{"id":"https://openalex.org/W2985374077","doi":"https://doi.org/10.1109/cluster.2019.8890989","title":"Quantifying the Impact of Memory Errors in Deep Learning","display_name":"Quantifying the Impact of Memory Errors in Deep Learning","publication_year":2019,"publication_date":"2019-09-01","ids":{"openalex":"https://openalex.org/W2985374077","doi":"https://doi.org/10.1109/cluster.2019.8890989","mag":"2985374077"},"language":"en","primary_location":{"id":"doi:10.1109/cluster.2019.8890989","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cluster.2019.8890989","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Cluster Computing (CLUSTER)","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/A5100422993","display_name":"Zhao Zhang","orcid":"https://orcid.org/0000-0001-9165-1439"},"institutions":[{"id":"https://openalex.org/I4388891828","display_name":"Texas Advanced Computing Center","ror":"https://ror.org/00xg4bh43","country_code":null,"type":"facility","lineage":["https://openalex.org/I4388891828","https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhao Zhang","raw_affiliation_strings":["Texas Advanced Computing Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texas Advanced Computing Center","institution_ids":["https://openalex.org/I4388891828"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101670806","display_name":"Lei Huang","orcid":"https://orcid.org/0000-0003-0502-168X"},"institutions":[{"id":"https://openalex.org/I4388891828","display_name":"Texas Advanced Computing Center","ror":"https://ror.org/00xg4bh43","country_code":null,"type":"facility","lineage":["https://openalex.org/I4388891828","https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lei Huang","raw_affiliation_strings":["Texas Advanced Computing Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texas Advanced Computing Center","institution_ids":["https://openalex.org/I4388891828"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057218817","display_name":"Ruizhu Huang","orcid":"https://orcid.org/0000-0003-3285-1945"},"institutions":[{"id":"https://openalex.org/I4388891828","display_name":"Texas Advanced Computing Center","ror":"https://ror.org/00xg4bh43","country_code":null,"type":"facility","lineage":["https://openalex.org/I4388891828","https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruizhu Huang","raw_affiliation_strings":["Texas Advanced Computing Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texas Advanced Computing Center","institution_ids":["https://openalex.org/I4388891828"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101883722","display_name":"Weijia Xu","orcid":"https://orcid.org/0000-0002-5134-6381"},"institutions":[{"id":"https://openalex.org/I4388891828","display_name":"Texas Advanced Computing Center","ror":"https://ror.org/00xg4bh43","country_code":null,"type":"facility","lineage":["https://openalex.org/I4388891828","https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weijia Xu","raw_affiliation_strings":["Texas Advanced Computing Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texas Advanced Computing Center","institution_ids":["https://openalex.org/I4388891828"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061630529","display_name":"Daniel S. Katz","orcid":"https://orcid.org/0000-0001-5934-7525"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I4210135837","display_name":"National Center for Supercomputing Applications","ror":"https://ror.org/03r10zj06","country_code":"US","type":"facility","lineage":["https://openalex.org/I157725225","https://openalex.org/I4210135837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel S. Katz","raw_affiliation_strings":["NCSA & CS & ECE & iSchool, University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NCSA & CS & ECE & iSchool, University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225","https://openalex.org/I4210135837"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11005","display_name":"Radiation Effects in Electronics","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9894000291824341,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9883999824523926,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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":0.81268709897995},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.7025906443595886},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6483345627784729},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.5327919125556946},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5287717580795288},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5112898349761963},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.4710167646408081},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4349398612976074},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.4228874742984772},{"id":"https://openalex.org/keywords/portfolio","display_name":"Portfolio","score":0.4124053716659546},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40119674801826477},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3835434317588806},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.37347543239593506},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.24793800711631775},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24459657073020935},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.21435508131980896},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11758410930633545},{"id":"https://openalex.org/keywords/finance","display_name":"Finance","score":0.11475971341133118}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.81268709897995},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.7025906443595886},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6483345627784729},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.5327919125556946},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5287717580795288},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5112898349761963},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.4710167646408081},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4349398612976074},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.4228874742984772},{"id":"https://openalex.org/C2780821815","wikidata":"https://www.wikidata.org/wiki/Q5340806","display_name":"Portfolio","level":2,"score":0.4124053716659546},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40119674801826477},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3835434317588806},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.37347543239593506},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.24793800711631775},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24459657073020935},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.21435508131980896},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11758410930633545},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.11475971341133118},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cluster.2019.8890989","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cluster.2019.8890989","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Cluster