{"id":"https://openalex.org/W3205698808","doi":"https://doi.org/10.1145/3466752.3480111","title":"Characterizing\u00a0and\u00a0Mitigating\u00a0Soft\u00a0Errors in GPU DRAM","display_name":"Characterizing\u00a0and\u00a0Mitigating\u00a0Soft\u00a0Errors in GPU DRAM","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3205698808","doi":"https://doi.org/10.1145/3466752.3480111","mag":"3205698808"},"language":"en","primary_location":{"id":"doi:10.1145/3466752.3480111","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3466752.3480111","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"MICRO-54: 54th Annual IEEE/ACM International Symposium on Microarchitecture","raw_type":"proceedings-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":"https://openalex.org/A5076752182","display_name":"Michael B. Sullivan","orcid":"https://orcid.org/0000-0001-6537-2065"},"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":true,"raw_author_name":"Michael B. Sullivan","raw_affiliation_strings":["NVIDIA, United States of America"],"affiliations":[{"raw_affiliation_string":"NVIDIA, United States of America","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058543385","display_name":"N.R. 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, United States of America"],"affiliations":[{"raw_affiliation_string":"NVIDIA, United States of America","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055699570","display_name":"Mike O\u2019Connor","orcid":"https://orcid.org/0000-0003-0944-2393"},"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":"Mike O'Connor","raw_affiliation_strings":["NVIDIA, United States of America"],"affiliations":[{"raw_affiliation_string":"NVIDIA, United States of America","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101991475","display_name":"Donghyuk Lee","orcid":"https://orcid.org/0009-0001-9572-5391"},"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":"Donghyuk Lee","raw_affiliation_strings":["NVIDIA, United States of America"],"affiliations":[{"raw_affiliation_string":"NVIDIA, United States of America","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085364010","display_name":"Paul Racunas","orcid":null},"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":"Paul Racunas","raw_affiliation_strings":["NVIDIA, United States of America"],"affiliations":[{"raw_affiliation_string":"NVIDIA, United States of America","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065625558","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, United States of America"],"affiliations":[{"raw_affiliation_string":"NVIDIA, United States of America","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027550136","display_name":"Timothy Tsai","orcid":"https://orcid.org/0000-0001-8190-675X"},"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":"Timothy Tsai","raw_affiliation_strings":["NVIDIA, United States of America"],"affiliations":[{"raw_affiliation_string":"NVIDIA, United States of America","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054590774","display_name":"Siva Kumar Sastry 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 Kumar Sastry Hari","raw_affiliation_strings":["NVIDIA, United States of America"],"affiliations":[{"raw_affiliation_string":"NVIDIA, United States of America","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063354509","display_name":"Stephen W. Keckler","orcid":"https://orcid.org/0000-0001-6701-6099"},"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":"Stephen W. Keckler","raw_affiliation_strings":["NVIDIA, United States of America"],"affiliations":[{"raw_affiliation_string":"NVIDIA, United States of America","institution_ids":["https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5076752182"],"corresponding_institution_ids":["https://openalex.org/I4210127875"],"apc_list":null,"apc_paid":null,"fwci":2.9079,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.91474491,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"641","last_page":"653"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11005","display_name":"Radiation Effects in Electronics","score":0.9998999834060669,"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":0.9998999834060669,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9937000274658203,"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/T10472","display_name":"Semiconductor materials and devices","score":0.9922999739646912,"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/dram","display_name":"Dram","score":0.8594129085540771},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8456118106842041},{"id":"https://openalex.org/keywords/soft-error","display_name":"Soft error","score":0.6156266927719116},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.5721294283866882},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.38052108883857727},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.34529218077659607},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.12913727760314941},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.11916586756706238}],"concepts":[{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.8594129085540771},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8456118106842041},{"id":"https://openalex.org/C154474529","wikidata":"https://www.wikidata.org/wiki/Q1658917","display_name":"Soft error","level":2,"score":0.6156266927719116},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.5721294283866882},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.38052108883857727},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.34529218077659607},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12913727760314941},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.11916586756706238},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3466752.3480111","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3466752.3480111","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"MICRO-54: 