Radiation-Induced Soft Error Assessment of a Multithreaded MobileNet CNN Model Running in a Multicore Edge Processor

Convolutional neural networks (CNNs) have become a standard technology in numerous industrial Internet of Things (IoT) applications and sectors, such as automotive and aerospace. Recent advancements in hardware and software (e.g., application programming interface (API)/libraries) components have en...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE transactions on nuclear science Ročník 72; číslo 8; s. 2821 - 2829
Hlavní autoři:	Gava, Jonas, Sherjil, Areeb, Laurini, Luiz H., Atukpor, Emmanuel, Bastos, Rodrigo Possamai, Moraes, Fernando, Reis, Ricardo, Ost, Luciano
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	New York IEEE 01.08.2025 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	Application programming interface Artificial neural networks Convolutional neural networks Energy efficiency Error correction codes Field programmable gate arrays Industrial applications Industrial Internet of Things Microprocessors MobileNet Multicore processing multicore processors multithreaded convolutional neural network (CNN) models Neural networks Neutron radiation Neutrons Radiation Radiation effects Reliability Reliability analysis Resilience Safety critical Single instruction multiple data soft error reliability Soft errors Thermal neutrons
ISSN:	0018-9499, 1558-1578
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	Convolutional neural networks (CNNs) have become a standard technology in numerous industrial Internet of Things (IoT) applications and sectors, such as automotive and aerospace. Recent advancements in hardware and software (e.g., application programming interface (API)/libraries) components have enabled the efficient execution of multithreaded CNN models on edge devices. As the complexity and adoption of CNNs in safety-critical systems continue to grow, ensuring their resilience becomes key and increasingly challenging. In this context, this work promotes two original contributions: 1) the proposal of a multithreaded implementation of MobileNet, which achieves a <inline-formula> <tex-math notation="LaTeX">2.67\times </tex-math></inline-formula> speedup and an energy reduction of 16% with four worker threads, and 2) the first soft error reliability assessment of a multithreaded CNN model running in a multicore processor under high-energy and thermal neutron radiation flux. Results from the radiation campaigns, with more than 31k runs, suggest that multithreaded executions can increase the occurrence of critical faults by up to <inline-formula> <tex-math notation="LaTeX">5\times </tex-math></inline-formula>. Results also show a greater number of events during the thermal neutron campaign, and some input images are significantly more robust against silent data corruption (SDC) events.
AbstractList	Convolutional neural networks (CNNs) have become a standard technology in numerous industrial Internet of Things (IoT) applications and sectors, such as automotive and aerospace. Recent advancements in hardware and software (e.g., application programming interface (API)/libraries) components have enabled the efficient execution of multithreaded CNN models on edge devices. As the complexity and adoption of CNNs in safety-critical systems continue to grow, ensuring their resilience becomes key and increasingly challenging. In this context, this work promotes two original contributions: 1) the proposal of a multithreaded implementation of MobileNet, which achieves a [Formula Omitted] speedup and an energy reduction of 16% with four worker threads, and 2) the first soft error reliability assessment of a multithreaded CNN model running in a multicore processor under high-energy and thermal neutron radiation flux. Results from the radiation campaigns, with more than 31k runs, suggest that multithreaded executions can increase the occurrence of critical faults by up to [Formula Omitted]. Results also show a greater number of events during the thermal neutron campaign, and some input images are significantly more robust against silent data corruption (SDC) events. Convolutional neural networks (CNNs) have become a standard technology in numerous industrial Internet of Things (IoT) applications and sectors, such as automotive and aerospace. Recent advancements in hardware and software (e.g., application programming interface (API)/libraries) components have enabled the efficient execution of multithreaded CNN models on edge devices. As the complexity and adoption of CNNs in safety-critical systems continue to grow, ensuring their resilience becomes key and increasingly challenging. In this context, this work promotes two original contributions: 1) the proposal of a multithreaded implementation of MobileNet, which achieves a <inline-formula> <tex-math notation="LaTeX">2.67\times </tex-math></inline-formula> speedup and an energy reduction of 16% with four worker threads, and 2) the first soft error reliability assessment of a multithreaded CNN model running in a multicore processor under high-energy and thermal neutron radiation flux. Results from the radiation campaigns, with more than 31k runs, suggest that multithreaded executions can increase the occurrence of critical faults by up to <inline-formula> <tex-math notation="LaTeX">5\times </tex-math></inline-formula>. Results also show a greater number of events during the thermal neutron campaign, and some input images are significantly more robust against silent data corruption (SDC) events.
