{"id":"https://openalex.org/W2167208373","doi":"https://doi.org/10.1145/1996130.1996139","title":"Six degrees of scientific data","display_name":"Six degrees of scientific data","publication_year":2011,"publication_date":"2011-06-08","ids":{"openalex":"https://openalex.org/W2167208373","doi":"https://doi.org/10.1145/1996130.1996139","mag":"2167208373"},"language":"en","primary_location":{"id":"doi:10.1145/1996130.1996139","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1996130.1996139","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th international symposium on High performance distributed computing","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/A5027992164","display_name":"Jay Lofstead","orcid":"https://orcid.org/0000-0002-4697-2919"},"institutions":[{"id":"https://openalex.org/I4210104735","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jay Lofstead","raw_affiliation_strings":["Sandia National Laboratories, Albuquerque, NM, USA"],"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories, Albuquerque, NM, USA","institution_ids":["https://openalex.org/I4210104735"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016776573","display_name":"Milo Polte","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Milo Polte","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041431830","display_name":"Garth A. Gibson","orcid":"https://orcid.org/0000-0002-6656-7080"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Garth Gibson","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030373337","display_name":"Scott Klasky","orcid":"https://orcid.org/0000-0003-3559-5772"},"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":"Scott Klasky","raw_affiliation_strings":["Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111483107","display_name":"Karsten Schwan","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karsten Schwan","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108471980","display_name":"Ron A. Oldfield","orcid":null},"institutions":[{"id":"https://openalex.org/I4210104735","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ron Oldfield","raw_affiliation_strings":["Sandia National Laboratories, Albuquerque, NM, USA"],"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories, Albuquerque, NM, USA","institution_ids":["https://openalex.org/I4210104735"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015973975","display_name":"Matthew Wolf","orcid":"https://orcid.org/0000-0002-8393-4436"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Wolf","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100345183","display_name":"Qing Liu","orcid":"https://orcid.org/0000-0002-0592-171X"},"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":"Qing Liu","raw_affiliation_strings":["Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5027992164"],"corresponding_institution_ids":["https://openalex.org/I4210104735"],"apc_list":null,"apc_paid":null,"fwci":10.8524,"has_fulltext":false,"cited_by_count":85,"citation_normalized_percentile":{"value":0.98633219,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"49","last_page":"60"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":1.0,"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":1.0,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9984999895095825,"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":0.998199999332428,"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/petascale-computing","display_name":"Petascale computing","score":0.9524818658828735},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8714789152145386},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5856376886367798},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5313005447387695},{"id":"https://openalex.org/keywords/middleware","display_name":"Middleware (distributed applications)","score":0.5179144740104675},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4213443994522095},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.40528738498687744},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3877519369125366},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.3244694769382477},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2951769232749939},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.16810515522956848}],"concepts":[{"id":"https://openalex.org/C185410017","wikidata":"https://www.wikidata.org/wiki/Q7171778","display_name":"Petascale computing","level":3,"score":0.9524818658828735},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8714789152145386},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5856376886367798},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5313005447387695},{"id":"https://openalex.org/C169468491","wikidata":"https://www.wikidata.org/wiki/Q146923","display_name":"Middleware (distributed