{"id":"https://openalex.org/W4394922822","doi":"https://doi.org/10.1145/3627703.3629554","title":"Aceso: Efficient Parallel DNN Training through Iterative Bottleneck Alleviation","display_name":"Aceso: Efficient Parallel DNN Training through Iterative Bottleneck Alleviation","publication_year":2024,"publication_date":"2024-04-18","ids":{"openalex":"https://openalex.org/W4394922822","doi":"https://doi.org/10.1145/3627703.3629554"},"language":"en","primary_location":{"id":"doi:10.1145/3627703.3629554","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3627703.3629554","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Nineteenth European Conference on Computer Systems","raw_type":"proceedings-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/A5081827601","display_name":"G. H. Liu","orcid":"https://orcid.org/0000-0003-0335-9628"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Guodong Liu","raw_affiliation_strings":["State Key Lab of Processors, Institute of Computing Technology, CAS, Univ. of Chinese Academy of Sciences, and Microsoft Research (Asia)"],"affiliations":[{"raw_affiliation_string":"State Key Lab of Processors, Institute of Computing Technology, CAS, Univ. of Chinese Academy of Sciences, and Microsoft Research (Asia)","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038","https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075076538","display_name":"Youshan Miao","orcid":"https://orcid.org/0000-0002-2395-9965"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Youshan Miao","raw_affiliation_strings":["Microsoft Research"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027752718","display_name":"Zhiqi Lin","orcid":"https://orcid.org/0000-0002-8050-6196"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqi Lin","raw_affiliation_strings":["University of Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054091574","display_name":"Xiaoxiang Shi","orcid":"https://orcid.org/0009-0000-6840-4691"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoxiang Shi","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5095770941","display_name":"Saeed Maleki","orcid":"https://orcid.org/0000-0002-7998-3681"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Saeed Maleki","raw_affiliation_strings":["Microsoft Research"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100346602","display_name":"Fan Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Fan Yang","raw_affiliation_strings":["Microsoft Research"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101807410","display_name":"Yungang Bao","orcid":"https://orcid.org/0000-0001-6565-5276"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yungang Bao","raw_affiliation_strings":["State Key Lab of Processors, Institute of Computing Technology, CAS, Univ. of Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"State Key Lab of Processors, Institute of Computing Technology, CAS, Univ. of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033922611","display_name":"Sa Wang","orcid":"https://orcid.org/0000-0002-9629-0860"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sa Wang","raw_affiliation_strings":["State Key Lab of Processors, Institute of Computing Technology, CAS, Univ. of Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"State Key Lab of Processors, Institute of Computing Technology, CAS, Univ. of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5081827601"],"corresponding_institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210113369","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":1.9943,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.87180146,"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":"163","last_page":"181"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9995999932289124,"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":0.9995999932289124,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9962000250816345,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.992900013923645,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8597255945205688},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.8013908267021179},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.7733137011528015},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7394962906837463},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7256909608840942},{"id":"https://openalex.org/keywords/data-parallelism","display_name":"Data parallelism","score":0.6362970471382141},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.44061827659606934},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.41684532165527344},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34433192014694214},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.09298878908157349}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8597255945205688},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.8013908267021179},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.7733137011528015},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7394962906837463},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7256909608840942},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.6362970471382141},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.44061827659606934},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.41684532165527344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34433192014694214},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.09298878908157349},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3627703.3629554","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3627703.3629554","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Nineteenth European Conference on Computer Systems","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":30,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W2120432001","https://openalex.org/W2145406052","https://openalex.org/W2152558130","https://openalex.org/W2194775991","https://openalex.org/W2252170720","https://openalex.org/W2734941459","https://openalex.org/W2883830791","https://openalex.org/W2884700152","https://openalex.org/W2893813411","https://openalex.org/W2896167334","https://openalex.org/W2969388332","https://openalex.org/W2975712713","https://openalex.org/W2979044977","https://openalex.org/W2981852735","https://openalex.org/W2996063004","https://openalex.org/W3037639655","https://openalex.org/W3037847693","https://openalex.org/W3039050620","https://openalex.org/W3081168214","https://openalex.org/W3101104221","https://openalex.org/W3132107458","https://openalex.org/W3138516171","https://openalex.org/W3203426023","https://openalex.org/W3204998121","https://openalex.org/W3206832494","https://openalex.org/W4220741164","https://openalex.org/W4287750421","https://openalex.org/W4288089799","https://openalex.org/W4312349930"],"related_works":["https://openalex.org/W2950520577","https://openalex.org/W1554644772","https://openalex.org/W2003935582","https://openalex.org/W2494130044","https://openalex.org/W2033862586","https://openalex.org/W3170887803","https://openalex.org/W74409296","https://openalex.org/W3209384898","https://openalex.org/W4400951174","https://openalex.org/W141404642"],"abstract_inverted_index":{"Many":[0],"parallel":[1],"mechanisms,":[2],"including":[3],"data":[4],"parallelism,":[5,7,10],"tensor":[6],"and":[8,14,34],"pipeline":[9],"have":[11,55],"been":[12,56],"proposed":[13,57],"combined":[15],"together":[16],"to":[17,58,72],"support":[18],"training":[19],"increasingly":[20],"large":[21,73],"deep":[22],"neural":[23],"networks":[24],"(DNN)":[25],"on":[26],"massive":[27],"GPU":[28,35],"devices.":[29,77],"Given":[30],"a":[31,61],"DNN":[32],"model":[33],"cluster,":[36],"finding":[37],"the":[38],"optimal":[39],"configuration":[40,62],"by":[41],"combining":[42],"these":[43],"parallelism":[44],"mechanisms":[45],"is":[46],"an":[47],"NP-hard":[48],"problem.":[49],"Widely":[50],"adopted":[51],"mathematical":[52],"programming":[53],"approaches":[54],"search":[59],"in":[60],"subspace,":[63],"but":[64],"they":[65],"are":[66],"still":[67],"too":[68],"costly":[69],"when":[70],"scaling":[71],"models":[74],"over":[75],"numerous":[76]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}