{"id":"https://openalex.org/W4401482586","doi":"https://doi.org/10.1145/3687483","title":"Transient Fault Detection in Tensor Cores for Modern GPUs","display_name":"Transient Fault Detection in Tensor Cores for Modern GPUs","publication_year":2024,"publication_date":"2024-08-10","ids":{"openalex":"https://openalex.org/W4401482586","doi":"https://doi.org/10.1145/3687483"},"language":"en","primary_location":{"id":"doi:10.1145/3687483","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3687483","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3687483","source":{"id":"https://openalex.org/S136160450","display_name":"ACM Transactions on Embedded Computing Systems","issn_l":"1539-9087","issn":["1539-9087","1558-3465"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Embedded Computing Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3687483","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093991002","display_name":"Mohammad Hafezan","orcid":"https://orcid.org/0009-0004-9745-9375"},"institutions":[{"id":"https://openalex.org/I72541430","display_name":"Lakehead University","ror":"https://ror.org/023p7mg82","country_code":"CA","type":"education","lineage":["https://openalex.org/I72541430"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mohammad Hassan Hafezan","raw_affiliation_strings":["Electrical and Computer Engineering, Lakehead University, Thunder Bay, Canada"],"raw_orcid":"https://orcid.org/0009-0004-9745-9375","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, Lakehead University, Thunder Bay, Canada","institution_ids":["https://openalex.org/I72541430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012159659","display_name":"Ehsan Atoofian","orcid":"https://orcid.org/0000-0002-1662-5334"},"institutions":[{"id":"https://openalex.org/I72541430","display_name":"Lakehead University","ror":"https://ror.org/023p7mg82","country_code":"CA","type":"education","lineage":["https://openalex.org/I72541430"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ehsan Atoofian","raw_affiliation_strings":["Electrical and Computer Engineering, Lakehead University, Thuner Bay, Canada"],"raw_orcid":"https://orcid.org/0000-0002-1662-5334","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, Lakehead University, Thuner Bay, Canada","institution_ids":["https://openalex.org/I72541430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I72541430"],"apc_list":null,"apc_paid":null,"fwci":0.8623,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.71474677,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"23","issue":"5","first_page":"1","last_page":"29"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994000196456909,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9940000176429749,"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/computer-science","display_name":"Computer science","score":0.8009816408157349},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.7183688879013062},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5763444900512695},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.5456957221031189},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.5269901156425476},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5028743147850037},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.49072086811065674},{"id":"https://openalex.org/keywords/fault-injection","display_name":"Fault injection","score":0.47306501865386963},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.4706924259662628},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4521607756614685},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.43715885281562805},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.4270697832107544},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3685078024864197},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.27799659967422485},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.23505455255508423},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10322701930999756}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8009816408157349},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7183688879013062},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5763444900512695},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5456957221031189},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.5269901156425476},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5028743147850037},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.49072086811065674},{"id":"https://openalex.org/C2775928411","wikidata":"https://www.wikidata.org/wiki/Q2041312","display_name":"Fault injection","level":3,"score":0.47306501865386963},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.4706924259662628},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4521607756614685},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.43715885281562805},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4270697832107544},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3685078024864197},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.27799659967422485},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23505455255508423},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10322701930999756},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3687483","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3687483","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3687483","source":{"id":"https://openalex.org/S136160450","display_name":"ACM