{"id":"https://openalex.org/W2054153667","doi":"https://doi.org/10.1109/iiswc.2014.6983058","title":"Characterizing and subsetting big data workloads","display_name":"Characterizing and subsetting big data workloads","publication_year":2014,"publication_date":"2014-10-01","ids":{"openalex":"https://openalex.org/W2054153667","doi":"https://doi.org/10.1109/iiswc.2014.6983058","mag":"2054153667"},"language":"en","primary_location":{"id":"doi:10.1109/iiswc.2014.6983058","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iiswc.2014.6983058","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Symposium on Workload Characterization (IISWC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1409.0792","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zhen Jia","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhen Jia","raw_affiliation_strings":["University of Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jianfeng Zhan","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianfeng Zhan","raw_affiliation_strings":["State Key Laboratory Computer Architecture, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory Computer Architecture, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lei Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Wang","raw_affiliation_strings":["State Key Laboratory Computer Architecture, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory Computer Architecture, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Rui Han","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Han","raw_affiliation_strings":["State Key Laboratory Computer Architecture, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory Computer Architecture, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Sally A. McKee","orcid":null},"institutions":[{"id":"https://openalex.org/I66862912","display_name":"Chalmers University of Technology","ror":"https://ror.org/040wg7k59","country_code":"SE","type":"education","lineage":["https://openalex.org/I66862912"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Sally A. McKee","raw_affiliation_strings":["Chalmers University of Technology, Sweden"],"affiliations":[{"raw_affiliation_string":"Chalmers University of Technology, Sweden","institution_ids":["https://openalex.org/I66862912"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qiang Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Yang","raw_affiliation_strings":["State Key Laboratory Computer Architecture, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory Computer Architecture, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chunjie Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunjie Luo","raw_affiliation_strings":["State Key Laboratory Computer Architecture, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory Computer Architecture, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jingwei Li","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingwei Li","raw_affiliation_strings":["State Key Laboratory Computer Architecture, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory Computer Architecture, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":20.4511,"has_fulltext":false,"cited_by_count":54,"citation_normalized_percentile":{"value":0.99170214,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"6","issue":null,"first_page":"191","last_page":"201"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9991999864578247,"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"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9987999796867371,"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/big-data","display_name":"Big data","score":0.9476000070571899},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7091000080108643},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5400999784469604},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5070000290870667},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.4875999987125397},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4336000084877014}],"concepts":[{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.9476000070571899},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8185999989509583},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7091000080108643},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5741000175476074},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5400999784469604},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5217999815940857},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5070000290870667},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4875999987125397},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4336000084877014},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3199999928474426},{"id":"https://openalex.org/C3019257732","wikidata":"https://www.wikidata.org/wiki/Q567759","display_name":"Map reduce","level":3,"score":0.2750000059604645},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.27410000562667847},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.26919999718666077}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iiswc.2014.6983058","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iiswc.2014.6983058","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Symposium on Workload Characterization (IISWC)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1409.0792","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1409.0792","pdf_url":"https://arxiv.org/pdf/1409.0792","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:research.chalmers.se:236156","is_oa":false,"landing_page_url":"https://research.chalmers.se/en/publication/236156","pdf_url":null,"source":{"id":"https://openalex.org/S4306402469","display_name":"Chalmers Research (Chalmers University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66862912","host_organization_name":"Chalmers University of Technology","host_organization_lineage":["https://openalex.org/I66862912"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1409.0792","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1409.0792","pdf_url":"https://arxiv.org/pdf/1409.0792","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W279457913","https://openalex.org/W1494578055","https://openalex.org/W1656486128","https://openalex.org/W1798754286","https://openalex.org/W1983965236","https://openalex.org/W1985229168","https://openalex.org/W2010540152","https://openalex.org/W2024270436","https://openalex.org/W2036094156","https://openalex.org/W2040766944","https://openalex.org/W2056272925","https://openalex.org/W2060204338","https://openalex.org/W2080048189","https://openalex.org/W2110086534","https://openalex.org/W2114303224","https://openalex.org/W2127643746","https://openalex.org/W2141181087","https://openalex.org/W2144461192","https://openalex.org/W2146968471","https://openalex.org/W2150478767","https://openalex.org/W2153456949","https://openalex.org/W2169875292","https://openalex.org/W2285144687","https://openalex.org/W2534461193","https://openalex.org/W2537522345","https://openalex.org/W3099514962","https://openalex.org/W4234767864","https://openalex.org/W4243970730","https://openalex.org/W4256470818","https://openalex.org/W6632476604","https://openalex.org/W6635035540","https://openalex.org/W6679815717","https://openalex.org/W6684887918"],"related_works":[],"abstract_inverted_index":{"Big":[0],"data":[1,9,19,62,81,109,116,139,153,161],"benchmark":[2,117],"suites":[3],"must":[4],"include":[5],"a":[6,44,113,122],"diversity":[7],"of":[8,43,46,79,146],"and":[10,21,68,141,167],"workloads":[11,110,162],"to":[12,38,75,97,106,125,133],"be":[13],"useful":[14],"in":[15],"fairly":[16],"evaluating":[17],"big":[18,58,61,80,108,115,138,152,160],"systems":[20],"architectures.":[22],"However,":[23],"using":[24],"truly":[25],"comprehensive":[26,114],"benchmarks":[27],"poses":[28],"great":[29],"challenges":[30],"for":[31,57,151],"the":[32,41,77,99,126,131,135,144,169],"architecture":[33],"community.":[34],"First,":[35],"we":[36,90,120,142,156],"need":[37],"thoroughly":[39],"understand":[40],"behaviors":[42],"variety":[45],"workloads.":[47],"Second,":[48,119],"our":[49],"usual":[50],"simulation-based":[51],"research":[52],"methods":[53],"become":[54],"prohibitively":[55],"expensive":[56],"data.":[59],"As":[60],"is":[63,174],"an":[64],"emerging":[65],"field,":[66],"more":[67,69],"software":[70,149],"stacks":[71,150],"are":[72],"being":[73],"proposed":[74],"facilitate":[76],"development":[78],"applications,":[82],"which":[83,173],"aggravates":[84],"these":[85],"challenges.":[86],"In":[87],"this":[88],"paper,":[89],"first":[91],"use":[92],"Principle":[93],"Component":[94],"Analysis":[95],"(PCA)":[96],"identify":[98],"most":[100],"important":[101],"characteristics":[102],"from":[103,111,130,177],"45":[104],"metrics":[105],"characterize":[107],"BigDataBench,":[112],"suite.":[118],"apply":[121],"clustering":[123],"technique":[124],"principle":[127],"components":[128],"obtained":[129],"PCA":[132],"investigate":[134],"similarity":[136],"among":[137],"workloads,":[140],"verify":[143],"importance":[145],"including":[147],"different":[148],"benchmarking.":[154],"Third,":[155],"select":[157],"seven":[158],"representative":[159],"by":[163],"removing":[164],"redundant":[165],"ones":[166],"release":[168],"BigDataBench":[170],"simulation":[171],"version,":[172],"publicly":[175],"available":[176],"http://prof.ict.ac.cn/BigDataBench/simulatorversion/.":[178]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":4}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2016-06-24T00:00:00"}