{"id":"https://openalex.org/W2081235423","doi":"https://doi.org/10.1145/2063384.2063444","title":"Modeling and tolerating heterogeneous failures in large parallel systems","display_name":"Modeling and tolerating heterogeneous failures in large parallel systems","publication_year":2011,"publication_date":"2011-11-08","ids":{"openalex":"https://openalex.org/W2081235423","doi":"https://doi.org/10.1145/2063384.2063444","mag":"2081235423"},"language":"en","primary_location":{"id":"doi:10.1145/2063384.2063444","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2063384.2063444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"type":"preprint","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/A5058317359","display_name":"E. M. Heien","orcid":null},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en informatique et en automatique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Eric Heien","raw_affiliation_strings":["INRIA, France"],"affiliations":[{"raw_affiliation_string":"INRIA, France","institution_ids":["https://openalex.org/I1326498283"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087185379","display_name":"Derrick Kondo","orcid":null},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en informatique et en automatique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Derrick Kondo","raw_affiliation_strings":["INRIA, France"],"affiliations":[{"raw_affiliation_string":"INRIA, France","institution_ids":["https://openalex.org/I1326498283"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021627261","display_name":"Ana Gainaru","orcid":"https://orcid.org/0000-0002-1375-9468"},"institutions":[{"id":"https://openalex.org/I61641377","display_name":"Universitatea Na\u021bional\u0103 de \u0218tiin\u021b\u0103 \u0219i Tehnologie Politehnica Bucure\u0219ti","ror":"https://ror.org/0558j5q12","country_code":"RO","type":"education","lineage":["https://openalex.org/I61641377"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Ana Gainaru","raw_affiliation_strings":["University Politehnica of Bucharest","University Politehnica of Bucharest,,,,,"],"affiliations":[{"raw_affiliation_string":"University Politehnica of Bucharest","institution_ids":["https://openalex.org/I61641377"]},{"raw_affiliation_string":"University Politehnica of Bucharest,,,,,","institution_ids":["https://openalex.org/I61641377"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079243072","display_name":"Daniel LaPine","orcid":"https://orcid.org/0009-0002-4361-2093"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dan LaPine","raw_affiliation_strings":["UIUC, NCSA, Urbana, IL"],"affiliations":[{"raw_affiliation_string":"UIUC, NCSA, Urbana, IL","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053243747","display_name":"Bill Kramer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bill Kramer","raw_affiliation_strings":["NCSA, UIUC, Urbana, IL","NCSA - UIUC, Urbana, IL"],"affiliations":[{"raw_affiliation_string":"NCSA, UIUC, Urbana, IL","institution_ids":[]},{"raw_affiliation_string":"NCSA - UIUC, Urbana, IL","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046613458","display_name":"Franck Cappello","orcid":"https://orcid.org/0000-0002-7890-3934"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en informatique et en automatique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Franck Cappello","raw_affiliation_strings":["INRIA, France, UIUC, Urbana, IL","INRIA, France, UIUC, Urbana, IL#TAB#"],"affiliations":[{"raw_affiliation_string":"INRIA, France, UIUC, Urbana, IL","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"INRIA, France, UIUC, Urbana, IL#TAB#","institution_ids":["https://openalex.org/I1326498283"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5058317359"],"corresponding_institution_ids":["https://openalex.org/I1326498283"],"apc_list":null,"apc_paid":null,"fwci":10.6396069,"has_fulltext":false,"cited_by_count":87,"citation_normalized_percentile":{"value":0.98443487,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9998000264167786,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9998000264167786,"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":0.9994000196456909,"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":0.9993000030517578,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.7896745204925537},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7888522148132324},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.6329401731491089},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4745643734931946},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.3381723165512085},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10068446397781372}],"concepts":[{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.7896745204925537},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7888522148132324},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6329401731491089},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4745643734931946},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.3381723165512085},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10068446397781372},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2063384.2063444","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2063384.2063444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6911753282","display_name":null,"funder_award_id":"9J-30281-0008A","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W71644105","https://openalex.org/W1510496002","https://openalex.org/W1533617723","https://openalex.org/W1553593313","https://openalex.org/W1558516248","https://openalex.org/W2011834550","https://openalex.org/W2019208548","https://openalex.org/W2023917386","https://openalex.org/W2033656974","https://openalex.org/W2036641664","https://openalex.org/W2095487435","https://openalex.org/W2121122863","https://openalex.org/W2122249806","https://openalex.org/W2131629153","https://openalex.org/W2136159049","https://openalex.org/W2138985109","https://openalex.org/W2139244298","https://openalex.org/W2150981663","https://openalex.org/W2170310381","https://openalex.org/W2171530261","https://openalex.org/W2799002609","https://openalex.org/W3102490463","https://openalex.org/W6751060025"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W2530322880"],"abstract_inverted_index":{"As":[0],"supercomputers":[1],"and":[2,7,65],"clusters":[3],"increase":[4],"in":[5,63],"size":[6],"complexity,":[8],"system":[9],"failures":[10,33],"are":[11,61],"inevitable.":[12],"Different":[13],"hardware":[14],"components":[15],"(such":[16],"as":[17],"memory,":[18],"disk,":[19],"or":[20],"network)":[21],"of":[22],"such":[23],"systems":[24],"can":[25],"have":[26],"different":[27],"failure":[28,44,59],"rates.":[29],"Prior":[30],"works":[31],"assume":[32],"equally":[34],"affect":[35],"an":[36],"application,":[37],"whereas":[38],"our":[39],"goal":[40],"is":[41,55],"to":[42],"provide":[43],"models":[45],"for":[46],"applications":[47],"that":[48],"reflect":[49],"their":[50],"specific":[51],"component":[52,58],"usage.":[53],"This":[54],"challenging":[56],"because":[57],"dynamics":[60],"heterogeneous":[62],"space":[64],"time.":[66]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":13},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":12},{"year":2012,"cited_by_count":8}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}