885661469"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2018.2864299","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2018.2864299","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"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 Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},"type":"article","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/A5063860382","display_name":"Xiaqing Li","orcid":"https://orcid.org/0000-0002-7748-7967"},"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":"Xiaqing Li","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102854878","display_name":"Guangyan Zhang","orcid":"https://orcid.org/0000-0002-3480-5902"},"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":"Guangyan Zhang","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3480-5902","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022698382","display_name":"Zhufan Wang","orcid":null},"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":"Zhufan Wang","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108050911","display_name":"Weimin Zheng","orcid":"https://orcid.org/0000-0002-4450-5428"},"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":"Weimin Zheng","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.5202,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.70635169,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"30","issue":"2","first_page":"388","last_page":"399"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9980999827384949,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9952999949455261,"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":0.8958456516265869},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.7693622708320618},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7405039668083191},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.7215747833251953},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6019530296325684},{"id":"https://openalex.org/keywords/usability","display_name":"Usability","score":0.5909250974655151},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.48645517230033875},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4476878345012665},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.4109612703323364},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.40865352749824524},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3694896996021271},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3540528416633606},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.353410542011261},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.32587891817092896},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27036434412002563},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2609426975250244},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.12904465198516846},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10055747628211975}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8958456516265869},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.7693622708320618},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7405039668083191},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.7215747833251953},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6019530296325684},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.5909250974655151},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.48645517230033875},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4476878345012665},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4109612703323364},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.40865352749824524},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3694896996021271},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3540528416633606},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.353410542011261},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32587891817092896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27036434412002563},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2609426975250244},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.12904465198516846},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10055747628211975}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2018.2864299","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2018.2864299","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"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 Transactions on Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6518094076","display_name":"\u8d44\u6e90\u5168\u5c40\u5171\u4eab\u7684\u5b58\u50a8\u9635\u5217\u5173\u952e\u6280\u672f\u7814\u7a76","funder_award_id":"61672315","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W753012316","https://openalex.org/W1524680991","https://openalex.org/W1536680647","https://openalex.org/W1667652561","https://openalex.org/W1677182931","https://openalex.org/W1686810756","https://openalex.org/W1789336918","https://openalex.org/W1833917188","https://openalex.org/W1849277567","https://openalex.org/W1931639407","https://openalex.org/W2009832130","https://openalex.org/W2060393849","https://openalex.org/W2062118960","https://openalex.org/W2070192690","https://openalex.org/W2083842231","https://openalex.org/W2097117768","https://openalex.org/W2102605133","https://openalex.org/W2109255472","https://openalex.org/W2112739286","https://openalex.org/W2112796928","https://openalex.org/W2112980946","https://openalex.org/W2125203716","https://openalex.org/W2147414309","https://openalex.org/W2152175008","https://openalex.org/W2152839228","https://openalex.org/W2153579005","https://openalex.org/W2155541015","https://openalex.org/W2155893237","https://openalex.org/W2162390675","https://openalex.org/W2163605009","https://openalex.org/W2168231600","https://openalex.org/W2193413348","https://openalex.org/W2339765813","https://openalex.org/W2521727659","https://openalex.org/W2613718673","https://openalex.org/W2962835968","https://openalex.org/W2963340555","https://openalex.org/W2963367891","https://openalex.org/W2963542991","https://openalex.org/W4212788319","https://openalex.org/W4294170691","https://openalex.org/W4294375521","https://openalex.org/W4302296459","https://openalex.org/W4383818563","https://openalex.org/W6620707391","https://openalex.org/W6622239757","https://openalex.org/W6629368666","https://openalex.org/W6637151318","https://openalex.org/W6637373629","https://openalex.org/W6638020065","https://openalex.org/W6638533276","https://openalex.org/W6639204139","https://openalex.org/W6640442106","https://openalex.org/W6682691769","https://openalex.org/W6682778277","https://openalex.org/W6683722107","https://openalex.org/W6684191040","https://openalex.org/W6684859321","https://openalex.org/W6687566353"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2027972911","https://openalex.org/W2146343568","https://openalex.org/W2013643406","https://openalex.org/W2157978810","https://openalex.org/W3157543420","https://openalex.org/W2115380918"],"abstract_inverted_index":{"Existing":[0],"GPU-based":[1],"approaches":[2,124],"cannot":[3],"yet":[4],"meet":[5],"the":[6,22,38,42,73,95,104,115,168],"performance":[7,159],"requirement":[8],"for":[9,83,103,160],"training":[10,23],"very":[11],"large":[12],"convolutional":[13,18],"neural":[14],"networks":[15],"(CNNs),":[16],"where":[17],"layers":[19],"(Conv-layers)":[20],"dominate":[21],"time.":[24],"In":[25],"this":[26],"paper,":[27],"we":[28,46],"find":[29],"that":[30,112,154],"no":[31],"single":[32,128,163],"convolution":[33,64],"policy":[34,59,75],"can":[35,148],"always":[36],"perform":[37],"fastest":[39,74],"across":[40],"all":[41,114],"computing":[43,84],"phases.":[44],"Then,":[45],"propose":[47],"an":[48],"approach":[49],"called":[50],"HyConv":[51,61,88,120,155,166],"to":[52,93,137,141,170],"accelerating":[53],"multi-phase":[54],"CNN":[55,118],"computation":[56],"by":[57,151],"fine-grained":[58],"selection.":[60],"encapsulates":[62],"existing":[63,123],"policies":[65],"into":[66],"a":[67,90,127],"set":[68],"of":[69,135,162],"modules,":[70],"and":[71,139,176],"selects":[72],"(a.k.a.,":[76],"winner":[77,91,97],"policy)":[78],"via":[79],"one-round":[80],"runtime":[81],"measurement":[82,101],"each":[85],"phase.":[86],"Furthermore,":[87,165],"uses":[89],"database":[92],"record":[94],"current":[96],"policies,":[98],"avoiding":[99],"duplicate":[100],"later":[102],"same":[105],"parameter":[106,174],"configuration.":[107],"Our":[108],"experimental":[109],"results":[110],"indicate":[111],"over":[113,143],"used":[116],"real-world":[117],"networks,":[119],"consistently":[121],"outperforms":[122],"on":[125],"either":[126],"GPU":[129],"or":[130],"four":[131],"GPUs,":[132],"with":[133,172],"speedups":[134],"up":[136,140],"3.3\u00d7":[138],"1.6\u00d7":[142],"cuDNN-MM":[144],"respectively.":[145],"Such":[146],"improvement":[147],"be":[149],"explained":[150],"our":[152],"result":[153],"delivers":[156],"obviously":[157],"better":[158,179],"most":[161],"Conv-layers.":[164],"has":[167],"ability":[169],"work":[171],"any":[173],"configuration":[175],"thus":[177],"keeps":[178],"usability.":[180]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}