{"id":"https://openalex.org/W3022067362","doi":"https://doi.org/10.1109/tdsc.2020.2991136","title":"Characterizing and Exploiting Soft Error Vulnerability Phase Behavior in GPU Applications","display_name":"Characterizing and Exploiting Soft Error Vulnerability Phase Behavior in GPU Applications","publication_year":2020,"publication_date":"2020-04-28","ids":{"openalex":"https://openalex.org/W3022067362","doi":"https://doi.org/10.1109/tdsc.2020.2991136","mag":"3022067362"},"language":"en","primary_location":{"id":"doi:10.1109/tdsc.2020.2991136","doi":"https://doi.org/10.1109/tdsc.2020.2991136","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tdsc.2020.2991136","pdf_url":null,"source":{"id":"https://openalex.org/S133795288","display_name":"IEEE Transactions on Dependable and Secure Computing","issn_l":"1545-5971","issn":["1545-5971","1941-0018","2160-9209"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","ccf-a","cwts-core","dongbi-a","jufo-3","norway-2","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Dependable and Secure Computing","raw_type":"journal-article"},"volume":null,"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/A5015262116","display_name":"Fritz Gerald Previlon","orcid":"https://orcid.org/0000-0002-1424-0908","observed_orcids":["https://orcid.org/0000-0002-1424-0908"]},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fritz Previlon","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-1424-0908","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086493644","display_name":"Charu Kalra","orcid":"https://orcid.org/0009-0004-8952-7999","observed_orcids":["https://orcid.org/0009-0004-8952-7999"]},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charu Kalra","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074406596","display_name":"Devesh Tiwari","orcid":"https://orcid.org/0000-0002-7253-2458","observed_orcids":["https://orcid.org/0000-0002-7253-2458"]},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Devesh Tiwari","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061128237","display_name":"David R Kaeli","orcid":"https://orcid.org/0000-0002-5692-0151","observed_orcids":["https://orcid.org/0000-0002-5692-0151"]},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Kaeli","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-5692-0151","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I12912129"],"apc_list":{"value":2045,"currency":"USD","value_usd":2045},"apc_paid":null,"fwci":0.9035,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.74694697,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":98},"biblio":{"volume":"19","issue":"1","first_page":"288","last_page":"300"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.5845000147819519,"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":0.5845000147819519,"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":0.24740000069141388,"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":0.0860000029206276,"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/soft-errors","display_name":"soft errors","score":0.843999981880188},{"id":"https://openalex.org/keywords/transient-faults","display_name":"transient faults","score":0.921999990940094},{"id":"https://openalex.org/keywords/gpu-reliability","display_name":"GPU reliability","score":0.7110000252723694},{"id":"https://openalex.org/keywords/fault-injection","display_name":"fault injection","score":0.699999988079071},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"fault tolerance","score":0.5529999732971191}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8714777231216431},{"id":"https://openalex.org/C2775928411","wikidata":"https://www.wikidata.org/wiki/Q2041312","display_name":"Fault injection","level":3,"score":0.7118718028068542},{"id":"https://openalex.org/C154474529","wikidata":"https://www.wikidata.org/wiki/Q1658917","display_name":"Soft error","level":2,"score":0.6556527614593506},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.639305830001831},{"id":"https://openalex.org/C2779585090","wikidata":"https://www.wikidata.org/wiki/Q3457762","display_name":"Resilience (materials science)","level":2,"score":0.6118558645248413},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5917884111404419},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5553996562957764},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.5228241682052612},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.5030607581138611},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.4880124628543854},{"id":"https://openalex.org/C2780799671","wikidata":"https://www.wikidata.org/wiki/Q17087362","display_name":"Transient (computer