{"id":"https://openalex.org/W2799237774","doi":"https://doi.org/10.14778/3192965.3192971","title":"Selecting subexpressions to materialize at datacenter scale","display_name":"Selecting subexpressions to materialize at datacenter scale","publication_year":2018,"publication_date":"2018-03-01","ids":{"openalex":"https://openalex.org/W2799237774","doi":"https://doi.org/10.14778/3192965.3192971","mag":"2799237774"},"language":"en","primary_location":{"id":"doi:10.14778/3192965.3192971","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3192965.3192971","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},"type":"article","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/A5079846990","display_name":"Alekh Jindal","orcid":"https://orcid.org/0000-0001-8844-8165"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Alekh Jindal","raw_affiliation_strings":["Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053293674","display_name":"Konstantinos Karanasos","orcid":"https://orcid.org/0009-0007-6975-2568"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Konstantinos Karanasos","raw_affiliation_strings":["Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070183492","display_name":"Sriram Rao","orcid":"https://orcid.org/0000-0002-3265-6165"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sriram Rao","raw_affiliation_strings":["Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042701714","display_name":"Hiren Patel","orcid":"https://orcid.org/0000-0003-1128-8110"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hiren Patel","raw_affiliation_strings":["Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5079846990"],"corresponding_institution_ids":["https://openalex.org/I4210164937"],"apc_list":null,"apc_paid":null,"fwci":19.3086,"has_fulltext":false,"cited_by_count":78,"citation_normalized_percentile":{"value":0.9925455,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"11","issue":"7","first_page":"800","last_page":"812"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9993000030517578,"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":0.9993000030517578,"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/T11106","display_name":"Data Management and Algorithms","score":0.9944999814033508,"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":0.9940999746322632,"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":0.873822808265686},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.6456129550933838},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.5501169562339783},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4962530732154846},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4961794316768646},{"id":"https://openalex.org/keywords/scope","display_name":"Scope (computer science)","score":0.45468923449516296},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.44459161162376404},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.44146043062210083},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4233856201171875},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3439907431602478},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.16950926184654236},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1684972047805786},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.16529855132102966},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1438542902469635},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1045466959476471}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.873822808265686},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.6456129550933838},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.5501169562339783},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4962530732154846},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4961794316768646},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.45468923449516296},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.44459161162376404},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.44146043062210083},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4233856201171875},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3439907431602478},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.16950926184654236},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1684972047805786},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.16529855132102966},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1438542902469635},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1045466959476471}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3192965.3192971","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3192965.3192971","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.44999998807907104,