Author	Gava, Jonas Moraes, Fernando Sherjil, Areeb Laurini, Luiz H. Reis, Ricardo Ost, Luciano Bastos, Rodrigo Possamai Atukpor, Emmanuel
Author_xml	– sequence: 1 givenname: Jonas orcidid: 0000-0001-7113-6448 surname: Gava fullname: Gava, Jonas organization: Instituto de Informática, PGMicro, Universidade Federal do Rio Grande do Sul, Porto Alegre, Brazil – sequence: 2 givenname: Areeb orcidid: 0009-0007-3825-1322 surname: Sherjil fullname: Sherjil, Areeb organization: Wolfson School, Loughborough University, Loughborough, U.K – sequence: 3 givenname: Luiz H. orcidid: 0009-0008-9562-1446 surname: Laurini fullname: Laurini, Luiz H. organization: Université Grenoble Alpes, CNRS, Grenoble INP, TIMA, Grenoble, France – sequence: 4 givenname: Emmanuel orcidid: 0009-0001-0627-1114 surname: Atukpor fullname: Atukpor, Emmanuel organization: Institut Laue-Langevin, Grenoble, France – sequence: 5 givenname: Rodrigo Possamai orcidid: 0000-0002-9964-0424 surname: Bastos fullname: Bastos, Rodrigo Possamai organization: Université Grenoble Alpes, CNRS, Grenoble INP, TIMA, Grenoble, France – sequence: 6 givenname: Fernando orcidid: 0000-0001-6126-6847 surname: Moraes fullname: Moraes, Fernando organization: School of Technology, Pontifical Catholic University of Rio Grande do Sul, Porto Alegre, Brazil – sequence: 7 givenname: Ricardo orcidid: 0000-0001-5781-5858 surname: Reis fullname: Reis, Ricardo organization: Instituto de Informática, PGMicro, Universidade Federal do Rio Grande do Sul, Porto Alegre, Brazil – sequence: 8 givenname: Luciano orcidid: 0000-0002-5160-5232 surname: Ost fullname: Ost, Luciano email: l.ost@lboro.ac.uk organization: Wolfson School, Loughborough University, Loughborough, U.K
BookMark	eNpFkE1LAzEQhoMo2FbvHjwEPG9Nspv9OJZStdCu0tbzkmYnNWWb1CR78N-b0orMYXjhmXnhGaJrYw0g9EDJmFJSPW_q9ZgRxscpL-NUV2hAOS8TyovyGg0IoWVSZVV1i4be72PMOOEDFFai1SJoa5K5aXsJLV5bFfDMOevwxHvw_gAmYKuwwMu-Czp8ORBtBJd2qzuoIeBpXcfUQodXvTHa7LA2f7i0DvCs3QH-cFbGd9bdoRslOg_3lz1Cny-zzfQtWby_zqeTRSJZVoREqIJWuSyZymXOgfCsyKqWy0LlVNCSiJIJwlJIGdtSrpRqBSFMSBBkW7AM0hF6Ov89Ovvdgw_N3vbOxMomjQ3RFOM8UuRMSWe9d6Cao9MH4X4aSpqT2ya6bU5um4vbePJ4PtEA8I9TUjCW5ukvLV93ZA
CODEN	IETNAE
Cites_doi	10.1109/TNS.2023.3262448 10.1109/ISVLSI.2019.00099 10.1109/TNS.2018.2884460 10.1145/3180155.3180220 10.1109/TR.2018.2878387 10.1109/TCAD.2019.2944584 10.1109/TNS.2022.3142092 10.1109/TNS.2024.3378807 10.1109/ISVLSI59464.2023.10238535 10.1109/COASE.2018.8560564 10.1145/3526241.3530351 10.1145/1113841.1113843 10.1109/TNS.2022.3224538 10.1145/3063180 10.1109/LASCAS53948.2022.9789088 10.1109/TNS.2021.3062014 10.1109/TNS.2021.3050707 10.1109/ITC44170.2019.9000150
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025
DBID	97E RIA RIE AAYXX CITATION 7QF 7QL 7QQ 7SC 7SE 7SP 7SR 7T7 7TA 7TB 7U5 7U9 8BQ 8FD C1K F28 FR3 H8D H94 JG9 JQ2 KR7 L7M L~C L~D M7N P64
DOI	10.1109/TNS.2025.3585859
