{"id":"https://openalex.org/W2407318071","doi":"https://doi.org/10.1145/2912152.2912154","title":"Experiences with Performing MapReduce Analysis of Scientific Data on HPC Platforms","display_name":"Experiences with Performing MapReduce Analysis of Scientific Data on HPC Platforms","publication_year":2016,"publication_date":"2016-05-27","ids":{"openalex":"https://openalex.org/W2407318071","doi":"https://doi.org/10.1145/2912152.2912154","mag":"2407318071"},"language":"en","primary_location":{"id":"doi:10.1145/2912152.2912154","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2912152.2912154","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM International Workshop on Data-Intensive Distributed 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/A5064457907","display_name":"Diana Moise","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Diana Moise","raw_affiliation_strings":["Cray Inc., Basel, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cray Inc., Basel, Switzerland","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5064457907"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2525,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.36618377,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"11","last_page":"18"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9988999962806702,"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"}},"topics":[{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9988999962806702,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9965000152587891,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9955999851226807,"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/big-data","display_name":"Big data","score":0.8731222748756409},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8207788467407227},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.7589927911758423},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.6541578769683838},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6423838138580322},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5045853853225708},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.49303457140922546},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3058592975139618},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.17940205335617065},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.17428550124168396}],"concepts":[{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.8731222748756409},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8207788467407227},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.7589927911758423},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6541578769683838},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6423838138580322},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5045853853225708},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.49303457140922546},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3058592975139618},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.17940205335617065},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.17428550124168396},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2912152.2912154","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2912152.2912154","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM International Workshop on Data-Intensive Distributed Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320324","display_name":"University of Nottingham","ror":"https://ror.org/01ee9ar58"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W26797728","https://openalex.org/W1868798185","https://openalex.org/W1968781019","https://openalex.org/W1989017925","https://openalex.org/W1991001523","https://openalex.org/W2014056498","https://openalex.org/W2071704971","https://openalex.org/W2081612620","https://openalex.org/W2096812688","https://openalex.org/W2102130607","https://openalex.org/W2105947650","https://openalex.org/W2118233996","https://openalex.org/W2119738171","https://openalex.org/W2131229759","https://openalex.org/W2131645490","https://openalex.org/W2173213060","https://openalex.org/W2189465200"],"related_works":["https://openalex.org/W2384867379","https://openalex.org/W4400094300","https://openalex.org/W2329539859","https://openalex.org/W2227905990","https://openalex.org/W2765823764","https://openalex.org/W2770234245","https://openalex.org/W3214280620","https://openalex.org/W3191490922","https://openalex.org/W96612179","https://openalex.org/W1599154403"],"abstract_inverted_index":{"The":[0,46],"growing":[1],"interest":[2],"in":[3,161,177,198,228],"being":[4,85],"able":[5],"to":[6,11,19,65,67,75,94,142,166],"apply":[7],"Big":[8,69,126,186,238],"Data":[9,70,127,187,239],"techniques":[10],"scientific":[12,53,96,150],"data":[13,81,109,151,155,157,160],"generated":[14,86],"using":[15],"HPC":[16,30,89,113,131,153,172,191,211,236],"simulations":[17,108],"led":[18],"the":[20,28,37,73,80,88,111,137,164,168,171,205,216,229,232,235],"question":[21],"of":[22,170,185,210,215,231,234],"whether":[23],"this":[24,49],"is":[25,36,51,84,193],"achievable":[26],"on":[27,43,79,87,110,115,129,149,152,189],"same":[29,112],"platform,":[31],"and":[32,59,196,213,226,237],"if":[33],"so,":[34],"what":[35],"performance":[38,206],"that":[39,104,139,181],"can":[40,91,220],"be":[41,92,221],"obtained":[42],"these":[44],"systems.":[45],"motivation":[47],"behind":[48],"approach":[50],"twofold:":[52],"datasets":[54],"are":[55],"often":[56],"very":[57],"large,":[58],"would":[60],"take":[61],"a":[62,101,178,199],"long":[63],"time":[64],"transfer":[66],"external":[68],"clusters;":[71],"furthermore,":[72],"ability":[74],"perform":[76],"live":[77],"analysis":[78,128,188],"as":[82,99,223],"it":[83,117],"platform":[90,114],"crucial":[93],"many":[95],"applications.":[97],"Using":[98],"case-study":[100],"Hadoop-based":[102,147],"application":[103],"analyzes":[105],"Molecular":[106],"Dynamics":[107],"which":[116],"was":[118],"produced,":[119],"we":[120,202],"present":[121],"our":[122],"experiences":[123],"with":[124,144],"performing":[125,146],"an":[130,183,190],"system.":[132],"This":[133],"work":[134,175],"also":[135],"describes":[136],"challenges":[138],"one":[140],"has":[141],"deal":[143],"when":[145],"computations":[148],"platforms:":[154],"storage,":[156],"formats,":[158],"ingesting":[159],"Hadoop,":[162],"optimizing":[163],"deployment":[165],"overcome":[167],"limitations":[169],"environment.":[173],"Our":[174,218],"shows":[176],"first":[179],"phase":[180],"such":[182],"instantiation":[184],"system":[192],"both":[194],"relevant":[195],"feasible;":[197],"second":[200],"phase,":[201],"greatly":[203],"improve":[204],"by":[207],"efficient":[208],"configuration":[209],"resources":[212],"tuning":[214],"application.":[217],"findings":[219],"shared":[222],"best":[224],"practices":[225],"recommendations":[227],"context":[230],"convergence":[233],"environments.":[240]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}