{"id":"https://openalex.org/W2975712713","doi":"https://doi.org/10.1145/3341301.3359642","title":"A generic communication scheduler for distributed DNN training acceleration","display_name":"A generic communication scheduler for distributed DNN training acceleration","publication_year":2019,"publication_date":"2019-10-21","ids":{"openalex":"https://openalex.org/W2975712713","doi":"https://doi.org/10.1145/3341301.3359642","mag":"2975712713"},"language":"en","primary_location":{"id":"doi:10.1145/3341301.3359642","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3341301.3359642","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM Symposium on Operating Systems Principles","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/A5013856812","display_name":"Yanghua Peng","orcid":"https://orcid.org/0000-0003-3989-4358"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yanghua Peng","raw_affiliation_strings":["The University of Hong Kong and ByteDance Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong and ByteDance Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028120333","display_name":"Yibo Zhu","orcid":"https://orcid.org/0000-0002-9113-2660"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yibo Zhu","raw_affiliation_strings":["ByteDance Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062504314","display_name":"Yangrui Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yangrui Chen","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054679083","display_name":"Yixin Bao","orcid":"https://orcid.org/0000-0002-6921-2154"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yixin Bao","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057151557","display_name":"Bairen Yi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bairen Yi","raw_affiliation_strings":["ByteDance Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112577748","display_name":"Chang Lan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chang Lan","raw_affiliation_strings":["ByteDance Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012597518","display_name":"Chuan Wu","orcid":"https://orcid.org/0000-0002-3144-4398"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chuan Wu","raw_affiliation_strings":["ByteDance Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Inc","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054205326","display_name":"Chuanxiong Guo","orcid":"https://orcid.org/0000-0002-0730-8468"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chuanxiong Guo","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5013856812"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":17.6653,"has_fulltext":false,"cited_by_count":318,"citation_normalized_percentile":{"value":0.99330033,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"16","last_page":"29"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9926000237464905,"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/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9901000261306763,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8659221529960632},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.6237435340881348},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5928632020950317},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.46014416217803955},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.442755788564682},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.34839266538619995}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8659221529960632},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6237435340881348},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5928632020950317},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.46014416217803955},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.442755788564682},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.34839266538619995},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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:10.1145/3341301.3359642","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3341301.3359642","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM Symposium on Operating Systems Principles","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1984788566","https://openalex.org/W2060393849","https://openalex.org/W2078945459","https://openalex.org/W2083842231","https://openalex.org/W2099201756","https://openalex.org/W2112474496","https://openalex.org/W2132737349","https://openalex.org/W2149939304","https://openalex.org/W2155893237","https://openalex.org/W2163605009","https://openalex.org/W2168231600","https://openalex.org/W2186615578","https://openalex.org/W2194775991","https://openalex.org/W2513383847","https://openalex.org/W2604856537","https://openalex.org/W2617766261","https://openalex.org/W2740001873","https://openalex.org/W2742145794","https://openalex.org/W2751343396","https://openalex.org/W2769644379","https://openalex.org/W2790598069","https://openalex.org/W2798515322","https://openalex.org/W2883830791","https://openalex.org/W2899771611","https://openalex.org/W2919594608","https://openalex.org/W2944793600","https://openalex.org/W2950182411","https://openalex.org/W2953384591","https://openalex.org/W2962758826","https://openalex.org/W2963288913","https://openalex.org/W3037875189","https://openalex.org/W3101104221","https://openalex.org/W4232940466","https://openalex.org/W6684859321","https://openalex.org/W6713134421"],"related_works":["https://openalex.org/W2045155990","https://openalex.org/W4313163053","https://openalex.org/W4300973204","https://openalex.org/W1483408780","https://openalex.org/W4284884309","https://openalex.org/W4243842598","https://openalex.org/W2105980483","https://openalex.org/W2007666006","https://openalex.org/W2062712797","https://openalex.org/W2393232088"],"abstract_inverted_index":{"We":[0,74],"present":[1],"ByteScheduler,":[2],"a":[3,54,58,77],"generic":[4],"communication":[5,64],"scheduler":[6],"for":[7,47,89,120],"distributed":[8],"DNN":[9,49,141],"training":[10,50,91,134],"acceleration.":[11],"ByteScheduler":[12,44,97,132],"is":[13],"based":[14],"on":[15],"our":[16],"principled":[17],"analysis":[18],"that":[19,131],"partitioning":[20],"and":[21,33,57,86,102,109,117,140],"rearranging":[22],"the":[23,68],"tensor":[24,83],"transmissions":[25],"can":[26],"result":[27],"in":[28,31,36,71],"optimal":[29],"results":[30],"theory":[32],"good":[34],"performance":[35],"real-world":[37],"even":[38],"with":[39,112,135],"scheduling":[40,65],"overhead.":[41],"To":[42],"make":[43],"work":[45],"generally":[46],"various":[48,94],"frameworks,":[51],"we":[52],"introduce":[53,76],"unified":[55],"abstraction":[56],"Dependency":[59],"Proxy":[60],"mechanism":[61],"to":[62,81,145],"enable":[63],"without":[66,104],"breaking":[67],"original":[69,150],"dependencies":[70],"framework":[72],"engines.":[73],"further":[75],"Bayesian":[78],"Optimization":[79],"approach":[80],"auto-tune":[82],"partition":[84],"size":[85],"other":[87],"parameters":[88],"different":[90],"models":[92],"under":[93],"networking":[95],"conditions.":[96],"now":[98],"supports":[99],"TensorFlow,":[100],"PyTorch,":[101],"MXNet":[103],"modifying":[105],"their":[106],"source":[107],"code,":[108],"works":[110],"well":[111],"both":[113],"Parameter":[114],"Server":[115],"(PS)":[116],"all-reduce":[118],"architectures":[119],"gradient":[121],"synchronization,":[122],"using":[123],"either":[124],"TCP":[125],"or":[126],"RDMA.":[127],"Our":[128],"experiments":[129],"show":[130],"accelerates":[133],"all":[136],"experimented":[137],"system":[138],"configurations":[139],"models,":[142],"by":[143],"up":[144],"196%":[146],"(or":[147],"2.96X":[148],"of":[149],"speed).":[151]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":42},{"year":2024,"cited_by_count":52},{"year":2023,"cited_by_count":44},{"year":2022,"cited_by_count":43},{"year":2021,"cited_by_count":71},{"year":2020,"cited_by_count":56},{"year":2019,"cited_by_count":3}],"updated_date":"2026-04-25T08:17:42.794288","created_date":"2025-10-10T00:00:00"}