{"id":"https://openalex.org/W2902078285","doi":"https://doi.org/10.1109/sc.2018.00072","title":"PRISM: Predicting Resilience of GPU Applications Using Statistical Methods","display_name":"PRISM: Predicting Resilience of GPU Applications Using Statistical Methods","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2902078285","doi":"https://doi.org/10.1109/sc.2018.00072","mag":"2902078285"},"language":"en","primary_location":{"id":"doi:10.1109/sc.2018.00072","doi":"https://doi.org/10.1109/sc.2018.00072","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sc.2018.00072","pdf_url":null,"source":{"id":"https://openalex.org/S4363608557","display_name":"International Conference for High Performance Computing, Networking, Storage and Analysis (SC)","issn_l":"2167-4337","issn":["2167-4337"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SC18: International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/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":["Northeastern University, Boston, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, MA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","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":["Northeastern University, Boston, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, MA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100460303","display_name":"Xiangyu Li","orcid":"https://orcid.org/0000-0001-5538-7829","observed_orcids":["https://orcid.org/0000-0001-5538-7829"]},"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":"Xiangyu Li","raw_affiliation_strings":["Northeastern University, Boston, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, MA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036463155","display_name":"Norman Rubin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Norman Rubin","raw_affiliation_strings":["NVIDIA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"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":["Northeastern University, Boston, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, MA","institution_ids":["https://openalex.org/I12912129"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.3097,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.95874595,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"866","last_page":"879"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.6151999831199646,"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":0.6151999831199646,"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":0.17720000445842743,"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"}},{"id":"https://openalex.org/T11005","display_name":"Radiation Effects in Electronics","score":0.1282999962568283,"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/transient-faults","display_name":"transient faults","score":0.8600000143051147},{"id":"https://openalex.org/keywords/fault-prediction","display_name":"fault prediction","score":0.8130000233650208},{"id":"https://openalex.org/keywords/data-corruption","display_name":"data corruption","score":0.5799999833106995},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"fault tolerance","score":0.503000020980835},{"id":"https://openalex.org/keywords/fault-injection","display_name":"fault injection","score":0.652999997138977},{"id":"https://openalex.org/keywords/gpu-reliability","display_name":"GPU reliability","score":0.7289999723434448},{"id":"https://openalex.org/keywords/high-performance-computing","display_name":"high-performance computing","score":0.6420000195503235}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8157485127449036},{"id":"https://openalex.org/C67666897","wikidata":"https://www.wikidata.org/wiki/Q165896","display_name":"Prism","level":2,"score":0.7192211151123047},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.621016263961792},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.5723240971565247},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.5388516783714294},{"id":"https://openalex.org/C2779585090","wikidata":"https://www.wikidata.org/wiki/Q3457762","display_name":"Resilience (materials science)","level":2,"score":0.5374084115028381},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.49076828360557556},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4539293646812439},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.45381730794906616},{"id":"https://openalex.org/C2775928411","wikidata":"https://www.wikidata.org/wiki/Q2041312","display_name":"Fault injection","level":3,"score":0.428510844707489},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3657117187976837},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3619503974914551},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.26350632309913635},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.16718348860740662},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09915977716445923},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.08695214986801147},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sc.2018.00072","doi":"https://doi.org/10.1109/sc.2018.00072","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sc.2018.00072","pdf_url":null,"source":{"id":"https://openalex.org/S4363608557","display_name":"International