{"id":"https://openalex.org/W3158312191","doi":"https://doi.org/10.1145/3448016.3457270","title":"Instance-Optimized Data Layouts for Cloud Analytics Workloads","display_name":"Instance-Optimized Data Layouts for Cloud Analytics Workloads","publication_year":2021,"publication_date":"2021-06-09","ids":{"openalex":"https://openalex.org/W3158312191","doi":"https://doi.org/10.1145/3448016.3457270","mag":"3158312191"},"language":"en","primary_location":{"id":"doi:10.1145/3448016.3457270","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3448016.3457270","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3448016.3457270","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 2021 International Conference on Management of Data","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3448016.3457270","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103942334","display_name":"Jialin Ding","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jialin Ding","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032253873","display_name":"Umar Farooq Minhas","orcid":"https://orcid.org/0009-0005-6520-3794"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Umar Farooq Minhas","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067654293","display_name":"Badrish Chandramouli","orcid":"https://orcid.org/0000-0002-8468-4037"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Badrish Chandramouli","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100342208","display_name":"Chi Wang","orcid":"https://orcid.org/0000-0002-2033-0870"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chi Wang","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100599400","display_name":"Yinan Li","orcid":"https://orcid.org/0000-0002-3300-8098"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yinan Li","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA","Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100414220","display_name":"Ying Li","orcid":"https://orcid.org/0000-0002-4077-1075"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ying Li","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA","Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111504785","display_name":"Donald Kossmann","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Donald Kossmann","raw_affiliation_strings":["Microsoft Research, Redmond, WA, Switzerland"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, Switzerland","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023537206","display_name":"Johannes Gehrke","orcid":"https://orcid.org/0009-0006-6293-5209"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Johannes Gehrke","raw_affiliation_strings":["Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034086130","display_name":"Tim Kraska","orcid":"https://orcid.org/0009-0003-2414-2759"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tim Kraska","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5103942334"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":3.68,"has_fulltext":true,"cited_by_count":33,"citation_normalized_percentile":{"value":0.93060517,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"418","last_page":"431"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9990000128746033,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9990000128746033,"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/T11106","display_name":"Data Management and Algorithms","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9954000115394592,"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/computer-science","display_name":"Computer science","score":0.8389394879341125},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.6901327967643738},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.6619868874549866},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.6523078083992004},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.620481014251709},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.5670180916786194},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.4558819532394409},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.4517792761325836},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4341517984867096},{"id":"https://openalex.org/keywords/materialized-view","display_name":"Materialized view","score":0.42181485891342163},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.26634761691093445},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.24323248863220215},{"id":"https://openalex.org/keywords/view","display_name":"View","score":0.0938635766506195}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8389394879341125},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.6901327967643738},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.6619868874549866},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.6523078083992004},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.620481014251709},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.5670180916786194},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.4558819532394409},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.4517792761325836},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4341517984867096},{"id":"https://openalex.org/C98199447","wikidata":"https://www.wikidata.org/wiki/Q2445044","display_name":"Materialized view","level":4,"score":0.42181485891342163},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26634761691093445},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.24323248863220215},{"id":"https://openalex.org/C54239708","wikidata":"https://www.wikidata.org/wiki/Q1329910","display_name":"View","level":3,"score":0.0938635766506195},{"id":"https://openalex.org/C148840519","wikidata":"https://www.wikidata.org/wiki/Q1049878","display_name":"Database