{"id":"https://openalex.org/W2905158619","doi":"https://doi.org/10.1109/ftxs.2018.00004","title":"Towards Ad Hoc Recovery for Soft Errors","display_name":"Towards Ad Hoc Recovery for Soft Errors","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2905158619","doi":"https://doi.org/10.1109/ftxs.2018.00004","mag":"2905158619"},"language":"en","primary_location":{"id":"doi:10.1109/ftxs.2018.00004","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ftxs.2018.00004","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":true,"oa_status":"green","oa_url":"https://hdl.handle.net/2117/133802","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078142249","display_name":"Nuria Losada","orcid":"https://orcid.org/0000-0002-1327-0478"},"institutions":[{"id":"https://openalex.org/I11019714","display_name":"Universidade da Coru\u00f1a","ror":"https://ror.org/01qckj285","country_code":"ES","type":"education","lineage":["https://openalex.org/I11019714"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Nuria Losada","raw_affiliation_strings":["Universidade da Coru\u00f1a A Coru\u00f1a, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidade da Coru\u00f1a A Coru\u00f1a, Spain","institution_ids":["https://openalex.org/I11019714"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013543252","display_name":"Leonardo Bautista-Gomez","orcid":"https://orcid.org/0000-0002-0814-5779"},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Leonardo Bautista-Gomez","raw_affiliation_strings":["Barcelona Supercomputing Center, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014760960","display_name":"Kai Keller","orcid":"https://orcid.org/0000-0002-7023-6890"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]},{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Kai Keller","raw_affiliation_strings":["Barcelona Supercomputing Center, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075162875","display_name":"Osman \u00dcnsal","orcid":"https://orcid.org/0000-0002-0544-9697"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]},{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Osman Unsal","raw_affiliation_strings":["Barcelona Supercomputing Center, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5078142249"],"corresponding_institution_ids":["https://openalex.org/I11019714"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14112751,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"11","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":1.0,"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":1.0,"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":0.9994999766349792,"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/T10472","display_name":"Semiconductor materials and devices","score":0.9911999702453613,"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/computer-science","display_name":"Computer science","score":0.8483633995056152},{"id":"https://openalex.org/keywords/dram","display_name":"Dram","score":0.7750916481018066},{"id":"https://openalex.org/keywords/soft-error","display_name":"Soft error","score":0.7075417041778564},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5654965043067932},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.4695095717906952},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.4454091489315033},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.42104262113571167},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.37979432940483093},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3240087628364563},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3230815529823303},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2330869436264038},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.2226831018924713},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10659697651863098}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8483633995056152},{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.7750916481018066},{"id":"https://openalex.org/C154474529","wikidata":"https://www.wikidata.org/wiki/Q1658917","display_name":"Soft error","level":2,"score":0.7075417041778564},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5654965043067932},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.4695095717906952},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.4454091489315033},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.42104262113571167},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.37979432940483093},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3240087628364563},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3230815529823303},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2330869436264038},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.2226831018924713},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10659697651863098},{"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},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/ftxs.2018.00004","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ftxs.2018.00004","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"},{"id":"pmh:oai:upcommons.upc.edu:2117/133802","is_oa":true,"landing_page_url":"https://hdl.handle.net/2117/133802","pdf_url":null,"source":{"id":"https://openalex.org/S4377196262","display_name":"UPCommons institutional repository (Universitat Polit\u00e8cnica de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9617848","host_organization_name":"Universitat Polit\u00e8cnica de Catalunya","host_organization_lineage":["https://openalex.org/I9617848"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:recercat.cat:2072/356815","is_oa":true,"landing_page_url":"http://hdl.handle.net/2117/133802","pdf_url":null,"source":{"id":"https://openalex.org/S4306402147","display_name":"RECERCAT (Consorci de Serveis Universitaris de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210090028","host_organization_name":"Consorci de Serveis Universitaris de