{"id":"https://openalex.org/W4414934603","doi":"https://doi.org/10.1145/3770920","title":"Runtime Fault Localization in Deep Neural Network Accelerators","display_name":"Runtime Fault Localization in Deep Neural Network Accelerators","publication_year":2025,"publication_date":"2025-10-08","ids":{"openalex":"https://openalex.org/W4414934603","doi":"https://doi.org/10.1145/3770920"},"language":"en","primary_location":{"id":"doi:10.1145/3770920","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3770920","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3770920","source":{"id":"https://openalex.org/S105046310","display_name":"ACM Transactions on Design Automation of Electronic Systems","issn_l":"1084-4309","issn":["1084-4309","1557-7309"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Design Automation of Electronic Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3770920","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031942262","display_name":"Wei-Kai Liu","orcid":"https://orcid.org/0000-0003-4075-3499"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei-Kai Liu","raw_affiliation_strings":["Electrical and Computer Engineering, Duke University","Electrical and Computer Engineering, Duke University, Durham, United States"],"raw_orcid":"https://orcid.org/0000-0003-4075-3499","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, Duke University","institution_ids":["https://openalex.org/I170897317"]},{"raw_affiliation_string":"Electrical and Computer Engineering, Duke University, Durham, United States","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017274857","display_name":"Jonti Talukdar","orcid":"https://orcid.org/0000-0001-7079-5281"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonti Talukdar","raw_affiliation_strings":["Electrical and Computer Engineering, Duke University","Electrical and Computer Engineering, Duke University, Durham, United States"],"raw_orcid":"https://orcid.org/0000-0001-7079-5281","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, Duke University","institution_ids":["https://openalex.org/I170897317"]},{"raw_affiliation_string":"Electrical and Computer Engineering, Duke University, Durham, United States","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069388936","display_name":"Benjamin Tan","orcid":"https://orcid.org/0000-0002-7642-3638"},"institutions":[{"id":"https://openalex.org/I168635309","display_name":"University of Calgary","ror":"https://ror.org/03yjb2x39","country_code":"CA","type":"education","lineage":["https://openalex.org/I168635309"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Benjamin Tan","raw_affiliation_strings":["Electrical and Software Engineering, University of Calgary","Electrical and Software Engineering, University of Calgary, Calgary, Canada"],"raw_orcid":"https://orcid.org/0000-0002-7642-3638","affiliations":[{"raw_affiliation_string":"Electrical and Software Engineering, University of Calgary","institution_ids":["https://openalex.org/I168635309"]},{"raw_affiliation_string":"Electrical and Software Engineering, University of Calgary, Calgary, Canada","institution_ids":["https://openalex.org/I168635309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033880864","display_name":"Krishnendu Chakrabarty","orcid":"https://orcid.org/0000-0003-4475-6435"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Krishnendu Chakrabarty","raw_affiliation_strings":["Arizona State University","Arizona State University, Tempe, United States"],"raw_orcid":"https://orcid.org/0000-0003-4475-6435","affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]},{"raw_affiliation_string":"Arizona State University, Tempe, United States","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2216,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85563416,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"31","issue":"1","first_page":"1","last_page":"27"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10876","display_name":"Fault Detection and Control Systems","score":0.9957000017166138,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T11005","display_name":"Radiation Effects in Electronics","score":0.9944000244140625,"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/dataflow","display_name":"Dataflow","score":0.737500011920929},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6937000155448914},{"id":"https://openalex.org/keywords/checksum","display_name":"Checksum","score":0.6258999705314636},{"id":"https://openalex.org/keywords/fault-detection-and-isolation","display_name":"Fault detection and isolation","score":0.5613999962806702},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.5372999906539917},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5206999778747559},{"id":"https://openalex.org/keywords/fault-coverage","display_name":"Fault coverage","score":0.4999000132083893},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.48089998960494995},{"id":"https://openalex.org/keywords/systolic-array","display_name":"Systolic array","score":0.4171999990940094}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8792999982833862},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.737500011920929},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6937000155448914},{"id":"https://openalex.org/C162372511","wikidata":"https://www.wikidata.org/wiki/Q218341","display_name":"Checksum","level":2,"score":0.6258999705314636},{"id":"https://openalex.org/C152745839","wikidata":"https://www.wikidata.org/wiki/Q5438153","display_name":"Fault detection and isolation","level":3,"score":0.5613999962806702},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.5372999906539917},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5206999778747559},{"id":"https://openalex.org/C126953365","wikidata":"https://www.wikidata.org/wiki/Q5438152","display_name":"Fault coverage","level":3,"score":0.4999000132083893},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.48089998960494995},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4203999936580658},{"id":"https://openalex.org/C150741067","wikidata":"https://www.wikidata.org/wiki/Q2377218","display_name":"Systolic