{"id":"https://openalex.org/W2190012392","doi":"https://doi.org/10.14778/2831360.2831365","title":"Clash of the titans","display_name":"Clash of the titans","publication_year":2015,"publication_date":"2015-09-01","ids":{"openalex":"https://openalex.org/W2190012392","doi":"https://doi.org/10.14778/2831360.2831365","mag":"2190012392"},"language":"en","primary_location":{"id":"doi:10.14778/2831360.2831365","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2831360.2831365","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/A5112007116","display_name":"Juwei Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Juwei Shi","raw_affiliation_strings":["Renmin University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000442684","display_name":"Yunjie Qiu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunjie Qiu","raw_affiliation_strings":["IBM Research, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, China","institution_ids":["https://openalex.org/I4210126794"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032253873","display_name":"Umar Farooq Minhas","orcid":"https://orcid.org/0009-0005-6520-3794"},"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":"Umar Farooq Minhas","raw_affiliation_strings":["IBM Almaden Research Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076440257","display_name":"Limei Jiao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Limei Jiao","raw_affiliation_strings":["IBM Research, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, China","institution_ids":["https://openalex.org/I4210126794"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100337643","display_name":"Chen Wang","orcid":"https://orcid.org/0000-0003-0204-2362"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Wang","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036119025","display_name":"Berthold Reinwald","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":"Berthold Reinwald","raw_affiliation_strings":["IBM Almaden Research Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"last","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center","institution_ids":["https://openalex.org/I4210085935"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":89.0536,"has_fulltext":false,"cited_by_count":220,"citation_normalized_percentile":{"value":0.99952527,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":"8","issue":"13","first_page":"2110","last_page":"2121"},"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9919999837875366,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9855999946594238,"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":0.8774693012237549},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.761115312576294},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6824586391448975},{"id":"https://openalex.org/keywords/shuffling","display_name":"Shuffling","score":0.5985033512115479},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5522213578224182},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.5246132612228394},{"id":"https://openalex.org/keywords/sort","display_name":"sort","score":0.4838794469833374},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.4655372202396393},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.45743778347969055},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4528913199901581},{"id":"https://openalex.org/keywords/execution-model","display_name":"Execution model","score":0.44208744168281555},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.41070249676704407},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3412608504295349},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3310545086860657},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.25973814725875854},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09054529666900635}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8774693012237549},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.761115312576294},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6824586391448975},{"id":"https://openalex.org/C167927819","wikidata":"https://www.wikidata.org/wiki/Q1930567","display_name":"Shuffling","level":2,"score":0.5985033512115479},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5522213578224182},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.5246132612228394},{"id":"https://openalex.org/C88548561","wikidata":"https://www.wikidata.org/wiki/Q347599","display_name":"sort","level":2,"score":0.4838794469833374},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.4655372202396393},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.45743778347969055},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4528913199901581},{"id":"https://openalex.org/C2776834041","wikidata":"https://www.wikidata.org/wiki/Q25346349","display_name":"Execution model","level":2,"score":0.44208744168281555},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.41070249676704407},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3412608504295349},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3310545086860657},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.25973814725875854},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09054529666900635},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/2831360.2831365","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2831360.2831365","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W250290266","https://openalex.org/W1527809250","https://openalex.org/W2038157364","https://openalex.org/W2077738892","https://openalex.org/W2105947650","https://openalex.org/W2115022330","https://openalex.org/W2131975293","https://openalex.org/W2154983209","https://openalex.org/W2155072926","https://openalex.org/W2170616854","https://openalex.org/W2173213060","https://openalex.org/W2187341577","https://openalex.org/W2294316975"],"related_works":["https://openalex.org/W2989751065","https://openalex.org/W2922265598","https://openalex.org/W2931411095","https://openalex.org/W2961430130","https://openalex.org/W4246457924","https://openalex.org/W2113798034","https://openalex.org/W2095778029","https://openalex.org/W2241563432","https://openalex.org/W2091874706","https://openalex.org/W2129464725"],"abstract_inverted_index":{"MapReduce":[0,45,86,116,214],"and":[1,25,46,53,87,89,117,162,171,195],"Spark":[2,47,157],"are":[3,129,180],"two":[4,70,134],"very":[5],"popular":[6],"open":[7],"source":[8,140],"cluster":[9],"computing":[10],"frameworks":[11,18,48],"for":[12,84,104,167,188,212,229],"large":[13],"scale":[14],"data":[15,231],"analytics.":[16],"These":[17],"hide":[19],"the":[20,40,76,81,100,112,133,139,181,184,209],"complexity":[21],"of":[22,59,99,141,149,177,183],"task":[23,77,101],"parallelism":[24],"fault-tolerance,":[26],"by":[27,55,145],"exposing":[28],"a":[29,57,65,97,147],"simple":[30],"programming":[31],"API":[32],"to":[33,125,199,206],"users.":[34],"In":[35],"this":[36,92,207],"paper,":[37],"we":[38,68,110,120],"evaluate":[39],"major":[41],"architectural":[42],"components":[43,127],"in":[44,132,202],"including:":[49],"shuffle,":[50],"execution":[51,78,102,224],"model,":[52],"caching,":[54],"using":[56,146],"set":[58,148],"important":[60],"analytic":[61],"workloads.":[62],"To":[63],"conduct":[64],"detailed":[66,108],"analysis,":[67],"developed":[69],"profiling":[71],"tools:":[72],"(1)":[73],"We":[74,95,136,220],"correlate":[75],"plan":[79],"with":[80],"resource":[82],"utilization":[83],"both":[85],"Spark,":[88,233],"visually":[90],"present":[91],"correlation;":[93],"(2)":[94],"provide":[96],"break-down":[98],"time":[103],"in-depth":[105],"analysis.":[106],"Through":[107],"experiments,":[109],"quantify":[111],"performance":[113,123,143],"differences":[114,124,144],"between":[115],"Spark.":[118,203,219],"Furthermore,":[119],"attribute":[121],"these":[122,142,178],"different":[126],"which":[128,213],"architected":[130],"differently":[131],"frameworks.":[135],"further":[137],"expose":[138],"micro-benchmark":[150],"experiments.":[151],"Overall,":[152],"our":[153],"experiments":[154],"show":[155,221],"that":[156,222],"is":[158,208,215,226],"about":[159],"2.5x,":[160],"5x,":[161],"5x":[163],"faster":[164,217,238],"than":[165,218,232],"MapReduce,":[166],"Word":[168],"Count,":[169],"k-means,":[170],"PageRank,":[172],"respectively.":[173],"The":[174],"main":[175],"causes":[176],"speedups":[179],"efficiency":[182],"hash-based":[185],"aggregation":[186],"component":[187],"combine,":[189],"as":[190,192],"well":[191],"reduced":[193],"CPU":[194],"disk":[196],"overheads":[197],"due":[198],"RDD":[200],"caching":[201],"An":[204],"exception":[205],"Sort":[210,236],"workload,":[211],"2x":[216],"MapReduce's":[223],"model":[225],"more":[227],"efficient":[228],"shuffling":[230],"thus":[234],"making":[235],"run":[237],"on":[239],"MapReduce.":[240]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":20},{"year":2020,"cited_by_count":21},{"year":2019,"cited_by_count":30},{"year":2018,"cited_by_count":45},{"year":2017,"cited_by_count":37},{"year":2016,"cited_by_count":23},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":12}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
