{"id":"https://openalex.org/W4400682050","doi":"https://doi.org/10.1145/3672198.3673799","title":"TCCL: Co-optimizing Collective Communication and Traffic Routing for GPU-centric Clusters","display_name":"TCCL: Co-optimizing Collective Communication and Traffic Routing for GPU-centric Clusters","publication_year":2024,"publication_date":"2024-07-16","ids":{"openalex":"https://openalex.org/W4400682050","doi":"https://doi.org/10.1145/3672198.3673799"},"language":"en","primary_location":{"id":"doi:10.1145/3672198.3673799","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3672198.3673799","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/A5109171475","display_name":"Baojia Li","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Baojia Li","raw_affiliation_strings":["Tencent"],"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100369115","display_name":"Xiaoliang Wang","orcid":"https://orcid.org/0000-0002-5380-4489"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoliang Wang","raw_affiliation_strings":["Nanjing University"],"affiliations":[{"raw_affiliation_string":"Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102124350","display_name":"Jingzhu Wang","orcid":"https://orcid.org/0009-0007-5759-470X"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingzhu Wang","raw_affiliation_strings":["Tencent"],"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102718804","display_name":"Yifan Liu","orcid":"https://orcid.org/0009-0000-8809-3165"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Liu","raw_affiliation_strings":["Nanjing University","Tencent"],"affiliations":[{"raw_affiliation_string":"Nanjing University","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100561101","display_name":"Yuanyuan Gong","orcid":"https://orcid.org/0000-0002-2442-9894"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanyuan Gong","raw_affiliation_strings":["Tencent"],"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100537728","display_name":"Hao Lu","orcid":"https://orcid.org/0000-0002-3783-1348"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Lu","raw_affiliation_strings":["Tencent"],"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005159389","display_name":"Weizhen Dang","orcid":"https://orcid.org/0000-0003-2390-7978"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weizhen Dang","raw_affiliation_strings":["Tencent"],"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056028084","display_name":"Weifeng Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weifeng Zhang","raw_affiliation_strings":["Tencent"],"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108955875","display_name":"Xiaojie Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojie Huang","raw_affiliation_strings":["Tencent"],"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114192049","display_name":"Mingzhuo Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingzhuo Chen","raw_affiliation_strings":["Tencent"],"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103468553","display_name":"Jie Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Chen","raw_affiliation_strings":["Tencent"],"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061163569","display_name":"Chunzhi He","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunzhi He","raw_affiliation_strings":["Tencent"],"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109747634","display_name":"Yadong Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yadong Liu","raw_affiliation_strings":["Nanjing University","Tencent"],"affiliations":[{"raw_affiliation_string":"Nanjing University","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000261720","display_name":"Xiaoyuan Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyuan Hu","raw_affiliation_strings":["Tencent"],"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069890367","display_name":"Chen Liu","orcid":"https://orcid.org/0009-0008-9163-0492"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Liu","raw_affiliation_strings":["Tencent"],"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038443691","display_name":"Xuefeng Ji","orcid":"https://orcid.org/0000-0001-9848-7993"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuefeng Ji","raw_affiliation_strings":["Tencent"],"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019928403","display_name":"Yinben Xia","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinben Xia","raw_affiliation_strings":["Tencent"],"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100745285","display_name":"Xiang Li","orcid":"https://orcid.org/0009-0009-0556-5290"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Li","raw_affiliation_strings":["Tencent"],"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008004626","display_name":"Zekun He","orcid":"https://orcid.org/0009-0000-8020-0595"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zekun He","raw_affiliation_strings":["Tencent"],"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014928826","display_name":"Yachen Wang","orcid":"https://orcid.org/0009-0003-3669-1202"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yachen Wang","raw_affiliation_strings":["Tencent"],"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074492571","display_name":"Xianneng Zou","orcid":"https://orcid.org/0009-0005-5370-8162"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianneng Zou","raw_affiliation_strings":["Tencent"],"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":21,"corresponding_author_ids":["https://openalex.org/A5109171475"],"corresponding_institution_ids":["https://openalex.org/I2250653659"],"apc_list":null,"apc_paid":null,"fwci":1.502,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.8303994,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"48","last_page":"53"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.9973999857902527,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9973999857902527,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9923999905586243,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9883000254631042,"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":0.7655527591705322},{"id":"https://openalex.org/keywords/routing","display_name":"Routing (electronic design automation)","score":0.5245875716209412},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.4586517810821533},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.39768826961517334},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3255218267440796}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7655527591705322},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.5245875716209412},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.4586517810821533},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.39768826961517334},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3255218267440796}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3672198.3673799","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3672198.3673799","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":[{"display_name":"Reduced inequalities","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W2169246522","https://openalex.org/W2567693223","https://openalex.org/W3175449831","https://openalex.org/W3192114749","https://openalex.org/W4235732943","https://openalex.org/W4318541593","https://openalex.org/W4362566357"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"GPU-centric":[0,88,99,125],"clusters":[1],"are":[2],"increasingly":[3],"deployed":[4],"to":[5,42,71,86],"support":[6],"many":[7],"AI":[8],"services":[9],"including":[10],"the":[11,20,30,33,46,53,59,109,116,121,124,130,142],"task":[12],"of":[13,32,104,123,133,144],"large":[14],"language":[15],"model":[16],"(LLM)":[17],"training.":[18],"Notably,":[19],"corresponding":[21],"networks":[22,89,100,138],"have":[23],"demonstrated":[24],"multiple":[25],"new":[26,64],"characteristics,":[27],"such":[28],"as":[29],"boundary":[31],"network":[34,41,60,69,154],"operation":[35],"has":[36],"been":[37],"extended":[38],"from":[39],"switch":[40,137],"GPU":[43,94,135],"interconnection":[44],"network;":[45],"communication":[47,107,146],"pattern":[48],"is":[49,55],"regular":[50],"and":[51,66,111,136,152],"predictable;":[52],"training":[54],"easily":[56],"affected":[57],"by":[58,157],"jitters.":[61],"These":[62],"introduce":[63],"challenges":[65],"opportunities":[67],"for":[68],"operators":[70],"build":[72],"high-performance":[73],"resilient":[74],"networking":[75],"systems.":[76],"In":[77],"this":[78],"paper,":[79],"we":[80],"present":[81],"TCCL,":[82],"an":[83],"operational":[84],"practice":[85],"manage":[87],"with":[90,147],"over":[91],"10K":[92],"heterogeneous":[93],"cards.":[95],"We":[96],"argue":[97],"that":[98],"require":[101],"joint":[102],"optimization":[103],"topology-aware":[105],"collective":[106,145],"at":[108],"host":[110],"centralized":[112],"routing":[113],"management":[114],"in":[115,139],"multi-path":[117],"network.":[118],"By":[119],"leveraging":[120],"characteristics":[122],"network,":[126],"TCCL":[127],"fully":[128],"utilizes":[129],"high":[131],"bandwidth":[132],"both":[134],"parallel,":[140],"reduces":[141],"delay":[143],"short":[148],"paths":[149],"across":[150],"nodes,":[151],"avoids":[153],"congestion":[155],"caused":[156],"route":[158],"conflict":[159],"through":[160],"traffic":[161],"planning.":[162]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}
