{"id":"https://openalex.org/W2905530277","doi":"https://doi.org/10.1109/ftxs.2018.00006","title":"Improving Application Resilience by Extending Error Correction with Contextual Information","display_name":"Improving Application Resilience by Extending Error Correction with Contextual Information","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2905530277","doi":"https://doi.org/10.1109/ftxs.2018.00006","mag":"2905530277"},"language":"en","primary_location":{"id":"doi:10.1109/ftxs.2018.00006","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ftxs.2018.00006","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/ACM 8th Workshop on Fault Tolerance for HPC at eXtreme Scale (FTXS)","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/A5036647444","display_name":"Alexandra Poulos","orcid":"https://orcid.org/0000-0003-2890-3570"},"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":true,"raw_author_name":"Alexandra Poulos","raw_affiliation_strings":["Ultrascale Syst. Res. Center, Los Alamos Nat. Lab., Los Alamos, NM, USA"],"affiliations":[{"raw_affiliation_string":"Ultrascale Syst. Res. Center, Los Alamos Nat. Lab., Los Alamos, NM, USA","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089882862","display_name":"Dylan M Wallace","orcid":"https://orcid.org/0000-0003-2770-3614"},"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":"Dylan Wallace","raw_affiliation_strings":["Ultrascale Syst. Res. Center, Los Alamos Nat. Lab., Los Alamos, NM, USA"],"affiliations":[{"raw_affiliation_string":"Ultrascale Syst. Res. Center, Los Alamos Nat. Lab., Los Alamos, NM, USA","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027394799","display_name":"Robert Robey","orcid":"https://orcid.org/0000-0001-5018-5793"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Robert Robey","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006310347","display_name":"Laura Monroe","orcid":"https://orcid.org/0000-0002-7175-0103"},"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":"Laura Monroe","raw_affiliation_strings":["Ultrascale Syst. Res. Center, Los Alamos Nat. Lab., Los Alamos, NM, USA"],"affiliations":[{"raw_affiliation_string":"Ultrascale Syst. Res. Center, Los Alamos Nat. Lab., Los Alamos, NM, USA","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048163948","display_name":"Vanessa Job","orcid":"https://orcid.org/0000-0002-3240-5999"},"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":"Vanessa Job","raw_affiliation_strings":["Ultrascale Syst. Res. Center, Los Alamos Nat. Lab., Los Alamos, NM, USA"],"affiliations":[{"raw_affiliation_string":"Ultrascale Syst. Res. Center, Los Alamos Nat. Lab., Los Alamos, NM, USA","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036921385","display_name":"Sean Blanchard","orcid":"https://orcid.org/0000-0002-1119-7828"},"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":"Sean Blanchard","raw_affiliation_strings":["Ultrascale Syst. Res. Center, Los Alamos Nat. Lab., Los Alamos, NM, USA"],"affiliations":[{"raw_affiliation_string":"Ultrascale Syst. Res. Center, Los Alamos Nat. Lab., Los Alamos, NM, USA","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062187807","display_name":"William M. Jones","orcid":"https://orcid.org/0000-0002-3796-6330"},"institutions":[{"id":"https://openalex.org/I4210152127","display_name":"Conway School of Landscape Design","ror":"https://ror.org/04q7y8a54","country_code":"US","type":"education","lineage":["https://openalex.org/I4210152127"]},{"id":"https://openalex.org/I208081647","display_name":"Coastal Carolina University","ror":"https://ror.org/01621q256","country_code":"US","type":"education","lineage":["https://openalex.org/I208081647"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William Jones","raw_affiliation_strings":["Dept. of Comput. Sci., Coastal Carolina Univ., Conway, SC, USA"],"affiliations":[{"raw_affiliation_string":"Dept. of Comput. Sci., Coastal Carolina Univ., Conway, SC, USA","institution_ids":["https://openalex.org/I208081647","https://openalex.org/I4210152127"]}]},{"author_position":"last","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":["Ultrascale Syst. Res. Center, Los Alamos Nat. Lab., Los Alamos, NM, USA"],"affiliations":[{"raw_affiliation_string":"Ultrascale Syst. Res. Center, Los Alamos Nat. Lab., Los Alamos, NM, USA","institution_ids":["https://openalex.org/I1343871089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5036647444"],"corresponding_institution_ids":["https://openalex.org/I1343871089"],"apc_list":null,"apc_paid":null,"fwci":0.9013,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.76924902,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"19","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9991999864578247,"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":0.9955999851226807,"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":0.8431184887886047},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.7784414291381836},{"id":"https://openalex.org/keywords/resilience","display_name":"Resilience (materials science)","score":0.6406424045562744},{"id":"https://openalex.org/keywords/scope","display_name":"Scope (computer