{"id":"https://openalex.org/W4400682099","doi":"https://doi.org/10.1145/3672198.3673794","title":"Network Load Balancing with Parallel Flowlets for AI Training Clusters","display_name":"Network Load Balancing with Parallel Flowlets for AI Training Clusters","publication_year":2024,"publication_date":"2024-07-16","ids":{"openalex":"https://openalex.org/W4400682099","doi":"https://doi.org/10.1145/3672198.3673794"},"language":"en","primary_location":{"id":"doi:10.1145/3672198.3673794","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3672198.3673794","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 SIGCOMM Workshop on Networks for AI Computing","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/A5070612714","display_name":"Peirui Cao","orcid":"https://orcid.org/0000-0002-0222-4943"},"institutions":[{"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"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Peirui Cao","raw_affiliation_strings":["Microsoft Research Asia and Shanghai Jiao Tong university"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia and Shanghai Jiao Tong university","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024806055","display_name":"Wenxue Cheng","orcid":"https://orcid.org/0000-0001-6984-8913"},"institutions":[{"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenxue Cheng","raw_affiliation_strings":["Microsoft Research Asia"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075325244","display_name":"Shizhen Zhao","orcid":"https://orcid.org/0000-0001-8395-5109"},"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":"Shizhen Zhao","raw_affiliation_strings":["Shanghai Jiao Tong university"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong university","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100735357","display_name":"Yongqiang Xiong","orcid":"https://orcid.org/0000-0003-4175-0097"},"institutions":[{"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongqiang Xiong","raw_affiliation_strings":["Microsoft Research Asia"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5070612714"],"corresponding_institution_ids":["https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":4.5926,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.94994969,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"18","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9957000017166138,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9941999912261963,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7699007987976074},{"id":"https://openalex.org/keywords/load-balancing","display_name":"Load balancing (electrical power)","score":0.5671040415763855},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5284939408302307},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5006430149078369},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.37654587626457214},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06133154034614563}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7699007987976074},{"id":"https://openalex.org/C138959212","wikidata":"https://www.wikidata.org/wiki/Q1806783","display_name":"Load balancing (electrical power)","level":3,"score":0.5671040415763855},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5284939408302307},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5006430149078369},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.37654587626457214},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06133154034614563},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3672198.3673794","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3672198.3673794","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 SIGCOMM Workshop on Networks for AI Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1500155703","display_name":null,"funder_award_id":"62272292","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W1988150362","https://openalex.org/W2062362478","https://openalex.org/W2087178199","https://openalex.org/W2130531694","https://openalex.org/W2132320636","https://openalex.org/W2157990152","https://openalex.org/W2169246522","https://openalex.org/W2465793152","https://openalex.org/W2498764059","https://openalex.org/W2605280586","https://openalex.org/W2744567246","https://openalex.org/W2899540012","https://openalex.org/W2964412985","https://openalex.org/W2968108410","https://openalex.org/W3049093198","https://openalex.org/W3072623287","https://openalex.org/W3129488589","https://openalex.org/W3132727954","https://openalex.org/W3175449831","https://openalex.org/W3197167724","https://openalex.org/W4200617671","https://openalex.org/W4290991080","https://openalex.org/W4300973219","https://openalex.org/W4362566357","https://openalex.org/W4365790307","https://openalex.org/W4386385105","https://openalex.org/W4389989040","https://openalex.org/W6750532562","https://openalex.org/W7005924706"],"related_works":["https://openalex.org/W3004117068","https://openalex.org/W2043284556","https://openalex.org/W3175372827","https://openalex.org/W2488220206","https://openalex.org/W2146301767","https://openalex.org/W191730236","https://openalex.org/W4384948837","https://openalex.org/W4312680855","https://openalex.org/W3191990038","https://openalex.org/W1524016490"],"abstract_inverted_index":{"Unlike":[0],"traditional":[1],"data":[2],"center":[3],"traffic,":[4],"AI":[5,60],"training":[6,61],"traffic":[7],"primarily":[8],"consists":[9],"of":[10],"large-size":[11],"flows":[12],"that":[13],"are":[14,56],"fewer":[15],"in":[16,23,30,44],"number.":[17],"This":[18],"characteristic":[19],"poses":[20],"a":[21,41],"challenge":[22],"balancing":[24],"routing":[25,32],"granularity":[26],"with":[27,63],"reorder":[28],"overhead":[29],"existing":[31],"strategies.":[33],"Existing":[34],"serial":[35],"flowlet":[36],"schemes":[37],"aim":[38],"to":[39],"achieve":[40],"better":[42],"trade-off":[43],"TCP":[45],"scenarios":[46],"than":[47],"flow-level":[48],"or":[49],"packet":[50],"spraying":[51],"load":[52],"balancing.":[53],"However,":[54],"they":[55],"not":[57],"well-suited":[58],"for":[59],"clusters":[62],"high-performance":[64],"RDMA":[65],"networks.":[66]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}