{"id":"https://openalex.org/W4381746711","doi":"https://doi.org/10.1109/lats58125.2023.10154504","title":"Analyzing the Architectural Impact of Transient Fault Effects in SFUs of GPUs","display_name":"Analyzing the Architectural Impact of Transient Fault Effects in SFUs of GPUs","publication_year":2023,"publication_date":"2023-03-21","ids":{"openalex":"https://openalex.org/W4381746711","doi":"https://doi.org/10.1109/lats58125.2023.10154504"},"language":"en","primary_location":{"id":"doi:10.1109/lats58125.2023.10154504","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/lats58125.2023.10154504","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 24th Latin American Test Symposium (LATS)","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/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":true,"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":"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/A5081328597","display_name":"Edwar J. Pati\u00f1o N\u00fa\u00f1ez","orcid":null},"institutions":[{"id":"https://openalex.org/I222202552","display_name":"Pedagogical and Technological University of Colombia","ror":"https://ror.org/04vdmbk59","country_code":"CO","type":"education","lineage":["https://openalex.org/I222202552"]}],"countries":["CO"],"is_corresponding":false,"raw_author_name":"Edwar J. Pati\u00f1o N\u00fa\u00f1ez","raw_affiliation_strings":["Universidad Pedagogica y Tecnologica de Colombia (UPTC) - Electronic Engineering School"],"affiliations":[{"raw_affiliation_string":"Universidad Pedagogica y Tecnologica de Colombia (UPTC) - Electronic Engineering School","institution_ids":["https://openalex.org/I222202552"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092245973","display_name":"Robert Limas","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":"Robert Limas","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":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5107558399"],"corresponding_institution_ids":["https://openalex.org/I177477856"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05604706,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11005","display_name":"Radiation Effects in Electronics","score":0.9983000159263611,"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":0.9983000159263611,"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":0.9922999739646912,"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/T10933","display_name":"Real-Time Systems Scheduling","score":0.9660000205039978,"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/computer-science","display_name":"Computer science","score":0.7551571130752563},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.5752385258674622},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5693946480751038},{"id":"https://openalex.org/keywords/transient","display_name":"Transient (computer programming)","score":0.5069730281829834},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.4844512939453125},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.4243814945220947},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.41952139139175415},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.35719847679138184},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.22848635911941528},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.19665241241455078},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.1428772211074829},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1396474540233612}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7551571130752563},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5752385258674622},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5693946480751038},{"id":"https://openalex.org/C2780799671","wikidata":"https://www.wikidata.org/wiki/Q17087362","display_name":"Transient (computer programming)","level":2,"score":0.5069730281829834},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.4844512939453125},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.4243814945220947},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.41952139139175415},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.35719847679138184},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.22848635911941528},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.19665241241455078},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.1428772211074829},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1396474540233612},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/lats58125.2023.10154504","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/lats58125.2023.10154504","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 