{"id":"https://openalex.org/W2548933032","doi":"https://doi.org/10.1145/2972950","title":"Building a Hybrid Warehouse","display_name":"Building a Hybrid Warehouse","publication_year":2016,"publication_date":"2016-11-02","ids":{"openalex":"https://openalex.org/W2548933032","doi":"https://doi.org/10.1145/2972950","mag":"2548933032"},"language":"en","primary_location":{"id":"doi:10.1145/2972950","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2972950","pdf_url":null,"source":{"id":"https://openalex.org/S90119964","display_name":"ACM Transactions on Database Systems","issn_l":"0362-5915","issn":["0362-5915","1557-4644"],"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":"ACM Transactions on Database Systems","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/A5090562336","display_name":"Yuanyuan Tian","orcid":"https://orcid.org/0000-0002-6835-8434"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yuanyuan Tian","raw_affiliation_strings":["IBM Research -- Almaden, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research -- Almaden, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070638387","display_name":"Fatma \u00d6zcan","orcid":"https://orcid.org/0000-0002-4418-4724"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fatma \u00d6zcan","raw_affiliation_strings":["IBM Research -- Almaden, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research -- Almaden, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017841792","display_name":"Tao Zou","orcid":"https://orcid.org/0000-0001-7328-5703"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tao Zou","raw_affiliation_strings":["Google, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103276504","display_name":"Romulo Gon\u00e7alves","orcid":"https://orcid.org/0000-0003-2225-1428"},"institutions":[{"id":"https://openalex.org/I4210095242","display_name":"Netherlands eScience Center","ror":"https://ror.org/00rbjv475","country_code":"NL","type":"funder","lineage":["https://openalex.org/I2800991832","https://openalex.org/I4210090210","https://openalex.org/I4210095242"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Romulo Goncalves","raw_affiliation_strings":["The Netherlands eScience Center, Netherlands"],"affiliations":[{"raw_affiliation_string":"The Netherlands eScience Center, Netherlands","institution_ids":["https://openalex.org/I4210095242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083725187","display_name":"Hamid Pirahesh","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hamid Pirahesh","raw_affiliation_strings":["IBM Research -- Almaden, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research -- Almaden, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210085935"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5090562336"],"corresponding_institution_ids":["https://openalex.org/I4210085935"],"apc_list":null,"apc_paid":null,"fwci":7.2982,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.97085605,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"41","issue":"4","first_page":"1","last_page":"38"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9991000294685364,"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":0.9991000294685364,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9988999962806702,"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":0.9987000226974487,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8984125852584839},{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.7674046754837036},{"id":"https://openalex.org/keywords/data-warehouse","display_name":"Data warehouse","score":0.7634336352348328},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.6497292518615723},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.6379861831665039},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5485638976097107},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5360856652259827},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.5280455350875854},{"id":"https://openalex.org/keywords/nosql","display_name":"NoSQL","score":0.4619686007499695},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.33237749338150024},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.317119300365448},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09970030188560486}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8984125852584839},{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.7674046754837036},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.7634336352348328},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.6497292518615723},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.6379861831665039},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5485638976097107},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5360856652259827},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.5280455350875854},{"id":"https://openalex.org/C2779599972","wikidata":"https://www.wikidata.org/wiki/Q82231","display_name":"NoSQL","level":3,"score":0.4619686007499695},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.33237749338150024},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.317119300365448},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09970030188560486},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2972950","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2972950","pdf_url":null,"source":{"id":"https://openalex.org/S90119964","display_name":"ACM