{"id":"https://openalex.org/W3125666216","doi":"https://doi.org/10.1145/3428757.3429121","title":"Performance evaluation of Apache Hadoop and Apache Spark for parallelization of compute-intensive tasks","display_name":"Performance evaluation of Apache Hadoop and Apache Spark for parallelization of compute-intensive tasks","publication_year":2020,"publication_date":"2020-11-30","ids":{"openalex":"https://openalex.org/W3125666216","doi":"https://doi.org/10.1145/3428757.3429121","mag":"3125666216"},"language":"en","primary_location":{"id":"doi:10.1145/3428757.3429121","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3428757.3429121","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd International Conference on Information Integration and Web-based Applications & Services","raw_type":"proceedings-article"},"type":"conference-paper","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/A5037906958","display_name":"Alexander D\u00f6schl","orcid":"https://orcid.org/0000-0003-0625-9921"},"institutions":[{"id":"https://openalex.org/I174004417","display_name":"Munich University of Applied Sciences","ror":"https://ror.org/012k1v959","country_code":"DE","type":"education","lineage":["https://openalex.org/I174004417"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alexander D\u00f6schl","raw_affiliation_strings":["HM Hochschule M\u00fcnchen, University of Applied Sciences, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HM Hochschule M\u00fcnchen, University of Applied Sciences, Munich, Germany","institution_ids":["https://openalex.org/I174004417"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053515576","display_name":"Max-Emanuel Keller","orcid":"https://orcid.org/0000-0001-7923-3365"},"institutions":[{"id":"https://openalex.org/I174004417","display_name":"Munich University of Applied Sciences","ror":"https://ror.org/012k1v959","country_code":"DE","type":"education","lineage":["https://openalex.org/I174004417"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Max-Emanuel Keller","raw_affiliation_strings":["HM Hochschule M\u00fcnchen, University of Applied Sciences, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HM Hochschule M\u00fcnchen, University of Applied Sciences, Munich, Germany","institution_ids":["https://openalex.org/I174004417"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042685867","display_name":"Peter Mandl","orcid":"https://orcid.org/0000-0003-4508-7667"},"institutions":[{"id":"https://openalex.org/I174004417","display_name":"Munich University of Applied Sciences","ror":"https://ror.org/012k1v959","country_code":"DE","type":"education","lineage":["https://openalex.org/I174004417"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Peter Mandl","raw_affiliation_strings":["HM Hochschule M\u00fcnchen, University of Applied Sciences, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HM Hochschule M\u00fcnchen, University of Applied Sciences, Munich, Germany","institution_ids":["https://openalex.org/I174004417"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I174004417"],"apc_list":null,"apc_paid":null,"fwci":0.4544,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.63848256,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"313","last_page":"321"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9998999834060669,"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":0.9998999834060669,"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":0.998199999332428,"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":0.9943000078201294,"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/spark","display_name":"SPARK (programming language)","score":0.8318520188331604},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7697627544403076},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6561437845230103},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.6378716230392456},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.413574755191803},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.22231721878051758}],"concepts":[{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.8318520188331604},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7697627544403076},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6561437845230103},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.6378716230392456},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.413574755191803},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.22231721878051758}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3428757.3429121","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3428757.3429121","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd International Conference on Information Integration and Web-based Applications & Services","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.47999998927116394,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1897307202","https://openalex.org/W2058385539","https://openalex.org/W2070630412","https://openalex.org/W2216541755","https://openalex.org/W2507290484","https://openalex.org/W2755227905","https://openalex.org/W2884002274","https://openalex.org/W4312584427"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W4390608645","https://openalex.org/W2960264696","https://openalex.org/W3090563135","https://openalex.org/W2497432351","https://openalex.org/W2766461310","https://openalex.org/W4247566972","https://openalex.org/W4388692845","https://openalex.org/W3202731209","https://openalex.org/W3211874991"],"abstract_inverted_index":{"There":[0],"have":[1,6],"been":[2],"numerous":[3],"studies":[4,16],"that":[5,166],"examined":[7],"the":[8,19,72,81,95,117,131,152,167,183,196,200,203],"performance":[9,112,184],"of":[10,14,21,24,30,120,133,151,185,193,198],"distribution":[11],"frameworks.":[12],"Most":[13],"these":[15,31],"deal":[17],"with":[18,94,154,174],"processing":[20,118,168],"large":[22],"amounts":[23],"data.":[25],"This":[26],"work":[27],"compares":[28],"two":[29,91],"frameworks":[32],"for":[33,45,111],"their":[34],"ability":[35],"to":[36,66,128,178],"implement":[37],"CPU-intensive":[38],"distributed":[39,92],"algorithms.":[40],"As":[41],"a":[42,50,86,213],"case":[43],"study":[44],"our":[46,129],"experiments":[47],"we":[48],"used":[49],"simple":[51,87],"but":[52],"computationally":[53],"intensive":[54],"puzzle.":[55],"To":[56],"find":[57],"all":[58],"solutions":[59,93,122,153],"using":[60,85,199],"brute-force":[61],"search,":[62],"15!":[63],"permutations":[64],"had":[65],"be":[67,142],"calculated":[68],"and":[69,89,100,113,137,158],"tested":[70],"against":[71],"solution":[73],"rules.":[74],"Our":[75],"experimental":[76],"application":[77],"was":[78,176,208],"implemented":[79],"in":[80,108,171],"Java":[82,216],"programming":[83],"language":[84],"algorithm":[88],"having":[90],"paradigms":[96],"MapReduce":[97,155],"(Apache":[98,102,156,160],"Hadoop)":[99,157],"RDD":[101,159],"Spark).":[103],"The":[104,149],"implementations":[105],"were":[106],"benchmarked":[107],"Amazon-EC2/EMR":[109],"clusters":[110],"scalability":[114],"measurements,":[115],"where":[116],"time":[119,169],"both":[121],"scaled":[123],"approximately":[124],"linearly.":[125],"However,":[126],"according":[127],"experiments,":[130],"number":[132,192],"tasks,":[134],"hardware":[135],"utilization":[136],"other":[138],"aspects":[139],"should":[140],"also":[141],"taken":[143],"into":[144],"consideration":[145],"when":[146],"assessing":[147],"scalability.":[148],"comparison":[150],"Spark)":[161],"under":[162],"Amazon":[163],"EMR":[164],"showed":[165],"measured":[170],"CPU":[172],"minutes":[173],"Spark":[175,186,207],"up":[177],"30":[179],"%":[180],"lower,":[181],"while":[182],"especially":[187],"benefits":[188],"from":[189],"an":[190],"increasing":[191],"tasks.":[194],"Considering":[195],"efficiency":[197],"EC2":[201],"resources,":[202],"implementation":[204],"via":[205],"Apache":[206],"even":[209],"more":[210],"powerful":[211],"than":[212],"comparable":[214],"multithreaded":[215],"solution.":[217]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}