{"id":"https://openalex.org/W2068790862","doi":"https://doi.org/10.1109/hpcsim.2014.6903692","title":"Opportunistic application-level fault detection through adaptive redundant multithreading","display_name":"Opportunistic application-level fault detection through adaptive redundant multithreading","publication_year":2014,"publication_date":"2014-07-01","ids":{"openalex":"https://openalex.org/W2068790862","doi":"https://doi.org/10.1109/hpcsim.2014.6903692","mag":"2068790862"},"language":"en","primary_location":{"id":"doi:10.1109/hpcsim.2014.6903692","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcsim.2014.6903692","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 International Conference on High Performance Computing &amp; Simulation (HPCS)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/biblio/1141739","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065625558","display_name":"Saurabh Hukerikar","orcid":"https://orcid.org/0000-0002-2612-2001"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saurabh Hukerikar","raw_affiliation_strings":["Information Sciences Institute University of Southern California, Marina del Rey, CA, USA","Information Sciences Institute, University of Southern California, Marina Del Rey, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Sciences Institute University of Southern California, Marina del Rey, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Information Sciences Institute, University of Southern California, Marina Del Rey, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042540194","display_name":"Pedro C. Diniz","orcid":"https://orcid.org/0000-0003-3131-9367"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pedro C. Diniz","raw_affiliation_strings":["Information Sciences Institute University of Southern California, Marina del Rey, CA, USA","Information Sciences Institute, University of Southern California, Marina Del Rey, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Sciences Institute University of Southern California, Marina del Rey, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Information Sciences Institute, University of Southern California, Marina Del Rey, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025422213","display_name":"Robert F. Lucas","orcid":"https://orcid.org/0000-0003-1303-2012"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert F. Lucas","raw_affiliation_strings":["Information Sciences Institute University of Southern California, Marina del Rey, CA, USA","Information Sciences Institute, University of Southern California, Marina Del Rey, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Sciences Institute University of Southern California, Marina del Rey, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Information Sciences Institute, University of Southern California, Marina Del Rey, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019745966","display_name":"Keita Teranishi","orcid":"https://orcid.org/0000-0001-6647-2690"},"institutions":[{"id":"https://openalex.org/I192454743","display_name":"Sandia National Laboratories California","ror":"https://ror.org/058m7ey48","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1330989302","https://openalex.org/I192454743","https://openalex.org/I198811213","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Keita Teranishi","raw_affiliation_strings":["Sandia National Laboratories, Livermore, CA, USA","Sandia National Labs Livermore CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories, Livermore, CA, USA","institution_ids":["https://openalex.org/I192454743"]},{"raw_affiliation_string":"Sandia National Labs Livermore CA, USA","institution_ids":["https://openalex.org/I192454743"]}]}],"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":20,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"243","last_page":"250"},"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/T11005","display_name":"Radiation Effects in Electronics","score":0.9994999766349792,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9987999796867371,"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/computer-science","display_name":"Computer science","score":0.8593741059303284},{"id":"https://openalex.org/keywords/multithreading","display_name":"Multithreading","score":0.6582287549972534},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.6575287580490112},{"id":"https://openalex.org/keywords/programmer","display_name":"Programmer","score":0.5797485113143921},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.5500978231430054},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.528436005115509},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5176606774330139},{"id":"https://openalex.org/keywords/fault-detection-and-isolation","display_name":"Fault detection and isolation","score":0.4843548536300659},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.45182767510414124},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.44108352065086365},{"id":"https://openalex.org/keywords/runtime-system","display_name":"Runtime system","score":0.4183214008808136},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.38735488057136536},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.3808583617210388},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.22233238816261292},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1245209276676178}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8593741059303284},{"id":"https://openalex.org/C201410400","wikidata":"https://www.wikidata.org/wiki/Q1064412","display_name":"Multithreading","level":3,"score":0.6582287549972534},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6575287580490112},{"id":"https://openalex.org/C2778514511","wikidata":"https://www.wikidata.org/wiki/Q1374194","display_name":"Programmer","level":2,"score":0.5797485113143921},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.5500978231430054},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.528436005115509},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5176606774330139},{"id":"https://openalex.org/C152745839","wikidata":"https://www.wikidata.org/wiki/Q5438153","display_name":"Fault