{"id":"https://openalex.org/W2013344760","doi":"https://doi.org/10.14778/1920841.1920881","title":"HaLoop","display_name":"HaLoop","publication_year":2010,"publication_date":"2010-09-01","ids":{"openalex":"https://openalex.org/W2013344760","doi":"https://doi.org/10.14778/1920841.1920881","mag":"2013344760"},"language":"en","primary_location":{"id":"doi:10.14778/1920841.1920881","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1920841.1920881","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/A5102099238","display_name":"Yingyi Bu","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yingyi Bu","raw_affiliation_strings":["University of Washington, Seattle, WA","University Of Washington (Seattle, WA)"],"affiliations":[{"raw_affiliation_string":"University of Washington, Seattle, WA","institution_ids":["https://openalex.org/I201448701"]},{"raw_affiliation_string":"University Of Washington (Seattle, WA)","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007124763","display_name":"Bill Howe","orcid":"https://orcid.org/0000-0001-8588-8472"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bill Howe","raw_affiliation_strings":["University of Washington, Seattle, WA","University Of Washington (Seattle, WA)"],"affiliations":[{"raw_affiliation_string":"University of Washington, Seattle, WA","institution_ids":["https://openalex.org/I201448701"]},{"raw_affiliation_string":"University Of Washington (Seattle, WA)","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064988079","display_name":"Magdalena Ba\u0142azi\u0144ska","orcid":"https://orcid.org/0000-0002-6805-0325"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Magdalena Balazinska","raw_affiliation_strings":["University of Washington, Seattle, WA","University Of Washington (Seattle, WA)"],"affiliations":[{"raw_affiliation_string":"University of Washington, Seattle, WA","institution_ids":["https://openalex.org/I201448701"]},{"raw_affiliation_string":"University Of Washington (Seattle, WA)","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032068969","display_name":"Michael D. Ernst","orcid":"https://orcid.org/0000-0001-9379-277X"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael D. Ernst","raw_affiliation_strings":["University of Washington, Seattle, WA","University Of Washington (Seattle, WA)"],"affiliations":[{"raw_affiliation_string":"University of Washington, Seattle, WA","institution_ids":["https://openalex.org/I201448701"]},{"raw_affiliation_string":"University Of Washington (Seattle, WA)","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102099238"],"corresponding_institution_ids":["https://openalex.org/I201448701"],"apc_list":null,"apc_paid":null,"fwci":157.9775,"has_fulltext":false,"cited_by_count":688,"citation_normalized_percentile":{"value":0.99975803,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"3","issue":"1-2","first_page":"285","last_page":"296"},"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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"}}],"keywords":[{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.8774964809417725},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8708224296569824},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7191159129142761},{"id":"https://openalex.org/keywords/directed-acyclic-graph","display_name":"Directed acyclic graph","score":0.5127369165420532},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4659475088119507},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.44725045561790466},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.445462167263031},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.4383869469165802},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.41999661922454834},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.40668269991874695},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3038294315338135},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2832688093185425},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2611691355705261},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16274157166481018},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09154748916625977}],"concepts":[{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.8774964809417725},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8708224296569824},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7191159129142761},{"id":"https://openalex.org/C74197172","wikidata":"https://www.wikidata.org/wiki/Q1195339","display_name":"Directed acyclic graph","level":2,"score":0.5127369165420532},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4659475088119507},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44725045561790466},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.445462167263031},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.4383869469165802},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.41999661922454834},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.40668269991874695},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3038294315338135},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2832688093185425},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2611691355705261},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16274157166481018},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09154748916625977},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/1920841.1920881","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1920841.1920881","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":0.6499999761581421,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320310094","display_name":"University of Washington","ror":"https://ror.org/00cvxb145"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1854214752","https://openalex.org/W1997020216","https://openalex.org/W2098935637","https://openalex.org/W2100830825","https://openalex.org/W2102130607","https://openalex.org/W2114303224","https://openalex.org/W2122465391","https://openalex.org/W2125775320","https://openalex.org/W2132063146","https://openalex.org/W2138621811","https://openalex.org/W2160039748","https://openalex.org/W2170616854","https://openalex.org/W4255993952"],"related_works":["https://openalex.org/W2293118914","https://openalex.org/W2998381397","https://openalex.org/W4236419692","https://openalex.org/W3167919718","https://openalex.org/W4251718783","https://openalex.org/W2171015181","https://openalex.org/W2914790213","https://openalex.org/W2793205098","https://openalex.org/W2078379093","https://openalex.org/W2517841089"],"abstract_inverted_index":{"The":[0],"growing":[1],"demand":[2],"for":[3,53,101],"large-scale":[4],"data":[5,8,63,148],"mining":[6],"and":[7,15,28,71,116,128,142,151],"analysis":[9],"applications":[10,61],"has":[11],"led":[12],"both":[13],"industry":[14],"academia":[16],"to":[17,89],"design":[18],"new":[19],"types":[20],"of":[21,41,46,81,146],"highly":[22],"scalable":[23],"data-intensive":[24],"computing":[25],"platforms.":[26],"MapReduce":[27,84,97],"Dryad":[29],"are":[30],"two":[31],"popular":[32],"platforms":[33,49],"in":[34,59],"which":[35,56],"the":[36,39,82,112,147],"dataflow":[37],"takes":[38],"form":[40],"a":[42,78],"directed":[43],"acyclic":[44],"graph":[45,67],"operators.":[47],"These":[48],"lack":[50],"built-in":[51],"support":[52,100],"iterative":[54,102],"programs,":[55],"arise":[57],"naturally":[58],"many":[60],"including":[62],"mining,":[64],"web":[65],"ranking,":[66],"analysis,":[68],"model":[69],"fitting,":[70],"so":[72],"on.":[73],"This":[74],"paper":[75],"presents":[76],"HaLoop,":[77],"modified":[79],"version":[80],"Hadoop":[83],"framework":[85],"that":[86],"is":[87],"designed":[88],"serve":[90],"these":[91],"applications.":[92],"HaLoop":[93,124,136],"not":[94],"only":[95,144],"extends":[96],"with":[98,132],"programming":[99],"applications,":[103],"it":[104],"also":[105],"dramatically":[106],"improves":[107],"their":[108],"efficiency":[109],"by":[110,117,140],"making":[111],"task":[113],"scheduler":[114],"loop-aware":[115],"adding":[118],"various":[119],"caching":[120],"mechanisms.":[121],"We":[122],"evaluated":[123],"on":[125,134],"real":[126,129],"queries":[127],"datasets.":[130],"Compared":[131],"Hadoop,":[133],"average,":[135],"reduces":[137],"query":[138],"runtimes":[139],"1.85,":[141],"shuffles":[143],"4%":[145],"between":[149],"mappers":[150],"reducers.":[152]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":19},{"year":2019,"cited_by_count":39},{"year":2018,"cited_by_count":55},{"year":2017,"cited_by_count":45},{"year":2016,"cited_by_count":91},{"year":2015,"cited_by_count":86},{"year":2014,"cited_by_count":94},{"year":2013,"cited_by_count":111},{"year":2012,"cited_by_count":72}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2016-06-24T00:00:00"}
