{"id":"https://openalex.org/W2028226582","doi":"https://doi.org/10.1145/2452376.2452388","title":"Eagle-eyed elephant","display_name":"Eagle-eyed elephant","publication_year":2013,"publication_date":"2013-03-18","ids":{"openalex":"https://openalex.org/W2028226582","doi":"https://doi.org/10.1145/2452376.2452388","mag":"2028226582"},"language":"en","primary_location":{"id":"doi:10.1145/2452376.2452388","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2452376.2452388","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th International Conference on Extending Database Technology","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/A5074322354","display_name":"Mohamed Y. Eltabakh","orcid":"https://orcid.org/0000-0002-6344-8246"},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mohamed Y. Eltabakh","raw_affiliation_strings":["Worcester Polytechnic Institute, Worcester, MA","Worcester Polytechnic Institute, Worcester MA"],"affiliations":[{"raw_affiliation_string":"Worcester Polytechnic Institute, Worcester, MA","institution_ids":["https://openalex.org/I107077323"]},{"raw_affiliation_string":"Worcester Polytechnic Institute, Worcester MA","institution_ids":["https://openalex.org/I107077323"]}]},{"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 Almaden Research Center, San Jose, CA","IBM Almaden Research Center San Jose , CA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA","institution_ids":["https://openalex.org/I4210085935"]},{"raw_affiliation_string":"IBM Almaden Research Center San Jose , CA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048704801","display_name":"Yannis Sismanis","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":"Yannis Sismanis","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA","IBM Almaden Research Center San Jose , CA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA","institution_ids":["https://openalex.org/I4210085935"]},{"raw_affiliation_string":"IBM Almaden Research Center San Jose , CA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090729930","display_name":"Peter J. Haas","orcid":"https://orcid.org/0000-0001-5694-3065"},"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":"Peter J. Haas","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA","IBM Almaden Research Center San Jose , CA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA","institution_ids":["https://openalex.org/I4210085935"]},{"raw_affiliation_string":"IBM Almaden Research Center San Jose , CA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","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 Almaden Research Center, San Jose, CA","IBM Almaden Research Center San Jose , CA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA","institution_ids":["https://openalex.org/I4210085935"]},{"raw_affiliation_string":"IBM Almaden Research Center San Jose , CA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023410548","display_name":"Jan Vondr\u00e1k","orcid":"https://orcid.org/0000-0001-7568-6711"},"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":"Jan Vondrak","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA","IBM Almaden Research Center San Jose , CA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA","institution_ids":["https://openalex.org/I4210085935"]},{"raw_affiliation_string":"IBM Almaden Research Center San Jose , CA","institution_ids":["https://openalex.org/I4210085935"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5074322354"],"corresponding_institution_ids":["https://openalex.org/I107077323"],"apc_list":null,"apc_paid":null,"fwci":17.7971,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.98948159,"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":"89","last_page":"100"},"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":0.9980000257492065,"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":0.9966999888420105,"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":0.9046128988265991},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6817424893379211},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.5397845506668091},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4671672582626343},{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.4671318829059601},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.4647725224494934},{"id":"https://openalex.org/keywords/instruction-prefetch","display_name":"Instruction prefetch","score":0.43936651945114136},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.41152653098106384},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.39608484506607056},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3388911485671997},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.2879134714603424},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.17184650897979736},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10562518239021301}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9046128988265991},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6817424893379211},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.5397845506668091},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4671672582626343},{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.4671318829059601},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.4647725224494934},{"id":"https://openalex.org/C133588205","wikidata":"https://www.wikidata.org/wiki/Q28455645","display_name":"Instruction