{"id":"https://openalex.org/W2735078864","doi":"https://doi.org/10.1177/1094342017712976","title":"Anatomy of machine learning algorithm implementations in MPI, Spark, and Flink","display_name":"Anatomy of machine learning algorithm implementations in MPI, Spark, and Flink","publication_year":2017,"publication_date":"2017-07-02","ids":{"openalex":"https://openalex.org/W2735078864","doi":"https://doi.org/10.1177/1094342017712976","mag":"2735078864"},"language":"en","primary_location":{"id":"doi:10.1177/1094342017712976","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342017712976","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"0890-2720","issn":["0890-2720","1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","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/A5046534488","display_name":"Supun Kamburugamuve","orcid":"https://orcid.org/0000-0002-4282-1419"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Supun Kamburugamuve","raw_affiliation_strings":["School of Informatics and Computing Indiana University, Bloomington, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics and Computing Indiana University, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022147541","display_name":"Pulasthi Wickramasinghe","orcid":"https://orcid.org/0000-0002-9145-1151"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pulasthi Wickramasinghe","raw_affiliation_strings":["School of Informatics and Computing Indiana University, Bloomington, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics and Computing Indiana University, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080593862","display_name":"Saliya Ekanayake","orcid":null},"institutions":[{"id":"https://openalex.org/I4210151352","display_name":"Biocom","ror":"https://ror.org/03ymdxs56","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210151352"]},{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saliya Ekanayake","raw_affiliation_strings":["Network Dynamics and Simulation Science Laboratory Biocomplexity Institute, Virginia Tech, Blacksburg, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Network Dynamics and Simulation Science Laboratory Biocomplexity Institute, Virginia Tech, Blacksburg, VA, USA","institution_ids":["https://openalex.org/I4210151352","https://openalex.org/I859038795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108016089","display_name":"Geoffrey Fox","orcid":"https://orcid.org/0000-0001-8198-4117"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Geoffrey C Fox","raw_affiliation_strings":["School of Informatics and Computing Indiana University, Bloomington, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics and Computing Indiana University, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5108016089"],"corresponding_institution_ids":["https://openalex.org/I4210119109"],"apc_list":{"value":4400,"currency":"USD","value_usd":4400},"apc_paid":null,"fwci":10.2289,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.98002566,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"32","issue":"1","first_page":"61","last_page":"73"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9979000091552734,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9732999801635742,"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":0.8849564790725708},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8805121183395386},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.7005550265312195},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.6679612398147583},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.5358162522315979},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5317496061325073},{"id":"https://openalex.org/keywords/message-passing-interface","display_name":"Message Passing Interface","score":0.49058786034584045},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4569130837917328},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4394189119338989},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.43601125478744507},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.43321043252944946},{"id":"https://openalex.org/keywords/unstructured-data","display_name":"Unstructured data","score":0.42121443152427673},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.3870322108268738},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.17650896310806274},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15176796913146973}],"concepts":[{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.8849564790725708},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8805121183395386},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.7005550265312195},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.6679612398147583},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.5358162522315979},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5317496061325073},{"id":"https://openalex.org/C166782233","wikidata":"https://www.wikidata.org/wiki/Q127879","display_name":"Message Passing Interface","level":3,"score":0.49058786034584045},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4569130837917328},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4394189119338989},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.43601125478744507},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.43321043252944946},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.42121443152427673},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.3870322108268738},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.17650896310806274},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15176796913146973},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0},{"id":"https://openalex.org/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/1094342017712976","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342017712976","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"0890-2720","issn":["0890-2720","1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.44999998807907104,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1123101191","https://openalex.org/W1448681276","https://openalex.org/W1515811018","https://openalex.org/W1968781019","https://openalex.org/W1974396493","https://openalex.org/W1976860187","https://openalex.org/W2097484305","https://openalex.org/W2108444517","https://openalex.org/W2112651225","https://openalex.org/W2114383418","https://openalex.org/W2131975293","https://openalex.org/W2150175750","https://openalex.org/W2150478767","https://openalex.org/W2152825437","https://openalex.org/W2170616854","https://openalex.org/W2189465200","https://openalex.org/W2247317079","https://openalex.org/W2498111289","https://openalex.org/W2529401206","https://openalex.org/W2557880573","https://openalex.org/W2566979091","https://openalex.org/W2584490897","https://openalex.org/W2963288913","https://openalex.org/W2963891150","https://openalex.org/W3104065274"],"related_works":["https://openalex.org/W2844620057","https://openalex.org/W2124048060","https://openalex.org/W1902983110","https://openalex.org/W2378910916","https://openalex.org/W4386915331","https://openalex.org/W2116006827","https://openalex.org/W2086666199","https://openalex.org/W1511717675","https://openalex.org/W2361929291","https://openalex.org/W1493716264"],"abstract_inverted_index":{"With":[0],"the":[1,109,126,131],"ever-increasing":[2],"need":[3,36,47],"to":[4,10,17,37,48,56],"analyze":[5],"large":[6,40],"amounts":[7],"of":[8,31,134],"data":[9,28,41,91,102,110],"get":[11],"useful":[12,58],"insights,":[13],"it":[14],"is":[15,68],"essential":[16],"develop":[18],"complex":[19],"parallel":[20,32,95],"machine":[21,96,150],"learning":[22,151],"algorithms":[23,35,76,152],"that":[24],"can":[25,136],"scale":[26],"with":[27,51],"and":[29,84,115,157,159,163,166],"number":[30],"processes.":[33],"These":[34],"run":[38],"on":[39],"sets":[42],"as":[43,45,89],"well":[44],"they":[46,107],"be":[49,137],"executed":[50],"minimal":[52],"time":[53],"in":[54,60,77,139,142,154,168],"order":[55],"extract":[57],"information":[59],"a":[61,69],"time-constrained":[62],"environment.":[63],"Message":[64],"passing":[65],"interface":[66],"(MPI)":[67],"widely":[70],"used":[71,138],"model":[72,112,120],"for":[73,93,113],"developing":[74],"such":[75],"high-performance":[78],"computing":[79],"paradigm,":[80],"while":[81],"Apache":[82,85],"Spark":[83],"Flink":[86,158],"are":[87,104],"emerging":[88],"big":[90,101],"platforms":[92],"large-scale":[94],"learning.":[97],"Even":[98],"though":[99],"these":[100],"frameworks":[103],"designed":[105],"differently,":[106],"follow":[108],"flow":[111,119],"execution":[114,128],"user":[116],"APIs.":[117],"Data":[118],"offers":[121],"fundamentally":[122],"different":[123],"capabilities":[124],"than":[125],"MPI":[127],"model,":[129],"but":[130],"same":[132],"type":[133],"parallelism":[135],"applications":[140],"developed":[141],"both":[143],"models.":[144],"This":[145],"article":[146],"presents":[147],"three":[148],"distinct":[149],"implemented":[153],"MPI,":[155],"Spark,":[156],"compares":[160],"their":[161],"performance":[162],"identifies":[164],"strengths":[165],"weaknesses":[167],"each":[169],"platform.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}