{"id":"https://openalex.org/W3121910442","doi":"https://doi.org/10.1145/3458817.3476181","title":"Clairvoyant prefetching for distributed machine learning I/O","display_name":"Clairvoyant prefetching for distributed machine learning I/O","publication_year":2021,"publication_date":"2021-10-21","ids":{"openalex":"https://openalex.org/W3121910442","doi":"https://doi.org/10.1145/3458817.3476181","mag":"3121910442"},"language":"en","primary_location":{"id":"doi:10.1145/3458817.3476181","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3458817.3476181","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2101.08734","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066306669","display_name":"Nikoli Dryden","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":"Nikoli Dryden","raw_affiliation_strings":["ETH Z\u00fcrich, Switzerland","ETH Z\u00fcrich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"ETH Z\u00fcrich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048159765","display_name":"Roman B\u00f6hringer","orcid":"https://orcid.org/0009-0000-7141-1286"},"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":"Roman B\u00f6hringer","raw_affiliation_strings":["ETH Z\u00fcrich, Switzerland","ETH Zurich, SWITZERLAND"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"ETH Zurich, SWITZERLAND","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002615744","display_name":"Tal Ben\u2010Nun","orcid":"https://orcid.org/0000-0002-3657-6568"},"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":"Tal Ben-Nun","raw_affiliation_strings":["ETH Z\u00fcrich, Switzerland","ETH Zurich, SWITZERLAND"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"ETH Zurich, SWITZERLAND","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026990786","display_name":"Torsten Hoefler","orcid":"https://orcid.org/0000-0002-1333-9797"},"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":"Torsten Hoefler","raw_affiliation_strings":["ETH Z\u00fcrich, Switzerland","ETH Zurich, SWITZERLAND"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"ETH Zurich, SWITZERLAND","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":0.2826,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.51953637,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"15"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9980999827384949,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9980999827384949,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9966999888420105,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9965000152587891,"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/bottleneck","display_name":"Bottleneck","score":0.9603642225265503},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7949132919311523},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7829253077507019},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.6426832675933838},{"id":"https://openalex.org/keywords/middleware","display_name":"Middleware (distributed applications)","score":0.6035097241401672},{"id":"https://openalex.org/keywords/random-access","display_name":"Random access","score":0.4515657424926758},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.437975138425827},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.4296894669532776},{"id":"https://openalex.org/keywords/data-access","display_name":"Data access","score":0.4158511459827423},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3892415761947632},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2022227644920349},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.17944645881652832},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.12213221192359924}],"concepts":[{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.9603642225265503},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7949132919311523},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7829253077507019},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6426832675933838},{"id":"https://openalex.org/C169468491","wikidata":"https://www.wikidata.org/wiki/Q146923","display_name":"Middleware (distributed applications)","level":2,"score":0.6035097241401672},{"id":"https://openalex.org/C101722063","wikidata":"https://www.wikidata.org/wiki/Q218825","display_name":"Random access","level":2,"score":0.4515657424926758},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.437975138425827},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.4296894669532776},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.4158511459827423},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3892415761947632},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2022227644920349},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.17944645881652832},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.12213221192359924}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3458817.3476181","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3458817.3476181","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2101.08734","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2101.08734","pdf_url":"https://arxiv.org/pdf/2101.08734","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":null},{"id":"doi:10.48550/arxiv.2101.08734","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2101.08734","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"mag:3121910442","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2101.08734","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2101.08734","pdf_url":"https://arxiv.org/pdf/2101.08734","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":null},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2869170175","display_name":"MAchinE Learning for Scalable meTeoROlogy and