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Aluminium Industry Abstracts Bacteriology Abstracts (Microbiology B) Ceramic Abstracts Computer and Information Systems Abstracts Corrosion Abstracts Electronics & Communications Abstracts Engineered Materials Abstracts Industrial and Applied Microbiology Abstracts (Microbiology A) Materials Business File Mechanical & Transportation Engineering Abstracts Solid State and Superconductivity Abstracts Virology and AIDS Abstracts METADEX Technology Research Database Environmental Sciences and Pollution Management ANTE: Abstracts in New Technology & Engineering Engineering Research Database Aerospace Database AIDS and Cancer Research Abstracts Materials Research Database ProQuest Computer Science Collection Civil Engineering Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional Algology Mycology and Protozoology Abstracts (Microbiology C) Biotechnology and BioEngineering Abstracts
DatabaseTitle	CrossRef Materials Research Database Technology Research Database Computer and Information Systems Abstracts – Academic Mechanical & Transportation Engineering Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Materials Business File Environmental Sciences and Pollution Management Aerospace Database Engineered Materials Abstracts Bacteriology Abstracts (Microbiology B) Algology Mycology and Protozoology Abstracts (Microbiology C) AIDS and Cancer Research Abstracts Industrial and Applied Microbiology Abstracts (Microbiology A) Advanced Technologies Database with Aerospace ANTE: Abstracts in New Technology & Engineering Civil Engineering Abstracts Aluminium Industry Abstracts Virology and AIDS Abstracts Electronics & Communications Abstracts Ceramic Abstracts METADEX Biotechnology and BioEngineering Abstracts Computer and Information Systems Abstracts Professional Solid State and Superconductivity Abstracts Engineering Research Database Corrosion Abstracts
DatabaseTitleList	Materials Research Database
Database_xml	– sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	1558-1578
EndPage	2829
ExternalDocumentID	10_1109_TNS_2025_3585859 11072236
Genre	orig-research
GrantInformation_xml	– fundername: Technological Research Institute (IRT) Nanoelec grantid: ANR-10-AIRT-05 – fundername: French Program d’Investissements d’Avenir (PIA)] – fundername: Fundação de Amparo à Pesquisa do Estado do Rio Grande do Sul (FAPERGS) grantid: 21/2551-0002047-4 – fundername: Université Grenoble Alpes (UGA)/Laboratoire de Physique Subatomique et de Cosmologie (LPSC)/Generator of Neutrons for Science and Irradiations (GENESIS) Platform
GroupedDBID	.DC .GJ 0R~ 29I 3O- 4.4 53G 5GY 5RE 5VS 6IK 8WZ 97E A6W AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK ACNCT ACPRK AENEX AETEA AETIX AFRAH AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD F5P HZ~ H~9 IAAWW IBMZZ ICLAB IDIHD IFIPE IFJZH IPLJI JAVBF LAI M43 MS~ O9- OCL P2P RIA RIE RNS TAE TN5 VH1 VOH AAYXX CITATION 7QF 7QL 7QQ 7SC 7SE 7SP 7SR 7T7 7TA 7TB 7U5 7U9 8BQ 8FD C1K F28 FR3 H8D H94 JG9 JQ2 KR7 L7M L~C L~D M7N P64
ID	FETCH-LOGICAL-c247t-af7196c82f6c65e054749d5c7f61a180a82a023e322b15fffda002acea0b724e3
IEDL.DBID	RIE
ISICitedReferencesCount	0
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001555522300003&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0018-9499
IngestDate	Sat Nov 15 17:42:17 EST 2025 Sat Nov 29 07:38:49 EST 2025 Wed Aug 27 07:36:50 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	8
