{"id":"https://openalex.org/W4399144001","doi":"https://doi.org/10.1109/vts60656.2024.10538940","title":"Analyzing the Impact of Scheduling Policies on the Reliability of GPUs Running CNN Operations","display_name":"Analyzing the Impact of Scheduling Policies on the Reliability of GPUs Running CNN Operations","publication_year":2024,"publication_date":"2024-04-22","ids":{"openalex":"https://openalex.org/W4399144001","doi":"https://doi.org/10.1109/vts60656.2024.10538940"},"language":"en","primary_location":{"id":"doi:10.1109/vts60656.2024.10538940","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/vts60656.2024.10538940","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 42nd VLSI Test Symposium (VTS)","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/A5006252702","display_name":"Robert Limas Sierra","orcid":"https://orcid.org/0000-0001-5206-3757"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Polytechnic University of Turin","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Robert Limas Sierra","raw_affiliation_strings":["Politecnico di Torino,Department of Control and Computer Engineering (DAUIN)","Department of Control and Computer Engineering (DAUIN), Politecnico di Torino"],"affiliations":[{"raw_affiliation_string":"Politecnico di Torino,Department of Control and Computer Engineering (DAUIN)","institution_ids":["https://openalex.org/I177477856"]},{"raw_affiliation_string":"Department of Control and Computer Engineering (DAUIN), Politecnico di Torino","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046650816","display_name":"Juan-David Guerrero-Balaguera","orcid":"https://orcid.org/0000-0001-6852-2372"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Polytechnic University of Turin","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Juan-David Guerrero-Balaguera","raw_affiliation_strings":["Politecnico di Torino,Department of Control and Computer Engineering (DAUIN)","Department of Control and Computer Engineering (DAUIN), Politecnico di Torino"],"affiliations":[{"raw_affiliation_string":"Politecnico di Torino,Department of Control and Computer Engineering (DAUIN)","institution_ids":["https://openalex.org/I177477856"]},{"raw_affiliation_string":"Department of Control and Computer Engineering (DAUIN), Politecnico di Torino","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5098932940","display_name":"Francesco Pessia","orcid":null},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Polytechnic University of Turin","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Francesco Pessia","raw_affiliation_strings":["Politecnico di Torino,Department of Control and Computer Engineering (DAUIN)","Department of Control and Computer Engineering (DAUIN), Politecnico di Torino"],"affiliations":[{"raw_affiliation_string":"Politecnico di Torino,Department of Control and Computer Engineering (DAUIN)","institution_ids":["https://openalex.org/I177477856"]},{"raw_affiliation_string":"Department of Control and Computer Engineering (DAUIN), Politecnico di Torino","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107558399","display_name":"Josie E. Rodriguez Condia","orcid":"https://orcid.org/0000-0001-5957-5624"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Polytechnic University of Turin","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Josie E. Rodriguez Condia","raw_affiliation_strings":["Politecnico di Torino,Department of Control and Computer Engineering (DAUIN)","Department of Control and Computer Engineering (DAUIN), Politecnico di Torino"],"affiliations":[{"raw_affiliation_string":"Politecnico di Torino,Department of Control and Computer Engineering (DAUIN)","institution_ids":["https://openalex.org/I177477856"]},{"raw_affiliation_string":"Department of Control and Computer Engineering (DAUIN), Politecnico di Torino","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058555274","display_name":"M. Sonza Reorda","orcid":"https://orcid.org/0000-0003-2899-7669"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Polytechnic University of Turin","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Matteo Sonza Reorda","raw_affiliation_strings":["Politecnico di Torino,Department of Control and Computer Engineering (DAUIN)","Department of Control and Computer Engineering (DAUIN), Politecnico di Torino"],"affiliations":[{"raw_affiliation_string":"Politecnico di Torino,Department of Control and Computer Engineering (DAUIN)","institution_ids":["https://openalex.org/I177477856"]},{"raw_affiliation_string":"Department of Control and Computer Engineering (DAUIN), Politecnico di Torino","institution_ids":["https://openalex.org/I177477856"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5006252702"],"corresponding_institution_ids":["https://openalex.org/I177477856"],"apc_list":null,"apc_paid":null,"fwci":0.7305,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.70117367,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.7353000044822693,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.7353000044822693,"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/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.7035999894142151,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/T10763","display_name":"Digital