54th Annual IEEE/ACM International Symposium on Microarchitecture","raw_type":"proceedings-article"},{"id":"pmh:oai:purl.org/net/epubs:work/50833952","is_oa":false,"landing_page_url":"http://purl.org/net/epubs/work/50833952","pdf_url":null,"source":{"id":"https://openalex.org/S4306400600","display_name":"ePubs (Science and Technology Facilities Council, Research Councils UK)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I162524378","host_organization_name":"Science and Technology Facilities Council","host_organization_lineage":["https://openalex.org/I162524378"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.8299999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1594652978","https://openalex.org/W1601793793","https://openalex.org/W1606480398","https://openalex.org/W1966243865","https://openalex.org/W1978082708","https://openalex.org/W1986905947","https://openalex.org/W1989061323","https://openalex.org/W2012473825","https://openalex.org/W2015026878","https://openalex.org/W2021708499","https://openalex.org/W2025024269","https://openalex.org/W2040379684","https://openalex.org/W2065171379","https://openalex.org/W2094127360","https://openalex.org/W2104493171","https://openalex.org/W2114260887","https://openalex.org/W2118637853","https://openalex.org/W2141461871","https://openalex.org/W2141527188","https://openalex.org/W2141765579","https://openalex.org/W2143160443","https://openalex.org/W2162457113","https://openalex.org/W2171323246","https://openalex.org/W2172248936","https://openalex.org/W2233147800","https://openalex.org/W2238285554","https://openalex.org/W2318507312","https://openalex.org/W2326201358","https://openalex.org/W2334439626","https://openalex.org/W2470243357","https://openalex.org/W2522781526","https://openalex.org/W2561865895","https://openalex.org/W2620776621","https://openalex.org/W2621253603","https://openalex.org/W2741005141","https://openalex.org/W2762122197","https://openalex.org/W2765567583","https://openalex.org/W2767321582","https://openalex.org/W2768990461","https://openalex.org/W2795308992","https://openalex.org/W2795570316","https://openalex.org/W2796649226","https://openalex.org/W2806983213","https://openalex.org/W2903241786","https://openalex.org/W2942537621","https://openalex.org/W3093933627","https://openalex.org/W3094070534","https://openalex.org/W3094406919","https://openalex.org/W3209598344","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2162457113","https://openalex.org/W1528863892","https://openalex.org/W2007444174","https://openalex.org/W1528544434","https://openalex.org/W2138596439","https://openalex.org/W2543484774","https://openalex.org/W2152643014","https://openalex.org/W1489210541","https://openalex.org/W2000563648","https://openalex.org/W3141188004"],"abstract_inverted_index":{"GPUs":[0,13],"are":[1,95],"used":[2],"in":[3,152,158,225],"high-reliability":[4],"systems,":[5],"including":[6],"high-performance":[7],"computers":[8],"and":[9,20,37,51,110,133,146,219,231,254,257],"autonomous":[10],"vehicles.":[11],"Because":[12],"employ":[14],"a":[15,26,70],"high-bandwidth,":[16],"wide-interface":[17],"to":[18,82,108,129,165,184,193,199,212],"DRAM":[19,28,49],"fetch":[21],"each":[22],"memory":[23,54,68],"access":[24],"from":[25,88,113,149],"single":[27],"device,":[29],"implementing":[30],"full-device":[31],"correction":[32,234],"through":[33],"ECC":[34,182,221,245],"is":[35,41],"expensive":[36],"impractical.":[38],"This":[39,56],"challenge":[40],"compounded":[42],"by":[43,85,140,191,210],"worsening":[44],"relative":[45,143,198],"rates":[46,145],"of":[47,98,116,135,169,196,207],"multi-bit":[48,160],"errors":[50,78,94,151,209],"increasing":[52],"GPU":[53,153],"capacities.":[55],"paper":[57],"first":[58],"presents":[59],"high-energy":[60],"neutron":[61],"beam":[62,117,126],"testing":[63,100,118,127],"results":[64,74,115,128],"for":[65],"the":[66,89,99,114,123,131,142,159,166,170,186,205],"HBM2":[67,171],"on":[69,106,174],"compute-class":[71],"GPU.":[72],"These":[73,241],"uncovered":[75],"unexpected":[76],"intermittent":[77],"that":[79,223],"we":[80,102,121,163,178],"determine":[81],"be":[83],"caused":[84],"cell":[86],"damage":[87],"high-intensity":[90],"beam.":[91],"As":[92],"these":[93,175],"an":[96],"artifact":[97],"apparatus,":[101],"provide":[103],"best-practice":[104],"guidance":[105],"how":[107],"identify":[109],"filter":[111],"them":[112],"campaigns.":[119],"Second,":[120],"use":[122],"soft":[124,150],"error":[125,137,144,147,176,233],"inform":[130],"design":[132,227],"evaluation":[134],"system-level":[136],"protection":[138],"mechanisms":[139],"reporting":[141],"patterns":[148],"DRAM.":[154],"We":[155,215],"observe":[156],"locality":[157],"errors,":[161],"which":[162],"attribute":[164],"underlying":[167],"structure":[168],"memory.":[172],"Based":[173],"patterns,":[177],"propose":[179],"several":[180],"novel":[181,217],"schemes":[183,242],"decrease":[185],"silent":[187],"data":[188],"corruption":[189],"risk":[190],"up":[192,211],"five":[194],"orders":[195],"magnitude":[197],"SEC-DED":[200,244],"ECC,":[201],"while":[202],"also":[203],"reducing":[204],"number":[206],"uncorrectable":[208],"7.87":[213],"\u00d7.":[214],"compare":[216],"binary":[218],"symbol-based":[220],"organizations":[222],"differ":[224],"their":[226],"complexity,":[228],"hardware":[229],"overheads,":[230],"permanent":[232],"abilities,":[235],"ultimately":[236],"recommending":[237],"two":[238],"promising":[239],"organizations.":[240],"replace":[243],"with":[246],"no":[247,251],"additional":[248],"redundancy,":[249],"likely":[250],"performance":[252],"impacts,":[253],"modest":[255],"area":[256],"complexity":[258],"costs.":[259]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2021-10-25T00:00:00"}