{"id":"https://openalex.org/W2083176370","doi":"https://doi.org/10.1145/2465813.2465820","title":"Using unreliable virtual hardware to inject errors in extreme-scale systems","display_name":"Using unreliable virtual hardware to inject errors in extreme-scale systems","publication_year":2013,"publication_date":"2013-06-18","ids":{"openalex":"https://openalex.org/W2083176370","doi":"https://doi.org/10.1145/2465813.2465820","mag":"2083176370"},"language":"en","primary_location":{"id":"doi:10.1145/2465813.2465820","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2465813.2465820","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd Workshop on Fault-tolerance for HPC at extreme scale","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/A5018865548","display_name":"Scott Levy","orcid":"https://orcid.org/0000-0002-2232-3201"},"institutions":[{"id":"https://openalex.org/I169521973","display_name":"University of New Mexico","ror":"https://ror.org/05fs6jp91","country_code":"US","type":"education","lineage":["https://openalex.org/I169521973"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Scott Levy","raw_affiliation_strings":["University of New Mexico, Albuquerque, NM, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New Mexico, Albuquerque, NM, USA","institution_ids":["https://openalex.org/I169521973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025874342","display_name":"Matthew G. F. Dosanjh","orcid":"https://orcid.org/0000-0001-5141-9176"},"institutions":[{"id":"https://openalex.org/I169521973","display_name":"University of New Mexico","ror":"https://ror.org/05fs6jp91","country_code":"US","type":"education","lineage":["https://openalex.org/I169521973"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew G.F. Dosanjh","raw_affiliation_strings":["University of New Mexico, Albuquerque, NM, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New Mexico, Albuquerque, NM, USA","institution_ids":["https://openalex.org/I169521973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052769561","display_name":"Patrick G. Bridges","orcid":"https://orcid.org/0000-0003-4801-0390"},"institutions":[{"id":"https://openalex.org/I169521973","display_name":"University of New Mexico","ror":"https://ror.org/05fs6jp91","country_code":"US","type":"education","lineage":["https://openalex.org/I169521973"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Patrick G. Bridges","raw_affiliation_strings":["University of New Mexico, Albuquerque, NM, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New Mexico, Albuquerque, NM, USA","institution_ids":["https://openalex.org/I169521973"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020783484","display_name":"Kurt Brian Ferreira","orcid":"https://orcid.org/0000-0001-5607-5691"},"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":"Kurt B. Ferreira","raw_affiliation_strings":["Sandia National Laboratories, Albuquerque, NM, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories, Albuquerque, NM, USA","institution_ids":["https://openalex.org/I4210104735"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"21","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11005","display_name":"Radiation Effects in Electronics","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9986000061035156,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9919000267982483,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7662440538406372},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7579159736633301},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.7272814512252808},{"id":"https://openalex.org/keywords/interrupt","display_name":"Interrupt","score":0.7126225233078003},{"id":"https://openalex.org/keywords/virtualization","display_name":"Virtualization","score":0.6502532362937927},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5572383403778076},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.5351883172988892},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5068936944007874},{"id":"https://openalex.org/keywords/virtual-machine","display_name":"Virtual machine","score":0.5057628154754639},{"id":"https://openalex.org/keywords/hypervisor","display_name":"Hypervisor","score":0.4999990463256836},{"id":"https://openalex.org/keywords/software-fault-tolerance","display_name":"Software fault