{"id":"https://openalex.org/W4393213046","doi":"https://doi.org/10.1145/3767295.3803571","title":"Arena: Efficiently Training Large Models via Dynamic Scheduling and Adaptive Parallelism Co-Design","display_name":"Arena: Efficiently Training Large Models via Dynamic Scheduling and Adaptive Parallelism Co-Design","publication_year":2026,"publication_date":"2026-04-24","ids":{"openalex":"https://openalex.org/W4393213046","doi":"https://doi.org/10.1145/3767295.3803571"},"language":"en","primary_location":{"id":"doi:10.1145/3767295.3803571","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767295.3803571","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st European Conference on Computer Systems","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3767295.3803571","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111875369","display_name":"Chunyu Xue","orcid":null},"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":true,"raw_author_name":"Chunyu Xue","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0008-9272-1732","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008837660","display_name":"Weihao Cui","orcid":"https://orcid.org/0000-0002-6646-5260"},"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":"Weihao Cui","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-6646-5260","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Quan Chen","orcid":"https://orcid.org/0000-0001-5832-0347"},"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":"Quan Chen","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-5832-0347","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chen Chen","orcid":"https://orcid.org/0000-0001-9480-5632"},"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":"Chen Chen","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-9480-5632","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Han Zhao","orcid":"https://orcid.org/0000-0002-1561-5329"},"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":"Han Zhao","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-1561-5329","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shulai Zhang","orcid":"https://orcid.org/0000-0002-0802-7203"},"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":"Shulai Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-0802-7203","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Linmei Wang","orcid":"https://orcid.org/0009-0006-7089-9199"},"institutions":[{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linmei Wang","raw_affiliation_strings":["Lenovo Research, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-7089-9199","affiliations":[{"raw_affiliation_string":"Lenovo Research, Beijing, China","institution_ids":["https://openalex.org/I4210156165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100354322","display_name":"Shaobo Li","orcid":"https://orcid.org/0000-0003-4759-6000"},"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":"Yan Li","raw_affiliation_strings":["Microsoft, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-4063-0772","affiliations":[{"raw_affiliation_string":"Microsoft, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Limin Xiao","orcid":"https://orcid.org/0000-0001-9438-9181"},"institutions":[{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Limin Xiao","raw_affiliation_strings":["Lenovo Research, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9438-9181","affiliations":[{"raw_affiliation_string":"Lenovo Research, Beijing, China","institution_ids":["https://openalex.org/I4210156165"]}]},{"author_position":"middle","author":{"id":null,"display_name":"WeiFeng Zhang","orcid":"https://orcid.org/0000-0002-4529-1679"},"institutions":[{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"WeiFeng Zhang","raw_affiliation_strings":["Lenovo Research, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4529-1679","affiliations":[{"raw_affiliation_string":"Lenovo Research, Beijing, China","institution_ids":["https://openalex.org/I4210156165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068498375","display_name":"Jing Yang","orcid":"https://orcid.org/0000-0003-4664-5528"},"institutions":[{"id":"https://openalex.org/I178232147","display_name":"Guizhou University","ror":"https://ror.org/02wmsc916","country_code":"CN","type":"education","lineage":["https://openalex.org/I178232147"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Yang","raw_affiliation_strings":["Guizhou University, Guiyang, Guizhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1915-9487","affiliations":[{"raw_affiliation_string":"Guizhou University, Guiyang, Guizhou, China","institution_ids":["https://openalex.org/I178232147"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Bingsheng He","orcid":"https://orcid.org/0000-0001-8618-4581"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Bingsheng He","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-8618-4581","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039318240","display_name":"Minyi Guo","orcid":"https://orcid.org/0000-0003-0034-2302"},"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":"Minyi Guo","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-0034-2302","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":13,"corresponding_author_ids":["https://openalex.org/A5111875369"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00141346,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"89","last_page":"107"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9315000176429749,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9315000176429749,"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/parallel-computing","display_name":"Parallel computing","score":0.7031494975090027},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6992720365524292},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6145225167274475},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.43778735399246216},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.38992375135421753},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.37569037079811096},{"id":"https://openalex.org/keywords/operations-management","display_name":"Operations management","score":0.0981670618057251},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0797756016254425},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.056221842765808105}],"concepts":[{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7031494975090027},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6992720365524292},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6145225167274475},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.43778735399246216},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.38992375135421753},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.37569037079811096},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0981670618057251},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0797756016254425},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.056221842765808105},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3767295.3803571","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767295.3803571","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st European Conference on Computer Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2403.16125","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.16125","pdf_url":"https://arxiv.org/pdf/2403.16125","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2403.16125","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2403.16125","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1145/3767295.3803571","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767295.3803571","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st European Conference on Computer Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2495260952","https://openalex.org/W4366179611","https://openalex.org/W2996078371"],"abstract_inverted_index":{"Efficiently":[0],"training":[1,58],"large-scale":[2],"models":[3],"(LMs)":[4],"in":[5,112],"GPU":[6],"clusters":[7],"involves":[8],"two":[9],"separate":[10],"avenues:":[11],"inter-job":[12],"dynamic":[13,22,62],"scheduling":[14,27,36,63,74],"and":[15,37,48,64,85,114,117,131,143],"intra-job":[16],"adaptive":[17,65],"parallelism":[18,34,66],"(AP).":[19],"However,":[20],"existing":[21],"schedulers":[23],"struggle":[24],"with":[25,123],"large-model":[26,57],"due":[28],"to":[29,41,67,141,149],"the":[30,95],"mismatch":[31],"between":[32],"static":[33],"(SP)-aware":[35],"AP-based":[38],"execution,":[39],"leading":[40],"cluster":[42,70,145],"inefficiencies":[43],"such":[44],"as":[45],"degraded":[46],"throughput":[47,146],"prolonged":[49],"job":[50,136],"queuing.":[51],"This":[52],"paper":[53],"presents":[54],"Arena,":[55],"a":[56,101],"system":[59],"that":[60],"co-designs":[61],"achieve":[68],"high":[69],"efficiency.":[71],"To":[72],"reduce":[73],"costs":[75],"while":[76,90],"improving":[77],"decision":[78],"quality,":[79],"Arena":[80,107,134],"designs":[81],"low-cost,":[82],"disaggregated":[83],"profiling":[84],"AP-tailored,":[86],"load-aware":[87],"performance":[88],"estimation,":[89],"unifying":[91],"them":[92,119],"by":[93,139,147],"sharding":[94],"joint":[96],"scheduling-parallelism":[97],"optimization":[98],"space":[99],"via":[100],"grid":[102],"abstraction.":[103],"Building":[104],"on":[105,128],"this,":[106],"dynamically":[108],"schedules":[109],"profiled":[110],"jobs":[111],"elasticity":[113],"heterogeneity":[115],"dimensions,":[116],"executes":[118],"using":[120],"efficient":[121],"AP":[122],"pruned":[124],"search":[125],"space.":[126],"Evaluated":[127],"heterogeneous":[129],"testbeds":[130],"production":[132],"workloads,":[133],"reduces":[135],"completion":[137],"time":[138],"up":[140,148],"49.3%":[142],"improves":[144],"1.6X.":[150]},"counts_by_year":[],"updated_date":"2026-04-26T06:01:38.667478","created_date":"2024-03-27T00:00:00"}