Transactions on Embedded Computing Systems","issn_l":"1539-9087","issn":["1539-9087","1558-3465"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Embedded Computing Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3687483","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3687483","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3687483","source":{"id":"https://openalex.org/S136160450","display_name":"ACM Transactions on Embedded Computing Systems","issn_l":"1539-9087","issn":["1539-9087","1558-3465"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Embedded Computing Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.5199999809265137,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401482586.pdf"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W104184427","https://openalex.org/W1501501999","https://openalex.org/W1971695022","https://openalex.org/W1977295820","https://openalex.org/W1979527452","https://openalex.org/W1988425770","https://openalex.org/W1988449951","https://openalex.org/W2043051266","https://openalex.org/W2056109788","https://openalex.org/W2097117768","https://openalex.org/W2105102111","https://openalex.org/W2117539524","https://openalex.org/W2123475473","https://openalex.org/W2130942839","https://openalex.org/W2152781336","https://openalex.org/W2162546540","https://openalex.org/W2194775991","https://openalex.org/W2293634267","https://openalex.org/W2312658635","https://openalex.org/W2340472861","https://openalex.org/W2570343428","https://openalex.org/W2618530766","https://openalex.org/W2767260595","https://openalex.org/W2901848761","https://openalex.org/W2904087936","https://openalex.org/W2907886210","https://openalex.org/W2949413532","https://openalex.org/W2952682304","https://openalex.org/W2963989532","https://openalex.org/W2979439447","https://openalex.org/W2980186997","https://openalex.org/W3009452684","https://openalex.org/W3012032150","https://openalex.org/W3100434865","https://openalex.org/W3121542217","https://openalex.org/W3135074210","https://openalex.org/W3156988338","https://openalex.org/W3187908937","https://openalex.org/W3206892724","https://openalex.org/W4211189626","https://openalex.org/W4251575795","https://openalex.org/W4297337546","https://openalex.org/W4309535831","https://openalex.org/W4310501993","https://openalex.org/W6674914833","https://openalex.org/W6679436768"],"related_works":["https://openalex.org/W2604133224","https://openalex.org/W3122756779","https://openalex.org/W4234532445","https://openalex.org/W2062132293","https://openalex.org/W2373300491","https://openalex.org/W2378744544","https://openalex.org/W2159677757","https://openalex.org/W4396674251","https://openalex.org/W73121515","https://openalex.org/W2060611139"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"networks":[2],"(DNNs)":[3],"have":[4,58],"emerged":[5],"as":[6,74,82,90,92,138,140],"an":[7],"effective":[8],"solution":[9],"for":[10],"many":[11],"machine":[12],"learning":[13],"applications.":[14],"However,":[15,73],"the":[16,21,46,64,67,85,99,130,145,192],"great":[17],"success":[18],"comes":[19],"with":[20,176,212],"cost":[22],"of":[23,66,71,87,103,156,194],"excessive":[24],"computation.":[25],"The":[26,153],"Volta":[27],"graphics":[28],"processing":[29],"unit":[30,38],"(GPU)":[31],"from":[32,135,144],"NVIDIA":[33],"introduced":[34],"a":[35,107,177],"specialized":[36],"hardware":[37,111],"called":[39,113],"tensor":[40,117,151],"core":[41,118],"(TC)":[42],"aiming":[43],"at":[44],"meeting":[45],"growing":[47],"computation":[48],"demand":[49],"needed":[50],"by":[51],"DNNs.":[52],"Most":[53],"previous":[54],"studies":[55],"on":[56,60,183],"TCs":[57,88,104],"focused":[59],"performance":[61,172,214],"improvement":[62],"through":[63],"utilization":[65],"TC's":[68],"high":[69,154],"degree":[70],"parallelism.":[72],"DNNs":[75],"are":[76,200],"deployed":[77],"into":[78],"security-sensitive":[79],"applications":[80,175],"such":[81],"autonomous":[83],"driving,":[84],"reliability":[86],"is":[89],"important":[91],"performance.":[93],"In":[94,126],"this":[95],"work,":[96],"we":[97],"exploit":[98],"unique":[100],"architectural":[101],"characteristics":[102],"and":[105,109,165,216],"propose":[106],"simple":[108],"implementation-efficient":[110],"technique":[112],"fault":[114,210],"detection":[115],"in":[116,124,158,220],"(FDTC)":[119],"to":[120,149,162,170,186],"detect":[121],"transient":[122],"faults":[123],"TCs.":[125,221],"particular,":[127],"FDTC":[128,161,181,190,207],"exploits":[129],"zero-valued":[131],"weights":[132],"that":[133,206],"stem":[134],"network":[136],"pruning":[137],"well":[139],"sparse":[141],"activations":[142],"arising":[143],"common":[146],"ReLU":[147],"operator":[148],"verify":[150],"operations.":[152],"level":[155],"sparsity":[157,179],"tensors":[159],"allows":[160],"run":[163],"original":[164],"verifying":[166,195],"products":[167,196],"simultaneously,":[168],"leading":[169],"zero":[171],"penalty.":[173],"For":[174],"low":[178],"rate,":[180],"relies":[182],"temporal":[184],"redundancy":[185],"re-execute":[187],"effectual":[188],"products.":[189],"schedules":[191],"execution":[193],"only":[197],"when":[198],"multipliers":[199],"idle.":[201],"Our":[202],"experimental":[203],"results":[204],"reveal":[205],"offers":[208],"100%":[209],"coverage":[211],"no":[213],"penalty":[215],"small":[217],"energy":[218],"overhead":[219]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}