{"id":"https://openalex.org/W2771222977","doi":"https://doi.org/10.1145/3147213.3155012","title":"Components and Rationale of a Big Data Toolkit Spanning HPC, Grid, Edge and Cloud Computing","display_name":"Components and Rationale of a Big Data Toolkit Spanning HPC, Grid, Edge and Cloud Computing","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2771222977","doi":"https://doi.org/10.1145/3147213.3155012","mag":"2771222977"},"language":"en","primary_location":{"id":"doi:10.1145/3147213.3155012","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3147213.3155012","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the10th International Conference on Utility and Cloud Computing","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/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 Fox","raw_affiliation_strings":["Indiana University, Bloomington, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indiana University, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5108016089"],"corresponding_institution_ids":["https://openalex.org/I4210119109"],"apc_list":null,"apc_paid":null,"fwci":0.8631,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.77216977,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9991000294685364,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9944000244140625,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8694708347320557},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.7645185589790344},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.7049724459648132},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.6852914094924927},{"id":"https://openalex.org/keywords/grid-computing","display_name":"Grid computing","score":0.6308215260505676},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.5417971611022949},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5303203463554382},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.5259024500846863},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4938560128211975},{"id":"https://openalex.org/keywords/edge-computing","display_name":"Edge computing","score":0.44797319173812866},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.43544620275497437},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.42086923122406006},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.30383145809173584},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.252291202545166},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.15427270531654358}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8694708347320557},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.7645185589790344},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.7049724459648132},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.6852914094924927},{"id":"https://openalex.org/C70429105","wikidata":"https://www.wikidata.org/wiki/Q249999","display_name":"Grid computing","level":3,"score":0.6308215260505676},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.5417971611022949},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5303203463554382},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.5259024500846863},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4938560128211975},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.44797319173812866},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.43544620275497437},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.42086923122406006},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.30383145809173584},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.252291202545166},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.15427270531654358},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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:10.1145/3147213.3155012","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3147213.3155012","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the10th International Conference on Utility and Cloud Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G4716253616","display_name":"CIF21 DIBBs: Middleware and High Performance Analytics Libraries for Scalable Data Science","funder_award_id":"1443054","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"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":5,"referenced_works":["https://openalex.org/W2735078864","https://openalex.org/W2751079326","https://openalex.org/W2888364732","https://openalex.org/W4233549502","https://openalex.org/W6730233577"],"related_works":["https://openalex.org/W2116677773","https://openalex.org/W2155261584","https://openalex.org/W2584231425","https://openalex.org/W2150611273","https://openalex.org/W4207086172","https://openalex.org/W2042919702","https://openalex.org/W4225981436","https://openalex.org/W2156185805","https://openalex.org/W2770353918","https://openalex.org/W2122502560"],"abstract_inverted_index":{"We":[0,107,133,143],"look":[1],"again":[2],"at":[3],"Big":[4],"Data":[5],"Programming":[6],"environments":[7],"such":[8,17,27],"as":[9,18,28],"Hadoop,":[10],"Spark,":[11],"Flink,":[12],"Heron,":[13],"Pregel;":[14],"HPC":[15],"concepts":[16],"MPI":[19],"and":[20,24,34,47,90,97,125,156],"Asynchronous":[21],"Many-Task":[22],"runtimes":[23],"Cloud/Grid/Edge":[25],"ideas":[26],"event-driven":[29],"computing,":[30,32],"serverless":[31],"workflow,":[33],"Services.":[35],"These":[36],"cross":[37],"many":[38,57,146],"research":[39],"communities":[40],"including":[41,153],"distributed":[42,104],"systems,":[43],"databases,":[44],"cyberphysical":[45],"systems":[46,62],"parallel":[48],"computing":[49],"which":[50,63],"sometimes":[51],"have":[52,93],"inconsistent":[53],"worldviews.":[54],"There":[55],"are":[56,64],"common":[58],"capabilities":[59],"across":[60],"these":[61,122],"often":[65],"implemented":[66],"differently":[67],"in":[68,149],"each":[69,130],"packaged":[70],"environment.":[71],"For":[72],"example,":[73],"communication":[74],"can":[75,84,92,99,111],"be":[76,85,100],"bulk":[77],"synchronous":[78],"processing":[79],"or":[80,87,102,105],"data":[81,98],"flow;":[82],"scheduling":[83],"dynamic":[86],"static;":[88],"state":[89],"fault-tolerance":[91],"different":[94,123],"models;":[95],"execution":[96],"streaming":[101],"batch,":[103],"local.":[106],"suggest":[108],"that":[109,120],"one":[110],"usefully":[112],"build":[113],"a":[114],"toolkit":[115],"(called":[116],"Twister2":[117,138],"by":[118,139],"us)":[119],"supports":[121],"choices":[124],"allows":[126],"fruitful":[127],"customization":[128],"for":[129],"application":[131],"area.":[132],"illustrate":[134],"the":[135,145],"design":[136],"of":[137],"several":[140],"point":[141],"studies.":[142],"stress":[144],"open":[147],"questions":[148],"very":[150],"traditional":[151],"areas":[152],"scheduling,":[154],"messaging":[155],"checkpointing.":[157]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2018,"cited_by_count":1}],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}
