{"id":"https://openalex.org/W4401176799","doi":"https://doi.org/10.1145/3651890.3672265","title":"Alibaba HPN: A Data Center Network for Large Language Model Training","display_name":"Alibaba HPN: A Data Center Network for Large Language Model Training","publication_year":2024,"publication_date":"2024-07-31","ids":{"openalex":"https://openalex.org/W4401176799","doi":"https://doi.org/10.1145/3651890.3672265"},"language":"en","primary_location":{"id":"doi:10.1145/3651890.3672265","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3651890.3672265","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM SIGCOMM 2024 Conference","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/A5008523628","display_name":"Kun Qian","orcid":"https://orcid.org/0000-0001-9882-9279"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kun Qian","raw_affiliation_strings":["Alibaba Cloud, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Cloud, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072932748","display_name":"Yongqing Xi","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongqing Xi","raw_affiliation_strings":["Alibaba Cloud, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Cloud, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114200761","display_name":"Jiamin Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiamin Cao","raw_affiliation_strings":["Alibaba Cloud, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Cloud, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050612924","display_name":"Jiaqi Gao","orcid":"https://orcid.org/0000-0003-3548-2030"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]},{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiaqi Gao","raw_affiliation_strings":["Alibaba Cloud, Bellevue, USA"],"affiliations":[{"raw_affiliation_string":"Alibaba Cloud, Bellevue, USA","institution_ids":["https://openalex.org/I4210095624","https://openalex.org/I4210108985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048809434","display_name":"Yichi Xu","orcid":"https://orcid.org/0000-0002-7436-171X"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yichi Xu","raw_affiliation_strings":["Alibaba Cloud, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Cloud, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000348407","display_name":"Yu Guan","orcid":"https://orcid.org/0000-0002-0726-3933"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Guan","raw_affiliation_strings":["Alibaba Cloud, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Cloud, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006224078","display_name":"Binzhang Fu","orcid":"https://orcid.org/0009-0008-1213-0554"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Binzhang Fu","raw_affiliation_strings":["Alibaba Cloud, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Cloud, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072738452","display_name":"Xuemei Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuemei Shi","raw_affiliation_strings":["Alibaba Cloud, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Cloud, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Fangbo Zhu","orcid":"https://orcid.org/0009-0008-9592-0438"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangbo Zhu","raw_affiliation_strings":["Alibaba Cloud, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Cloud, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045286171","display_name":"Rui Miao","orcid":"https://orcid.org/0000-0002-1436-2374"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rui Miao","raw_affiliation_strings":["Alibaba Cloud, Sunnyvale, USA"],"affiliations":[{"raw_affiliation_string":"Alibaba Cloud, Sunnyvale, USA","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101116608","display_name":"Chao Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Wang","raw_affiliation_strings":["Alibaba Cloud, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Cloud, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Peng Wang","orcid":"https://orcid.org/0009-0005-3743-8596"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Wang","raw_affiliation_strings":["Alibaba Cloud, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Cloud, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101406782","display_name":"Pengcheng Zhang","orcid":"https://orcid.org/0009-0001-6740-227X"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengcheng Zhang","raw_affiliation_strings":["Alibaba Cloud, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Cloud, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109756297","display_name":"Xianlong Zeng","orcid":"https://orcid.org/0009-0008-2015-189X"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianlong Zeng","raw_affiliation_strings":["Alibaba Cloud, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Cloud, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050073015","display_name":"Eddie Ruan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eddie Ruan","raw_affiliation_strings":["Alibaba Cloud, Sunnyvale, USA"],"affiliations":[{"raw_affiliation_string":"Alibaba Cloud, Sunnyvale, USA","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104165651","display_name":"Zhiping Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiping Yao","raw_affiliation_strings":["Alibaba Cloud, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Cloud, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103040133","display_name":"Ennan Zhai","orcid":"https://orcid.org/0000-0003-4352-7497"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ennan Zhai","raw_affiliation_strings":["Alibaba