{"id":"https://openalex.org/W4407197296","doi":"https://doi.org/10.1145/3669940.3707223","title":"Concerto: Automatic Communication Optimization and Scheduling for Large-Scale Deep Learning","display_name":"Concerto: Automatic Communication Optimization and Scheduling for Large-Scale Deep Learning","publication_year":2025,"publication_date":"2025-02-06","ids":{"openalex":"https://openalex.org/W4407197296","doi":"https://doi.org/10.1145/3669940.3707223"},"language":"en","primary_location":{"id":"doi:10.1145/3669940.3707223","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3669940.3707223","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 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 1","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3669940.3707223","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037038779","display_name":"Shenggan Cheng","orcid":"https://orcid.org/0000-0002-7966-2941"},"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":true,"raw_author_name":"Shenggan Cheng","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-7966-2941","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103636118","display_name":"Sheng-Jie Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shengjie Lin","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, USA"],"raw_orcid":"https://orcid.org/0009-0004-6794-9293","affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020574416","display_name":"Lansong Diao","orcid":"https://orcid.org/0009-0000-6193-6126"},"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":"Lansong Diao","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-6193-6126","affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109756842","display_name":"Hao Wu","orcid":"https://orcid.org/0009-0003-6318-4505"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Wu","raw_affiliation_strings":["George Mason University, Fairfax, USA"],"raw_orcid":"https://orcid.org/0009-0003-6318-4505","affiliations":[{"raw_affiliation_string":"George Mason University, Fairfax, USA","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103089036","display_name":"Siyu Wang","orcid":"https://orcid.org/0009-0002-4064-6984"},"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":"Siyu Wang","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-4064-6984","affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101049663","display_name":"Chang Si","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":"Chang Si","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-4612-7371","affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101924544","display_name":"Ziming Liu","orcid":"https://orcid.org/0009-0009-3355-6770"},"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":"Ziming Liu","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0009-3355-6770","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102796963","display_name":"Xuanlei Zhao","orcid":"https://orcid.org/0009-0000-4877-3115"},"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":"Xuanlei Zhao","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0000-4877-3115","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024085713","display_name":"Jiangsu Du","orcid":"https://orcid.org/0000-0003-4707-9492"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangsu Du","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-4707-9492","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100636012","display_name":"Wei Lin","orcid":"https://orcid.org/0000-0002-3003-0150"},"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":"Wei Lin","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-3003-0150","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100658705","display_name":"Yang You","orcid":"https://orcid.org/0000-0003-2816-4384"},"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":"Yang You","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-2816-4384","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5037038779"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":4.3093,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.91578406,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"198","last_page":"213"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994000196456909,"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":0.9975000023841858,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9919000267982483,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.7123871445655823},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5894024968147278},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4780564606189728},{"id":"https://openalex.org/keywords/concerto","display_name":"Concerto","score":0.47284772992134094},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47247833013534546},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.43503522872924805},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13393869996070862},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.07791069149971008},{"id":"https://openalex.org/keywords/piano","display_name":"Piano","score":0.06621354818344116},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.06534534692764282},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.06417721509933472},{"id":"https://openalex.org/keywords/operations-management","display_name":"Operations