Conference for High Performance Computing, Networking, Storage and Analysis (SC)","issn_l":"2167-4337","issn":["2167-4337"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SC18: International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W169270739","https://openalex.org/W429766147","https://openalex.org/W1491178396","https://openalex.org/W1652659619","https://openalex.org/W1903359506","https://openalex.org/W1963880259","https://openalex.org/W1987888496","https://openalex.org/W1999900893","https://openalex.org/W2017337590","https://openalex.org/W2031533321","https://openalex.org/W2046607737","https://openalex.org/W2047028564","https://openalex.org/W2052887509","https://openalex.org/W2055881261","https://openalex.org/W2080592089","https://openalex.org/W2087309216","https://openalex.org/W2098290747","https://openalex.org/W2101473122","https://openalex.org/W2102480715","https://openalex.org/W2118033476","https://openalex.org/W2119222363","https://openalex.org/W2121082877","https://openalex.org/W2122111042","https://openalex.org/W2122224409","https://openalex.org/W2123907700","https://openalex.org/W2124861237","https://openalex.org/W2134633067","https://openalex.org/W2139375423","https://openalex.org/W2143798346","https://openalex.org/W2144512449","https://openalex.org/W2148844272","https://openalex.org/W2149693551","https://openalex.org/W2169184353","https://openalex.org/W2171029115","https://openalex.org/W2183936775","https://openalex.org/W2267020949","https://openalex.org/W2273440736","https://openalex.org/W2292469857","https://openalex.org/W2316016107","https://openalex.org/W2435251607","https://openalex.org/W2486564422","https://openalex.org/W2522581075","https://openalex.org/W2546044294","https://openalex.org/W2562388813","https://openalex.org/W2735162286","https://openalex.org/W3015571647","https://openalex.org/W4229668875","https://openalex.org/W4231474137","https://openalex.org/W4234698323","https://openalex.org/W4239813889","https://openalex.org/W4244241786","https://openalex.org/W4249144718","https://openalex.org/W4256365438","https://openalex.org/W4308067211"],"related_works":["https://openalex.org/W4253596634","https://openalex.org/W2091212189","https://openalex.org/W6906992339","https://openalex.org/W2316016107","https://openalex.org/W2346552078","https://openalex.org/W2027716782","https://openalex.org/W3026559766","https://openalex.org/W3130225809","https://openalex.org/W3012032150","https://openalex.org/W4408564311"],"abstract_inverted_index":{"As":[0],"Graphics":[1],"Processing":[2],"Units":[3],"(GPUs)":[4],"become":[5],"more":[6],"pervasive":[7],"in":[8,28,48,90,117],"High":[9],"Performance":[10],"Computing":[11],"(HPC)":[12],"and":[13],"safety-":[14],"critical":[15],"domains,":[16],"ensuring":[17],"that":[18],"GPU":[19,91,149],"applications":[20,46,118],"can":[21,132],"be":[22,134],"protected":[23],"from":[24],"data":[25],"corruption":[26],"grows":[27],"importance.":[29],"Despite":[30],"prior":[31],"efforts":[32],"to":[33,55,87,98,106,114,136,144],"mitigate":[34],"errors,":[35],"we":[36,76],"still":[37],"lack":[38],"a":[39,70,78,84],"clear":[40],"understanding":[41],"of":[42,51,59,148],"how":[43],"resilient":[44],"these":[45,60],"are":[47],"the":[49,56,127,146],"presence":[50],"transient":[52],"faults.":[53],"Due":[54],"random":[57],"nature":[58],"faults,":[61],"predicting":[62],"whether":[63],"they":[64],"will":[65],"alter":[66],"program":[67,100],"output":[68],"is":[69],"challenging":[71],"problem.":[72],"In":[73],"this":[74],"paper,":[75],"build":[77],"framework":[79],"named":[80],"PRISM":[81,93,111,131],"which":[82,102],"uses":[83],"systematic":[85],"approach":[86],"predict":[88,115],"failures":[89,116],"programs.":[92],"extracts":[94],"micro-architecture":[95],"agnostic":[96],"features":[97],"characterize":[99],"resiliency,":[101],"serve":[103],"as":[104],"predictors":[105],"drive":[107],"our":[108],"statistical":[109],"model.":[110],"enables":[112],"us":[113],"without":[119],"running":[120],"exhaustive":[121],"fault":[122],"injection":[123],"campaigns,":[124],"thereby":[125],"reducing":[126],"error":[128],"estimation":[129],"effort.":[130],"also":[133],"used":[135],"gain":[137],"insight":[138],"into":[139],"potential":[140],"architectural":[141],"support":[142],"required":[143],"improve":[145],"reliability":[147],"applications.":[150]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":8}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2018-12-11T00:00:00"}