Transformation in Industry","score":0.6715999841690063,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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":0.7928173542022705},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6587762236595154},{"id":"https://openalex.org/keywords/processor-scheduling","display_name":"Processor scheduling","score":0.5760142803192139},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5651288032531738},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4985795021057129},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.16239210963249207},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0743151307106018},{"id":"https://openalex.org/keywords/operations-management","display_name":"Operations management","score":0.05589854717254639}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7928173542022705},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6587762236595154},{"id":"https://openalex.org/C2984822820","wikidata":"https://www.wikidata.org/wiki/Q1123036","display_name":"Processor scheduling","level":3,"score":0.5760142803192139},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5651288032531738},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4985795021057129},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.16239210963249207},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0743151307106018},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.05589854717254639},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"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/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/vts60656.2024.10538940","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/vts60656.2024.10538940","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 42nd VLSI Test Symposium (VTS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1809394610","https://openalex.org/W2128410848","https://openalex.org/W2101285930","https://openalex.org/W2102390841","https://openalex.org/W2118368532","https://openalex.org/W2126232624","https://openalex.org/W2434525066","https://openalex.org/W3140149227","https://openalex.org/W2130555437","https://openalex.org/W3023290810"],"abstract_inverted_index":{"The":[0],"programming":[1],"flexibility":[2],"and":[3,17,48,57,83,121,130,144,190],"parallelism":[4],"of":[5,27,77,94,107,119,135,186],"Graphics":[6],"Processing":[7],"Units":[8],"(GPUs)":[9],"contribute":[10],"to":[11,66,174],"their":[12,191],"effective":[13],"adoption":[14],"in":[15,24,36,81,152],"complex":[16],"data-intensive":[18],"fields":[19],"like":[20],"Machine":[21],"Learning,":[22],"especially":[23],"the":[25,75,91,105,132,141,145,153,160,169,183,187,198],"deployment":[26],"Convolutional":[28],"Neural":[29],"Networks":[30],"(CNNs).":[31],"CNNs":[32],"are":[33],"also":[34],"used":[35],"some":[37,165],"safety-critical":[38],"applications":[39],"with":[40],"severe":[41],"reliability":[42,72,92],"constraints,":[43],"such":[44],"as":[45],"autonomous":[46],"driving":[47],"robotics.":[49],"Modern":[50],"GPUs":[51,82,98],"efficiently":[52],"combine":[53],"hardware":[54],"schedulers":[55],"controllers":[56],"in-chip":[58],"accelerators":[59],"(e.g.,":[60],"Tensor":[61],"Core":[62],"Units,":[63],"or":[64],"TCUs)":[65],"enhance":[67],"CNN\u2019s":[68],"performance.":[69],"Interestingly,":[70],"fine-grain":[71],"analyses":[73,90],"combining":[74],"operation":[76],"task":[78],"scheduling":[79,95,128,146,188],"policies":[80,96,129,166,189],"TCUs":[84],"have":[85],"remained":[86],"unexplored.":[87],"This":[88],"work":[89],"impact":[93],"on":[97,193,197],"when":[99],"permanent":[100],"faults":[101],"affect":[102],"TCUs,":[103],"during":[104],"execution":[106,134],"CNN":[108],"operations.":[109],"We":[110],"developed":[111],"a":[112,149],"configurable":[113],"architectural":[114],"GPU":[115],"model":[116],"(in":[117],"terms":[118],"clusters":[120],"parallel":[122],"cores)":[123],"that":[124,140,164],"implements":[125],"five":[126],"selectable":[127],"supports":[131],"instruction-accurate":[133],"TCUs.":[136,158],"Our":[137],"results":[138],"indicate":[139],"GPU\u2019s":[142],"architecture":[143],"policy":[147],"play":[148],"crucial":[150],"role":[151],"application\u2019s":[154,199],"corruption":[155,170],"from":[156],"faulty":[157],"From":[159],"experiments,":[161],"we":[162,181],"found":[163],"can":[167],"reduce":[168],"effects":[171,196],"by":[172],"up":[173],"22%":[175],"for":[176],"large":[177],"GPUs.":[178],"In":[179],"addition,":[180],"evaluated":[182],"dynamic":[184],"variability":[185],"complexity":[192],"identifying":[194],"deterministic":[195],"outputs.":[200]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}