management","score":0.06364035606384277}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7123871445655823},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5894024968147278},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4780564606189728},{"id":"https://openalex.org/C40462162","wikidata":"https://www.wikidata.org/wiki/Q9748","display_name":"Concerto","level":3,"score":0.47284772992134094},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47247833013534546},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.43503522872924805},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13393869996070862},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.07791069149971008},{"id":"https://openalex.org/C124086623","wikidata":"https://www.wikidata.org/wiki/Q5994","display_name":"Piano","level":2,"score":0.06621354818344116},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.06534534692764282},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.06417721509933472},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.06364035606384277},{"id":"https://openalex.org/C52119013","wikidata":"https://www.wikidata.org/wiki/Q50637","display_name":"Art history","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3669940.3707223","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3669940.3707223","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 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 1","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3669940.3707223","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3669940.3707223","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 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 1","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W123670719","https://openalex.org/W2132777761","https://openalex.org/W2560452411","https://openalex.org/W2894576937","https://openalex.org/W2914209329","https://openalex.org/W2975712713","https://openalex.org/W3081168214","https://openalex.org/W3086105743","https://openalex.org/W3124352525","https://openalex.org/W3129831491","https://openalex.org/W3138516171","https://openalex.org/W3177828909","https://openalex.org/W3193985311","https://openalex.org/W3204998121","https://openalex.org/W3206832494","https://openalex.org/W3213101878","https://openalex.org/W4212986322","https://openalex.org/W4226199141","https://openalex.org/W4280611847","https://openalex.org/W4281758439","https://openalex.org/W4288093768","https://openalex.org/W4292779060","https://openalex.org/W4312060029","https://openalex.org/W4318541538","https://openalex.org/W4318541593","https://openalex.org/W4382202854","https://openalex.org/W4386348101","https://openalex.org/W4391952907","https://openalex.org/W4394998532","https://openalex.org/W4394998995","https://openalex.org/W6600662749","https://openalex.org/W6769475105"],"related_works":["https://openalex.org/W2731899572","https://openalex.org/W3215138031","https://openalex.org/W3009238340","https://openalex.org/W4360585206","https://openalex.org/W4321369474","https://openalex.org/W4285208911","https://openalex.org/W3082895349","https://openalex.org/W4213079790","https://openalex.org/W2248239756","https://openalex.org/W3086377361"],"abstract_inverted_index":{"With":[0],"the":[1,22,79,94,137],"exponential":[2],"growth":[3],"of":[4,52,126,150],"deep":[5],"learning":[6],"(DL),":[7],"there":[8],"arises":[9],"an":[10],"escalating":[11],"need":[12],"for":[13,104],"scalability.":[14],"Despite":[15],"significant":[16],"advancements":[17],"in":[18,50],"communication":[19,26,141],"hardware":[20],"capabilities,":[21],"time":[23],"consumed":[24],"by":[25,71],"remains":[27],"a":[28,63,83,147],"bottleneck":[29],"during":[30],"training.":[31],"The":[32],"existing":[33],"various":[34],"optimizations":[35],"are":[36],"coupled":[37],"within":[38],"parallel":[39,117,138],"systems":[40],"to":[41,67,92,100,146],"implement":[42],"specific":[43],"computation-communication":[44],"overlap.":[45],"These":[46],"approaches":[47],"pose":[48],"challenges":[49,70],"terms":[51],"performance,":[53],"programmability,":[54],"and":[55,74,88,123,140],"generality.":[56],"In":[57],"this":[58],"paper,":[59],"we":[60],"introduce":[61],"Concerto,":[62],"compiler":[64],"framework":[65],"designed":[66],"address":[68],"these":[69],"automatically":[72],"optimizing":[73],"scheduling":[75,80,86],"communication.":[76,107],"We":[77],"formulate":[78],"problem":[81,87],"as":[82],"resource-constrained":[84],"project":[85],"use":[89,98],"off-the-shelf":[90],"solver":[91],"get":[93],"near-optimal":[95],"scheduling.":[96],"And":[97],"auto-decomposition":[99],"create":[101],"overlap":[102],"opportunity":[103],"critical":[105],"(synchronous)":[106],"Our":[108],"evaluation":[109],"shows":[110],"Concerto":[111,135],"can":[112,144],"match":[113],"or":[114],"outperform":[115],"state-of-the-art":[116],"frameworks,":[118],"including":[119],"Megatron-LM,":[120],"JAX/XLA,":[121],"DeepSpeed,":[122],"Alpa,":[124],"all":[125],"which":[127],"include":[128],"extensive":[129],"hand-crafted":[130],"optimization.":[131,154],"Unlike":[132],"previous":[133],"works,":[134],"decouples":[136],"approach":[139],"optimization,":[142],"then":[143],"generalize":[145],"wide":[148],"variety":[149],"parallelisms":[151],"without":[152],"manual":[153]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}
