{"id":"https://openalex.org/W4414736061","doi":"https://doi.org/10.1145/3731569.3764839","title":"Sailor: Automating Distributed Training over Dynamic, Heterogeneous, and Geo-distributed Clusters","display_name":"Sailor: Automating Distributed Training over Dynamic, Heterogeneous, and Geo-distributed Clusters","publication_year":2025,"publication_date":"2025-10-01","ids":{"openalex":"https://openalex.org/W4414736061","doi":"https://doi.org/10.1145/3731569.3764839"},"language":"en","primary_location":{"id":"doi:10.1145/3731569.3764839","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731569.3764839","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 ACM SIGOPS 31st Symposium on Operating Systems Principles","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3731569.3764839","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049951876","display_name":"Foteini Strati","orcid":"https://orcid.org/0000-0003-3364-2109"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Foteini Strati","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0003-3364-2109","affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102907609","display_name":"Zhendong Zhang","orcid":"https://orcid.org/0009-0007-0843-6457"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Zhendong Zhang","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0009-0007-0843-6457","affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119806979","display_name":"George Manos","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"George Manos","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0009-0002-5767-8325","affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071352480","display_name":"Ixeia S\u00e1nchez P\u00e9riz","orcid":"https://orcid.org/0000-0002-1810-353X"},"institutions":[{"id":"https://openalex.org/I4210114961","display_name":"The Geneva Association","ror":"https://ror.org/02hrbfc73","country_code":"CH","type":"nonprofit","lineage":["https://openalex.org/I4210114961"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Ixeia S\u00e1nchez P\u00e9riz","raw_affiliation_strings":["Unaffiliated, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-1810-353X","affiliations":[{"raw_affiliation_string":"Unaffiliated, Zurich, Switzerland","institution_ids":["https://openalex.org/I4210114961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035921543","display_name":"Qinghao Hu","orcid":"https://orcid.org/0000-0003-1034-7502"},"institutions":[{"id":"https://openalex.org/I4210110987","display_name":"IIT@MIT","ror":"https://ror.org/01wp8zh54","country_code":"US","type":"facility","lineage":["https://openalex.org/I30771326","https://openalex.org/I4210110987"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qinghao Hu","raw_affiliation_strings":["MIT, Cambridge, USA"],"raw_orcid":"https://orcid.org/0000-0003-1034-7502","affiliations":[{"raw_affiliation_string":"MIT, Cambridge, USA","institution_ids":["https://openalex.org/I4210110987"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015040114","display_name":"Tiancheng Chen","orcid":"https://orcid.org/0009-0002-8071-2552"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Tiancheng Chen","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0009-0002-8071-2552","affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007778213","display_name":"Berk Buzcu","orcid":"https://orcid.org/0000-0003-1320-8006"},"institutions":[{"id":"https://openalex.org/I4210129267","display_name":"HES-SO Valais-Wallis","ror":"https://ror.org/03r5zec51","country_code":"CH","type":"education","lineage":["https://openalex.org/I173439891","https://openalex.org/I4210129267"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Berk Buzcu","raw_affiliation_strings":["HES-SO Valais/Wallis, Sierre, Switzerland"],"raw_orcid":"https://orcid.org/0000-0003-1320-8006","affiliations":[{"raw_affiliation_string":"HES-SO Valais/Wallis, Sierre, Switzerland","institution_ids":["https://openalex.org/I4210129267"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070926896","display_name":"Song Han","orcid":"https://orcid.org/0000-0002-4186-7618"},"institutions":[{"id":"https://openalex.org/I4210110987","display_name":"IIT@MIT","ror":"https://ror.org/01wp8zh54","country_code":"US","type":"facility","lineage":["https://openalex.org/I30771326","https://openalex.org/I4210110987"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Song Han","raw_affiliation_strings":["MIT, Cambridge, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-4186-7618","affiliations":[{"raw_affiliation_string":"MIT, Cambridge, Switzerland","institution_ids":["https://openalex.org/I4210110987"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047900768","display_name":"Pamela Delgado","orcid":"https://orcid.org/0000-0002-9187-8497"},"institutions":[{"id":"https://openalex.org/I4210129267","display_name":"HES-SO Valais-Wallis","ror":"https://ror.org/03r5zec51","country_code":"CH","type":"education","lineage":["https://openalex.org/I173439891","https://openalex.org/I4210129267"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Pamela Delgado","raw_affiliation_strings":["HES-SO Valais/Wallis, Sierre, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-9187-8497","affiliations":[{"raw_affiliation_string":"HES-SO Valais/Wallis, Sierre, Switzerland","institution_ids":["https://openalex.org/I4210129267"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000009841","display_name":"Ana Klimovic","orcid":"https://orcid.org/0000-0001-8559-0529"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Ana