science)","score":0.5913752913475037},{"id":"https://openalex.org/keywords/closeness","display_name":"Closeness","score":0.5549371242523193},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.5453020334243774},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5357828140258789},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.5067513585090637},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5060996413230896},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3748914897441864},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3610408306121826},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3391031324863434},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2653982639312744},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08743977546691895}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8431184887886047},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.7784414291381836},{"id":"https://openalex.org/C2779585090","wikidata":"https://www.wikidata.org/wiki/Q3457762","display_name":"Resilience (materials science)","level":2,"score":0.6406424045562744},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.5913752913475037},{"id":"https://openalex.org/C2779545769","wikidata":"https://www.wikidata.org/wiki/Q5135364","display_name":"Closeness","level":2,"score":0.5549371242523193},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.5453020334243774},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5357828140258789},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.5067513585090637},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5060996413230896},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3748914897441864},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3610408306121826},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3391031324863434},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2653982639312744},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08743977546691895},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ftxs.2018.00006","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ftxs.2018.00006","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/ACM 8th Workshop on Fault Tolerance for HPC at eXtreme Scale (FTXS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W177148063","https://openalex.org/W1906576859","https://openalex.org/W1986624837","https://openalex.org/W1986905947","https://openalex.org/W2021708499","https://openalex.org/W2027254858","https://openalex.org/W2037342473","https://openalex.org/W2083613288","https://openalex.org/W2083774980","https://openalex.org/W2232241911","https://openalex.org/W2289794612","https://openalex.org/W2342204193","https://openalex.org/W2529344296","https://openalex.org/W2617703063","https://openalex.org/W2631994569"],"related_works":["https://openalex.org/W2156910174","https://openalex.org/W1995054232","https://openalex.org/W2011510925","https://openalex.org/W1667647204","https://openalex.org/W1557920161","https://openalex.org/W2404647514","https://openalex.org/W1556709767","https://openalex.org/W4247536566","https://openalex.org/W2394408226","https://openalex.org/W4389168214"],"abstract_inverted_index":{"Extreme-scale":[0],"systems":[1,16],"are":[2,17,25,92,109,116],"growing":[3],"in":[4,14,101,140,150],"scope":[5],"and":[6,41,45,57,73,111,132,188],"complexity":[7],"as":[8],"we":[9,32],"approach":[10,49],"exascale.":[11],"Uncorrectable":[12],"faults":[13],"such":[15],"also":[18],"increasing,":[19],"so":[20],"resilience":[21],"efforts":[22],"addressing":[23],"these":[24],"of":[26,107,135,142,146,152,157,164,183,192],"great":[27,174],"importance.":[28],"In":[29],"this":[30,62,81,128,158,201],"paper,":[31],"extend":[33],"a":[34,104,177,190,204],"method":[35,64],"that":[36,50,78,88,199],"augments":[37],"hardware":[38],"error":[39],"detection":[40],"correction":[42,95],"(EDAC)":[43],"contextually,":[44],"show":[46,87],"an":[47],"application-based":[48,63],"takes":[51],"detectable":[52],"uncorrectable":[53],"(DUE)":[54],"data":[55,67,115],"errors":[56,68],"corrects":[58],"them.":[59],"We":[60,86,121],"applied":[61],"successfully":[65],"to":[66,119,195],"found":[69],"using":[70],"common":[71],"EDAC,":[72],"discuss":[74],"operating":[75],"system":[76],"changes":[77,194],"will":[79],"make":[80,200],"possible":[82,202],"on":[83,176,203],"existing":[84],"systems.":[85],"even":[89,112],"when":[90],"there":[91],"many":[93],"acceptable":[94],"choices":[96],"(which":[97],"may":[98],"be":[99],"seen":[100],"floating":[102],"point),":[103],"large":[105],"percentage":[106],"DUEs":[108],"corrected,":[110],"the":[113,162,181,196],"miscorrected":[114],"very":[117],"close":[118],"correct.":[120],"developed":[122],"two":[123,184],"different":[124,185],"contextual":[125,168,186],"criteria":[126],"for":[127],"application:":[129],"local":[130],"averaging":[131,149],"global":[133],"conservation":[134,145],"mass.":[136],"Both":[137],"did":[138],"well":[139],"terms":[141,151],"closeness,":[143],"but":[144],"mass":[147],"outperformed":[148],"actual":[153],"correctness.":[154],"The":[155],"contributions":[156],"paper":[159],"are:":[160],"1)":[161],"idea":[163],"application-":[165],"specific":[166],"EDAC-based":[167],"correction,":[169],"2)":[170],"its":[171],"demonstration":[172],"with":[173],"success":[175],"real":[178,205],"application,":[179],"3)":[180],"development":[182],"criteria,":[187],"4)":[189],"discussion":[191],"attainable":[193],"OS":[197],"kernel":[198],"system.":[206]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
