{"id":"https://openalex.org/W4399487271","doi":"https://doi.org/10.1145/3649476.3658717","title":"PerFT-N: Low-overhead Permanent Fault-Tolerance Mechanism for Neural Processing Units","display_name":"PerFT-N: Low-overhead Permanent Fault-Tolerance Mechanism for Neural Processing Units","publication_year":2024,"publication_date":"2024-06-10","ids":{"openalex":"https://openalex.org/W4399487271","doi":"https://doi.org/10.1145/3649476.3658717"},"language":"en","primary_location":{"id":"doi:10.1145/3649476.3658717","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3649476.3658717","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Great Lakes Symposium on VLSI 2024","raw_type":"proceedings-article"},"type":"conference-paper","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/A5043508204","display_name":"H. B. Jian","orcid":"https://orcid.org/0009-0008-4396-9766"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haojie Jian","raw_affiliation_strings":["Advanced Computing and Digital Engineering Research Institute, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0009-0008-4396-9766","affiliations":[{"raw_affiliation_string":"Advanced Computing and Digital Engineering Research Institute, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210145761","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100408301","display_name":"Chao Chen","orcid":"https://orcid.org/0000-0001-6488-224X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Chen","raw_affiliation_strings":["Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0000-0001-6488-224X","affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210145761","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100401156","display_name":"Zheng Wang","orcid":"https://orcid.org/0000-0003-2855-9570"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Wang","raw_affiliation_strings":["Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0000-0003-2855-9570","affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210145761","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009657969","display_name":"P. T. Wu","orcid":"https://orcid.org/0009-0003-2053-4114"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengfei Wu","raw_affiliation_strings":["Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0009-0003-2053-4114","affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210145761","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"25","last_page":"31"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11005","display_name":"Radiation Effects in Electronics","score":0.9976000189781189,"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":0.9976000189781189,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.9919999837875366,"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/T11032","display_name":"VLSI and Analog Circuit Testing","score":0.9904000163078308,"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":0.7000079154968262},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.6897841095924377},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6534798741340637},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.6056616902351379},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4238932430744171},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.23403888940811157},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.12366417050361633}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7000079154968262},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.6897841095924377},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6534798741340637},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.6056616902351379},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4238932430744171},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.23403888940811157},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.12366417050361633},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3649476.3658717","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3649476.3658717","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Great Lakes Symposium on VLSI 2024","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":7,"referenced_works":["https://openalex.org/W2045554437","https://openalex.org/W2745575658","https://openalex.org/W3102800594","https://openalex.org/W4226335630","https://openalex.org/W4252211612","https://openalex.org/W4285255445","https://openalex.org/W4319990419"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W1862835629","https://openalex.org/W2099111379","https://openalex.org/W2136799148","https://openalex.org/W2897533804","https://openalex.org/W2890506991"],"abstract_inverted_index":{"The":[0],"reliability":[1],"of":[2,19,50,52,134,143],"neural":[3,63],"network":[4],"(NN)":[5],"accelerators":[6],"is":[7,111],"one":[8],"key":[9],"to":[10,36,68,90],"ensuring":[11],"inference":[12],"accuracy.":[13],"Relying":[14],"solely":[15],"on":[16,113],"the":[17,28,75,87,114,124,129,140],"robustness":[18],"NN":[20],"can":[21],"only":[22],"tolerate":[23],"transient":[24],"faults,":[25,32],"and":[26,48,94,147],"once":[27],"circuit":[29],"encounters":[30],"permanent":[31,78,107],"it":[33],"will":[34],"lead":[35],"a":[37,56],"serious":[38],"accuracy":[39],"drop.":[40],"We,":[41],"by":[42,99],"employing":[43],"processing":[44,64],"elements":[45],"(PEs)":[46],"checking":[47],"re-scheduling":[49],"threads":[51],"functional":[53,136],"units,":[54],"propose":[55],"new":[57],"fault-tolerant":[58,71],"mechanism":[59],"named":[60],"PerFT-N":[61,73,125],"for":[62,117],"units":[65,137],"(NPUs).":[66],"Compared":[67],"previous":[69],"NPU":[70],"methods,":[72],"recovers":[74],"execution":[76],"facing":[77],"faults":[79],"with":[80,132],"minimal":[81],"hardware":[82],"overhead.":[83],"Specifically,":[84],"we":[85],"utilize":[86],"existing":[88],"resources":[89],"achieve":[91],"fault":[92,108],"detection":[93],"localization,":[95],"while":[96,138],"achieving":[97],"recovery":[98],"re-linking":[100],"unfailed":[101],"threads.":[102],"Furthermore,":[103],"an":[104],"instruction-based":[105],"programmable":[106],"emulation":[109],"scheme":[110],"deployed":[112],"FPGA":[115],"platform":[116],"fast":[118],"verification.":[119],"Experimental":[120],"results":[121],"demonstrate":[122],"that":[123],"architecture":[126],"works":[127],"in":[128,145,149],"extreme":[130],"case":[131],"98.5%":[133],"failed":[135],"incurring":[139],"physical":[141],"overheads":[142],"2.7%":[144],"area":[146],"3.6%":[148],"power":[150],"consumption":[151],"under":[152],"40nm":[153],"SMIC":[154],"standard":[155],"cell":[156],"library.":[157]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