cliMate","funder_award_id":"955513","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G3664611006","display_name":null,"funder_award_id":"955513","funder_id":"https://openalex.org/F4320334678","funder_display_name":"European Research Council"},{"id":"https://openalex.org/G6531846704","display_name":"Empowering Computational Science using Data-Centric Programming","funder_award_id":"185778","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"},{"id":"https://openalex.org/F4320334678","display_name":"European Research Council","ror":"https://ror.org/0472cxd90"},{"id":"https://openalex.org/F4320337144","display_name":"National Supercomputing Center, Korea Institute of Science and Technology Information","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3121910442.pdf","grobid_xml":"https://content.openalex.org/works/W3121910442.grobid-xml"},"referenced_works_count":67,"referenced_works":["https://openalex.org/W200016408","https://openalex.org/W229826274","https://openalex.org/W1516312903","https://openalex.org/W1523918800","https://openalex.org/W1595324470","https://openalex.org/W1608568416","https://openalex.org/W1667652561","https://openalex.org/W1866529865","https://openalex.org/W1969484964","https://openalex.org/W1980193784","https://openalex.org/W1983997639","https://openalex.org/W1987225815","https://openalex.org/W2062011830","https://openalex.org/W2068975988","https://openalex.org/W2074919500","https://openalex.org/W2083766832","https://openalex.org/W2108598243","https://openalex.org/W2110946051","https://openalex.org/W2112796928","https://openalex.org/W2114664874","https://openalex.org/W2117539524","https://openalex.org/W2120823056","https://openalex.org/W2130836080","https://openalex.org/W2140041027","https://openalex.org/W2156077349","https://openalex.org/W2194775991","https://openalex.org/W2253769547","https://openalex.org/W2279098554","https://openalex.org/W2414434731","https://openalex.org/W2524365899","https://openalex.org/W2580688187","https://openalex.org/W2604701668","https://openalex.org/W2621239346","https://openalex.org/W2622263826","https://openalex.org/W2732026016","https://openalex.org/W2740453188","https://openalex.org/W2787998955","https://openalex.org/W2810464562","https://openalex.org/W2899505139","https://openalex.org/W2900014775","https://openalex.org/W2900042580","https://openalex.org/W2913752846","https://openalex.org/W2935041335","https://openalex.org/W2949507647","https://openalex.org/W2950094539","https://openalex.org/W2951947775","https://openalex.org/W2952046647","https://openalex.org/W2953212265","https://openalex.org/W2962843773","https://openalex.org/W2963304552","https://openalex.org/W2963433607","https://openalex.org/W2963703197","https://openalex.org/W2963809228","https://openalex.org/W2970971581","https://openalex.org/W2972087877","https://openalex.org/W2987776948","https://openalex.org/W2998689333","https://openalex.org/W3040779178","https://openalex.org/W3097002536","https://openalex.org/W3101543398","https://openalex.org/W3105067168","https://openalex.org/W3113588636","https://openalex.org/W3116040173","https://openalex.org/W3123457082","https://openalex.org/W3136964960","https://openalex.org/W3210232381","https://openalex.org/W6718220094"],"related_works":["https://openalex.org/W3206418153","https://openalex.org/W2037526662","https://openalex.org/W3207553910","https://openalex.org/W2894112326","https://openalex.org/W3014712216","https://openalex.org/W3003319291","https://openalex.org/W2997111522","https://openalex.org/W3194536142","https://openalex.org/W106762293","https://openalex.org/W2611127597","https://openalex.org/W3173185171","https://openalex.org/W2951841641","https://openalex.org/W2963717807","https://openalex.org/W2084406381","https://openalex.org/W2981186140","https://openalex.org/W2425037143","https://openalex.org/W2798542661","https://openalex.org/W2477987941","https://openalex.org/W3194685608","https://openalex.org/W139145041"],"abstract_inverted_index":{"I/O":[0,19,30,64,76,133],"is":[1],"emerging":[2],"as":[3,21,23,35],"a":[4,45,61,68,100,115],"major":[5],"bottleneck":[6,31],"for":[7,89],"machine":[8,62],"learning":[9,63],"training,":[10],"especially":[11],"in":[12],"distributed":[13,120],"environments.":[14],"Indeed,":[15],"at":[16],"large":[17],"scale,":[18],"takes":[20],"much":[22],"85%":[24],"of":[25,111],"training":[26,90,138],"time.":[27],"Addressing":[28],"this":[29,107],"necessitates":[32],"careful":[33],"optimization,":[34],"optimal":[36],"data":[37],"ingestion":[38],"pipelines":[39],"differ":[40],"between":[41,48],"systems,":[42],"and":[43,55,71,98,114,128,135,147],"require":[44],"delicate":[46],"balance":[47],"access":[49,87,112],"to":[50,74,118,125,141],"local":[51],"storage,":[52],"external":[53],"filesystems,":[54],"remote":[56],"nodes.":[57],"We":[58,105],"introduce":[59],"NoPFS,":[60],"middleware,":[65],"which":[66],"provides":[67],"scalable,":[69],"flexible,":[70],"easy-to-use":[72],"solution":[73],"the":[75,82,85,144],"bottleneck.":[77],"NoPFS":[78,131],"uses":[79],"clairvoyance:":[80],"Given":[81],"seed":[83],"generating":[84],"random":[86],"pattern":[88],"with":[91,108],"SGD,":[92],"it":[93],"can":[94],"exactly":[95],"predict":[96],"when":[97],"where":[99],"sample":[101],"will":[102],"be":[103],"accessed.":[104],"combine":[106],"an":[109],"analysis":[110],"patterns":[113],"performance":[116],"model":[117],"provide":[119],"caching":[121],"policies":[122],"that":[123],"adapt":[124],"different":[126],"datasets":[127],"storage":[129],"hierarchies.":[130],"reduces":[132],"times":[134],"improves":[136],"end-to-end":[137],"by":[139],"up":[140],"5.4\u00d7":[142],"on":[143],"ImageNet-1k,":[145],"ImageNet-22k,":[146],"CosmoFlow":[148],"datasets.":[149]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-11T18:08:03.149640","created_date":"2025-10-10T00:00:00"}