{"id":"https://openalex.org/W4402044817","doi":"https://doi.org/10.1145/3625549.3658686","title":"Reinforcement Learning-based Adaptive Mitigation of Uncorrected DRAM Errors in the Field","display_name":"Reinforcement Learning-based Adaptive Mitigation of Uncorrected DRAM Errors in the Field","publication_year":2024,"publication_date":"2024-06-03","ids":{"openalex":"https://openalex.org/W4402044817","doi":"https://doi.org/10.1145/3625549.3658686"},"language":"en","primary_location":{"id":"doi:10.1145/3625549.3658686","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3625549.3658686","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2407.16377","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011658445","display_name":"Isaac Boixaderas","orcid":"https://orcid.org/0000-0002-7738-524X"},"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":true,"raw_author_name":"Isaac Boixaderas","raw_affiliation_strings":["Barcelona Supercomputing Center, Barcelona, Spain"],"raw_orcid":"https://orcid.org/0000-0002-7738-524X","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/A5052647347","display_name":"Sergi Mor\u00e9","orcid":"https://orcid.org/0009-0004-8997-4051"},"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":"Sergi Mor\u00e9","raw_affiliation_strings":["Barcelona Supercomputing Center, Barcelona, Spain"],"raw_orcid":"https://orcid.org/0009-0004-8997-4051","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/A5103814812","display_name":"Javier Bartolome","orcid":"https://orcid.org/0000-0002-5785-4942"},"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":"Javier Bartolome","raw_affiliation_strings":["Barcelona Supercomputing Center, Barcelona, Spain"],"raw_orcid":"https://orcid.org/0000-0002-5785-4942","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/A5068897597","display_name":"D. Vicente","orcid":"https://orcid.org/0000-0002-1584-1182"},"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":"David Vicente","raw_affiliation_strings":["Barcelona Supercomputing Center, Barcelona, Spain"],"raw_orcid":"https://orcid.org/0000-0002-1584-1182","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/A5021600526","display_name":"Petar Radojkovi\u0107","orcid":"https://orcid.org/0000-0002-9334-3330"},"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":"Petar Radojkovi\u0107","raw_affiliation_strings":["Barcelona Supercomputing Center, Barcelona, Spain"],"raw_orcid":"https://orcid.org/0000-0002-9334-3330","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/A5047069371","display_name":"Paul Carpenter","orcid":"https://orcid.org/0000-0002-9392-0521"},"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":"Paul M. Carpenter","raw_affiliation_strings":["Barcelona Supercomputing Center, Barcelona, Spain"],"raw_orcid":"https://orcid.org/0000-0002-9392-0521","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/A5075755125","display_name":"Eduard Ayguad\u00e9","orcid":"https://orcid.org/0000-0002-5146-103X"},"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":"Eduard Ayguad\u00e9","raw_affiliation_strings":["Barcelona Supercomputing Center, Barcelona, Spain","Universitat Polit\u00e8cnica de Catalunya, Barcelona, Spain"],"raw_orcid":"https://orcid.org/0000-0002-5146-103X","affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]},{"raw_affiliation_string":"Universitat Polit\u00e8cnica de Catalunya, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5011658445"],"corresponding_institution_ids":["https://openalex.org/I2799803557","https://openalex.org/I9617848"],"apc_list":null,"apc_paid":null,"fwci":0.1949,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.50169514,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"240","last_page":"252"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11005","display_name":"Radiation Effects in Electronics","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"}},"topics":[{"id":"https://openalex.org/T11005","display_name":"Radiation Effects in Electronics","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"}},{"id":"https://openalex.org/T12423","display_name":"Software Reliability and Analysis Research","score":0.991599977016449,"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"}},{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9750999808311462,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8515925407409668},{"id":"https://openalex.org/keywords/dram","display_name":"Dram","score":0.8458766937255859},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7046456336975098},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5684012770652771},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.507925808429718},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33245792984962463},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15652447938919067},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.14369690418243408}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8515925407409668},{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.8458766937255859},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7046456336975098},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5684012770652771},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.507925808429718},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33245792984962463},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15652447938919067},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.14369690418243408},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3625549.3658686","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3625549.3658686","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2407.16377","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.16377","pdf_url":"https://arxiv.org/pdf/2407.16377","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:upcommons.upc.edu:2117/427571","is_oa":true,"landing_page_url":"https://hdl.handle.net/2117/427571","pdf_url":"https://upcommons.upc.edu/bitstreams/705b5f58-eb03-4e8b-b809-b2760119d18e/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/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2407.16377","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.16377","pdf_url":"https://arxiv.org/pdf/2407.16377","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Climate