{"id":"https://openalex.org/W1967093902","doi":"https://doi.org/10.1145/2213836.2213963","title":"Optimizing analytic data flows for multiple execution engines","display_name":"Optimizing analytic data flows for multiple execution engines","publication_year":2012,"publication_date":"2012-05-20","ids":{"openalex":"https://openalex.org/W1967093902","doi":"https://doi.org/10.1145/2213836.2213963","mag":"1967093902"},"language":"en","primary_location":{"id":"doi:10.1145/2213836.2213963","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2213836.2213963","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2012 ACM SIGMOD International Conference on Management of Data","raw_type":"proceedings-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/A5072082268","display_name":"Alkis Simitsis","orcid":"https://orcid.org/0009-0006-6078-5323"},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Alkis Simitsis","raw_affiliation_strings":["HP Labs, Palo Alto, CA, USA","HP Labs, Palo ALto, CA, USA"],"affiliations":[{"raw_affiliation_string":"HP Labs, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]},{"raw_affiliation_string":"HP Labs, Palo ALto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086875579","display_name":"Kevin Wilkinson","orcid":null},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Wilkinson","raw_affiliation_strings":["HP Labs, Palo Alto, CA, USA","HP Labs, Palo ALto, CA, USA"],"affiliations":[{"raw_affiliation_string":"HP Labs, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]},{"raw_affiliation_string":"HP Labs, Palo ALto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110218927","display_name":"Mal\u00fa Castellanos","orcid":null},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Malu Castellanos","raw_affiliation_strings":["HP Labs, Palo Alto, CA, USA","HP Labs, Palo ALto, CA, USA"],"affiliations":[{"raw_affiliation_string":"HP Labs, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]},{"raw_affiliation_string":"HP Labs, Palo ALto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045738980","display_name":"Umeshwar Dayal","orcid":null},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Umeshwar Dayal","raw_affiliation_strings":["HP Labs, Palo Alto, CA, USA","HP Labs, Palo ALto, CA, USA"],"affiliations":[{"raw_affiliation_string":"HP Labs, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]},{"raw_affiliation_string":"HP Labs, Palo ALto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5072082268"],"corresponding_institution_ids":["https://openalex.org/I1324840837"],"apc_list":null,"apc_paid":null,"fwci":25.5798,"has_fulltext":false,"cited_by_count":86,"citation_normalized_percentile":{"value":0.99451474,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"829","last_page":"840"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9983000159263611,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9937000274658203,"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":0.8692985773086548},{"id":"https://openalex.org/keywords/orchestration","display_name":"Orchestration","score":0.706437349319458},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.6639224290847778},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.6466528177261353},{"id":"https://openalex.org/keywords/nosql","display_name":"NoSQL","score":0.59839928150177},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4440625309944153},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4426896870136261},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3812805414199829},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3626124858856201},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.29186689853668213},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2111215591430664}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8692985773086548},{"id":"https://openalex.org/C199168358","wikidata":"https://www.wikidata.org/wiki/Q3367000","display_name":"Orchestration","level":3,"score":0.706437349319458},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.6639224290847778},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.6466528177261353},{"id":"https://openalex.org/C2779599972","wikidata":"https://www.wikidata.org/wiki/Q82231","display_name":"NoSQL","level":3,"score":0.59839928150177},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4440625309944153},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4426896870136261},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3812805414199829},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3626124858856201},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29186689853668213},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2111215591430664},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2213836.2213963","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2213836.2213963","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2012 ACM SIGMOD International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W167093911","https://openalex.org/W1487337216","https://openalex.org/W1507469828","https://openalex.org/W1575324001","https://openalex.org/W1911170630","https://openalex.org/W1920644729","https://openalex.org/W1993892970","https://openalex.org/W2002472616","https://openalex.org/W2010279913","https://openalex.org/W2019448824","https://openalex.org/W2035543557","https://openalex.org/W2058978608","https://openalex.org/W2060280513","https://openalex.org/W2098935637","https://openalex.org/W2100830825","https://openalex.org/W2119558533","https://openalex.org/W2125775320","https://openalex.org/W2149229014","https://openalex.org/W2149877754","https://openalex.org/W2150304332","https://openalex.org/W2158643472","https://openalex.org/W2164645353","https://openalex.org/W6640291201"],"related_works":["https://openalex.org/W1994346114","https://openalex.org/W2121003636","https://openalex.org/W3034269975","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"],"abstract_inverted_index":{"Next":[0],"generation":[1],"business":[2],"intelligence":[3],"involves":[4],"data":[5,32,137,142,153],"flows":[6,33,50,91,104],"that":[7,105,151],"span":[8,106],"different":[9],"execution":[10,84,100],"engines,":[11],"contain":[12],"complex":[13],"functionality":[14],"like":[15],"data/text":[16],"analytics,":[17],"machine":[18],"learning":[19],"operations,":[20],"and":[21,42,46,65,112,157,160],"need":[22],"to":[23,132],"be":[24],"optimized":[25],"against":[26],"various":[27,174],"objectives.":[28],"Creating":[29],"correct":[30],"analytic":[31,75],"in":[34],"such":[35],"an":[36,53,113,117],"environment":[37],"is":[38,43,51,59,125],"a":[39,82,93,107,109,128],"challenging":[40],"task":[41],"both":[44],"labor-intensive":[45],"time-consuming.":[47],"Optimizing":[48],"these":[49],"currently":[52],"ad-hoc":[54],"process":[55],"where":[56],"the":[57,63,68,177],"result":[58],"largely":[60],"dependent":[61],"on":[62,89],"abilities":[64],"experience":[66],"of":[67,135,140,179],"flow":[69,76,149,164],"designer.":[70],"Our":[71],"previous":[72],"work":[73],"addressed":[74],"optimization":[77],"for":[78,92,168,173],"multiple":[79,99,169],"objectives":[80],"over":[81,98],"single":[83,94],"engine.":[85],"This":[86,123],"paper":[87],"focuses":[88],"optimizing":[90],"objective,":[95],"namely":[96],"performance,":[97],"engines.":[101,170],"We":[102,147],"consider":[103],"DBMS,":[108],"Map-Reduce":[110],"engine,":[111],"orchestration":[114],"engine":[115],"(e.g.,":[116,143],"ETL":[118],"tool":[119],"or":[120],"scripting":[121],"language).":[122],"configuration":[124],"emerging":[126],"as":[127],"common":[129],"paradigm":[130],"used":[131],"combine":[133],"analysis":[134,139],"unstructured":[136],"with":[138],"structured":[141],"NoSQL":[144],"plus":[145],"SQL).":[146],"present":[148],"transformations":[150],"model":[152],"shipping,":[154,156],"function":[155],"operation":[158],"decomposition":[159],"we":[161],"describe":[162],"how":[163],"graphs":[165],"are":[166],"generated":[167],"Performance":[171],"results":[172],"configurations":[175],"demonstrate":[176],"benefit":[178],"optimization.":[180]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":14},{"year":2013,"cited_by_count":14},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}