Computing (CLUSTER)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.8199999928474426}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":67,"referenced_works":["https://openalex.org/W1500893261","https://openalex.org/W1584278023","https://openalex.org/W1861492603","https://openalex.org/W1947481528","https://openalex.org/W1986905947","https://openalex.org/W1999900893","https://openalex.org/W2027716782","https://openalex.org/W2066677768","https://openalex.org/W2079421586","https://openalex.org/W2080019739","https://openalex.org/W2096865422","https://openalex.org/W2106549758","https://openalex.org/W2108598243","https://openalex.org/W2114901829","https://openalex.org/W2116314988","https://openalex.org/W2122249806","https://openalex.org/W2125169487","https://openalex.org/W2132835375","https://openalex.org/W2142395917","https://openalex.org/W2143128278","https://openalex.org/W2144512449","https://openalex.org/W2146351362","https://openalex.org/W2148605318","https://openalex.org/W2151917022","https://openalex.org/W2159216681","https://openalex.org/W2163605009","https://openalex.org/W2167502740","https://openalex.org/W2194775991","https://openalex.org/W2197075213","https://openalex.org/W2318507312","https://openalex.org/W2337082154","https://openalex.org/W2605277893","https://openalex.org/W2735162286","https://openalex.org/W2736123080","https://openalex.org/W2767224631","https://openalex.org/W2767260595","https://openalex.org/W2767321582","https://openalex.org/W2769856846","https://openalex.org/W2770102447","https://openalex.org/W2787998955","https://openalex.org/W2795147506","https://openalex.org/W2806167418","https://openalex.org/W2901848761","https://openalex.org/W2919115771","https://openalex.org/W2943768976","https://openalex.org/W2962747323","https://openalex.org/W2962780982","https://openalex.org/W2964108906","https://openalex.org/W3000292756","https://openalex.org/W3004493283","https://openalex.org/W3118608800","https://openalex.org/W3151762208","https://openalex.org/W3187317723","https://openalex.org/W4249144718","https://openalex.org/W4294641903","https://openalex.org/W4300658771","https://openalex.org/W4301239768","https://openalex.org/W6634921276","https://openalex.org/W6684191040","https://openalex.org/W6685065516","https://openalex.org/W6741285702","https://openalex.org/W6743955621","https://openalex.org/W6746419290","https://openalex.org/W6746514494","https://openalex.org/W6748645090","https://openalex.org/W6749823088","https://openalex.org/W6787972765"],"related_works":["https://openalex.org/W1667647204","https://openalex.org/W2404647514","https://openalex.org/W4247536566","https://openalex.org/W2018477250","https://openalex.org/W3119814709","https://openalex.org/W4241418540","https://openalex.org/W2116314988","https://openalex.org/W168676510","https://openalex.org/W2394408226","https://openalex.org/W4389168214"],"abstract_inverted_index":{"The":[0,46,113],"use":[1],"of":[2,48,77,118,136,145,181,199],"deep":[3],"learning":[4],"(DL)":[5],"on":[6,50,67,72,160,185],"HPC":[7,44,73],"resources":[8],"has":[9,231],"become":[10],"common":[11],"as":[12,229],"scientists":[13],"explore":[14],"and":[15,84,105,123,168,235,243],"exploit":[16],"DL":[17,51,54,69],"methods":[18],"to":[19,39,143,225,239],"solve":[20],"domain":[21],"problems.":[22],"On":[23],"the":[24,28,75,102,110,125,133,164,179,200,215],"other":[25],"hand,":[26],"in":[27,74,128,141,178,214],"coming":[29],"exascale":[30],"computing":[31,152],"era,":[32],"a":[33,86,137,211],"high":[34],"error":[35,188],"rate":[36,127],"is":[37,139],"expected":[38],"be":[40,207],"problematic":[41],"for":[42,171],"most":[43],"applications.":[45],"impact":[47],"errors":[49,99,205],"applications,":[52],"especially":[53],"training,":[55],"remains":[56],"unclear":[57],"given":[58],"their":[59,161,176],"stochastic":[60],"nature.":[61],"In":[62],"this":[63,148,221],"paper,":[64],"we":[65,82,219],"focus":[66],"understanding":[68],"training":[70,107,121,182,212],"applications":[71,92],"presence":[76],"silent":[78,96],"data":[79,97],"corruption.":[80],"Specifically,":[81],"design":[83,103,157],"perform":[85],"quantification":[87],"study":[88],"with":[89,109],"three":[90],"representative":[91],"by":[93,210],"manually":[94],"injecting":[95],"corruption":[98],"(SDCs)":[100],"across":[101],"space":[104,236],"compare":[106],"results":[108,114,183],"error-free":[111],"baseline.":[112],"show":[115],"only":[116],"0.61-1.76%":[117],"SDCs":[119,201],"cause":[120,203],"failures,":[122],"taking":[124],"SDC":[126],"modern":[129],"hardware":[130],"into":[131],"account,":[132],"actual":[134],"chance":[135],"failure":[138,166],"one":[140],"thousands":[142],"millions":[144],"executions.":[146],"With":[147],"quantitatively":[149],"measured":[150],"impact,":[151],"centers":[153],"can":[154,206],"make":[155],"rational":[156],"decisions":[158],"based":[159],"application":[162],"portfolio,":[163],"acceptable":[165],"rate,":[167],"financial":[169],"constraints;":[170],"example,":[172],"they":[173],"might":[174],"determine":[175],"confidence":[177],"correctness":[180],"performed":[184],"processors":[186],"without":[187],"correction":[189],"code":[190],"(ECC)":[191],"RAM.":[192],"We":[193],"also":[194],"discover":[195],"that":[196,202],"over":[197],"75-90%":[198],"catastrophic":[204,227],"easily":[208],"detected":[209],"loss":[213],"next":[216],"iteration.":[217],"Thus":[218],"propose":[220],"error-aware":[222],"software":[223],"solution":[224],"correct":[226],"errors,":[228],"it":[230],"significantly":[232],"lower":[233],"time":[234],"overhead":[237],"compared":[238],"algorithm-based":[240],"fault-tolerance":[241],"(ABFT)":[242],"ECC.":[244]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}