{"id":"https://openalex.org/W2915972664","doi":"https://doi.org/10.1109/cahpc.2018.8645856","title":"Predicting the Reliability Behavior of HPC Applications","display_name":"Predicting the Reliability Behavior of HPC Applications","publication_year":2018,"publication_date":"2018-09-01","ids":{"openalex":"https://openalex.org/W2915972664","doi":"https://doi.org/10.1109/cahpc.2018.8645856","mag":"2915972664"},"language":"en","primary_location":{"id":"doi:10.1109/cahpc.2018.8645856","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cahpc.2018.8645856","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 30th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD)","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/A5060947874","display_name":"Daniel Oliveira","orcid":"https://orcid.org/0000-0002-8752-3992"},"institutions":[{"id":"https://openalex.org/I130442723","display_name":"Universidade Federal do Rio Grande do Sul","ror":"https://ror.org/041yk2d64","country_code":"BR","type":"education","lineage":["https://openalex.org/I130442723"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Daniel Oliveira","raw_affiliation_strings":["UFRGS, Institute of Informatics, Porto Alegre, Brazil"],"affiliations":[{"raw_affiliation_string":"UFRGS, Institute of Informatics, Porto Alegre, Brazil","institution_ids":["https://openalex.org/I130442723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043896061","display_name":"Francis B. Moreira","orcid":"https://orcid.org/0000-0002-0926-3865"},"institutions":[{"id":"https://openalex.org/I130442723","display_name":"Universidade Federal do Rio Grande do Sul","ror":"https://ror.org/041yk2d64","country_code":"BR","type":"education","lineage":["https://openalex.org/I130442723"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Francis Birck Moreira","raw_affiliation_strings":["UFRGS, Institute of Informatics, Porto Alegre, Brazil"],"affiliations":[{"raw_affiliation_string":"UFRGS, Institute of Informatics, Porto Alegre, Brazil","institution_ids":["https://openalex.org/I130442723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054264208","display_name":"Paolo Rech","orcid":"https://orcid.org/0000-0002-9597-1007"},"institutions":[{"id":"https://openalex.org/I130442723","display_name":"Universidade Federal do Rio Grande do Sul","ror":"https://ror.org/041yk2d64","country_code":"BR","type":"education","lineage":["https://openalex.org/I130442723"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Paolo Rech","raw_affiliation_strings":["UFRGS, Institute of Informatics, Porto Alegre, Brazil"],"affiliations":[{"raw_affiliation_string":"UFRGS, Institute of Informatics, Porto Alegre, Brazil","institution_ids":["https://openalex.org/I130442723"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091234084","display_name":"Philippe O. A. Navaux","orcid":"https://orcid.org/0000-0002-9957-5861"},"institutions":[{"id":"https://openalex.org/I130442723","display_name":"Universidade Federal do Rio Grande do Sul","ror":"https://ror.org/041yk2d64","country_code":"BR","type":"education","lineage":["https://openalex.org/I130442723"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Philippe Navaux","raw_affiliation_strings":["UFRGS, Institute of Informatics, Porto Alegre, Brazil"],"affiliations":[{"raw_affiliation_string":"UFRGS, Institute of Informatics, Porto Alegre, Brazil","institution_ids":["https://openalex.org/I130442723"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5060947874"],"corresponding_institution_ids":["https://openalex.org/I130442723"],"apc_list":null,"apc_paid":null,"fwci":0.2609,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.60335373,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"124","last_page":"131"},"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T11424","display_name":"Security and Verification in Computing","score":0.9839000105857849,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8059179782867432},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.686254620552063},{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.5852391123771667},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.5816437602043152},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5574065446853638},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5209997296333313},{"id":"https://openalex.org/keywords/sorting","display_name":"Sorting","score":0.4945370852947235},{"id":"https://openalex.org/keywords/sorting-algorithm","display_name":"Sorting algorithm","score":0.4154677987098694},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3958624303340912},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2759106159210205},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2753174901008606}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8059179782867432},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.686254620552063},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.5852391123771667},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.5816437602043152},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5574065446853638},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5209997296333313},{"id":"https://openalex.org/C111696304","wikidata":"https://www.wikidata.org/wiki/Q2303697","display_name":"Sorting","level":2,"score":0.4945370852947235},{"id":"https://openalex.org/C108094655","wikidata":"https://www.wikidata.org/wiki/Q181593","display_name":"Sorting