{"id":"https://openalex.org/W2153889808","doi":"https://doi.org/10.14778/1978665.1978670","title":"Automatic optimization for MapReduce programs","display_name":"Automatic optimization for MapReduce programs","publication_year":2011,"publication_date":"2011-03-01","ids":{"openalex":"https://openalex.org/W2153889808","doi":"https://doi.org/10.14778/1978665.1978670","mag":"2153889808"},"language":"en","primary_location":{"id":"doi:10.14778/1978665.1978670","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1978665.1978670","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/A5000868394","display_name":"Eaman Jahani","orcid":null},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eaman Jahani","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039133265","display_name":"Michael Cafarella","orcid":"https://orcid.org/0000-0001-6122-0590"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael J. Cafarella","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103852640","display_name":"Christopher R\u00e9","orcid":null},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher R\u00e9","raw_affiliation_strings":["University of Wisconsin, Madison, WI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wisconsin, Madison, WI","institution_ids":["https://openalex.org/I135310074"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":70.3006,"has_fulltext":false,"cited_by_count":177,"citation_normalized_percentile":{"value":0.99907728,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"4","issue":"6","first_page":"385","last_page":"396"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9968000054359436,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8992586731910706},{"id":"https://openalex.org/keywords/programmer","display_name":"Programmer","score":0.8138724565505981},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.6168341636657715},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.6147680878639221},{"id":"https://openalex.org/keywords/ask-price","display_name":"Ask price","score":0.5569943189620972},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.49967050552368164},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.49531999230384827},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.48939386010169983},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.4665073752403259},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.34168267250061035},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.09986060857772827},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.08994579315185547}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8992586731910706},{"id":"https://openalex.org/C2778514511","wikidata":"https://www.wikidata.org/wiki/Q1374194","display_name":"Programmer","level":2,"score":0.8138724565505981},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.6168341636657715},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.6147680878639221},{"id":"https://openalex.org/C90329073","wikidata":"https://www.wikidata.org/wiki/Q914232","display_name":"Ask price","level":2,"score":0.5569943189620972},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.49967050552368164},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.49531999230384827},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.48939386010169983},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.4665073752403259},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.34168267250061035},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.09986060857772827},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.08994579315185547},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C136264566","wikidata":"https://www.wikidata.org/wiki/Q159810","display_name":"Economy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/1978665.1978670","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1978665.1978670","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":[{"score":0.47999998927116394,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1491178396","https://openalex.org/W1570477871","https://openalex.org/W1861377444","https://openalex.org/W1988637082","https://openalex.org/W2013344760","https://openalex.org/W2022678927","https://openalex.org/W2022865143","https://openalex.org/W2026427349","https://openalex.org/W2035543557","https://openalex.org/W2075620950","https://openalex.org/W2088675571","https://openalex.org/W2098935637","https://openalex.org/W2114303224","https://openalex.org/W2118269922","https://openalex.org/W2122465391","https://openalex.org/W2123686039","https://openalex.org/W2125775320","https://openalex.org/W2128686935","https://openalex.org/W2133873843","https://openalex.org/W2154894831","https://openalex.org/W2340519882","https://openalex.org/W3130471702","https://openalex.org/W3138367763"],"related_works":["https://openalex.org/W2379153735","https://openalex.org/W2046172023","https://openalex.org/W2170146914","https://openalex.org/W2972896947","https://openalex.org/W2168627904","https://openalex.org/W2083974823","https://openalex.org/W2355105570","https://openalex.org/W2515552481","https://openalex.org/W156769215","https://openalex.org/W2072751097"],"abstract_inverted_index":{"The":[0],"MapReduce":[1,28,80,132,174],"distributed":[2],"programming":[3],"framework":[4],"has":[5],"become":[6],"popular,":[7],"despite":[8],"evidence":[9],"that":[10,115,151,164],"current":[11],"implementations":[12],"are":[13,30],"inefficient,":[14],"requiring":[15,140],"far":[16],"more":[17],"hardware":[18],"than":[19],"a":[20,68,76,79,158],"traditional":[21,34],"relational":[22],"databases":[23],"to":[24,32,99,170],"complete":[25],"similar":[26],"tasks.":[27],"jobs":[29],"amenable":[31],"many":[33],"database":[35],"query":[36],"optimizations":[37],"(B+Trees":[38],"for":[39,43,122],"selections,":[40],"column-store-style":[41],"techniques":[42],"projections,":[44],"etc":[45],"),":[46],"but":[47,75,108],"existing":[48],"systems":[49],"do":[50],"not":[51,118],"apply":[52],"them,":[53],"substantially":[54],"because":[55],"free-form":[56],"user":[57,121],"code":[58,86],"obscures":[59],"the":[60,97,104,120,147],"true":[61],"data":[62,106,161],"operation":[63],"being":[64],"performed.":[65],"For":[66],"example,":[67],"selection":[69,77],"in":[70,78,84],"SQL":[71],"is":[72,82,113],"easily":[73],"detected,":[74],"program":[81,92],"embedded":[83],"Java":[85],"along":[87],"with":[88],"lots":[89],"of":[90,110,160,168],"other":[91],"logic.":[93],"We":[94,149],"could":[95],"ask":[96,119],"programmer":[98],"provide":[100],"explicit":[101],"hints":[102],"about":[103],"program's":[105],"semantics,":[107],"one":[109],"MapReduce's":[111],"attractions":[112],"precisely":[114],"it":[116,165],"does":[117],"such":[123],"information.":[124],"This":[125],"paper":[126],"covers":[127],"Manimal,":[128],"which":[129],"automatically":[130],"analyzes":[131],"programs":[133],"and":[134,163],"applies":[135],"appropriate":[136],"data-aware":[137],"optimizations,":[138],"thereby":[139],"no":[141],"additional":[142],"help":[143],"at":[144],"all":[145],"from":[146],"programmer.":[148],"show":[150],"Manimal":[152],"successfully":[153],"detects":[154],"optimization":[155],"opportunities":[156],"across":[157],"range":[159],"operations,":[162],"yields":[166],"speedups":[167],"up":[169],"1,121%":[171],"on":[172],"previously-written":[173],"programs.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":21},{"year":2015,"cited_by_count":29},{"year":2014,"cited_by_count":28},{"year":2013,"cited_by_count":26},{"year":2012,"cited_by_count":30}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
