{"id":"https://openalex.org/W2046300712","doi":"https://doi.org/10.1145/2802658.2802665","title":"Detecting Silent Data Corruption for Extreme-Scale MPI Applications","display_name":"Detecting Silent Data Corruption for Extreme-Scale MPI Applications","publication_year":2015,"publication_date":"2015-09-01","ids":{"openalex":"https://openalex.org/W2046300712","doi":"https://doi.org/10.1145/2802658.2802665","mag":"2046300712"},"language":"en","primary_location":{"id":"doi:10.1145/2802658.2802665","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2802658.2802665","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2802665&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd European MPI Users' Group Meeting","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=2802665&type=pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013543252","display_name":"Leonardo Bautista-Gomez","orcid":"https://orcid.org/0000-0002-0814-5779"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Leonardo Bautista-Gomez","raw_affiliation_strings":["Argonne National Laboratory","argonne national laboratory"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory","institution_ids":["https://openalex.org/I1282105669"]},{"raw_affiliation_string":"argonne national laboratory","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046613458","display_name":"Franck Cappello","orcid":"https://orcid.org/0000-0002-7890-3934"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Franck Cappello","raw_affiliation_strings":["Argonne National Laboratory","argonne national laboratory"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory","institution_ids":["https://openalex.org/I1282105669"]},{"raw_affiliation_string":"argonne national laboratory","institution_ids":["https://openalex.org/I1282105669"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5013543252"],"corresponding_institution_ids":["https://openalex.org/I1282105669"],"apc_list":null,"apc_paid":null,"fwci":0.8029,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.76561582,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11005","display_name":"Radiation Effects in Electronics","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9991999864578247,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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":0.8384091258049011},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.7699611186981201},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5375515818595886},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5321798920631409},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.4725363552570343},{"id":"https://openalex.org/keywords/language-change","display_name":"Language change","score":0.4660533368587494},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.45714902877807617},{"id":"https://openalex.org/keywords/miniaturization","display_name":"Miniaturization","score":0.44037455320358276},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.39698830246925354},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.38202932476997375},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3318021297454834},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.21365132927894592},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1946067214012146},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15227878093719482},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10890308022499084},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.08583799004554749}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8384091258049011},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.7699611186981201},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5375515818595886},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5321798920631409},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.4725363552570343},{"id":"https://openalex.org/C2780027415","wikidata":"https://www.wikidata.org/wiki/Q524648","display_name":"Language change","level":2,"score":0.4660533368587494},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.45714902877807617},{"id":"https://openalex.org/C57528182","wikidata":"https://www.wikidata.org/wiki/Q1271842","display_name":"Miniaturization","level":2,"score":0.44037455320358276},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.39698830246925354},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.38202932476997375},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3318021297454834},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.21365132927894592},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1946067214012146},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15227878093719482},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10890308022499084},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.08583799004554749},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2802658.2802665","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2802658.2802665","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2802665&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd European MPI Users' Group Meeting","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/2802658.2802665","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2802658.2802665","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2802665&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd European MPI Users' Group Meeting","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.8199999928474426,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1015216249","display_name":null,"funder_award_id":"DE-AC02-06CH1135","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G1116540683","display_name":null,"funder_award_id":"DE-AC02-06CH11","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G1313983767","display_name":null,"funder_award_id":"DE-AC02","funder_id":"https://openalex.org/F4320338284","funder_display_name":"Argonne National Laboratory"},{"id":"https://openalex.org/G1751644051","display_name":null,"funder_award_id":"DE-AC02-06CH11357","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G1844751952","display_name":null,"funder_award_id":"DE-AC02_06CH11357","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G2777053550","display_name":null,"funder_award_id":"AC02-06CH11357","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G2784524989","display_name":null,"funder_award_id":"Contract