{"id":"https://openalex.org/W4402830425","doi":"https://doi.org/10.1109/ojcs.2024.3468895","title":"Enhancing Fault Tolerance in High-Performance Computing: A Real Hardware Case Study on a RISC-V Vector Processing Unit","display_name":"Enhancing Fault Tolerance in High-Performance Computing: A Real Hardware Case Study on a RISC-V Vector Processing Unit","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4402830425","doi":"https://doi.org/10.1109/ojcs.2024.3468895"},"language":"en","primary_location":{"id":"doi:10.1109/ojcs.2024.3468895","is_oa":true,"landing_page_url":"https://doi.org/10.1109/ojcs.2024.3468895","pdf_url":null,"source":{"id":"https://openalex.org/S4210176459","display_name":"IEEE Open Journal of the Computer Society","issn_l":"2644-1268","issn":["2644-1268"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Open Journal of the Computer Society","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/ojcs.2024.3468895","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002051086","display_name":"Marcello Barbirotta","orcid":"https://orcid.org/0000-0002-1902-7188"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marcello Barbirotta","raw_affiliation_strings":["Department of Information Engineering, Electronics and Telecommunications, Sapienza University of Rome, Via Eudossiana, Italy"],"raw_orcid":"https://orcid.org/0000-0002-1902-7188","affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Electronics and Telecommunications, Sapienza University of Rome, Via Eudossiana, Italy","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025463227","display_name":"Francesco Minervini","orcid":"https://orcid.org/0000-0001-8558-5690"},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Francesco Minervini","raw_affiliation_strings":["Barcelona Supercomputing Center, Barcelona, Spain"],"raw_orcid":"https://orcid.org/0000-0001-8558-5690","affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022679688","display_name":"Carlos Rojas","orcid":"https://orcid.org/0000-0002-7714-0277"},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Carlos Rojas Morales","raw_affiliation_strings":["Barcelona Supercomputing Center, Barcelona, Spain"],"raw_orcid":"https://orcid.org/0000-0002-7714-0277","affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084390427","display_name":"Adri\u00e1n Cristal","orcid":"https://orcid.org/0000-0003-1277-9296"},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Adrian Cristal","raw_affiliation_strings":["Barcelona Supercomputing Center, Barcelona, Spain"],"raw_orcid":"https://orcid.org/0000-0003-1277-9296","affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075162875","display_name":"Osman \u00dcnsal","orcid":"https://orcid.org/0000-0002-0544-9697"},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Osman Unsal","raw_affiliation_strings":["Barcelona Supercomputing Center, Barcelona, Spain"],"raw_orcid":"https://orcid.org/0000-0002-0544-9697","affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067054447","display_name":"Mauro Olivieri","orcid":"https://orcid.org/0000-0002-0214-9904"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Mauro Olivieri","raw_affiliation_strings":["Department of Information Engineering, Electronics and Telecommunications, Sapienza University of Rome, Via Eudossiana, Italy"],"raw_orcid":"https://orcid.org/0000-0002-0214-9904","affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Electronics and Telecommunications, Sapienza University of Rome, Via Eudossiana, Italy","institution_ids":["https://openalex.org/I861853513"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1750,"currency":"USD","value_usd":1750},"apc_paid":{"value":1750,"currency":"USD","value_usd":1750},"fwci":1.1137,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.7803552,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"5","issue":null,"first_page":"553","last_page":"565"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11005","display_name":"Radiation Effects in Electronics","score":0.9837999939918518,"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":0.9837999939918518,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9715999960899353,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.929099977016449,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.6550182104110718},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6180469989776611},{"id":"https://openalex.org/keywords/unit","display_name":"Unit (ring theory)","score":0.5658149719238281},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.4450819790363312},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3990262746810913},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3469664454460144},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3243102431297302},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11749988794326782},{"id":"https://openalex.org/keywords/mathematics-education","display_name":"Mathematics education","score":0.0705035924911499}],"concepts":[{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.6550182104110718},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6180469989776611},{"id":"https://openalex.org/C122637931","wikidata":"https://www.wikidata.org/wiki/Q118084","display_name":"Unit (ring theory)","level":2,"score":0.5658149719238281},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.4450819790363312},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3990262746810913},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3469664454460144},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3243102431297302},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11749988794326782},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.0705035924911499}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/ojcs.2024.3468895","is_oa":true,"landing_page_url":"https://doi.org/10.1109/ojcs.2024.3468895","pdf_url":null,"source":{"id":"https://openalex.org/S4210176459","display_name":"IEEE