prefetch","level":3,"score":0.43936651945114136},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.41152653098106384},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39608484506607056},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3388911485671997},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2879134714603424},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.17184650897979736},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10562518239021301},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2452376.2452388","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2452376.2452388","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th International Conference on Extending Database Technology","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W788498898","https://openalex.org/W1494049834","https://openalex.org/W1502629466","https://openalex.org/W1575324001","https://openalex.org/W1967051853","https://openalex.org/W1978690967","https://openalex.org/W1996468759","https://openalex.org/W2007901510","https://openalex.org/W2010279913","https://openalex.org/W2011039300","https://openalex.org/W2022858489","https://openalex.org/W2026891055","https://openalex.org/W2035543557","https://openalex.org/W2043099794","https://openalex.org/W2044490410","https://openalex.org/W2060322444","https://openalex.org/W2061601738","https://openalex.org/W2072424105","https://openalex.org/W2075620950","https://openalex.org/W2083036816","https://openalex.org/W2098935637","https://openalex.org/W2102294813","https://openalex.org/W2107998108","https://openalex.org/W2110086534","https://openalex.org/W2115613939","https://openalex.org/W2125775320","https://openalex.org/W2151930506","https://openalex.org/W2162709812","https://openalex.org/W2173213060","https://openalex.org/W6630004642"],"related_works":["https://openalex.org/W2140324148","https://openalex.org/W2121199344","https://openalex.org/W2285914869","https://openalex.org/W3117515082","https://openalex.org/W2113441357","https://openalex.org/W3022537591","https://openalex.org/W2126134823","https://openalex.org/W2336226224","https://openalex.org/W1974128693","https://openalex.org/W2141696484"],"abstract_inverted_index":{"An":[0],"increasingly":[1,65],"important":[2],"analytics":[3],"scenario":[4],"for":[5,44,52,73,170],"Hadoop":[6,145,178],"involves":[7],"multiple":[8],"(often":[9],"ad":[10],"hoc)":[11],"grouping":[12],"and":[13,37,39,56,102,158,205,220],"aggregation":[14],"queries":[15,25],"with":[16,234],"selection":[17],"predicates":[18],"over":[19,199],"a":[20],"slowly":[21],"changing":[22],"dataset.":[23],"These":[24],"are":[26,40,156,186],"typically":[27],"expressed":[28],"via":[29],"high-level":[30],"query":[31,82,113,175,190],"languages":[32],"such":[33,60],"as":[34,68],"Jaql,":[35],"Pig,":[36],"Hive,":[38],"used":[41],"either":[42],"directly":[43],"business-intelligence":[45],"applications":[46],"or":[47],"to":[48,76,94,150,188,230,236],"prepare":[49],"the":[50,95,120,129,165,172,189,215],"data":[51,78,138,153,183],"statistical":[53],"model":[54],"building":[55],"machine":[57],"learning.":[58],"In":[59],"scenarios":[61],"it":[62,116],"has":[63,89],"been":[64],"recognized":[66],"that,":[67],"in":[69,144,177,214],"classical":[70,92],"databases,":[71],"techniques":[72,93,195],"avoiding":[74,180],"access":[75,154],"irrelevant":[77,187,211],"can":[79,227],"dramatically":[80],"improve":[81],"performance.":[83],"Prior":[84],"work":[85],"on":[86,99],"Hadoop,":[87],"however,":[88],"simply":[90],"ported":[91],"MapReduce":[96],"setting,":[97],"focusing":[98],"record-level":[100,107],"indexing":[101,108],"key-based":[103,135],"partition":[104],"elimination.":[105],"Unfortunately,":[106],"only":[109],"slightly":[110],"improves":[111],"overall":[112],"performance,":[114],"because":[115],"does":[117],"not":[118],"minimize":[119],"number":[121,130],"of":[122,131,174,182,217],"mapper":[123],"\"waves\",":[124],"which":[125,140],"is":[126,141],"determined":[127],"by":[128,179],"processed":[132],"splits.":[133],"Moreover,":[134],"partitioning":[136],"requires":[137],"reorganization,":[139],"usually":[142],"impractical":[143],"settings.":[146],"We":[147],"therefore":[148],"need":[149],"re-envision":[151],"how":[152],"mechanisms":[155],"defined":[157],"implemented.":[159],"To":[160],"this":[161],"end,":[162],"we":[163],"introduce":[164],"Eagle-Eyed":[166],"Elephant":[167],"(E3)":[168],"framework":[169],"boosting":[171],"efficiency":[173],"processing":[176],"accesses":[181],"splits":[184,212],"that":[185,225],"at":[191],"hand.":[192],"Using":[193],"novel":[194],"involving":[196],"inverted":[197],"indexes":[198],"splits,":[200],"domain":[201],"segmentation,":[202],"materialized":[203],"views,":[204],"adaptive":[206],"caching,":[207],"E3":[208,226],"avoids":[209],"accessing":[210],"even":[213],"face":[216],"evolving":[218],"workloads":[219],"data.":[221],"Our":[222],"experiments":[223],"show":[224],"achieve":[228],"up":[229],"20x":[231],"cost":[232],"savings":[233],"small":[235],"moderate":[237],"storage":[238],"overheads.":[239]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}