Cloud, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Cloud, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043589586","display_name":"Dennis Cai","orcid":"https://orcid.org/0009-0001-7272-8143"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dennis Cai","raw_affiliation_strings":["Alibaba Cloud, Sunnyvale, United States of America"],"affiliations":[{"raw_affiliation_string":"Alibaba Cloud, Sunnyvale, United States of America","institution_ids":["https://openalex.org/I4210095624"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":18,"corresponding_author_ids":["https://openalex.org/A5008523628"],"corresponding_institution_ids":["https://openalex.org/I45928872"],"apc_list":null,"apc_paid":null,"fwci":71.763,"has_fulltext":false,"cited_by_count":95,"citation_normalized_percentile":{"value":0.99952436,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"691","last_page":"706"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9994000196456909,"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":0.9994000196456909,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9977999925613403,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9959999918937683,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7081571817398071},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5301671028137207},{"id":"https://openalex.org/keywords/center","display_name":"Center (category theory)","score":0.5148288607597351},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4770326316356659},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3770461976528168},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.27906328439712524}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7081571817398071},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5301671028137207},{"id":"https://openalex.org/C2779463800","wikidata":"https://www.wikidata.org/wiki/Q5062222","display_name":"Center (category theory)","level":2,"score":0.5148288607597351},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4770326316356659},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3770461976528168},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.27906328439712524},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C8010536","wikidata":"https://www.wikidata.org/wiki/Q160398","display_name":"Crystallography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3651890.3672265","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3651890.3672265","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM SIGCOMM 2024 Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6600000262260437,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1978175770","https://openalex.org/W2103110737","https://openalex.org/W2132320636","https://openalex.org/W2157614013","https://openalex.org/W2157990152","https://openalex.org/W2465793152","https://openalex.org/W2546660520","https://openalex.org/W2744567246","https://openalex.org/W2744698795","https://openalex.org/W4238465620","https://openalex.org/W4290990894","https://openalex.org/W4290991080","https://openalex.org/W4380874786","https://openalex.org/W4386365418"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W230091440","https://openalex.org/W2390279801","https://openalex.org/W2233261550","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2376932109"],"abstract_inverted_index":{"This":[0,59],"paper":[1],"presents":[2],"HPN,":[3,182],"Alibaba":[4],"Cloud's":[5],"data":[6,35,159],"center":[7,36,160],"network":[8],"for":[9,41,117,129,169],"large":[10],"language":[11],"model":[12],"(LLM)":[13],"training.":[14,43],"Due":[15],"to":[16,68,131,140,153],"the":[17,95,114,155,186],"differences":[18],"between":[19],"LLMs":[20],"and":[21,31,180],"general":[22],"cloud":[23],"computing":[24],"(e.g.,":[25,54],"in":[26,122,134,157,166,178,191],"terms":[27],"of":[28,50,61,85,189],"traffic":[29,76],"patterns":[30],"fault":[32],"tolerance),":[33],"traditional":[34,96,158],"networks":[37],"are":[38],"not":[39,105],"well-suited":[40],"LLM":[42,44,62,123],"training":[45,63,124],"produces":[46],"a":[47,80,101,149],"small":[48],"number":[49],"periodic,":[51],"bursty":[52],"flows":[53],"400Gbps)":[55],"on":[56,145],"each":[57],"host.":[58],"characteristic":[60],"predisposes":[64],"Equal-Cost":[65],"Multi-Path":[66],"(ECMP)":[67],"hash":[69,108],"polarization,":[70],"causing":[71],"issues":[72],"such":[73],"as":[74,183,185],"uneven":[75],"distribution.":[77],"HPN":[78,147,162,190],"introduces":[79],"2-tier,":[81],"dual-plane":[82],"architecture":[83,103],"capable":[84],"interconnecting":[86],"15K":[87],"GPUs":[88,130],"within":[89],"one":[90],"Pod,":[91],"typically":[92],"accommodated":[93],"by":[94],"3-tier":[97],"Clos":[98],"architecture.":[99],"Such":[100],"new":[102,150],"design":[104,152],"only":[106],"avoids":[107],"polarization":[109],"but":[110],"also":[111],"greatly":[112],"reduces":[113],"search":[115],"space":[116],"path":[118],"selection.":[119],"Another":[120],"challenge":[121],"is":[125],"that":[126],"its":[127],"requirement":[128],"complete":[132],"iterations":[133],"synchronization":[135],"makes":[136],"it":[137],"more":[138,170],"sensitive":[139],"singlepoint":[141],"failure":[142],"(typically":[143],"occurring":[144],"ToR).":[146],"proposes":[148],"dual-ToR":[151],"replace":[154],"single-ToR":[156],"networks.":[161],"has":[163],"been":[164],"deployed":[165],"our":[167,176],"production":[168],"than":[171],"eight":[172],"months.":[173],"We":[174],"share":[175],"experience":[177],"designing,":[179],"building":[181],"well":[184],"operational":[187],"lessons":[188],"production.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":11},{"year":2025,"cited_by_count":80},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