24th Latin American Test Symposium (LATS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1556045155","https://openalex.org/W1563078826","https://openalex.org/W1985956780","https://openalex.org/W2023630976","https://openalex.org/W2054095206","https://openalex.org/W2058521574","https://openalex.org/W2077268989","https://openalex.org/W2121043529","https://openalex.org/W2130956968","https://openalex.org/W2141957537","https://openalex.org/W2144693392","https://openalex.org/W2411279070","https://openalex.org/W2413549506","https://openalex.org/W2725179571","https://openalex.org/W2752470767","https://openalex.org/W2805459376","https://openalex.org/W2895125408","https://openalex.org/W2943218858","https://openalex.org/W2955081171","https://openalex.org/W2967483844","https://openalex.org/W3009452684","https://openalex.org/W3023609977","https://openalex.org/W3047406327","https://openalex.org/W3111271228","https://openalex.org/W3149134903","https://openalex.org/W3159809463","https://openalex.org/W3167531718","https://openalex.org/W3188924112","https://openalex.org/W3189398641","https://openalex.org/W4226512074","https://openalex.org/W4251213825","https://openalex.org/W4312758080","https://openalex.org/W4364302680","https://openalex.org/W6677752811"],"related_works":["https://openalex.org/W2378076731","https://openalex.org/W4286888643","https://openalex.org/W3210795196","https://openalex.org/W2088988140","https://openalex.org/W2358137648","https://openalex.org/W2803103875","https://openalex.org/W3128819368","https://openalex.org/W2951529875","https://openalex.org/W2220968517","https://openalex.org/W2007139677"],"abstract_inverted_index":{"<sup>1</sup><sup>1</sup>This":[0],"work":[1,109],"has":[2],"been":[3],"supported":[4],"by":[5,68],"the":[6,14,94,111,117,189],"National":[7,15],"Resilience":[8],"and":[9,21,36,51,60,72,93,128,134,136,142,192],"Recovery":[10],"Plan":[11],"(PNRR)":[12],"through":[13],"Center":[16],"for":[17,122,188,219],"HPC,":[18],"Big":[19],"Data":[20],"Quantum":[22],"Computing.Graphics":[23],"Processing":[24],"Units":[25],"(GPUs)":[26],"are":[27,64,86,178,193],"crucial":[28],"in":[29,46,58,89,102,116,205,211],"modern":[30],"safety-critical":[31],"systems":[32],"to":[33,73,139,151,181,186,199,226],"implement":[34],"complex":[35],"dense":[37],"algorithms,":[38],"so":[39],"their":[40,61,69,137],"reliability":[41,56,100,143],"plays":[42],"an":[43,158],"essential":[44],"role":[45],"several":[47],"domains":[48],"(e.g.,":[49],"automotive":[50],"autonomous":[52],"machines).":[53],"In":[54,77],"fact,":[55],"evaluations":[57,101],"GPUs":[59],"internal":[62],"units":[63],"of":[65,96,113,120,207],"special":[66],"interest":[67],"high":[70],"parallelism":[71],"identify":[74],"vulnerable":[75,180,225],"structures.":[76],"particular,":[78],"Special":[79],"Function":[80],"Unit":[81],"(SFU)":[82],"cores,":[83],"inside":[84],"GPUs,":[85],"highly":[87,106],"used":[88],"multimedia,":[90],"scientific":[91],"computing,":[92],"training":[95],"neural":[97],"networks.":[98],"However,":[99],"SFUs":[103,121,177],"have":[104],"remained":[105],"unexplored.":[107],"This":[108],"evaluates":[110],"impact":[112,144],"transient":[114,182],"faults":[115,183],"hardware":[118],"structures":[119],"GPUs.":[123],"We":[124],"focus":[125],"on":[126,145,170],"evaluating":[127],"analyzing":[129],"two":[130],"SFU":[131,172,216],"architectures":[132,173],"(\u2018fused\u2019":[133],"\u2018modular\u2019)":[135],"relations":[138],"energy,":[140],"area,":[141],"GPU":[146,161],"workloads.":[147],"The":[148,167],"evaluation":[149],"resorts":[150],"a":[152,214],"fine-grain":[153],"analysis":[154],"with":[155,164,213],"experiments":[156],"using":[157],"RTL":[159],"open-source":[160],"(FlexGripPlus)":[162],"instrumented":[163],"both":[165,171],"SFUs.":[166],"experimental":[168],"results":[169],"indicate":[174],"that":[175],"modular":[176],"less":[179],"(in":[184,197],"up":[185,198],"47%":[187],"analyzed":[190],"workloads)":[191],"more":[194,224],"power":[195],"efficient":[196],"36.6%)":[200],"but":[201,228],"require":[202],"additional":[203],"cost":[204],"terms":[206],"area":[208,230],"(about":[209],"27%)":[210],"comparison":[212],"fused":[215],"architecture":[217],"(base":[218],"commercial":[220],"devices),":[221],"which":[222],"seems":[223],"faults,":[227],"is":[229],"efficient.":[231]},"counts_by_year":[],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}