{"id":"https://openalex.org/W7098745455","doi":null,"title":"MapReduce: Simplified Data Processing on Large Clusters","display_name":"MapReduce: Simplified Data Processing on Large Clusters","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W7098745455"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.120.7010","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.120.7010","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.berkeley.edu/~randy/Courses/CS294.F07/3.2.pdf","raw_type":"text"},"volume":null,"type":"article","indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jeffrey Dean","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jeffrey Dean","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5012998255","display_name":"Sanjay Ghemawat","orcid":"https://orcid.org/0009-0005-6843-3093","observed_orcids":["https://orcid.org/0009-0005-6843-3093"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sanjay Ghemawat","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.78504372,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9883000254631042,"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":0.9883000254631042,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.004600000102072954,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.0034000000450760126,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/mapreduce","display_name":"MapReduce","score":1.0},{"id":"https://openalex.org/keywords/distributed-data-processing","display_name":"distributed data processing","score":0.8209999799728394},{"id":"https://openalex.org/keywords/large-scale-datasets","display_name":"large-scale datasets","score":0.6980000138282776},{"id":"https://openalex.org/keywords/parallel-programming-models","display_name":"parallel programming models","score":0.7630000114440918},{"id":"https://openalex.org/keywords/commodity-clusters","display_name":"commodity clusters","score":0.6010000109672546},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"fault tolerance","score":0.6650000214576721},{"id":"https://openalex.org/keywords/load-balancing","display_name":"load balancing","score":0.5009999871253967},{"id":"https://openalex.org/keywords/scalability","display_name":"scalability","score":0.6549999713897705},{"id":"https://openalex.org/keywords/functional-programming","display_name":"functional programming","score":0.5070000290870667},{"id":"https://openalex.org/keywords/big-data","display_name":"big data","score":0.3700000047683716}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8776999711990356},{"id":"https://openalex.org/C199683683","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Terabyte","level":2,"score":0.5849999785423279},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.504800021648407},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.4943000078201294},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4627000093460083},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4607999920845032},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.44749999046325684},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4325999915599823},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4178999960422516},{"id":"https://openalex.org/C2776245389","wikidata":"https://www.wikidata.org/wiki/Q962139","display_name":"Programming style","level":2,"score":0.415800005197525},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4092999994754791},{"id":"https://openalex.org/C29140674","wikidata":"https://www.wikidata.org/wiki/Q206637","display_name":"Computer cluster","level":2,"score":0.3946000039577484},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.38100001215934753},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.38019999861717224},{"id":"https://openalex.org/C76831024","wikidata":"https://www.wikidata.org/wiki/Q5227096","display_name":"Data-intensive computing","level":4,"score":0.3686000108718872},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.3621000051498413},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.3456999957561493},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.3221000134944916},{"id":"https://openalex.org/C96147967","wikidata":"https://www.wikidata.org/wiki/Q190686","display_name":"Subroutine","level":2,"score":0.3203999996185303},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.2944999933242798},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.28450000286102295},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.26589998602867126},{"id":"https://openalex.org/C106515295","wikidata":"https://www.wikidata.org/wiki/Q26806595","display_name":"Parallel processing","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C3019257732","wikidata":"https://www.wikidata.org/wiki/Q567759","display_name":"Map reduce","level":3,"score":0.2556000053882599}],"mesh":[],"locations_count":10,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.120.7010","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.120.7010","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.berkeley.edu/~randy/Courses/CS294.F07/3.2.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.135.4448","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.135.4448","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.ualberta.ca/~paullu/C605/mapreduce.dean.osdi.2004.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.163.5292","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.163.5292","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.princeton.edu/courses/archive/spring06/cos592/bib/map-reduce-dean04.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.169.5665","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.169.5665","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ece.rutgers.edu/%7Eparashar/Classes/08-09/ece572/readings/mapreduce-cacm-08.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.188.18","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.188.18","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ics.uci.edu/%7Esjavanma/IR/Assignments/Assignment4/mapreduce.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.229.4214","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.229.4214","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.stanford.edu/class/cs240/readings/cs240-annot-mapreduce.PDF","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.319.3683","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.319.3683","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ccs.neu.edu/home/lieber/courses/csg113/f08/materials/p107-dean.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.324.78","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.324.78","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.dcs.bbk.ac.uk/~dell/teaching/cc/paper/cacm08-01/p107-dean.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.89.9821","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.89.9821","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://labs.google.com/papers/mapreduce-osdi04.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.91.6124","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.91.6124","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://burtonator.files.wordpress.com/2008/01/p107-dean.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2122465391","https://openalex.org/W2173213060","https://openalex.org/W2588083655","https://openalex.org/W1987932453","https://openalex.org/W2391034221","https://openalex.org/W2735194986","https://openalex.org/W7100122409","https://openalex.org/W7096830492","https://openalex.org/W7096035754","https://openalex.org/W2302914195"],"abstract_inverted_index":{"MapReduce":[0,136,151,171,181],"is":[1,146],"a":[2,18,23,28,35,75,99,129,139,149],"programming":[3],"model":[4],"and":[5,11,34,72,106,120,145,176],"an":[6],"associated":[7,43],"implementation":[8,134],"for":[9],"processing":[10],"generating":[12],"large":[13,76,130,140],"data":[14,157],"sets.":[15],"Users":[16],"specify":[17],"map":[19],"function":[20,37],"that":[21,38],"processes":[22,153],"key/value":[24,32],"pair":[25],"to":[26,123,167],"generate":[27],"set":[29,100],"of":[30,78,86,89,101,128,135,142,156,160,170,178],"intermediate":[31,41,47],"pairs,":[33],"reduce":[36],"merges":[39],"all":[40],"values":[42],"with":[44,118],"the":[45,61,87,91,95,108,126,164],"same":[46],"key.":[48],"Many":[49],"real":[50],"world":[51],"tasks":[52],"are":[53,69,183],"expressible":[54],"in":[55,60,65],"this":[56,66],"model,":[57],"as":[58],"shown":[59],"paper.":[62],"Programs":[63],"written":[64],"functional":[67],"style":[68],"automatically":[70],"parallelized":[71],"executed":[73,184],"on":[74,138,158,185],"cluster":[77,141],"commodity":[79,143],"machines.":[80,161],"The":[81],"run-time":[82],"system":[83,165],"takes":[84],"care":[85],"details":[88],"partitioning":[90],"input":[92],"data,":[93],"scheduling":[94],"program\u2019s":[96],"execution":[97],"across":[98],"machines,":[102],"handling":[103],"machine":[104],"failures,":[105],"managing":[107],"required":[109],"inter-machine":[110],"communication.":[111],"This":[112],"allows":[113],"programmers":[114],"without":[115],"any":[116],"experience":[117],"parallel":[119],"distributed":[121,131],"systems":[122],"easily":[124],"utilize":[125],"resources":[127],"system.":[132],"Our":[133],"runs":[137],"machines":[144],"highly":[147],"scalable:":[148],"typical":[150],"computation":[152],"many":[154],"terabytes":[155],"thousands":[159],"Programmers":[162],"find":[163],"easy":[166],"use:":[168],"hundreds":[169],"programs":[172],"have":[173],"been":[174],"implemented":[175],"upwards":[177],"one":[179],"thousand":[180],"jobs":[182],"Google\u2019s":[186],"clusters":[187],"every":[188],"day.":[189],"1":[190]},"counts_by_year":[],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2025-10-27T00:00:00"}