Transactions on Database Systems","issn_l":"0362-5915","issn":["0362-5915","1557-4644"],"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":"ACM Transactions on Database Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1480809079","https://openalex.org/W1487093789","https://openalex.org/W1502629466","https://openalex.org/W1519752265","https://openalex.org/W1569375617","https://openalex.org/W1597532222","https://openalex.org/W1597688903","https://openalex.org/W1852059679","https://openalex.org/W1993226606","https://openalex.org/W1999883293","https://openalex.org/W2001040824","https://openalex.org/W2008750849","https://openalex.org/W2016758618","https://openalex.org/W2016829627","https://openalex.org/W2021724486","https://openalex.org/W2027752285","https://openalex.org/W2029036662","https://openalex.org/W2037027334","https://openalex.org/W2038412523","https://openalex.org/W2043099794","https://openalex.org/W2043934800","https://openalex.org/W2051244613","https://openalex.org/W2051756193","https://openalex.org/W2072001200","https://openalex.org/W2104615308","https://openalex.org/W2110086534","https://openalex.org/W2112101330","https://openalex.org/W2112668678","https://openalex.org/W2119400430","https://openalex.org/W2121810937","https://openalex.org/W2122949840","https://openalex.org/W2123845384","https://openalex.org/W2128350269","https://openalex.org/W2131975293","https://openalex.org/W2136625956","https://openalex.org/W2139429256","https://openalex.org/W2139445852","https://openalex.org/W2145812340","https://openalex.org/W2146183750","https://openalex.org/W2173213060","https://openalex.org/W2182304357","https://openalex.org/W2265297126","https://openalex.org/W2394680079","https://openalex.org/W4390575860"],"related_works":["https://openalex.org/W3209916128","https://openalex.org/W4385834214","https://openalex.org/W2621972978","https://openalex.org/W3129344858","https://openalex.org/W3001928035","https://openalex.org/W4320802139","https://openalex.org/W4301431331","https://openalex.org/W2588045195","https://openalex.org/W2957025774","https://openalex.org/W2889462242"],"abstract_inverted_index":{"The":[0],"Hadoop":[1,125,165],"Distributed":[2],"File":[3],"System":[4],"(HDFS)":[5],"has":[6,45],"become":[7],"an":[8],"important":[9],"data":[10,35,60,78,99,114,146,191],"repository":[11],"in":[12,80,94,101,198,228,252],"the":[13,16,31,47,67,87,97,102,113,116,120,124,149,164,169,190,195,202,240,253,259],"enterprise":[14,34],"as":[15,86],"center":[17],"for":[18,49,161,222,239],"all":[19,230],"business":[20,42],"analytics,":[21],"from":[22],"SQL":[23,131],"queries":[24],"and":[25,62,111,181,193,213,244,265],"machine":[26],"learning":[27],"to":[28,39,109,118,143,178,188,201,256],"reporting.":[29],"At":[30],"same":[32],"time,":[33],"warehouses":[36,224],"(EDWs)":[37],"continue":[38],"support":[40],"critical":[41],"analytics.":[43],"This":[44],"created":[46],"need":[48],"a":[50,54,157,208,218,235],"new":[51,209],"generation":[52],"of":[53],"special":[55],"federation":[56],"between":[57],"Hadoop-like":[58],"big":[59],"platforms":[61],"EDWs,":[63],"which":[64],"we":[65,136,154],"call":[66],"hybrid":[68,171,223,254],"warehouse":[69,172,255],".":[70],"There":[71],"are":[72],"many":[73],"applications":[74],"that":[75,89,123,138,153,215,225,246],"require":[76],"correlating":[77],"stored":[79,93,100],"HDFS":[81,95,110,150,182],"with":[82,96],"EDW":[83,117],"data,":[84],"such":[85],"analysis":[88],"associates":[90],"click":[91],"logs":[92],"sales":[98],"database.":[103],"All":[104],"existing":[105],"solutions":[106],"reach":[107],"out":[108],"read":[112],"into":[115],"perform":[119],"joins,":[121],"assuming":[122],"side":[126],"does":[127],"not":[128],"have":[129],"efficient":[130],"support.":[132],"In":[133],"this":[134],"article,":[135],"show":[137,214,245],"it":[139,216,247],"is":[140,217],"actually":[141],"better":[142],"do":[144],"most":[145],"processing":[147],"on":[148,163],"side,":[151],"provided":[152],"can":[155,248],"leverage":[156],"sophisticated":[158,236],"execution":[159],"engine":[160],"joins":[162],"side.":[166],"We":[167,184,206,232],"identify":[168],"best":[170],"architecture":[173],"by":[174],"studying":[175],"various":[176,241],"algorithms":[177,243],"join":[179,211,220,242,266],"database":[180],"tables.":[183],"utilize":[185],"Bloom":[186],"filters":[187],"minimize":[189],"movement":[192],"exploit":[194],"massive":[196],"parallelism":[197],"both":[199],"systems":[200],"fullest":[203],"extent":[204],"possible.":[205],"describe":[207],"zigzag":[210],"algorithm":[212,221,261],"robust":[219],"performs":[226],"well":[227],"almost":[229],"cases.":[231],"further":[233],"develop":[234],"cost":[237],"model":[238],"facilitate":[249],"query":[250],"optimization":[251],"correctly":[257],"choose":[258],"right":[260],"under":[262],"different":[263],"predicate":[264],"selectivities.":[267]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
