{"id":"https://openalex.org/W7115185763","doi":"https://doi.org/10.1109/mm.2025.3643799","title":"Silent Data Corruption: Optimal Mitigation Strategies for Data Center Computing","display_name":"Silent Data Corruption: Optimal Mitigation Strategies for Data Center Computing","publication_year":2025,"publication_date":"2025-12-15","ids":{"openalex":"https://openalex.org/W7115185763","doi":"https://doi.org/10.1109/mm.2025.3643799"},"language":null,"primary_location":{"id":"doi:10.1109/mm.2025.3643799","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mm.2025.3643799","pdf_url":null,"source":{"id":"https://openalex.org/S59697426","display_name":"IEEE Micro","issn_l":"0272-1732","issn":["0272-1732","1937-4143"],"is_oa":false,"is_in_doaj":false,"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 Micro","raw_type":"journal-article"},"type":"article","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":null,"display_name":"Nirmal Saxena","orcid":"https://orcid.org/0009-0001-1248-0721"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nirmal Saxena","raw_affiliation_strings":["Nvidia, Santa Clara, CA, USA"],"raw_orcid":"https://orcid.org/0009-0001-1248-0721","affiliations":[{"raw_affiliation_string":"Nvidia, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Saurabh Hukerikar","orcid":"https://orcid.org/0000-0002-2612-2001"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saurabh Hukerikar","raw_affiliation_strings":["Nvidia, Santa Clara, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-2612-2001","affiliations":[{"raw_affiliation_string":"Nvidia, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":null,"display_name":"Siva Hari","orcid":"https://orcid.org/0000-0001-8346-7981"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siva Hari","raw_affiliation_strings":["Nvidia, Santa Clara, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-8346-7981","affiliations":[{"raw_affiliation_string":"Nvidia, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210127875"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.545227,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"46","issue":"1","first_page":"10","last_page":"18"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.34040001034736633,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.34040001034736633,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.21699999272823334,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.18080000579357147,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/overhead","display_name":"Overhead (engineering)","score":0.6608999967575073},{"id":"https://openalex.org/keywords/fault-detection-and-isolation","display_name":"Fault detection and isolation","score":0.6394000053405762},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5090000033378601},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.49070000648498535},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.48840001225471497},{"id":"https://openalex.org/keywords/transient","display_name":"Transient (computer programming)","score":0.3840999901294708},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.37220001220703125},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.34610000252723694}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8765000104904175},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6608999967575073},{"id":"https://openalex.org/C152745839","wikidata":"https://www.wikidata.org/wiki/Q5438153","display_name":"Fault detection and isolation","level":3,"score":0.6394000053405762},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5200999975204468},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5090000033378601},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.49070000648498535},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.48840001225471497},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.4530999958515167},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3921000063419342},{"id":"https://openalex.org/C2780799671","wikidata":"https://www.wikidata.org/wiki/Q17087362","display_name":"Transient (computer programming)","level":2,"score":0.3840999901294708},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.37220001220703125},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.34610000252723694},{"id":"https://openalex.org/C175551986","wikidata":"https://www.wikidata.org/wiki/Q47089","display_name":"Fault (geology)","level":2,"score":0.335999995470047},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.3294000029563904},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3244999945163727},{"id":"https://openalex.org/C2775928411","wikidata":"https://www.wikidata.org/wiki/Q2041312","display_name":"Fault injection","level":3,"score":0.3118000030517578},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.30660000443458557},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.29350000619888306},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.2784999907016754},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C126953365","wikidata":"https://www.wikidata.org/wiki/Q5438152","display_name":"Fault coverage","level":3,"score":0.2632000148296356}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mm.2025.3643799","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mm.2025.3643799","pdf_url":null,"source":{"id":"https://openalex.org/S59697426","display_name":"IEEE Micro","issn_l":"0272-1732","issn":["0272-1732","1937-4143"],"is_oa":false,"is_in_doaj":false,"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 Micro","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.8157074451446533}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2003128690","https://openalex.org/W2033346530","https://openalex.org/W2033656974","https://openalex.org/W2133046454","https://openalex.org/W3006951979","https://openalex.org/W3171842021","https://openalex.org/W4211189626","https://openalex.org/W4312335373","https://openalex.org/W4312863009","https://openalex.org/W4386212580","https://openalex.org/W4396910092","https://openalex.org/W4401990398","https://openalex.org/W4404564237","https://openalex.org/W4409248377"],"related_works":[],"abstract_inverted_index":{"Given":[0],"current":[1],"datacenter":[2],"compute":[3,58,100],"scales,":[4],"extended":[5],"job":[6],"durations,":[7],"and":[8,26,38,70,88,128],"existing":[9,23],"detection":[10,24,82,146],"mechanisms,":[11],"the":[12,50,90,140],"risk":[13],"of":[14,142],"silent":[15],"data":[16],"corruption":[17],"(SDC)":[18],"exposure":[19],"is":[20,111,116],"substantial.":[21],"Leveraging":[22],"coverage":[25],"SDC":[27,32,56,74,106,145],"characteristics,":[28],"we":[29],"propose":[30],"optimized":[31],"mitigation":[33],"strategies":[34,42],"that":[35],"balance":[36],"availability":[37],"reliability.":[39],"These":[40],"optimization":[41],"strive":[43],"to":[44,84,96,98],"achieve":[45],"Shannon\u2019s":[46],"like":[47],"bounds":[48],"on":[49],"overhead":[51],"required":[52],"for":[53,79,92,105,133],"reliable":[54],"(meaning":[55],"mitigation)":[57],"channels.":[59],"While":[60],"error-correcting":[61],"codes":[62],"effectively":[63],"address":[64],"transient":[65],"faults":[66],"in":[67,108,147],"memory,":[68],"storage,":[69],"high-speed":[71],"links,":[72],"residual":[73],"risks":[75],"persist.":[76],"We":[77],"advocate":[78],"algorithm-based":[80],"error":[81],"(ABED)":[83],"bridge":[85],"this":[86],"gap":[87],"stress":[89],"need":[91],"ongoing":[93],"ABED":[94],"research":[95],"adapt":[97],"evolving":[99],"patterns.":[101],"Low-level":[102],"fault":[103,135],"simulation":[104],"assessment":[107],"long-running":[109],"jobs":[110],"impractical;":[112],"instead,":[113],"near-real-time":[114],"evaluation":[115],"essential.":[117],"Although":[118],"our":[119],"approach":[120],"partially":[121],"addresses":[122],"systematic":[123],"faults,":[124],"robust":[125],"design":[126],"verification":[127],"manufacturing":[129],"tests":[130],"remain":[131],"critical":[132],"comprehensive":[134],"management.":[136],"This":[137],"work":[138],"highlights":[139],"urgency":[141],"scalable,":[143],"efficient":[144],"large-scale":[148],"systems.":[149]},"counts_by_year":[],"updated_date":"2026-03-13T14:20:09.374765","created_date":"2025-12-15T00:00:00"}