tolerance","score":0.46466314792633057},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4287070333957672},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.37631598114967346},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.32607609033584595},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2723615765571594},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.19423776865005493},{"id":"https://openalex.org/keywords/microcontroller","display_name":"Microcontroller","score":0.1290532946586609},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11061114072799683}],"concepts":[{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7662440538406372},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7579159736633301},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.7272814512252808},{"id":"https://openalex.org/C41661131","wikidata":"https://www.wikidata.org/wiki/Q220764","display_name":"Interrupt","level":3,"score":0.7126225233078003},{"id":"https://openalex.org/C513985346","wikidata":"https://www.wikidata.org/wiki/Q270471","display_name":"Virtualization","level":3,"score":0.6502532362937927},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5572383403778076},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.5351883172988892},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5068936944007874},{"id":"https://openalex.org/C25344961","wikidata":"https://www.wikidata.org/wiki/Q192726","display_name":"Virtual machine","level":2,"score":0.5057628154754639},{"id":"https://openalex.org/C112904061","wikidata":"https://www.wikidata.org/wiki/Q1077480","display_name":"Hypervisor","level":4,"score":0.4999990463256836},{"id":"https://openalex.org/C50712370","wikidata":"https://www.wikidata.org/wiki/Q4269346","display_name":"Software fault tolerance","level":3,"score":0.46466314792633057},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4287070333957672},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.37631598114967346},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.32607609033584595},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2723615765571594},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.19423776865005493},{"id":"https://openalex.org/C173018170","wikidata":"https://www.wikidata.org/wiki/Q165678","display_name":"Microcontroller","level":2,"score":0.1290532946586609},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11061114072799683},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2465813.2465820","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2465813.2465820","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd Workshop on Fault-tolerance for HPC at extreme scale","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":25,"referenced_works":["https://openalex.org/W1547528813","https://openalex.org/W1558516248","https://openalex.org/W1568101540","https://openalex.org/W1641762327","https://openalex.org/W1988070283","https://openalex.org/W1993834204","https://openalex.org/W2009063162","https://openalex.org/W2040227800","https://openalex.org/W2053352232","https://openalex.org/W2059837529","https://openalex.org/W2060314659","https://openalex.org/W2063924830","https://openalex.org/W2084402884","https://openalex.org/W2089536264","https://openalex.org/W2101559328","https://openalex.org/W2106388306","https://openalex.org/W2111075806","https://openalex.org/W2120591095","https://openalex.org/W2120860555","https://openalex.org/W2123855468","https://openalex.org/W2135254996","https://openalex.org/W2161234420","https://openalex.org/W2166293939","https://openalex.org/W2488745596","https://openalex.org/W4232590519"],"related_works":["https://openalex.org/W2148749405","https://openalex.org/W2792289228","https://openalex.org/W2104105430","https://openalex.org/W1515917392","https://openalex.org/W2613320081","https://openalex.org/W1973516247","https://openalex.org/W2743348030","https://openalex.org/W2145292010","https://openalex.org/W2747005099","https://openalex.org/W2086039693"],"abstract_inverted_index":{"Fault":[0],"tolerance":[1,50,97],"is":[2,62,71],"a":[3,23,78,100,126],"key":[4],"obstacle":[5],"to":[6,29],"next":[7],"generation":[8],"extreme-scale":[9,25],"systems.":[10],"As":[11,22],"systems":[12,26],"scale,":[13],"the":[14,36,120],"Mean":[15],"Time":[16],"To":[17,38],"Interrupt":[18],"(MTTI)":[19],"decreases":[20],"proportionally.":[21],"result,":[24],"are":[27,108],"likely":[28],"experience":[30],"higher":[31],"rates":[32],"of":[33,95,103,117],"failure":[34,104],"in":[35,99],"future.":[37],"mitigate":[39],"this,":[40],"significant":[41],"research":[42],"has":[43],"focused":[44],"on":[45,68],"developing":[46],"and":[47,123],"validating":[48],"fault":[49,96],"techniques.":[51],"However,":[52],"evaluating":[53],"techniques":[54,98],"for":[55,81,92,112],"withstanding":[56],"hardware":[57],"failures":[58,67],"at":[59],"large":[60],"scale":[61],"challenging":[63],"because":[64],"replicating":[65],"those":[66],"small-scale":[69],"testbeds":[70,83],"difficult.":[72],"In":[73],"this":[74],"paper,":[75],"we":[76],"propose":[77],"virtualization-based":[79,127],"framework":[80],"creating":[82],"with":[84],"unreliable":[85,114],"virtual":[86],"hardware.":[87],"Our":[88],"proposed":[89],"approach":[90],"allows":[91],"comprehensive":[93],"evaluation":[94],"broad":[101],"range":[102],"regimes.":[105],"Although":[106],"there":[107],"many":[109],"other":[110],"approaches":[111],"mimicking":[113],"hardware,":[115],"none":[116],"them":[118],"offer":[119],"breadth,":[121],"scalability,":[122],"performance":[124],"that":[125],"solution":[128],"does.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