algorithm","level":3,"score":0.4154677987098694},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3958624303340912},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2759106159210205},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2753174901008606},{"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cahpc.2018.8645856","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cahpc.2018.8645856","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 30th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD)","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.unitn.it:11572/403746","is_oa":false,"landing_page_url":"https://ieeexplore.ieee.org/document/8645856/keywords#keywords","pdf_url":null,"source":{"id":"https://openalex.org/S4306401913","display_name":"Institutional Research Information System (Universit\u00e0 degli Studi di Trento)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193223587","host_organization_name":"University of Trento","host_organization_lineage":["https://openalex.org/I193223587"],"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":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320321992","display_name":"Minist\u00e9rio da Ci\u00eancia, Tecnologia e Inova\u00e7\u00e3o","ror":"https://ror.org/050zdnc69"},{"id":"https://openalex.org/F4320322468","display_name":"Petrobras","ror":"https://ror.org/0235kyq22"},{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W8143453","https://openalex.org/W83535271","https://openalex.org/W1686420892","https://openalex.org/W1906576859","https://openalex.org/W1967835393","https://openalex.org/W1986905947","https://openalex.org/W1999900893","https://openalex.org/W2009063162","https://openalex.org/W2052887509","https://openalex.org/W2080592089","https://openalex.org/W2093962471","https://openalex.org/W2094446102","https://openalex.org/W2099569658","https://openalex.org/W2101395364","https://openalex.org/W2112121929","https://openalex.org/W2118582701","https://openalex.org/W2119821739","https://openalex.org/W2121082877","https://openalex.org/W2123907700","https://openalex.org/W2137226992","https://openalex.org/W2138263042","https://openalex.org/W2145021036","https://openalex.org/W2148602057","https://openalex.org/W2152365194","https://openalex.org/W2169875292","https://openalex.org/W2201265203","https://openalex.org/W2292932312","https://openalex.org/W2529578574","https://openalex.org/W2621842477","https://openalex.org/W2623205199","https://openalex.org/W2767321582","https://openalex.org/W2884175902","https://openalex.org/W3004493283","https://openalex.org/W3008756550","https://openalex.org/W3149410719","https://openalex.org/W4235343816","https://openalex.org/W4239510810","https://openalex.org/W4244652158","https://openalex.org/W4248228503","https://openalex.org/W6637151178","https://openalex.org/W6680532697"],"related_works":["https://openalex.org/W1974923383","https://openalex.org/W2475524688","https://openalex.org/W2739740241","https://openalex.org/W2085105049","https://openalex.org/W2809748609","https://openalex.org/W2592417500","https://openalex.org/W2526069705","https://openalex.org/W2024016913","https://openalex.org/W2019153376","https://openalex.org/W2981664121"],"abstract_inverted_index":{"The":[0,139],"error":[1,125,142],"rate":[2],"of":[3,15,19,25,35,64,74,126,131],"current":[4],"High":[5],"Performance":[6],"Computing":[7],"(HPC)":[8],"systems":[9],"is":[10,147],"already":[11],"in":[12,80,87],"the":[13,22,32,38,48,62,71,88,112,116,164],"order":[14],"one":[16,41],"per":[17],"dozens":[18],"hours.":[20],"Understanding":[21],"reliability":[23,39,72],"behavior":[24,40,73],"HPC":[26,75,84],"applications":[27,85,167],"will":[28],"be":[29,157],"required":[30],"for":[31,47,128,143],"next":[33],"generation":[34],"supercomputers.":[36],"Using":[37],"can":[42,114,156],"select":[43,163],"efficient":[44],"mitigation":[45],"techniques":[46],"application":[49,63],"and":[50,95,137,152],"fine-tune":[51],"parameters":[52],"such":[53,133],"as":[54,134,159],"checkpoint":[55],"frequency.":[56],"In":[57],"this":[58],"paper,":[59],"we":[60],"investigate":[61],"a":[65,101,150,160],"machine":[66],"learning":[67],"model":[68,103,113,155],"to":[69,99,162,168],"predict":[70,115],"applications.":[76],"We":[77,109],"inject":[78],"faults":[79],"more":[81],"than":[82],"30":[83],"executing":[86],"Intel":[89],"Xeon":[90],"Phi":[91],"Knights":[92],"Landing":[93],"(KNL)":[94],"use":[96],"profiling":[97],"information":[98],"build":[100],"predictive":[102],"with":[104,121],"Support":[105],"Vector":[106],"Machines":[107],"(SVM).":[108],"show":[110],"that":[111],"Program":[117],"Vulnerability":[118],"Factor":[119],"(PVF)":[120],"an":[122,170],"average":[123,140],"relative":[124,141],"7%":[127],"certain":[129],"classes":[130,146],"algorithm,":[132],"linear":[135],"algebra":[136],"sorting.":[138],"all":[144],"algorithm":[145],"22%.":[148],"Such":[149],"fast":[151],"straightforward":[153],"prediction":[154],"effective":[158],"filter":[161],"most":[165],"unreliable":[166],"perform":[169],"in-depth":[171],"analysis.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2019-03-02T00:00:00"}