array","level":3,"score":0.4171999990940094},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.40119999647140503},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.3978999853134155},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.3856000006198883},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3849000036716461},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.3765000104904175},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3749000132083893},{"id":"https://openalex.org/C176727019","wikidata":"https://www.wikidata.org/wiki/Q1172415","display_name":"Dataflow architecture","level":3,"score":0.3425000011920929},{"id":"https://openalex.org/C175551986","wikidata":"https://www.wikidata.org/wiki/Q47089","display_name":"Fault (geology)","level":2,"score":0.3382999897003174},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3237000107765198},{"id":"https://openalex.org/C123614077","wikidata":"https://www.wikidata.org/wiki/Q1364905","display_name":"Propagation of uncertainty","level":2,"score":0.31869998574256897},{"id":"https://openalex.org/C13625343","wikidata":"https://www.wikidata.org/wiki/Q7627418","display_name":"Stuck-at fault","level":4,"score":0.3179999887943268},{"id":"https://openalex.org/C167391956","wikidata":"https://www.wikidata.org/wiki/Q1401211","display_name":"Fault model","level":3,"score":0.30709999799728394},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.2906000018119812},{"id":"https://openalex.org/C21267803","wikidata":"https://www.wikidata.org/wiki/Q5438159","display_name":"Fault indicator","level":4,"score":0.28769999742507935},{"id":"https://openalex.org/C2775928411","wikidata":"https://www.wikidata.org/wiki/Q2041312","display_name":"Fault injection","level":3,"score":0.27070000767707825},{"id":"https://openalex.org/C2778309119","wikidata":"https://www.wikidata.org/wiki/Q5121614","display_name":"Circuit reliability","level":4,"score":0.26269999146461487},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2565999925136566}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3770920","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3770920","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3770920","source":{"id":"https://openalex.org/S105046310","display_name":"ACM Transactions on Design Automation of Electronic Systems","issn_l":"1084-4309","issn":["1084-4309","1557-7309"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Design Automation of Electronic Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3770920","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3770920","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3770920","source":{"id":"https://openalex.org/S105046310","display_name":"ACM Transactions on Design Automation of Electronic Systems","issn_l":"1084-4309","issn":["1084-4309","1557-7309"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Design Automation of Electronic Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2323190205","display_name":null,"funder_award_id":"3065.001, 3106.001, and 3198.001","funder_id":"https://openalex.org/F4320306087","funder_display_name":"Semiconductor Research Corporation"}],"funders":[{"id":"https://openalex.org/F4320306087","display_name":"Semiconductor Research Corporation","ror":"https://ror.org/047z4n946"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414934603.pdf","grobid_xml":"https://content.openalex.org/works/W4414934603.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1994266431","https://openalex.org/W2072072075","https://openalex.org/W2083613288","https://openalex.org/W2565305208","https://openalex.org/W2583993537","https://openalex.org/W2614475470","https://openalex.org/W2767260595","https://openalex.org/W2913252637","https://openalex.org/W2944349874","https://openalex.org/W3031172388","https://openalex.org/W3082683867","https://openalex.org/W3100944043","https://openalex.org/W3114687924","https://openalex.org/W3131039502","https://openalex.org/W3135074210","https://openalex.org/W3165267979","https://openalex.org/W3179817273","https://openalex.org/W3205165858","https://openalex.org/W3210746327","https://openalex.org/W4205928000","https://openalex.org/W4225736874","https://openalex.org/W4233982390","https://openalex.org/W4235935333","https://openalex.org/W4242985528","https://openalex.org/W4308477919","https://openalex.org/W4316021959","https://openalex.org/W4319865974","https://openalex.org/W4321608010","https://openalex.org/W4321608012","https://openalex.org/W4385695859"],"related_works":[],"abstract_inverted_index":{"Systolic":[0],"arrays":[1,41],"are":[2],"a":[3,43,96,153,170],"popular":[4],"choice":[5],"for":[6,50,69,129,152],"accelerating":[7],"deep":[8],"neural":[9],"networks":[10],"(DNNs)":[11],"due":[12],"to":[13,81,112],"their":[14],"inherent":[15],"parallelism":[16],"and":[17,75,105,121,167],"efficient":[18],"data":[19,111],"reuse.":[20],"However,":[21],"ensuring":[22],"the":[23,83,127,140,160],"reliability":[24],"of":[25,46,59,85],"these":[26],"DNN":[27,70],"accelerators":[28],"is":[29,57],"crucial,":[30],"as":[31],"hardware":[32],"faults":[33],"can":[34,65],"significantly":[35],"degrade":[36],"inferencing":[37,67],"accuracy.":[38],"Because":[39],"systolic":[40,86,156,173],"utilize":[42],"large":[44],"number":[45],"processing":[47],"elements":[48],"(PEs)":[49],"parallel":[51],"processing,":[52],"dataflow":[53],"involving":[54],"faulty":[55],"PEs":[56,64],"especially":[58],"concern.":[60],"Error":[61],"propagation":[62],"through":[63],"reduce":[66],"accuracy":[68],"workloads.":[71],"Although":[72],"fault":[73,88,97,103,106,142,165],"detection":[74,104,120,166],"repair":[76],"techniques":[77],"have":[78],"been":[79],"proposed":[80,141,161],"enhance":[82],"robustness":[84],"arrays,":[87],"localization":[89,122,143,168],"remains":[90],"an":[91,146],"open":[92],"problem.":[93],"We":[94],"propose":[95],"tolerance":[98],"framework":[99],"including":[100],"run-time":[101],"based":[102],"localization,":[107],"both":[108],"leveraging":[109],"functional":[110],"generate":[113],"checksums":[114],"on-the-fly.":[115],"This":[116],"approach":[117],"enables":[118],"error":[119],"during":[123],"normal":[124],"operation,":[125],"avoiding":[126],"need":[128],"dedicated":[130],"test":[131],"patterns":[132],"or":[133],"additional":[134],"downtime.":[135],"Experimental":[136],"evaluation":[137],"shows":[138],"that":[139],"architecture":[144],"incurs":[145],"area":[147],"overhead":[148],"less":[149],"than":[150],"2%":[151],"256\u00d7":[154,171],"256":[155,172],"array.":[157,174],"In":[158],"simulations,":[159],"method":[162],"achieves":[163],"100%":[164],"in":[169]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}