Catalunya","host_organization_lineage":["https://openalex.org/I4210090028"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/submittedVersion"}],"best_oa_location":{"id":"pmh:oai:upcommons.upc.edu:2117/133802","is_oa":true,"landing_page_url":"https://hdl.handle.net/2117/133802","pdf_url":null,"source":{"id":"https://openalex.org/S4377196262","display_name":"UPCommons institutional repository (Universitat Polit\u00e8cnica de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9617848","host_organization_name":"Universitat Polit\u00e8cnica de Catalunya","host_organization_lineage":["https://openalex.org/I9617848"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1496055848","display_name":null,"funder_award_id":"ED431C","funder_id":"https://openalex.org/F4320326655","funder_display_name":"Xunta de Galicia"},{"id":"https://openalex.org/G2083635853","display_name":null,"funder_award_id":"TIN2016-75845-P","funder_id":"https://openalex.org/F4320321837","funder_display_name":"Ministerio de Econom\u00eda y Competitividad"},{"id":"https://openalex.org/G5136360197","display_name":null,"funder_award_id":"ED431C 2017/04","funder_id":"https://openalex.org/F4320326655","funder_display_name":"Xunta de Galicia"},{"id":"https://openalex.org/G5799383929","display_name":null,"funder_award_id":"TIN2016-75845-P","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7842005466","display_name":null,"funder_award_id":"Horizon 2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8821661476","display_name":"DURO: Deep-memory Ubiquity, Reliability and Optimization","funder_award_id":"708566","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321837","display_name":"Ministerio de Econom\u00eda y Competitividad","ror":"https://ror.org/034900433"},{"id":"https://openalex.org/F4320326655","display_name":"Xunta de Galicia","ror":"https://ror.org/0181xnw06"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W79276452","https://openalex.org/W1584278023","https://openalex.org/W1847519410","https://openalex.org/W1898823215","https://openalex.org/W1981432246","https://openalex.org/W1986905947","https://openalex.org/W1989653583","https://openalex.org/W2033656974","https://openalex.org/W2044681268","https://openalex.org/W2063924830","https://openalex.org/W2072072075","https://openalex.org/W2083613288","https://openalex.org/W2084293824","https://openalex.org/W2088552220","https://openalex.org/W2096504919","https://openalex.org/W2116115793","https://openalex.org/W2122249806","https://openalex.org/W2128577831","https://openalex.org/W2133046454","https://openalex.org/W2142812297","https://openalex.org/W2145071552","https://openalex.org/W2151984682","https://openalex.org/W2152652532","https://openalex.org/W2158344138","https://openalex.org/W2168405877","https://openalex.org/W2285867394","https://openalex.org/W2339228518","https://openalex.org/W2403702746","https://openalex.org/W2466095195","https://openalex.org/W2499897168","https://openalex.org/W2526559026","https://openalex.org/W2567223979","https://openalex.org/W2592134152","https://openalex.org/W2751243270","https://openalex.org/W2760795988","https://openalex.org/W2963258975","https://openalex.org/W6603243439","https://openalex.org/W6634921276","https://openalex.org/W6639032754","https://openalex.org/W6684440641","https://openalex.org/W6720024917","https://openalex.org/W6734607763","https://openalex.org/W6742789551","https://openalex.org/W6744941099"],"related_works":["https://openalex.org/W2162457113","https://openalex.org/W1528863892","https://openalex.org/W2007444174","https://openalex.org/W1528544434","https://openalex.org/W2138596439","https://openalex.org/W2152643014","https://openalex.org/W1489210541","https://openalex.org/W3141188004","https://openalex.org/W2000563648","https://openalex.org/W3146244088"],"abstract_inverted_index":{"The":[0,145],"coming":[1],"exascale":[2],"era":[3],"is":[4],"a":[5,39,90,113,166],"great":[6],"opportunity":[7],"for":[8,38,133],"high":[9,15],"performance":[10],"computing":[11],"(HPC)":[12],"applications.":[13],"However,":[14],"failure":[16],"rates":[17],"on":[18,155,168],"these":[19,104],"systems":[20],"will":[21,76],"hazard":[22],"the":[23,43,79,82,85,97,121,127,137,169],"successful":[24],"completion":[25],"of":[26,42,78,84,106,129],"their":[27],"execution.":[28],"Bit-flip":[29],"errors":[30,60,66,75],"in":[31,45],"dynamic":[32],"random":[33],"access":[34],"memory":[35],"(DRAM)":[36],"account":[37],"noticeable":[40],"share":[41],"failures":[44],"supercomputers.":[46],"Hardware":[47],"mechanisms,":[48],"such":[49],"as":[50],"error":[51],"correcting":[52],"code":[53],"(ECC),":[54],"can":[55,62,69],"detect":[56,63],"and":[57,61,87,110],"correct":[58],"single-bit":[59],"some":[64],"multi-bit":[65,74],"while":[67],"others":[68],"go":[70],"undiscovered.":[71],"Unfortunately,":[72],"detected":[73],"most":[77],"time":[80],"force":[81],"termination":[83],"application":[86],"lead":[88],"to":[89,102,111,125,174],"global":[91,114],"restart.":[92,115],"Thus,":[93],"other":[94],"strategies":[95,132],"at":[96],"software":[98],"level":[99],"are":[100,148],"needed":[101],"tolerate":[103],"type":[105],"faults":[107],"more":[108],"efficiently":[109],"avoid":[112],"In":[116],"this":[117],"work,":[118],"we":[119],"extend":[120],"FTI":[122],"checkpointing":[123],"library":[124],"facilitate":[126],"implementation":[128],"custom":[130],"recovery":[131,154,170],"MPI":[134],"applications,":[135],"minimizing":[136],"overhead":[138],"introduced":[139],"when":[140],"coping":[141],"with":[142,159],"soft":[143],"errors.":[144],"new":[146],"functionalities":[147],"evaluated":[149],"by":[150,172],"implementing":[151],"local":[152],"forward":[153],"three":[156],"HPC":[157],"benchmarks":[158],"different":[160],"reliability":[161],"requirements.":[162],"Our":[163],"results":[164],"demonstrate":[165],"reduction":[167],"times":[171],"up":[173],"14%.":[175]},"counts_by_year":[],"updated_date":"2026-05-09T13:55:54.758798","created_date":"2025-10-10T00:00:00"}
