{"id":"https://openalex.org/W4408893341","doi":"https://doi.org/10.1145/3676641.3715992","title":"Spindle: Efficient Distributed Training of Multi-Task Large Models via Wavefront Scheduling","display_name":"Spindle: Efficient Distributed Training of Multi-Task Large Models via Wavefront Scheduling","publication_year":2025,"publication_date":"2025-03-27","ids":{"openalex":"https://openalex.org/W4408893341","doi":"https://doi.org/10.1145/3676641.3715992"},"language":"en","primary_location":{"id":"doi:10.1145/3676641.3715992","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3676641.3715992","pdf_url":null,"source":null,"license":null,"license_id":null,"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 2","raw_type":"proceedings-article"},"type":"conference-paper","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/A5103276362","display_name":"Y X Wang","orcid":"https://orcid.org/0009-0000-8375-493X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yujie Wang","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-8375-493X","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016753128","display_name":"Shenhan Zhu","orcid":"https://orcid.org/0009-0004-0267-775X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shenhan Zhu","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-0267-775X","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039254679","display_name":"Fangcheng Fu","orcid":"https://orcid.org/0000-0003-1658-0380"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangcheng Fu","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1658-0380","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015552951","display_name":"Xupeng Miao","orcid":"https://orcid.org/0000-0002-9371-8358"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xupeng Miao","raw_affiliation_strings":["Purdue University, West Lafayette, IN, USA"],"raw_orcid":"https://orcid.org/0000-0002-9371-8358","affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jie Zhang","orcid":"https://orcid.org/0009-0003-5085-2535"},"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":"Jie Zhang","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-5085-2535","affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113534113","display_name":"Juan Zhu","orcid":"https://orcid.org/0009-0008-3318-1393"},"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":"Juan Zhu","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-3318-1393","affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101724996","display_name":"Fan Hong","orcid":"https://orcid.org/0000-0001-9698-2886"},"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":"Fan Hong","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9698-2886","affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092212363","display_name":"Yong Li","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":"Yong Li","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9072-3170","affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062357883","display_name":"Bin Cui","orcid":"https://orcid.org/0000-0003-1681-4677"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Cui","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1681-4677","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":31.107,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.99641395,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1139","last_page":"1155"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9950000047683716,"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"}},{"id":"https://openalex.org/T10888","display_name":"Augmented Reality Applications","score":0.993399977684021,"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":0.7834110260009766},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6080525517463684},{"id":"https://openalex.org/keywords/wavefront","display_name":"Wavefront","score":0.5927243828773499},{"id":"https://openalex.org/keywords/processor-scheduling","display_name":"Processor scheduling","score":0.5125601291656494},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.48693549633026123},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.47130143642425537},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3543076515197754},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.12784060835838318},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08098110556602478},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.07213875651359558}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7834110260009766},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6080525517463684},{"id":"https://openalex.org/C165699331","wikidata":"https://www.wikidata.org/wiki/Q461533","display_name":"Wavefront","level":2,"score":0.5927243828773499},{"id":"https://openalex.org/C2984822820","wikidata":"https://www.wikidata.org/wiki/Q1123036","display_name":"Processor scheduling","level":3,"score":0.5125601291656494},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.48693549633026123},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.47130143642425537},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3543076515197754},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.12784060835838318},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08098110556602478},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.07213875651359558},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3676641.3715992","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3676641.3715992","pdf_url":null,"source":null,"license":null,"license_id":null,"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 2","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W98859305","https://openalex.org/W398859631","https://openalex.org/W2024961395","https://openalex.org/W2560674852","https://openalex.org/W2734941459","https://openalex.org/W2798515322","https://openalex.org/W2962725887","https://openalex.org/W2969388332","https://openalex.org/W3081168214","https://openalex.org/W3086105743","https://openalex.org/W3129831491","https://openalex.org/W3138516171","https://openalex.org/W3176445421","https://openalex.org/W3177263144","https://openalex.org/W3187255235","https://openalex.org/W3203711169","https://openalex.org/W4205983429","https://openalex.org/W4214612132","https://openalex.org/W4246298309","https://openalex.org/W4247469449","https://openalex.org/W4254240460","https://openalex.org/W4287235399","https://openalex.org/W4310282800","https://openalex.org/W4311001273","https://openalex.org/W4312747027","https://openalex.org/W4366850747","https://openalex.org/W4372262787","https://openalex.org/W4372267410","https://openalex.org/W4381551031","https://openalex.org/W4383749415","https://openalex.org/W4384918448","https://openalex.org/W4386071687","https://openalex.org/W4386185600","https://openalex.org/W4386768656","https://openalex.org/W4390041933","https://openalex.org/W4392207935","https://openalex.org/W7093349750"],"related_works":["https://openalex.org/W1809394610","https://openalex.org/W2128410848","https://openalex.org/W2118368532","https://openalex.org/W2014085448","https://openalex.org/W2102390841","https://openalex.org/W3047653192","https://openalex.org/W2096289371","https://openalex.org/W2126232624","https://openalex.org/W2434525066","https://openalex.org/W3140149227"],"abstract_inverted_index":{"Recent":[0],"foundation":[1],"models":[2,33,73],"are":[3],"capable":[4],"of":[5,27,48,70,80,125],"handling":[6],"multiple":[7,10],"tasks":[8,50],"and":[9,19,44,51,67,90,102,110,123],"data":[11],"modalities":[12],"with":[13,127],"the":[14,40,45,85,92,120],"unified":[15],"base":[16],"model":[17,22,42,86],"structure":[18],"several":[20],"specialized":[21],"components.":[23],"However,":[24],"efficient":[25],"training":[26,62,69,136],"such":[28],"multi-task":[29],"(MT)":[30],"multi-modal":[31],"(MM)":[32],"poses":[34],"significant":[35],"system":[36,63,109],"challenges":[37],"due":[38],"to":[39,83,131,134],"sophisticated":[41],"architecture":[43],"heterogeneous":[46],"workloads":[47],"different":[49],"modalities.":[52],"In":[53],"this":[54],"paper,":[55],"we":[56],"propose":[57],"Spindle,":[58,126],"a":[59],"brand":[60],"new":[61],"tailored":[64],"for":[65],"resource-efficient":[66],"high-performance":[68],"MT":[71,115],"MM":[72,116],"via":[74],"wavefront":[75],"scheduling.":[76,105],"The":[77],"key":[78],"idea":[79],"Spindle":[81],"is":[82],"decompose":[84],"execution":[87,104],"into":[88],"waves":[89],"address":[91],"joint":[93],"optimization":[94],"problem":[95],"sequentially,":[96],"including":[97],"both":[98],"heterogeneity-aware":[99],"workload":[100],"parallelization":[101],"dependency-driven":[103],"We":[106],"build":[107],"our":[108],"evaluate":[111],"it":[112],"on":[113],"various":[114],"models.":[117],"Experiments":[118],"demonstrate":[119],"superior":[121],"performance":[122],"efficiency":[124],"speedup":[128],"ratio":[129],"up":[130],"71%":[132],"compared":[133],"state-of-the-art":[135],"systems.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}