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1161092233","https://openalex.org/W1185726409","https://openalex.org/W1480850417","https://openalex.org/W1493893823","https://openalex.org/W1581805425","https://openalex.org/W1631344868","https://openalex.org/W1783974455","https://openalex.org/W1963445704","https://openalex.org/W1983428358","https://openalex.org/W1992977903","https://openalex.org/W2010801412","https://openalex.org/W2017782374","https://openalex.org/W2025549137","https://openalex.org/W2033078763","https://openalex.org/W2037826478","https://openalex.org/W2058978608","https://openalex.org/W2066856139","https://openalex.org/W2081417442","https://openalex.org/W2082941608","https://openalex.org/W2090773975","https://openalex.org/W2093402788","https://openalex.org/W2098416578","https://openalex.org/W2103216163","https://openalex.org/W2106019582","https://openalex.org/W2106105896","https://openalex.org/W2109913494","https://openalex.org/W2110086534","https://openalex.org/W2112312025","https://openalex.org/W2114712170","https://openalex.org/W2122816893","https://openalex.org/W2123537546","https://openalex.org/W2126547925","https://openalex.org/W2132461362","https://openalex.org/W2141992894","https://openalex.org/W2143401113","https://openalex.org/W2151251992","https://openalex.org/W2152191782","https://openalex.org/W2169530972","https://openalex.org/W2170616854","https://openalex.org/W2171177618","https://openalex.org/W2399232213","https://openalex.org/W2528415359","https://openalex.org/W2535959639","https://openalex.org/W2546772565","https://openalex.org/W2586902511","https://openalex.org/W2612261081","https://openalex.org/W2799060872","https://openalex.org/W2964157613","https://openalex.org/W2996376215"],"related_works":["https://openalex.org/W2280422768","https://openalex.org/W3143197806","https://openalex.org/W4252555497","https://openalex.org/W178231042","https://openalex.org/W2360028903","https://openalex.org/W4280543773","https://openalex.org/W2366083136","https://openalex.org/W2387622493","https://openalex.org/W3121175838","https://openalex.org/W3016293053"],"abstract_inverted_index":{"We":[0,106,153,195],"observe":[1],"significant":[2],"overlaps":[3],"in":[4,11,24,138,193,205],"the":[5,18,81,101,202],"computations":[6,47],"performed":[7],"by":[8],"user":[9],"jobs":[10,49],"modern":[12],"shared":[13,35],"analytics":[14],"clusters.":[15,208],"Na\u00efvely":[16],"computing":[17],"same":[19],"subexpressions":[20,141,146],"multiple":[21],"times":[22],"results":[23],"wasting":[25],"cluster":[26,36,56],"resources":[27],"and":[28,58,96,114,144,168],"longer":[29],"execution":[30,165],"times.":[31],"Given":[32],"that":[33],"these":[34],"workloads":[37,68,180],"consist":[38],"of":[39,41,43,51,65,83,93,103,111,158,183,185,189],"tens":[40,182],"thousands":[42,184],"jobs,":[44,186],"identifying":[45],"overlapping":[46],"across":[48],"is":[50],"great":[52],"interest":[53],"to":[54,99,117,135,142,147,191],"both":[55],"operators":[57],"users.":[59],"Nevertheless,":[60],"existing":[61],"approaches":[62],"support":[63],"orders":[64],"magnitude":[66],"smaller":[67],"or":[69],"employ":[70],"heuristics":[71],"with":[72,181,201],"limited":[73],"effectiveness.":[74],"In":[75],"this":[76],"paper,":[77],"we":[78,124],"focus":[79],"on":[80],"problem":[82,113],"subexpression":[84],"selection":[85],"for":[86,149],"large":[87],"workloads,":[88],"i.e.,":[89],"selecting":[90],"common":[91],"parts":[92],"job":[94],"plans":[95],"materializing":[97],"them":[98],"speed-up":[100],"evaluation":[102],"subsequent":[104],"jobs.":[105],"provide":[107,154],"an":[108],"ILP-based":[109],"formulation":[110],"our":[112,159,162,199,206],"map":[115],"it":[116],"a":[118,131,155],"bipartite":[119],"graph":[120,133],"labeling":[121],"problem.":[122],"Then,":[123],"introduce":[125],"B":[126,175],"ig":[127,176],"S":[128,177],"ubs":[129,178],",":[130],"vertex-centric":[132],"algorithm":[134],"iteratively":[136],"choose":[137],"parallel":[139],"which":[140,145],"materialize":[143],"use":[148],"evaluating":[150],"each":[151],"job.":[152],"distributed":[156],"implementation":[157],"approach":[160],"using":[161],"internal":[163],"SQL-like":[164],"framework,":[166],"SCOPE,":[167],"assess":[169],"its":[170],"effectiveness":[171],"over":[172],"production":[173,207],"workloads.":[174],"supports":[179],"yielding":[187],"savings":[188],"up":[190],"40%":[192],"machine-hours.":[194],"are":[196],"currently":[197],"integrating":[198],"techniques":[200],"SCOPE":[203],"runtime":[204]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":18},{"year":2020,"cited_by_count":16},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":5}],"updated_date":"2026-03-29T08:15:47.926485","created_date":"2025-10-10T00:00:00"}