DE-AC02-06CH11357","funder_id":"https://openalex.org/F4320338284","funder_display_name":"Argonne National Laboratory"},{"id":"https://openalex.org/G3000213308","display_name":null,"funder_award_id":"DE-AC02-06CH113","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G3075337988","display_name":null,"funder_award_id":"06CH11357","funder_id":"https://openalex.org/F4320338284","funder_display_name":"Argonne National Laboratory"},{"id":"https://openalex.org/G3801222974","display_name":null,"funder_award_id":"DE-AC02-06CH1135","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G4145457401","display_name":null,"funder_award_id":"DE-AC02-06CH113","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G498139845","display_name":null,"funder_award_id":"DE-AC02","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G5082505137","display_name":null,"funder_award_id":"RESCUE","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G5085543421","display_name":null,"funder_award_id":"AC02-06CH11357","funder_id":"https://openalex.org/F4320338284","funder_display_name":"Argonne National Laboratory"},{"id":"https://openalex.org/G6085113958","display_name":null,"funder_award_id":"E-AC02-06CH11357","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G650626725","display_name":null,"funder_award_id":"E-AC02-06CH11357","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G6558272803","display_name":null,"funder_award_id":"DE-AC02","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G6848031779","display_name":null,"funder_award_id":"06CH11357","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G6918803902","display_name":null,"funder_award_id":"06CH11357","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G7230044214","display_name":null,"funder_award_id":"DE-AC02-06CH1135","funder_id":"https://openalex.org/F4320338284","funder_display_name":"Argonne National Laboratory"},{"id":"https://openalex.org/G7954425250","display_name":null,"funder_award_id":"DE-AC02-06CH11357","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8143874970","display_name":null,"funder_award_id":"AC02-06CH11357","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G8314672274","display_name":null,"funder_award_id":"DE-AC02-06CH11","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8414908677","display_name":null,"funder_award_id":"DE-AC0","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G878601127","display_name":null,"funder_award_id":"DE-AC02-06CH11357","funder_id":"https://openalex.org/F4320337506","funder_display_name":"Advanced Scientific Computing Research"},{"id":"https://openalex.org/G969889393","display_name":null,"funder_award_id":"DE-AC02-","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320313934","display_name":"Institut national de recherche en informatique et en automatique (INRIA)","ror":"https://ror.org/02kvxyf05"},{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320337506","display_name":"Advanced Scientific Computing Research","ror":"https://ror.org/0012c7r22"},{"id":"https://openalex.org/F4320338284","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2046300712.pdf","grobid_xml":"https://content.openalex.org/works/W2046300712.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W1981432246","https://openalex.org/W1988070283","https://openalex.org/W1989331073","https://openalex.org/W1993660990","https://openalex.org/W2010958160","https://openalex.org/W2053659711","https://openalex.org/W2056109788","https://openalex.org/W2083613288","https://openalex.org/W2104967192","https://openalex.org/W2116097016","https://openalex.org/W2118033476","https://openalex.org/W2125169487","https://openalex.org/W2128511938","https://openalex.org/W2148071590","https://openalex.org/W2155934041","https://openalex.org/W2164529645","https://openalex.org/W4229701516"],"related_works":["https://openalex.org/W2348807422","https://openalex.org/W2361025757","https://openalex.org/W2050837474","https://openalex.org/W2384867379","https://openalex.org/W4241592276","https://openalex.org/W2926730772","https://openalex.org/W1532462972","https://openalex.org/W2394408226","https://openalex.org/W4389168214","https://openalex.org/W4366457933"],"abstract_inverted_index":{"Next-generation":[0],"supercomputers":[1],"are":[2,22,51,77,183],"expected":[3,41],"to":[4,26,42,54,106,139,146,191],"have":[5],"more":[6],"components":[7],"and,":[8],"at":[9,57,110],"the":[10,27,35,46,72,111,121,124,147,170,187],"same":[11],"time,":[12],"consume":[13],"several":[14],"times":[15],"less":[16,162,175],"energy":[17],"per":[18],"operation.":[19],"These":[20],"trends":[21],"pushing":[23],"supercomputer":[24],"construction":[25],"limits":[28],"of":[29,37,66,100,123,158,165],"miniaturization":[30],"and":[31,127,135,178],"energy-saving":[32],"strategies.":[33],"Consequently,":[34],"number":[36],"soft":[38,61],"errors":[39,68,76,109],"is":[40,128,174],"increase":[43],"dramatically":[44],"in":[45,52,104,142],"coming":[47],"years.":[48],"While":[49],"mechanisms":[50],"place":[53],"correct":[55],"or":[56],"least":[58],"detect":[59,107,155],"some":[60],"errors,":[62],"a":[63,94,143],"significant":[64],"percentage":[65],"those":[67],"pass":[69],"unnoticed":[70],"by":[71],"hardware.":[73],"Such":[74],"silent":[75,108],"extremely":[78],"damaging":[79],"because":[80],"they":[81],"can":[82,154],"make":[83],"applications":[84,103],"silently":[85],"produce":[86],"wrong":[87],"results.":[88],"In":[89],"this":[90,152],"work":[91,140],"we":[92,136],"propose":[93,131],"technique":[95,115],"that":[96,151,169,179],"leverages":[97],"certain":[98],"properties":[99],"high-performance":[101],"computing":[102],"order":[105],"application":[112,125],"level.":[113],"Our":[114],"detects":[116],"corruption":[117,133],"based":[118],"solely":[119],"on":[120],"behavior":[122],"datasets":[126],"application-agnostic.":[129],"We":[130,149,167],"multiple":[132],"detectors,":[134],"couple":[137],"them":[138],"together":[141],"fashion":[144],"transparent":[145],"user.":[148],"demonstrate":[150],"strategy":[153],"over":[156,192],"80%":[157],"corruptions,":[159],"while":[160],"incurring":[161],"than":[163,176],"1%":[164,177],"overhead.":[166],"show":[168],"false":[171],"positive":[172],"rate":[173],"when":[180],"multi-bit":[181],"corruptions":[182],"taken":[184],"into":[185],"account,":[186],"detection":[188],"recall":[189],"increases":[190],"95%.":[193]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}