action","score":0.5,"id":"https://metadata.un.org/sdg/13"}],"awards":[{"id":"https://openalex.org/G1599646647","display_name":null,"funder_award_id":"PID2019","funder_id":"https://openalex.org/F4320338080","funder_display_name":"European Social Fund"},{"id":"https://openalex.org/G2262748287","display_name":null,"funder_award_id":"501100011033","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G3005324705","display_name":null,"funder_award_id":"501100011033","funder_id":"https://openalex.org/F4320321505","funder_display_name":"Generalitat de Catalunya"},{"id":"https://openalex.org/G3480869486","display_name":null,"funder_award_id":"13039","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G6218905885","display_name":null,"funder_award_id":"501100011033","funder_id":"https://openalex.org/F4320338080","funder_display_name":"European Social Fund"},{"id":"https://openalex.org/G6641934258","display_name":null,"funder_award_id":"PID2019-107255GB-C21","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G6833763678","display_name":null,"funder_award_id":"PID2019-107255GB","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G7084143925","display_name":null,"funder_award_id":"AEI/10","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G7266728691","display_name":null,"funder_award_id":"13039/501100011033","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G7425137858","display_name":null,"funder_award_id":"PID2019","funder_id":"https://openalex.org/F4320321505","funder_display_name":"Generalitat de Catalunya"},{"id":"https://openalex.org/G8684520763","display_name":null,"funder_award_id":"PID2019","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"}],"funders":[{"id":"https://openalex.org/F4320321505","display_name":"Generalitat de Catalunya","ror":"https://ror.org/01bg62x04"},{"id":"https://openalex.org/F4320335598","display_name":"Agencia Estatal de Investigaci\u00f3n","ror":null},{"id":"https://openalex.org/F4320338080","display_name":"European Social Fund","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402044817.pdf"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W560655873","https://openalex.org/W1990697197","https://openalex.org/W1998047408","https://openalex.org/W2023324599","https://openalex.org/W2040379684","https://openalex.org/W2076337359","https://openalex.org/W2142812297","https://openalex.org/W2767346922","https://openalex.org/W2944461282","https://openalex.org/W2990714382","https://openalex.org/W3021029666","https://openalex.org/W6669402789"],"related_works":["https://openalex.org/W3120961607","https://openalex.org/W4401568740","https://openalex.org/W2098207691","https://openalex.org/W3148568549","https://openalex.org/W1648516568","https://openalex.org/W361036515","https://openalex.org/W2269474412","https://openalex.org/W4386903460","https://openalex.org/W4211178602","https://openalex.org/W2433923775"],"abstract_inverted_index":{"Scaling":[0],"to":[1,12],"larger":[2],"systems,":[3],"with":[4,110,121,149],"current":[5,33,70],"levels":[6],"of":[7,17,21,64,118,127,133],"reliability,":[8],"requires":[9],"cost-effective":[10],"methods":[11],"mitigate":[13],"hardware":[14,22],"failures.":[15],"One":[16],"the":[18,32,40,46,62,81,86,91,116,122,128,137,157],"main":[19],"causes":[20],"failure":[23],"is":[24,75,153,164],"an":[25,65],"uncorrected":[26,52,66],"error":[27,53,67],"in":[28],"memory,":[29],"which":[30,114],"terminates":[31],"job":[34,92],"and":[35,68,80,89,152],"wastes":[36],"all":[37],"computation":[38],"since":[39],"last":[41],"checkpoint.":[42],"This":[43],"paper":[44],"presents":[45],"first":[47],"adaptive":[48],"method":[49,74,103,141],"for":[50],"triggering":[51],"mitigation.":[54],"It":[55],"uses":[56],"a":[57,97,111],"prediction":[58],"approach":[59],"that":[60],"considers":[61],"likelihood":[63],"its":[69],"potential":[71],"cost.":[72],"The":[73],"based":[76],"on":[77],"reinforcement":[78],"learning,":[79],"only":[82],"user-defined":[83],"parameters":[84],"are":[85],"mitigation":[87,98,119,151],"cost":[88,117],"whether":[90],"can":[93],"be":[94],"restarted":[95],"from":[96,124,136],"point.":[99],"We":[100],"evaluate":[101],"our":[102,140],"using":[104],"classical":[105],"machine":[106],"learning":[107],"metrics":[108],"together":[109],"cost-benefit":[112],"analysis,":[113],"compares":[115],"actions":[120],"benefits":[123],"mitigating":[125],"some":[126],"errors.":[129],"On":[130],"two":[131],"years":[132],"production":[134],"logs":[135],"MareNostrum":[138],"supercomputer,":[139],"reduces":[142],"lost":[143],"compute":[144],"time":[145],"by":[146],"54%":[147],"compared":[148],"no":[150],"just":[154],"6%":[155],"below":[156],"optimal":[158],"Oracle":[159],"method.":[160],"All":[161],"source":[162],"code":[163],"open":[165],"source.":[166]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-12T08:28:47.272897","created_date":"2024-08-31T00:00:00"}