design","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3448016.3457270","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3448016.3457270","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3448016.3457270","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 2021 International Conference on Management of Data","raw_type":"proceedings-article"},{"id":"pmh:oai:dspace.mit.edu:1721.1/143732","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/143732","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ACM","raw_type":"http://purl.org/eprint/type/ConferencePaper"}],"best_oa_location":{"id":"doi:10.1145/3448016.3457270","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3448016.3457270","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3448016.3457270","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 2021 International Conference on Management of Data","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.550000011920929}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3158312191.pdf","grobid_xml":"https://content.openalex.org/works/W3158312191.grobid-xml"},"referenced_works_count":56,"referenced_works":["https://openalex.org/W1578512165","https://openalex.org/W1964144121","https://openalex.org/W1981988185","https://openalex.org/W1999883293","https://openalex.org/W2020463726","https://openalex.org/W2021651899","https://openalex.org/W2079112936","https://openalex.org/W2093596628","https://openalex.org/W2105252819","https://openalex.org/W2108094106","https://openalex.org/W2122406210","https://openalex.org/W2130617154","https://openalex.org/W2133741724","https://openalex.org/W2134206624","https://openalex.org/W2140342613","https://openalex.org/W2145195191","https://openalex.org/W2146709231","https://openalex.org/W2150630976","https://openalex.org/W2153485419","https://openalex.org/W2574861468","https://openalex.org/W2583754181","https://openalex.org/W2613206411","https://openalex.org/W2613215397","https://openalex.org/W2756982556","https://openalex.org/W2794610196","https://openalex.org/W2798340189","https://openalex.org/W2885801653","https://openalex.org/W2890276152","https://openalex.org/W2893787142","https://openalex.org/W2913555551","https://openalex.org/W2913631065","https://openalex.org/W2923407516","https://openalex.org/W2945486614","https://openalex.org/W2948233700","https://openalex.org/W2955798121","https://openalex.org/W2962771342","https://openalex.org/W2963853546","https://openalex.org/W2968986602","https://openalex.org/W2970148517","https://openalex.org/W2990812675","https://openalex.org/W2991530444","https://openalex.org/W2992496917","https://openalex.org/W2993137170","https://openalex.org/W3000710917","https://openalex.org/W3020084632","https://openalex.org/W3029327553","https://openalex.org/W3029532343","https://openalex.org/W3029564598","https://openalex.org/W3097225903","https://openalex.org/W3098304379","https://openalex.org/W3102117087","https://openalex.org/W3103567827","https://openalex.org/W3106489949","https://openalex.org/W3107842002","https://openalex.org/W3124277639","https://openalex.org/W4237498818"],"related_works":["https://openalex.org/W2125738398","https://openalex.org/W2038176938","https://openalex.org/W2376402673","https://openalex.org/W2953224074","https://openalex.org/W1606751452","https://openalex.org/W2585331044","https://openalex.org/W2588278736","https://openalex.org/W2114713465","https://openalex.org/W2395940163","https://openalex.org/W1680377312"],"abstract_inverted_index":{"Today,":[0],"businesses":[1],"rely":[2],"on":[3,7,129,139],"efficiently":[4],"running":[5],"analytics":[6,24,30],"large":[8,55],"amounts":[9],"of":[10,58,64,78,89,121],"operational":[11],"and":[12,19,41,46,158],"historical":[13],"data":[14,29,48,141],"to":[15,103,109,113,135,144,154],"gain":[16],"business":[17],"insights":[18],"competitive":[20],"advantage.":[21],"Increasingly,":[22],"such":[23,32,96],"are":[25,101,107,133],"run":[26],"using":[27],"cloud-based":[28],"services,":[31,68],"as":[33,97],"Google":[34],"BigQuery,":[35],"Microsoft":[36],"Azure":[37],"Synapse,":[38],"Amazon":[39],"Redshift,":[40],"Snowflake.":[42],"These":[43],"services":[44,91],"persist":[45],"process":[47],"in":[49,54],"compressed,":[50],"columnar":[51],"formats,":[52],"stored":[53],"blocks,":[56],"each":[57],"which":[59,100],"contains":[60],"thousands":[61],"or":[62],"millions":[63],"records.":[65],"For":[66],"these":[67,161],"disk":[69],"I/O":[70],"from":[71],"(remote)":[72],"cloud":[73],"storage":[74],"is":[75,127],"often":[76,92],"one":[77],"the":[79,87,110,119,131,150,166],"dominant":[80],"costs":[81],"for":[82,168],"query":[83,115],"processing.":[84],"To":[85],"reduce":[86],"amount":[88],"I/O,":[90],"maintain":[93],"per-block":[94],"metadata,":[95],"zone":[98,125],"maps,":[99],"used":[102],"skip":[104],"blocks":[105],"that":[106],"irrelevant":[108],"query,":[111],"leading":[112],"lower":[114],"execution":[116],"times.":[117],"However,":[118,160],"effectiveness":[120],"block":[122,146,151],"skipping":[123,147],"via":[124],"maps":[126],"dependent":[128],"how":[130],"records":[132],"assigned":[134],"blocks.":[136],"Recent":[137],"work":[138],"instance-optimized":[140],"layouts":[142],"aims":[143],"maximize":[145],"by":[148],"specializing":[149],"assignment":[152],"strategy":[153],"a":[155,169],"specific":[156],"dataset":[157],"workload.":[159],"existing":[162],"approaches":[163],"only":[164],"optimize":[165],"layout":[167],"single":[170],"table.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