applications)","level":2,"score":0.5179144740104675},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4213443994522095},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.40528738498687744},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3877519369125366},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.3244694769382477},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2951769232749939},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.16810515522956848},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1996130.1996139","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1996130.1996139","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th international symposium on High performance distributed computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W16111976","https://openalex.org/W1581112758","https://openalex.org/W1824987472","https://openalex.org/W1981812667","https://openalex.org/W1999354630","https://openalex.org/W2006743077","https://openalex.org/W2019258238","https://openalex.org/W2039373661","https://openalex.org/W2065044274","https://openalex.org/W2072194809","https://openalex.org/W2089536264","https://openalex.org/W2097590615","https://openalex.org/W2104294113","https://openalex.org/W2108183412","https://openalex.org/W2113913767","https://openalex.org/W2116793716","https://openalex.org/W2120573711","https://openalex.org/W2130836080","https://openalex.org/W2150697658","https://openalex.org/W2152145783","https://openalex.org/W2155521027","https://openalex.org/W2156077349","https://openalex.org/W2157219191","https://openalex.org/W2234214857","https://openalex.org/W4229654780","https://openalex.org/W4237777791","https://openalex.org/W6668380138"],"related_works":["https://openalex.org/W1970451660","https://openalex.org/W2085974832","https://openalex.org/W2114834656","https://openalex.org/W2781598847","https://openalex.org/W2042262100","https://openalex.org/W157008363","https://openalex.org/W72498438","https://openalex.org/W2474015782","https://openalex.org/W2320909518","https://openalex.org/W2149470664"],"abstract_inverted_index":{"Petascale":[0],"science":[1],"simulations":[2],"generate":[3],"10s":[4],"of":[5,7,13,27,104,152,172,263],"TBs":[6],"application":[8,34,119],"data":[9,80,83,154,179,224,239,245,264],"per":[10],"day,":[11],"much":[12],"it":[14],"devoted":[15],"to":[16,32,37,47,54,74,77,141,148,160,176,198],"their":[17,96],"checkpoint/restart":[18],"fault":[19],"tolerance":[20],"mechanisms.":[21],"Previous":[22],"work":[23],"demonstrated":[24],"the":[25,50,55,101,107,114,127,150,161,169,187,192,202,216,261],"importance":[26],"carefully":[28],"managing":[29,67],"such":[30],"output":[31],"prevent":[33],"slowdown":[35],"due":[36],"IO":[38,51,144,236],"blocking,":[39],"resource":[40],"contention":[41],"negatively":[42],"impacting":[43],"simulation":[44],"performance":[45,162,189,217,237,262],"and":[46,66,91,156,221,227,247],"fully":[48],"exploit":[49],"bandwidth":[52],"available":[53],"petascale":[56],"machine.":[57],"This":[58],"paper":[59],"takes":[60],"a":[61,89,173],"further":[62],"step":[63],"in":[64,158,244,254,260],"understanding":[65],"extreme-scale":[68],"IO.":[69],"Specifically,":[70],"its":[71],"evaluations":[72],"seek":[73],"understand":[75,149],"how":[76,178],"efficiently":[78],"read":[79,129,137,188,228],"for":[81,182],"subsequent":[82],"analysis,":[84],"visualization,":[85],"checkpoint":[86],"restart":[87],"after":[88],"failure,":[90],"other":[92],"read-intensive":[93],"operations.":[94],"In":[95],"entirety,":[97],"these":[98,136],"actions":[99],"support":[100],"'end-to-end'":[102],"needs":[103],"scientists":[105],"enabling":[106],"scientific":[108],"processes":[109],"being":[110],"undertaken.":[111],"Contributions":[112],"include":[113],"following.":[115],"First,":[116],"working":[117],"with":[118,191,222],"scientists,":[120],"we":[121,184],"define":[122],"'read'":[123],"benchmarks":[124],"that":[125,199,233,241,256],"capture":[126],"common":[128],"patterns":[130,138,220],"used":[131,140,210],"by":[132,164,201,211],"analysis":[133,212],"codes.":[134],"Second,":[135],"are":[139],"evaluate":[142],"different":[143,223],"techniques":[145],"at":[146],"scale":[147],"effects":[151],"alternative":[153],"sizes":[155],"organizations":[157,240],"relation":[159],"seen":[163,190,200,218],"end":[165],"users.":[166],"Third,":[167],"defining":[168],"novel":[170],"notion":[171],"'data":[174],"district'":[175],"characterize":[177],"is":[180],"organized":[181],"reads,":[183],"experimentally":[185],"compare":[186],"ADIOS":[193],"middleware's":[194],"log-based":[195],"BP":[196],"format":[197],"logically":[203],"contiguous":[204],"NetCDF":[205],"or":[206],"HDF5":[207],"formats":[208],"commonly":[209],"tools.":[213],"Measurements":[214],"assess":[215],"across":[219],"sizes,":[225],"organizations,":[226],"process":[229],"counts.":[230],"Outcomes":[231],"demonstrate":[232],"high":[234],"end-to-end":[235],"requires":[238],"offer":[242],"flexibility":[243],"layout":[246],"placement":[248],"on":[249],"parallel":[250],"storage":[251],"targets,":[252],"including":[253],"ways":[255],"can":[257],"make":[258],"tradeoffs":[259],"writes":[265],"vs.":[266],"reads.":[267]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":13},{"year":2012,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