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c247t-af7196c82f6c65e054749d5c7f61a180a82a023e322b15fffda002acea0b724e3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0009-0007-3825-1322 0000-0001-5781-5858 0009-0001-0627-1114 0000-0002-9964-0424 0009-0008-9562-1446 0000-0002-5160-5232 0000-0001-6126-6847 0000-0001-7113-6448
PQID	3247358255
PQPubID	85457
PageCount	9
ParticipantIDs	crossref_primary_10_1109_TNS_2025_3585859 ieee_primary_11072236 proquest_journals_3247358255
PublicationCentury	2000
PublicationDate	2025-08-01
PublicationDateYYYYMMDD	2025-08-01
PublicationDate_xml	– month: 08 year: 2025 text: 2025-08-01 day: 01
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE transactions on nuclear science
PublicationTitleAbbrev	TNS
PublicationYear	2025
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref13 ref12 ref15 ref14 (ref23) 2025 Kale (ref22) 2024 ref11 ref10 (ref25) 2024 ref2 ref17 (ref29) 2014 Hosseininoorbin (ref8) 2021 ref19 ref18 Vimal (ref1) 2021; 22 (ref24) 2024 ref20 ref28 ref27 ref7 ref9 Cai (ref4) ref3 (ref16) 2024 (ref21) 2024 (ref26) 2024 ref6 ref5
References_xml	– ident: ref14 doi: 10.1109/TNS.2023.3262448 – volume: 22 start-page: 173 issue: 1 year: 2021 ident: ref1 article-title: IoT based smart health monitoring with CNN using edge computing publication-title: J. Internet Technol. – ident: ref6 doi: 10.1109/ISVLSI.2019.00099 – volume-title: MobileNet Implementation year: 2024 ident: ref16 – ident: ref18 doi: 10.1109/TNS.2018.2884460 – ident: ref3 doi: 10.1145/3180155.3180220 – ident: ref11 doi: 10.1109/TR.2018.2878387 – ident: ref7 doi: 10.1109/TCAD.2019.2944584 – ident: ref13 doi: 10.1109/TNS.2022.3142092 – ident: ref15 doi: 10.1109/TNS.2024.3378807 – ident: ref20 doi: 10.1109/ISVLSI59464.2023.10238535 – ident: ref2 doi: 10.1109/COASE.2018.8560564 – volume-title: DDR5: What is On-Die ECC? year: 2024 ident: ref26 – volume-title: Free Images year: 2025 ident: ref23 – ident: ref5 doi: 10.1145/3526241.3530351 – ident: ref28 doi: 10.1145/1113841.1113843 – volume-title: Pi 4 year: 2024 ident: ref24 – ident: ref10 doi: 10.1109/TNS.2022.3224538 – volume-title: Raspberry Pi 4 Model B Product Brief year: 2024 ident: ref25 – year: 2021 ident: ref8 article-title: Exploring deep neural networks on edge TPU publication-title: arXiv:2110.08826 – ident: ref27 doi: 10.1145/3063180 – ident: ref19 doi: 10.1109/LASCAS53948.2022.9789088 – ident: ref9 doi: 10.1109/TNS.2021.3062014 – volume-title: Loop Scheduling in OpenM year: 2024 ident: ref22 – start-page: 622 volume-title: Proc. Asian Conf. Mach. Learn. ident: ref4 article-title: NeuralPower: Predict and deploy energy-efficient convolutional neural networks – volume-title: Valgrind year: 2024 ident: ref21 – volume-title: Single Event Effects Test Method and Guidelines year: 2014 ident: ref29 – ident: ref12 doi: 10.1109/TNS.2021.3050707 – ident: ref17 doi: 10.1109/ITC44170.2019.9000150
SSID	ssj0014505
Score	2.4543455
Snippet	Convolutional neural networks (CNNs) have become a standard technology in numerous industrial Internet of Things (IoT) applications and sectors, such as...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Index Database Publisher
