{"id":"https://openalex.org/W2405051574","doi":"https://doi.org/10.1145/2909428.2909433","title":"In-Situ Mitigation of Silent Data Corruption in PDE Solvers","display_name":"In-Situ Mitigation of Silent Data Corruption in PDE Solvers","publication_year":2016,"publication_date":"2016-05-27","ids":{"openalex":"https://openalex.org/W2405051574","doi":"https://doi.org/10.1145/2909428.2909433","mag":"2405051574"},"language":"en","primary_location":{"id":"doi:10.1145/2909428.2909433","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2909428.2909433","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Workshop on Fault-Tolerance for HPC at Extreme Scale","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/servlets/purl/1365121","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081500966","display_name":"Maher Salloum","orcid":"https://orcid.org/0000-0002-4257-7591"},"institutions":[{"id":"https://openalex.org/I192454743","display_name":"Sandia National Laboratories California","ror":"https://ror.org/058m7ey48","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1330989302","https://openalex.org/I192454743","https://openalex.org/I198811213","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Maher Salloum","raw_affiliation_strings":["Sandia National Laboratories, Livermore, CA, USA"],"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories, Livermore, CA, USA","institution_ids":["https://openalex.org/I192454743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102487921","display_name":"Jackson R. Mayo","orcid":null},"institutions":[{"id":"https://openalex.org/I192454743","display_name":"Sandia National Laboratories California","ror":"https://ror.org/058m7ey48","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1330989302","https://openalex.org/I192454743","https://openalex.org/I198811213","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jackson R. Mayo","raw_affiliation_strings":["Sandia National Laboratories, Livermore, CA, USA"],"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories, Livermore, CA, USA","institution_ids":["https://openalex.org/I192454743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107252170","display_name":"Robert C. Armstrong","orcid":null},"institutions":[{"id":"https://openalex.org/I192454743","display_name":"Sandia National Laboratories California","ror":"https://ror.org/058m7ey48","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1330989302","https://openalex.org/I192454743","https://openalex.org/I198811213","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert C. Armstrong","raw_affiliation_strings":["Sandia National Laboratories, Livermore, CA, USA"],"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories, Livermore, CA, USA","institution_ids":["https://openalex.org/I192454743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5081500966"],"corresponding_institution_ids":["https://openalex.org/I192454743"],"apc_list":null,"apc_paid":null,"fwci":0.64,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.66657564,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"43","last_page":"48"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9988999962806702,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.754895031452179},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6894146800041199},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5836966037750244},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.5778629779815674},{"id":"https://openalex.org/keywords/dram","display_name":"Dram","score":0.5614534020423889},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5449799299240112},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.49027565121650696},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.42021942138671875},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3555148243904114},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.354553759098053},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.32491278648376465},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.12976014614105225},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09273579716682434}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.754895031452179},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6894146800041199},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5836966037750244},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.5778629779815674},{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.5614534020423889},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5449799299240112},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.49027565121650696},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.42021942138671875},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3555148243904114},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.354553759098053},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32491278648376465},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.12976014614105225},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09273579716682434},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2909428.2909433","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2909428.2909433","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Workshop