Open Journal of the Computer Society","issn_l":"2644-1268","issn":["2644-1268"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Open Journal of the Computer Society","raw_type":"journal-article"},{"id":"pmh:oai:upcommons.upc.edu:2117/433640","is_oa":true,"landing_page_url":"https://hdl.handle.net/2117/433640","pdf_url":"https://upcommons.upc.edu/bitstreams/3f20bd1e-6bb2-431e-9ae4-0eaf22c038be/download","source":{"id":"https://openalex.org/S4377196262","display_name":"UPCommons institutional repository (Universitat Polit\u00e8cnica de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9617848","host_organization_name":"Universitat Polit\u00e8cnica de Catalunya","host_organization_lineage":["https://openalex.org/I9617848"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:iris.uniroma1.it:11573/1739882","is_oa":true,"landing_page_url":"https://hdl.handle.net/11573/1739882","pdf_url":"https://iris.uniroma1.it/bitstream/11573/1739882/1/Barbirotta_Enhancing%20Fault%20Tolerance_2024.pdf","source":{"id":"https://openalex.org/S4377196107","display_name":"IRIS Research product catalog (Sapienza University of Rome)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:doaj.org/article:26116412d4934c9595d32832eb3f552f","is_oa":true,"landing_page_url":"https://doaj.org/article/26116412d4934c9595d32832eb3f552f","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Open Journal of the Computer Society, Vol 5, Pp 553-565 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/ojcs.2024.3468895","is_oa":true,"landing_page_url":"https://doi.org/10.1109/ojcs.2024.3468895","pdf_url":null,"source":{"id":"https://openalex.org/S4210176459","display_name":"IEEE Open Journal of the Computer Society","issn_l":"2644-1268","issn":["2644-1268"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Open Journal of the Computer Society","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1864485850","https://openalex.org/W1981432246","https://openalex.org/W1984564341","https://openalex.org/W2001495258","https://openalex.org/W2001984859","https://openalex.org/W2046517141","https://openalex.org/W2089536264","https://openalex.org/W2116059696","https://openalex.org/W2116115793","https://openalex.org/W2118476840","https://openalex.org/W2122142939","https://openalex.org/W2136510033","https://openalex.org/W2175874879","https://openalex.org/W2466095195","https://openalex.org/W2489596568","https://openalex.org/W2592594796","https://openalex.org/W2613264175","https://openalex.org/W2944240397","https://openalex.org/W3088817849","https://openalex.org/W3100547819","https://openalex.org/W3110268701","https://openalex.org/W3123542955","https://openalex.org/W4226530726","https://openalex.org/W4244668175","https://openalex.org/W4307980119","https://openalex.org/W4311995762","https://openalex.org/W4312226941","https://openalex.org/W4312565909","https://openalex.org/W4319833569","https://openalex.org/W4360605760","https://openalex.org/W4362558000","https://openalex.org/W4386124183","https://openalex.org/W4400447853","https://openalex.org/W6681647240","https://openalex.org/W6801741045","https://openalex.org/W6856124559","https://openalex.org/W7052057559"],"related_works":["https://openalex.org/W611386996","https://openalex.org/W2371343292","https://openalex.org/W2418291489","https://openalex.org/W629290331","https://openalex.org/W2068121105","https://openalex.org/W3096519538","https://openalex.org/W2744747300","https://openalex.org/W617685022","https://openalex.org/W4241166160","https://openalex.org/W2384826897"],"abstract_inverted_index":{"High-Performance":[0],"Computing":[1],"(HPC)":[2],"systems":[3,31],"are":[4],"designed":[5],"for":[6,99],"large-scale":[7],"processing":[8],"and":[9,16,36,42,48,62,106,143],"complex":[10,49],"dataset":[11],"analysis":[12],"leveraging":[13],"scalability,":[14],"efficiency,":[15],"parallelism,":[17],"often":[18],"integrating":[19],"specialized":[20],"hardware":[21,138],"structures":[22],"such":[23],"as":[24],"Vector":[25,75],"Processing":[26,76],"Units":[27],"(VPUs).":[28],"As":[29],"these":[30],"have":[32],"grown":[33],"in":[34,51,94,122,147],"complexity":[35],"scale,":[37],"their":[38],"vulnerability":[39],"to":[40],"errors":[41],"failures":[43],"has":[44],"become":[45],"an":[46,95,130],"important":[47],"issue":[50],"the":[52,69,79,86,104,112],"HPC":[53],"world.":[54],"Our":[55],"research":[56],"addresses":[57],"this":[58,84],"challenge":[59],"by":[60,129],"exploring":[61],"implementing":[63],"advanced":[64],"fault":[65,132],"tolerance":[66],"techniques":[67],"inside":[68,111],"Vitruvius+":[70],"architecture,":[71],"a":[72,118,137,144],"partial":[73],"out-of-order":[74],"Unit.":[77],"To":[78],"best":[80],"of":[81,91,108,120,140],"our":[82],"knowledge,":[83],"is":[85],"first":[87],"full":[88],"RTL-level":[89],"implementation":[90],"instruction":[92],"replication":[93],"HPC-class":[96],"vector":[97],"processor":[98],"reliability.":[100],"Specifically,":[101],"we":[102],"investigate":[103],"integration":[105],"interaction":[107],"redundancy":[109],"mechanisms":[110],"most":[113],"sensitive":[114],"architectural":[115],"units,":[116],"obtaining":[117],"reduction":[119],"75%":[121],"non-silent":[123],"faults":[124],"causing":[125],"system":[126],"failure,":[127],"proven":[128],"extensive":[131],"injection":[133],"simulation":[134],"campaign,":[135],"with":[136],"overhead":[139],"only":[141],"7.5%":[142],"negligible":[145],"variation":[146],"clock":[148],"frequency.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2024-09-26T00:00:00"}