{"id":"https://openalex.org/W3211483916","doi":"https://doi.org/10.1109/dac18074.2021.9586300","title":"Training Acceleration for Deep Neural Networks: A Hybrid Parallelization Strategy","display_name":"Training Acceleration for Deep Neural Networks: A Hybrid Parallelization Strategy","publication_year":2021,"publication_date":"2021-11-08","ids":{"openalex":"https://openalex.org/W3211483916","doi":"https://doi.org/10.1109/dac18074.2021.9586300","mag":"3211483916"},"language":"en","primary_location":{"id":"doi:10.1109/dac18074.2021.9586300","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac18074.2021.9586300","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 58th ACM/IEEE Design Automation Conference (DAC)","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/A5043552523","display_name":"Zihao Zeng","orcid":"https://orcid.org/0000-0002-4745-5331"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihao Zeng","raw_affiliation_strings":["College of Information Science and Engineering, Hunan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Hunan University, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006345319","display_name":"Chubo Liu","orcid":"https://orcid.org/0000-0002-2372-6715"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chubo Liu","raw_affiliation_strings":["College of Information Science and Engineering, Hunan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Hunan University, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008574161","display_name":"Zhuo Tang","orcid":"https://orcid.org/0000-0001-9081-8153"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuo Tang","raw_affiliation_strings":["College of Information Science and Engineering, Hunan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Hunan University, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072023674","display_name":"Wanli Chang","orcid":"https://orcid.org/0000-0002-4053-8898"},"institutions":[{"id":"https://openalex.org/I52099693","display_name":"University of York","ror":"https://ror.org/04m01e293","country_code":"GB","type":"education","lineage":["https://openalex.org/I52099693"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wanli Chang","raw_affiliation_strings":["University of York, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of York, UK","institution_ids":["https://openalex.org/I52099693"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078793726","display_name":"Kenli Li","orcid":"https://orcid.org/0000-0002-2635-7716"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kenli Li","raw_affiliation_strings":["College of Information Science and Engineering, Hunan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Hunan University, China","institution_ids":["https://openalex.org/I16609230"]}]}],"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":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1165","last_page":"1170"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9980999827384949,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9976999759674072,"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":0.892603874206543},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7057602405548096},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.6394450068473816},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5385881662368774},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5213795304298401},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5067289471626282},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.49301812052726746},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.4767645001411438},{"id":"https://openalex.org/keywords/data-parallelism","display_name":"Data parallelism","score":0.4750535488128662},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.44954437017440796},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4408086836338043},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.40714094042778015},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23733744025230408},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08869403600692749}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.892603874206543},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7057602405548096},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.6394450068473816},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5385881662368774},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5213795304298401},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5067289471626282},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.49301812052726746},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.4767645001411438},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.4750535488128662},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44954437017440796},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4408086836338043},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.40714094042778015},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23733744025230408},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08869403600692749},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dac18074.2021.9586300","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac18074.2021.9586300","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 58th ACM/IEEE Design Automation Conference (DAC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W1598866093","https://openalex.org/W1686810756","https://openalex.org/W2150856297","https://openalex.org/W2163605009","https://openalex.org/W2168231600","https://openalex.org/W2617766261","https://openalex.org/W2787998955","https://openalex.org/W2962934715","https://openalex.org/W2963351145","https://openalex.org/W2963358710","https://openalex.org/W2964004663","https://openalex.org/W2969388332","https://openalex.org/W2980268386","https://openalex.org/W2985738161","https://openalex.org/W2991040477","https://openalex.org/W3011751313","https://openalex.org/W4288094025","https://openalex.org/W4301239768","https://openalex.org/W6600983433","https://openalex.org/W6635810480","https://openalex.org/W6637373629","https://openalex.org/W6684191040","https://openalex.org/W6684859321","https://openalex.org/W6738460352","https://openalex.org/W6748645090","https://openalex.org/W6756379755","https://openalex.org/W6756718674","https://openalex.org/W6769275798","https://openalex.org/W6769865700"],"related_works":["https://openalex.org/W2950520577","https://openalex.org/W1554644772","https://openalex.org/W2003935582","https://openalex.org/W2494130044","https://openalex.org/W2177838837","https://openalex.org/W2963831937","https://openalex.org/W3209384898","https://openalex.org/W74409296","https://openalex.org/W1991844655","https://openalex.org/W1595834484"],"abstract_inverted_index":{"Deep":[0],"Neural":[1],"Networks":[2],"(DNNs)":[3],"are":[4],"widely":[5],"investigated":[6],"due":[7],"to":[8,35,47,71,139,153,155,168,181,186],"their":[9],"striking":[10],"performance":[11,103],"in":[12,53,81,84],"various":[13],"applications":[14],"of":[15,28,40,61,107,119,134,144,150,161],"artificial":[16],"intelligence.":[17],"However,":[18,83],"with":[19],"DNNs":[20],"becoming":[21],"larger":[22],"and":[23,64,92,98,104,136,165,183,191],"deeper,":[24],"the":[25,37,62,73,102,116,120,148,158,169],"computing":[26],"resource":[27,105],"a":[29,54,58,65,125,132,141,162],"single":[30],"hardware":[31],"accelerator":[32],"is":[33,45,69],"insufficient":[34],"meet":[36],"training":[38,143,178],"requirements":[39],"popular":[41],"DNNs.":[42,145],"Hence,":[43],"it":[44,68],"required":[46],"train":[48],"them":[49],"using":[50,112],"multiple":[51],"accelerators":[52,63],"distributed":[55,142],"setting.":[56],"For":[57],"better":[59],"utilization":[60,106],"faster":[66],"training,":[67],"necessary":[70],"partition":[72],"whole":[74],"process":[75],"into":[76],"segments":[77],"that":[78,130,175],"can":[79],"run":[80],"parallel.":[82],"this":[85],"context,":[86],"intra-layer":[87,135,192],"parallelization":[88,109,128,196],"techniques":[89,110,197],"(i.e.,":[90,111,189,193],"data":[91,194],"model":[93,164],"parallelization)":[94],"often":[95],"face":[96],"communication":[97],"memory":[99],"bottlenecks,":[100],"while":[101],"inter-layer":[108,137,188],"pipelining)":[113],"depend":[114],"on":[115],"partitioning":[117,160],"possibilities":[118],"model.":[121],"We":[122],"present":[123],"EffTra,":[124],"synchronous":[126],"hybrid":[127],"strategy,":[129],"uses":[131],"combination":[133],"parallelism":[138],"realize":[140],"EffTra":[146,176],"employs":[147],"idea":[149],"dynamic":[151],"programming":[152],"try":[154],"search":[156],"for":[157],"optimal":[159],"DNN":[163],"assigns":[166],"devices":[167],"obtained":[170],"partitions.":[171],"Our":[172],"evaluation":[173],"shows":[174],"accelerates":[177],"by":[179],"up":[180],"2.0x":[182],"1.78x":[184],"compared":[185],"state-of-the-art":[187],"GPipe)":[190],"parallelism)":[195],"respectively.":[198]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}