StartPage	2821
SubjectTerms	Application programming interface Artificial neural networks Convolutional neural networks Energy efficiency Error correction codes Field programmable gate arrays Industrial applications Industrial Internet of Things Microprocessors MobileNet Multicore processing multicore processors multithreaded convolutional neural network (CNN) models Neural networks Neutron radiation Neutrons Radiation Radiation effects Reliability Reliability analysis Resilience Safety critical Single instruction multiple data soft error reliability Soft errors Thermal neutrons
Title	Radiation-Induced Soft Error Assessment of a Multithreaded MobileNet CNN Model Running in a Multicore Edge Processor
URI	https://ieeexplore.ieee.org/document/11072236 https://www.proquest.com/docview/3247358255
Volume	72
WOSCitedRecordID	wos001555522300003&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 1558-1578 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014505 issn: 0018-9499 databaseCode: RIE dateStart: 19630101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT8MwDI5g4gAH3ojBQDlw4dCta9OkPU5oiAsVGiBxq9zEQUhoRV3H78dJOx5CHLj14KaVv9qO63w2YxephDIFKINYhBgIY02QAYRBWYIUFHFpk136YRMqz9Onp-yuI6t7Lgwi-sNnOHSXvpZvKr10v8pGLlehcCbX2bpSsiVrfZYM3Mqt2yULpkesapJhNnrI7ykTjJJhnLgyWPYjBvmhKr88sQ8v1zv_fLFdtt3tI_mkBX6PreF8n2196y54wJqZ6zvgFB-4AR0aDb8np8undV3VfPLZkpNXlgNvmbiELBgSvK1Kchc5Nvwqz7kbmPbKZ0s_3oi_zFfirgUmn5pn5B3foKoP2eP19OHqJuiGLAQ6EqoJwCoyQp1GVmqZIKGjRGYSrawcwzgNIY2A4jqS4ZfjxFprgJwoaISwVJHA-Ij15tUcjxnP4kTHlP5FsQARCQ1Cj0FihEpqq2PTZ5crtRdvbS-NwucgYVYQRIWDqOgg6rNDp-YvuU7DfTZYAVV01rYoaFOoHOM3SU7-uO2UbbrV25N7A9Zr6iWesQ393rws6nP_IX0A_U3G6g
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT9xADLYKrQQcaMtDLKXtHHrhEMhOZvI4IrQIVIgQLBK3yJnxIKRqU4Usvx_PJAtUFQduOTiZyF9sj-P5bIBfeYp1jlhHiYopUtbZqECMo7rGVHHE5U12HYZNZGWZ394WlwNZPXBhiCgcPqMDfxlq-bYxc_-r7NDnKhzO0iX4qJWScU_Xei4a-Gf3jpdtmBdZVCXj4nBaXnMuKPVBon0hrPgnCoWxKv_54hBgTj6_89W-wPqwkxRHPfRf4QPNNmDtVX_BTeiufOcBr_rIj-gwZMU1u10xadumFUfPTTlF4wSKnovL2KJlwYumZodRUieOy1L4kWl_xNU8DDgS97OFuG-CKSb2jsTAOGjaLbg5mUyPT6NhzEJkpMq6CF3GZmhy6VKTamJ8MlVYbTKXjnGcx5hL5MhObPr1WDvnLLIbRUMY15lUlGzD8qyZ0Q6IItEm4QRQJgqVVAaVGWNKkrLUOJPYEewv1F797btpVCELiYuKIao8RNUA0Qi2vJpf5AYNj2BvAVQ12NtDxdvCzHN-td5947afsHI6vTivzs_K399g1a_Un-Pbg-WundN3-GQeu_uH9kf4qJ4AgM3KMQ
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Radiation-Induced+Soft+Error+Assessment+of+a+Multithreaded+MobileNet+CNN+Model+Running+in+a+Multicore+Edge+Processor&rft.jtitle=IEEE+transactions+on+nuclear+science&rft.au=Gava%2C+Jonas&rft.au=Sherjil%2C+Areeb&rft.au=Laurini%2C+Luiz+H&rft.au=Atukpor%2C+Emmanuel&rft.date=2025-08-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.issn=0018-9499&rft.eissn=1558-1578&rft.volume=72&rft.issue=11&rft.spage=2821&rft.epage=2829&rft_id=info:doi/10.1109%2FTNS.2025.3585859&rft.externalDBID=NO_FULL_TEXT
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0018-9499&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0018-9499&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0018-9499&client=summon