{"id":"https://openalex.org/W4410949929","doi":"https://doi.org/10.1109/tetc.2025.3573522","title":"PipeDAP: An Efficient Communication Framework for Scheduling Decoupled All-Reduce Primitives in Distributed DNN Training","display_name":"PipeDAP: An Efficient Communication Framework for Scheduling Decoupled All-Reduce Primitives in Distributed DNN Training","publication_year":2025,"publication_date":"2025-06-02","ids":{"openalex":"https://openalex.org/W4410949929","doi":"https://doi.org/10.1109/tetc.2025.3573522"},"language":"en","primary_location":{"id":"doi:10.1109/tetc.2025.3573522","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetc.2025.3573522","pdf_url":null,"source":{"id":"https://openalex.org/S2496326734","display_name":"IEEE Transactions on Emerging Topics in Computing","issn_l":"2168-6750","issn":["2168-6750","2376-4562"],"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 Emerging Topics in Computing","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/A5011127712","display_name":"Yunqi Gao","orcid":"https://orcid.org/0009-0003-0599-8383"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunqi Gao","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0003-0599-8383","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102834373","display_name":"Bing Hu","orcid":"https://orcid.org/0000-0002-0594-8998"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Hu","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-0594-8998","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028862760","display_name":"Mahdi Boloursaz Mashhadi","orcid":"https://orcid.org/0000-0001-9948-9165"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mahdi Boloursaz Mashhadi","raw_affiliation_strings":["5GIC &#x0026; 6GIC, Institute for Communication Systems (ICS), University of Surrey, Guildford, U.K"],"raw_orcid":"https://orcid.org/0000-0001-9948-9165","affiliations":[{"raw_affiliation_string":"5GIC &#x0026; 6GIC, Institute for Communication Systems (ICS), University of Surrey, Guildford, U.K","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100392219","display_name":"Wei Wang","orcid":"https://orcid.org/0000-0003-2153-9075"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Wang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2153-9075","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032549075","display_name":"Rahim Tafazolli","orcid":"https://orcid.org/0000-0002-6062-8639"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Rahim Tafazolli","raw_affiliation_strings":["5GIC &#x0026; 6GIC, Institute for Communication Systems (ICS), University of Surrey, Guildford, U.K"],"raw_orcid":"https://orcid.org/0000-0002-6062-8639","affiliations":[{"raw_affiliation_string":"5GIC &#x0026; 6GIC, Institute for Communication Systems (ICS), University of Surrey, Guildford, U.K","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056145687","display_name":"M\u00e9rouane Debbah","orcid":"https://orcid.org/0000-0001-8941-8080"},"institutions":[{"id":"https://openalex.org/I176601375","display_name":"Khalifa University of Science and Technology","ror":"https://ror.org/05hffr360","country_code":"AE","type":"education","lineage":["https://openalex.org/I176601375"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"M\u00e9rouane Debbah","raw_affiliation_strings":["KU 6G Research Center, Department of Computer and Information Engineering, Khalifa University, Abu Dhabi, UAE"],"raw_orcid":"https://orcid.org/0000-0001-8941-8080","affiliations":[{"raw_affiliation_string":"KU 6G Research Center, Department of Computer and Information Engineering, Khalifa University, Abu Dhabi, UAE","institution_ids":["https://openalex.org/I176601375"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9389,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.75878932,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"13","issue":"3","first_page":"1170","last_page":"1184"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.9883999824523926,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9793999791145325,"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":0.8761799335479736},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6408698558807373},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5980455875396729},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.45408371090888977},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.4518267512321472},{"id":"https://openalex.org/keywords/processor-scheduling","display_name":"Processor