{"id":"https://openalex.org/W2887858869","doi":"https://doi.org/10.1145/3225058.3225119","title":"Modeling Application Resilience in Large-scale Parallel Execution","display_name":"Modeling Application Resilience in Large-scale Parallel Execution","publication_year":2018,"publication_date":"2018-08-08","ids":{"openalex":"https://openalex.org/W2887858869","doi":"https://doi.org/10.1145/3225058.3225119","mag":"2887858869"},"language":"en","primary_location":{"id":"doi:10.1145/3225058.3225119","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3225058.3225119","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International Conference on Parallel Processing","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/A5062590263","display_name":"Kai Wu","orcid":"https://orcid.org/0000-0002-7913-8322"},"institutions":[{"id":"https://openalex.org/I156087764","display_name":"University of California, Merced","ror":"https://ror.org/00d9ah105","country_code":"US","type":"education","lineage":["https://openalex.org/I156087764"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kai Wu","raw_affiliation_strings":["University of California, Merced"],"affiliations":[{"raw_affiliation_string":"University of California, Merced","institution_ids":["https://openalex.org/I156087764"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102994344","display_name":"Wenqian Dong","orcid":"https://orcid.org/0000-0002-8376-6647"},"institutions":[{"id":"https://openalex.org/I156087764","display_name":"University of California, Merced","ror":"https://ror.org/00d9ah105","country_code":"US","type":"education","lineage":["https://openalex.org/I156087764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenqian Dong","raw_affiliation_strings":["University of California, Merced"],"affiliations":[{"raw_affiliation_string":"University of California, Merced","institution_ids":["https://openalex.org/I156087764"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102787759","display_name":"Qiang Guan","orcid":"https://orcid.org/0000-0002-3804-8945"},"institutions":[{"id":"https://openalex.org/I149910238","display_name":"Kent State University","ror":"https://ror.org/049pfb863","country_code":"US","type":"education","lineage":["https://openalex.org/I149910238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qiang Guan","raw_affiliation_strings":["Kent State University"],"affiliations":[{"raw_affiliation_string":"Kent State University","institution_ids":["https://openalex.org/I149910238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056569157","display_name":"Nathan DeBardeleben","orcid":"https://orcid.org/0000-0002-5593-9205"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nathan DeBardeleben","raw_affiliation_strings":["Los Alamos National Laboratory"],"affiliations":[{"raw_affiliation_string":"Los Alamos National Laboratory","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100722420","display_name":"Dong Li","orcid":"https://orcid.org/0000-0002-2560-9432"},"institutions":[{"id":"https://openalex.org/I156087764","display_name":"University of California, Merced","ror":"https://ror.org/00d9ah105","country_code":"US","type":"education","lineage":["https://openalex.org/I156087764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Li","raw_affiliation_strings":["University of California, Merced"],"affiliations":[{"raw_affiliation_string":"University of California, Merced","institution_ids":["https://openalex.org/I156087764"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5062590263"],"corresponding_institution_ids":["https://openalex.org/I156087764"],"apc_list":null,"apc_paid":null,"fwci":0.1288,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.47858982,"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":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11005","display_name":"Radiation Effects in Electronics","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11005","display_name":"Radiation Effects in Electronics","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9993000030517578,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9983000159263611,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/fault-injection","display_name":"Fault injection","score":0.9150224328041077},{"id":"https://openalex.org/keywords/resilience","display_name":"Resilience (materials science)","score":0.8028983473777771},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7530980110168457},{"id":"https://openalex.org/keywords/software-fault-tolerance","display_name":"Software fault tolerance","score":0.6482821702957153},{"id":"https://openalex.org/keywords/fault","display_name":"Fault (geology)","score":0.5191594362258911},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.515596330165863},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.4994494915008545},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.48215383291244507},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.46001291275024414},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4493445158004761},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.377285897731781},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.24327462911605835},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11221450567245483}],"concepts":[{"id":"https://openalex.org/C2775928411","wikidata":"https://www.wikidata.org/wiki/Q2041312","display_name":"Fault injection","level":3,"score":0.9150224328041077},{"id":"https://openalex.org/C2779585090","wikidata":"https://www.wikidata.org/wiki/Q3457762","display_name":"Resilience (materials science)","level":2,"score":0.8028983473777771},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7530980110168457},{"id":"https://openalex.org/C50712370","wikidata":"https://www.wikidata.org/wiki/Q4269346","display_name":"Software fault tolerance","level":3,"score":0.6482821702957153},{"id":"https://openalex.org/C175551986","wikidata":"https://www.wikidata.org/wiki/Q47089","display_name":"Fault (geology)","level":2,"score":0.5191594362258911},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.515596330165863},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.4994494915008545},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.48215383291244507},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.46001291275024414},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4493445158004761},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.377285897731781},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.24327462911605835},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11221450567245483},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C165205528","wikidata":"https://www.wikidata.org/wiki/Q83371","display_name":"Seismology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3225058.3225119","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3225058.3225119","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W8870360","https://openalex.org/W255480450","https://openalex.org/W1488205854","https://openalex.org/W1964782602","https://openalex.org/W1965069357","https://openalex.org/W1965936844","https://openalex.org/W1978082708","https://openalex.org/W1988070283","https://openalex.org/W1997843200","https://openalex.org/W2011341849","https://openalex.org/W2021337678","https://openalex.org/W2026387607","https://openalex.org/W2026441832","https://openalex.org/W2046607737","https://openalex.org/W2053691501","https://openalex.org/W2055934382","https://openalex.org/W2071051794","https://openalex.org/W2081235423","https://openalex.org/W2083176370","https://openalex.org/W2094127360","https://openalex.org/W2102148524","https://openalex.org/W2107594045","https://openalex.org/W2136797898","https://openalex.org/W2147657366","https://openalex.org/W2147732182","https://openalex.org/W2150267144","https://openalex.org/W2158907675","https://openalex.org/W2169315529","https://openalex.org/W2291533962","https://openalex.org/W2561860907","https://openalex.org/W2577153905","https://openalex.org/W2604133224","https://openalex.org/W2885636707","https://openalex.org/W3149134903","https://openalex.org/W4285751737","https://openalex.org/W6600367688"],"related_works":["https://openalex.org/W1906576859","https://openalex.org/W3014207222","https://openalex.org/W2971479921","https://openalex.org/W2607474334","https://openalex.org/W2138861322","https://openalex.org/W3145923041","https://openalex.org/W2946906624","https://openalex.org/W841176518","https://openalex.org/W1978919910","https://openalex.org/W188714996"],"abstract_inverted_index":{"Understanding":[0],"how":[1],"the":[2,20,26,31,42,51],"application":[3,18,21,32,43],"is":[4,11,25],"resilient":[5],"to":[6,13,50],"hardware":[7,55],"and":[8],"software":[9],"errors":[10],"critical":[12],"high-performance":[14],"computing.":[15],"To":[16],"evaluate":[17],"resilience,":[19],"level":[22,33],"fault":[23,34,58],"injection":[24,35],"most":[27],"common":[28],"method.":[29],"However,":[30],"can":[36],"be":[37],"very":[38],"expensive":[39],"when":[40],"running":[41],"in":[44,46],"parallel":[45],"large":[47],"scales":[48],"due":[49],"high":[52],"requirement":[53],"for":[54],"resource":[56],"during":[57],"injection.":[59]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