programming)","level":2,"score":0.48789143562316895},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.43383553624153137},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4194168746471405},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.32943636178970337},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.2113630771636963},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.12292507290840149},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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":1,"locations":[{"id":"doi:10.1109/tdsc.2020.2991136","doi":"https://doi.org/10.1109/tdsc.2020.2991136","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tdsc.2020.2991136","pdf_url":null,"source":{"id":"https://openalex.org/S133795288","display_name":"IEEE Transactions on Dependable and Secure Computing","issn_l":"1545-5971","issn":["1545-5971","1941-0018","2160-9209"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","ccf-a","cwts-core","dongbi-a","jufo-3","norway-2","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Dependable and Secure Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1493984463","https://openalex.org/W1652659619","https://openalex.org/W1825939613","https://openalex.org/W1902930330","https://openalex.org/W1969241238","https://openalex.org/W1987971958","https://openalex.org/W1997162567","https://openalex.org/W2019510539","https://openalex.org/W2027716782","https://openalex.org/W2028687031","https://openalex.org/W2052887509","https://openalex.org/W2080592089","https://openalex.org/W2098290747","https://openalex.org/W2111204461","https://openalex.org/W2123475473","https://openalex.org/W2124164102","https://openalex.org/W2148602057","https://openalex.org/W2148644350","https://openalex.org/W2154702295","https://openalex.org/W2169184353","https://openalex.org/W2234148183","https://openalex.org/W2267020949","https://openalex.org/W2318507312","https://openalex.org/W2411279070","https://openalex.org/W2534849208","https://openalex.org/W2612733213","https://openalex.org/W2735162286","https://openalex.org/W2760096114","https://openalex.org/W2767321582","https://openalex.org/W2770705319","https://openalex.org/W2799222055","https://openalex.org/W2883034956","https://openalex.org/W2902078285","https://openalex.org/W2902203584","https://openalex.org/W2905075051","https://openalex.org/W2945222589","https://openalex.org/W2981834872","https://openalex.org/W3003337951","https://openalex.org/W3015385986","https://openalex.org/W3031001329","https://openalex.org/W3146229818","https://openalex.org/W4234144196","https://openalex.org/W4235185688","https://openalex.org/W4244241786","https://openalex.org/W4244593655","https://openalex.org/W4248228503","https://openalex.org/W4249144718","https://openalex.org/W4250247110","https://openalex.org/W4252854535","https://openalex.org/W4255616683"],"related_works":["https://openalex.org/W7221385016","https://openalex.org/W3211099997","https://openalex.org/W4310449167","https://openalex.org/W3026559766","https://openalex.org/W4253596634","https://openalex.org/W6906992339","https://openalex.org/W2945222589","https://openalex.org/W2981834872","https://openalex.org/W2027716782","https://openalex.org/W4408564311"],"abstract_inverted_index":{"System":[0],"reliability":[1,142],"has":[2],"become":[3],"a":[4,113],"first-class":[5],"design":[6],"constraint.":[7],"As":[8],"the":[9,32,43,59,93,109,137],"use":[10],"of":[11,34,42,46,62,83,96,144,150],"Graphics":[12],"Processing":[13],"Units":[14],"(GPU)":[15],"continues":[16],"to":[17,117,135],"increase":[18],"in":[19,37,50,108,121],"compute":[20],"applications,":[21,29],"including":[22],"High":[23],"Performance":[24],"Computing":[25],"(HPC)":[26],"and":[27,70,103,152],"safety-critical":[28],"so":[30],"do":[31,86],"number":[33],"transient":[35,47],"faults":[36],"GPUs.":[38],"However,":[39],"our":[40],"understanding":[41],"potential":[44],"impact":[45],"fault":[48,138],"propagation":[49],"GPU":[51,63,84,97,145],"applications":[52],"remains":[53],"limited.":[54],"This":[55],"study":[56],"shows":[57],"that":[58,105],"resilience":[60,81,159],"characteristics":[61,72,82],"programs":[64,85,146],"change":[65],"significantly":[66],"during":[67,112],"program":[68],"execution":[69,115,124],"these":[71,78,130],"show":[73],"repetitive,":[74,79],"time-varying":[75],"behavior.":[76],"Interestingly,":[77],"time-varying,":[80],"not":[87],"align":[88],"or":[89],"correlate":[90],"well":[91],"with":[92,119],"performance":[94],"phases":[95],"programs.":[98],"Furthermore,":[99],"this":[100],"work":[101],"discovers":[102],"validates":[104],"temporal":[106],"changes":[107,120],"vulnerability":[110],"behavior":[111],"kernel":[114],"tends":[116],"coincide":[118],"basic":[122],"block":[123],"paths.":[125],"Finally,":[126],"we":[127],"demonstrate":[128],"how":[129],"observations":[131],"can":[132],"be":[133],"exploited":[134],"accelerate":[136],"injection":[139],"campaigns":[140],"for":[141,155],"assessment":[143],"by":[147],"an":[148],"order":[149],"magnitude":[151],"open":[153],"opportunities":[154],"designing":[156],"other":[157],"effective":[158],"mitigation":[160],"strategies.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2020-05-13T00:00:00"}