{"id":"https://openalex.org/W2584983941","doi":"https://doi.org/10.1109/bigdata.2016.7840861","title":"Big data analytics on HPC architectures: Performance and cost","display_name":"Big data analytics on HPC architectures: Performance and cost","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2584983941","doi":"https://doi.org/10.1109/bigdata.2016.7840861","mag":"2584983941"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2016.7840861","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2016.7840861","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-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/A5036139759","display_name":"Peter Xenopoulos","orcid":"https://orcid.org/0000-0001-8594-3400"},"institutions":[{"id":"https://openalex.org/I177881444","display_name":"Pomona College","ror":"https://ror.org/0074grg94","country_code":"US","type":"education","lineage":["https://openalex.org/I177881444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Xenopoulos","raw_affiliation_strings":["Pomona College, Claremont, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pomona College, Claremont, CA","institution_ids":["https://openalex.org/I177881444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108541705","display_name":"Jamison Daniel","orcid":null},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jamison Daniel","raw_affiliation_strings":["Advanced Data and Workflows Group, Oak Ridge National Laboratory, Oak Ridge, TN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Data and Workflows Group, Oak Ridge National Laboratory, Oak Ridge, TN","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012951247","display_name":"Michael A. Matheson","orcid":"https://orcid.org/0000-0003-1512-5255"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Matheson","raw_affiliation_strings":["Advanced Data and Workflows Group, Oak Ridge National Laboratory, Oak Ridge, TN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Data and Workflows Group, Oak Ridge National Laboratory, Oak Ridge, TN","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079418386","display_name":"Sreenivas R. Sukumar","orcid":"https://orcid.org/0000-0003-4031-2888"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sreenivas Sukumar","raw_affiliation_strings":["Advanced Data and Workflows Group, Oak Ridge National Laboratory, Oak Ridge, TN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Data and Workflows Group, Oak Ridge National Laboratory, Oak Ridge, TN","institution_ids":["https://openalex.org/I1289243028"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.8325,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.95569646,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2286","last_page":"2295"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9991999864578247,"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":0.9991999864578247,"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/T11181","display_name":"Advanced Data Storage Technologies","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"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9968000054359436,"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":0.8510470390319824},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.739608108997345},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.700607180595398},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5972723364830017},{"id":"https://openalex.org/keywords/terabyte","display_name":"Terabyte","score":0.5154901146888733},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.5087218880653381},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.47583842277526855},{"id":"https://openalex.org/keywords/petabyte","display_name":"Petabyte","score":0.47350695729255676},{"id":"https://openalex.org/keywords/data-analysis","display_name":"Data analysis","score":0.44884735345840454},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4388328790664673},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3753821849822998},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.31930649280548096},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.12749680876731873}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8510470390319824},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.739608108997345},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.700607180595398},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5972723364830017},{"id":"https://openalex.org/C199683683","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Terabyte","level":2,"score":0.5154901146888733},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.5087218880653381},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.47583842277526855},{"id":"https://openalex.org/C13600138","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Petabyte","level":3,"score":0.47350695729255676},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.44884735345840454},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4388328790664673},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3753821849822998},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.31930649280548096},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.12749680876731873},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2016.7840861","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2016.7840861","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.6000000238418579}],"awards":[],"funders":[{"id":"https://openalex.org/F4320338287","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W410850256","https://openalex.org/W1918839972","https://openalex.org/W1978723563","https://openalex.org/W2009514331","https://openalex.org/W2032756564","https://openalex.org/W2054575785","https://openalex.org/W2082839002","https://openalex.org/W2090244259","https://openalex.org/W2098533231","https://openalex.org/W2103128343","https://openalex.org/W2108399535","https://openalex.org/W2117756735","https://openalex.org/W2118411523","https://openalex.org/W2131056547","https://openalex.org/W2131975293","https://openalex.org/W2283571372","https://openalex.org/W2331206060","https://openalex.org/W2482213519","https://openalex.org/W2963288913","https://openalex.org/W3150630553","https://openalex.org/W6614148910"],"related_works":["https://openalex.org/W1538652242","https://openalex.org/W2011521129","https://openalex.org/W4379164835","https://openalex.org/W2461968736","https://openalex.org/W4386544342","https://openalex.org/W1971438544","https://openalex.org/W2481053450","https://openalex.org/W2034909456","https://openalex.org/W4254487859","https://openalex.org/W2514911858"],"abstract_inverted_index":{"Data":[0],"driven":[1],"science,":[2],"accompanied":[3],"by":[4],"the":[5,40,98,152,172],"explosion":[6],"of":[7,9,64,81,100,155],"petabytes":[8],"data,":[10],"has":[11,51],"called":[12],"into":[13],"need":[14],"dedicated":[15],"analytics":[16,20,121],"computing":[17,66,130],"resources.":[18],"Dedicated":[19],"clusters":[21],"require":[22],"large":[23,109],"capital":[24],"outlays":[25],"due":[26],"to":[27,161],"their":[28],"expensive":[29],"hardware":[30],"requirements.":[31],"Additionally,":[32,84,149],"if":[33],"such":[34,174],"resources":[35],"are":[36,115],"located":[37],"far":[38],"from":[39],"data":[41,48,71,120,139,162],"they":[42,44],"analyze,":[43],"also":[45,126],"incur":[46],"substantial":[47],"transfer,":[49],"which":[50],"both":[52],"cost":[53,79,133,145],"and":[54,111,157],"latency":[55],"implications.":[56],"In":[57],"this":[58],"paper,":[59],"we":[60,85,150,166],"benchmark":[61],"a":[62,78],"variety":[63],"high-performance":[65],"(HPC)":[67],"architectures":[68,107],"for":[69,118,135,171],"classic":[70],"science":[72,163],"algorithms,":[73],"as":[74,76,91,93,175],"well":[75,92],"conduct":[77],"analysis":[80],"these":[82],"architectures.":[83],"compare":[86],"algorithms":[87],"across":[88],"analytic":[89],"frameworks,":[90],"explore":[94],"hidden":[95,153],"costs":[96,154],"in":[97,184],"form":[99],"queuing":[101,156],"mechanisms.":[102],"We":[103,125],"observe":[104,167],"that":[105,128,168],"node":[106],"with":[108],"memory":[110,113],"high":[112],"bandwidth":[114],"better":[116],"suited":[117],"big":[119],"on":[122],"HPC":[123,142,185],"hardware.":[124],"conclude":[127],"cloud":[129],"is":[131,143],"more":[132,144],"effective":[134,146],"small":[136],"or":[137],"experimental":[138],"workloads,":[140],"but":[141],"at":[147],"scale.":[148],"quantify":[151],"how":[158],"it":[159],"relates":[160],"workloads.":[164],"Finally,":[165],"software":[169],"developed":[170],"cloud,":[173],"Spark,":[176],"performs":[177],"significantly":[178],"worse":[179],"than":[180],"pbdR":[181],"when":[182],"run":[183],"environments.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}