scheduling","score":0.42770156264305115},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.10255640745162964}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8761799335479736},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6408698558807373},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5980455875396729},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.45408371090888977},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.4518267512321472},{"id":"https://openalex.org/C2984822820","wikidata":"https://www.wikidata.org/wiki/Q1123036","display_name":"Processor scheduling","level":3,"score":0.42770156264305115},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.10255640745162964},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tetc.2025.3573522","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetc.2025.3573522","pdf_url":null,"source":{"id":"https://openalex.org/S2496326734","display_name":"IEEE Transactions on Emerging Topics in Computing","issn_l":"2168-6750","issn":["2168-6750","2376-4562"],"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 Emerging Topics in Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6284364839","display_name":null,"funder_award_id":"202406320382","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"}],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2083842231","https://openalex.org/W2108598243","https://openalex.org/W2186615578","https://openalex.org/W2194775991","https://openalex.org/W2535374105","https://openalex.org/W2580688187","https://openalex.org/W2622263826","https://openalex.org/W2884711234","https://openalex.org/W2896457183","https://openalex.org/W2901541570","https://openalex.org/W2919632853","https://openalex.org/W2920397365","https://openalex.org/W2963786636","https://openalex.org/W2969388332","https://openalex.org/W2973727699","https://openalex.org/W2975712713","https://openalex.org/W2982475424","https://openalex.org/W3039165326","https://openalex.org/W3047537431","https://openalex.org/W3193250980","https://openalex.org/W3193985311","https://openalex.org/W3203336515","https://openalex.org/W4283217358","https://openalex.org/W4292779060","https://openalex.org/W4301239768","https://openalex.org/W4387544258","https://openalex.org/W4388544075","https://openalex.org/W4390660070","https://openalex.org/W4399694321","https://openalex.org/W4401024791"],"related_works":["https://openalex.org/W2128410848","https://openalex.org/W2118368532","https://openalex.org/W2102390841","https://openalex.org/W3047653192","https://openalex.org/W2096289371","https://openalex.org/W2126232624","https://openalex.org/W2434525066","https://openalex.org/W3140149227","https://openalex.org/W2946406471","https://openalex.org/W2130555437"],"abstract_inverted_index":{"Communication":[0],"scheduling":[1,21,62,110,179],"effectively":[2],"improves":[3],"the":[4,36,54,90,101,108,113,131,136,176],"scalability":[5],"of":[6,95,112,123,148,171],"distributed":[7,146],"deep":[8],"learning":[9],"by":[10],"overlapping":[11],"computation":[12],"and":[13,49,92,106,115,125,142,166],"communication":[14,20,55,75,122,178],"tasks":[15],"during":[16],"training.":[17],"However,":[18],"existing":[19],"frameworks":[22],"based":[23],"on":[24,139,154],"tensor":[25],"partitioning":[26,33,51],"suffer":[27],"from":[28],"two":[29,155],"fundamental":[30],"issues:":[31],"(1)":[32],"schemes":[34,52],"at":[35,53,185],"data":[37],"volume":[38],"level":[39,57],"introduce":[40],"extensive":[41],"startup":[42,132],"overheads":[43],"leading":[44],"to":[45,88,128,163,169,175],"higher":[46],"energy":[47,93,172],"consumption,":[48],"(2)":[50],"primitive":[56],"do":[58],"not":[59],"provide":[60],"optimal":[61],"resulting":[63],"in":[64,84],"longer":[65],"training":[66,96,147],"time.":[67],"In":[68],"this":[69],"paper,":[70],"we":[71,119],"propose":[72],"an":[73],"efficient":[74],"mechanism,":[76],"namely":[77],"PipeDAP,":[78],"which":[79],"schedules":[80],"decoupled":[81],"all-reduce":[82],"operations":[83,127],"a":[85],"near-optimal":[86,109],"order":[87,111],"minimize":[89],"time":[91],"consumption":[94,173],"DNN":[97,150],"models.":[98,151],"We":[99,134],"build":[100],"mathematical":[102],"model":[103],"for":[104,145],"PipeDAP":[105,137,160],"derive":[107],"reduce-scatter":[114,124],"all-gather":[116,126],"operations.":[117],"Meanwhile,":[118],"leverage":[120],"simultaneous":[121],"further":[129],"reduce":[130],"overheads.":[133],"implement":[135],"architecture":[138],"PyTorch":[140],"framework,":[141],"apply":[143],"it":[144],"benchmark":[149],"Experimental":[152],"results":[153],"GPU":[156],"clusters":[157],"demonstrate":[158],"that":[159],"achieves":[161],"up":[162,168],"1.82x":[164],"speedup":[165],"saves":[167],"45.4%":[170],"compared":[174],"state-of-the-art":[177],"frameworks.":[180],"PipeDAP's":[181],"code":[182],"is":[183],"available":[184],"<uri":[186],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[187],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/ZJU-CNLAB/PipeDAP</uri>.":[188]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