detection and isolation","level":3,"score":0.4843548536300659},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.45182767510414124},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.44108352065086365},{"id":"https://openalex.org/C2780870223","wikidata":"https://www.wikidata.org/wiki/Q1004415","display_name":"Runtime system","level":2,"score":0.4183214008808136},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.38735488057136536},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.3808583617210388},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.22233238816261292},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1245209276676178},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.0},{"id":"https://openalex.org/C172707124","wikidata":"https://www.wikidata.org/wiki/Q423488","display_name":"Actuator","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/hpcsim.2014.6903692","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcsim.2014.6903692","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 International Conference on High Performance Computing &amp; Simulation (HPCS)","raw_type":"proceedings-article"},{"id":"pmh:oai:osti.gov:1141739","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1141739","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},{"id":"pmh:oai:osti.gov:1145854","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1145854","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:osti.gov:1141739","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1141739","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W79276452","https://openalex.org/W1579215414","https://openalex.org/W2012179240","https://openalex.org/W2034593585","https://openalex.org/W2036641664","https://openalex.org/W2037459596","https://openalex.org/W2038238534","https://openalex.org/W2063924830","https://openalex.org/W2102480715","https://openalex.org/W2113036804","https://openalex.org/W4295098767","https://openalex.org/W6603243439","https://openalex.org/W6637900507","https://openalex.org/W6675837356"],"related_works":["https://openalex.org/W4244698026","https://openalex.org/W35114839","https://openalex.org/W1581434145","https://openalex.org/W1471781652","https://openalex.org/W973343392","https://openalex.org/W2110897014","https://openalex.org/W2158819012","https://openalex.org/W66392291","https://openalex.org/W2087364340","https://openalex.org/W2187874404"],"abstract_inverted_index":{"As":[0],"the":[1,14,60,64,75,119,146,153,156,184,189,216,223,237,246,250],"scale":[2],"and":[3,19,21,41,66,94,134,165,181,239],"complexity":[4],"of":[5,17,38,59,78,145,155,188,225,236,241,252],"future":[6,82],"High":[7],"Performance":[8],"Computing":[9],"systems":[10,85],"continues":[11],"to":[12,32,71,218,227,230],"grow,":[13],"rising":[15],"frequency":[16],"faults":[18],"errors":[20,141],"their":[22,135,171],"impact":[23],"on":[24,110],"HPC":[25],"applications":[26],"will":[27,150],"make":[28],"it":[29],"increasingly":[30],"difficult":[31],"accomplish":[33],"useful":[34],"computation.":[35],"Traditional":[36],"means":[37],"fault":[39,104,185,199],"detection":[40,93,105],"correction":[42],"are":[43,129,221],"either":[44],"hardware":[45],"based":[46,50,53,109],"or":[47,63],"use":[48,77],"software":[49],"redundancy.":[51,211],"Redundancy":[52],"approaches":[54],"usually":[55],"entail":[56],"complete":[57,258],"replication":[58],"program":[61,147],"state":[62,148,187],"computation":[65],"therefore":[67],"incurs":[68],"substantial":[69],"overhead":[70,248],"application":[72,102,157,197,219],"performance.":[73],"Therefore,":[74],"wide-scale":[76],"full":[79,210],"redundancy":[80],"in":[81,142,222,249],"exascale":[83],"class":[84],"is":[86,108,255],"not":[87],"a":[88,115,166],"viable":[89],"solution":[90],"for":[91,196],"error":[92],"correction.":[95],"In":[96],"this":[97],"paper":[98],"we":[99,138],"present":[100],"an":[101],"level":[103,117],"approach":[106,202],"that":[107,149,215,254],"adaptive":[111],"redundant":[112,174],"multithreading.":[113],"Through":[114],"language":[116],"directive,":[118],"programmer":[120],"can":[121,139],"define":[122],"structured":[123],"code":[124,163],"blocks.":[125],"When":[126],"these":[127],"blocks":[128,164,195],"executed":[130],"by":[131,173,178,257],"multiple":[132],"threads":[133,175],"outputs":[136],"compared,":[137],"detect":[140],"specific":[143,198],"parts":[144],"ultimately":[151],"determine":[152],"correctness":[154],"outcome.":[158],"The":[159],"compiler":[160],"outlines":[161],"such":[162],"runtime":[167,231],"system":[168,232,242],"reasons":[169],"whether":[170],"execution":[172],"should":[176],"enabled/disabled":[177],"continuously":[179,234],"observing":[180],"learning":[182],"about":[183],"tolerance":[186],"system.":[190],"By":[191],"providing":[192],"flexible":[193],"building":[194],"detection,":[200],"our":[201],"makes":[203],"possible":[204],"more":[205],"reasonable":[206],"performance":[207,220],"overheads":[208,217],"than":[209,245],"Our":[212],"results":[213],"show":[214],"range":[224],"4%":[226],"70%":[228],"due":[229],"being":[233],"aware":[235],"rate":[238],"source":[240],"faults,":[243],"rather":[244],"usual":[247],"excess":[251],"100%":[253],"incurred":[256],"replication.":[259]},"counts_by_year":[{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