Klimovic","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0001-8559-0529","affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5049951876"],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":5.7202,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.96321498,"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":"204","last_page":"220"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.989300012588501,"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":0.989300012588501,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9847999811172485,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9836999773979187,"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/training","display_name":"Training (meteorology)","score":0.6963000297546387},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.6536999940872192},{"id":"https://openalex.org/keywords/homogeneous","display_name":"Homogeneous","score":0.6283000111579895},{"id":"https://openalex.org/keywords/symmetric-multiprocessor-system","display_name":"Symmetric multiprocessor system","score":0.4846000075340271},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.4429999887943268},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.38929998874664307},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3634999990463257}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8237000107765198},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6963000297546387},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.6536999940872192},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.650600016117096},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.6283000111579895},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.4846000075340271},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.4429999887943268},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.38929998874664307},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3634999990463257},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.3294000029563904},{"id":"https://openalex.org/C13670688","wikidata":"https://www.wikidata.org/wiki/Q3500548","display_name":"Space partitioning","level":2,"score":0.2994000017642975},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.2728999853134155},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C3739613","wikidata":"https://www.wikidata.org/wiki/Q679003","display_name":"Distributed Computing Environment","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.2547000050544739}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3731569.3764839","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731569.3764839","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 ACM SIGOPS 31st Symposium on Operating Systems Principles","raw_type":"proceedings-article"},{"id":"pmh:oai:hesso.tind.io:17014","is_oa":false,"landing_page_url":"http://arodes.hes-so.ch/record/17014","pdf_url":null,"source":{"id":"https://openalex.org/S4306402432","display_name":"ArODES (HES-SO (https://www.hes-so.ch/))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210088449","host_organization_name":"HES-SO Gen\u00e8ve","host_organization_lineage":["https://openalex.org/I4210088449"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arodes.hes-so.ch/record/17014","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1145/3731569.3764839","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731569.3764839","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 ACM SIGOPS 31st Symposium on Operating Systems Principles","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W2734941459","https://openalex.org/W2755443794","https://openalex.org/W2757024591","https://openalex.org/W2963149401","https://openalex.org/W2969388332","https://openalex.org/W3155703940","https://openalex.org/W3205803342","https://openalex.org/W4220741164","https://openalex.org/W4310282800","https://openalex.org/W4318541641","https://openalex.org/W4383749415","https://openalex.org/W4385329445","https://openalex.org/W4386840193","https://openalex.org/W4388041017","https://openalex.org/W4388076418","https://openalex.org/W4394922822","https://openalex.org/W4394945032","https://openalex.org/W4395020669","https://openalex.org/W4401211558","https://openalex.org/W4404400583","https://openalex.org/W4407216788","https://openalex.org/W4407218342","https://openalex.org/W4408846413","https://openalex.org/W4408894415","https://openalex.org/W4413267772"],"related_works":[],"abstract_inverted_index":{"The":[0],"high":[1],"GPU":[2],"demand":[3],"of":[4,15,56,110],"ML":[5,40],"training":[6,39,66,79,104,114],"makes":[7],"it":[8],"hard":[9],"to":[10,112],"allocate":[11],"large":[12,53],"homogeneous":[13],"clusters":[14],"high-end":[16],"GPUs":[17,25],"in":[18],"a":[19,35,52,74,102],"single":[20],"availability":[21],"zone.":[22],"Leveraging":[23],"heterogeneous":[24,43,69],"available":[26,85],"within":[27],"and":[28,51,83,97,101,116],"across":[29],"zones":[30],"can":[31],"improve":[32],"throughput":[33,115],"at":[34],"reasonable":[36],"cost.":[37,117],"However,":[38],"models":[41,67],"on":[42,68],"resources":[44],"introduces":[45],"significant":[46],"challenges,":[47],"such":[48],"as":[49],"stragglers":[50],"search":[54,91],"space":[55,92],"possible":[57],"job":[58],"configurations.":[59],"Current":[60],"systems":[61],"lack":[62],"support":[63],"for":[64],"efficiently":[65],"resources.":[70,86],"We":[71],"present":[72],"Sailor,":[73],"system":[75],"that":[76,106],"automates":[77],"distributed":[78,103],"over":[80],"heterogeneous,":[81],"geo-distributed,":[82],"dynamically":[84],"Sailor":[87],"combines":[88],"an":[89],"efficient":[90],"exploration":[93],"algorithm,":[94],"accurate":[95],"runtime":[96],"memory":[98],"footprint":[99],"simulation,":[100],"framework":[105],"supports":[107],"different":[108],"types":[109],"heterogeneity":[111],"optimize":[113]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-04-30T09:15:22.047038","created_date":"2025-10-10T00:00:00"}