on Fault-Tolerance for HPC at Extreme Scale","raw_type":"proceedings-article"},{"id":"pmh:oai:osti.gov:1365121","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1365121","pdf_url":"https://www.osti.gov/servlets/purl/1365121","source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},{"id":"pmh:oai:osti.gov:1368825","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1368825","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:osti.gov:1365121","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1365121","pdf_url":"https://www.osti.gov/servlets/purl/1365121","source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.8199999928474426,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G3017597143","display_name":null,"funder_award_id":"DE-AC04-94AL85000","funder_id":"https://openalex.org/F4320338291","funder_display_name":"Sandia National Laboratories"},{"id":"https://openalex.org/G3521526233","display_name":null,"funder_award_id":"DE-AC04-94AL8","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G5827802491","display_name":null,"funder_award_id":"DE-AC04-94AL85000","funder_id":"https://openalex.org/F4320332369","funder_display_name":"National Nuclear Security Administration"},{"id":"https://openalex.org/G7318852158","display_name":null,"funder_award_id":"AC04-94AL85000","funder_id":"https://openalex.org/F4320338291","funder_display_name":"Sandia National Laboratories"},{"id":"https://openalex.org/G7768351324","display_name":null,"funder_award_id":"DE-AC04-94AL850","funder_id":"https://openalex.org/F4320332369","funder_display_name":"National Nuclear Security Administration"},{"id":"https://openalex.org/G7953487069","display_name":null,"funder_award_id":"DE-AC04-94AL8500","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/G8456466421","display_name":null,"funder_award_id":"AC04-94AL85000","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8564910944","display_name":null,"funder_award_id":"DE-AC04-94AL8500","funder_id":"https://openalex.org/F4320332369","funder_display_name":"National Nuclear Security Administration"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320332369","display_name":"National Nuclear Security Administration","ror":"https://ror.org/03sk1we31"},{"id":"https://openalex.org/F4320338291","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2405051574.pdf","grobid_xml":"https://content.openalex.org/works/W2405051574.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W1506342804","https://openalex.org/W1584278023","https://openalex.org/W1657039127","https://openalex.org/W1972490838","https://openalex.org/W1978082708","https://openalex.org/W1988425770","https://openalex.org/W2005440670","https://openalex.org/W2035448730","https://openalex.org/W2072072075","https://openalex.org/W2095954861","https://openalex.org/W2148039812","https://openalex.org/W2179059335","https://openalex.org/W2295827435","https://openalex.org/W2336044659","https://openalex.org/W2400044739","https://openalex.org/W2471470479","https://openalex.org/W2488945070","https://openalex.org/W2953326931","https://openalex.org/W4250725282","https://openalex.org/W6636790160"],"related_works":["https://openalex.org/W1604758548","https://openalex.org/W2804126825","https://openalex.org/W4367553810","https://openalex.org/W2104142636","https://openalex.org/W1549048322","https://openalex.org/W2015141752","https://openalex.org/W2731831065","https://openalex.org/W4283162424","https://openalex.org/W2271439649","https://openalex.org/W2011940952"],"abstract_inverted_index":{"We":[0,26],"present":[1],"algorithmic":[2],"techniques":[3],"for":[4,37,69],"parallel":[5],"PDE":[6],"solvers":[7],"that":[8,59,83,123],"leverage":[9],"numerical":[10],"smoothness":[11],"properties":[12],"of":[13,35,90,98,138],"physics":[14],"simulation":[15],"to":[16,62,79,142],"detect":[17],"and":[18,53,72,107],"correct":[19],"silent":[20,30,124],"data":[21,125,132],"corruption":[22,126],"within":[23],"local":[24],"computations.":[25],"initially":[27],"model":[28],"such":[29],"hardware":[31],"errors":[32],"(which":[33],"are":[34],"concern":[36],"extreme":[38],"scale)":[39],"via":[40],"injected":[41],"DRAM":[42],"bit":[43],"flips.":[44],"Our":[45],"mitigation":[46,86],"approach":[47,100],"generalizes":[48],"previously":[49],"developed":[50],"\"robust":[51],"stencils\"":[52],"uses":[54],"modified":[55],"linear":[56],"algebra":[57],"operations":[58],"spatially":[60],"interpolate":[61],"replace":[63],"large":[64],"outlier":[65],"values.":[66],"Prototype":[67],"implementations":[68],"1D":[70],"hyperbolic":[71],"3D":[73],"elliptic":[74],"solvers,":[75],"tested":[76],"on":[77],"up":[78],"2048":[80],"cores,":[81],"show":[82],"this":[84],"error":[85],"enables":[87],"tolerating":[88],"orders":[89],"magnitude":[91],"higher":[92],"bit-flip":[93],"rates.":[94],"The":[95],"runtime":[96],"overhead":[97],"the":[99,136],"generally":[101],"decreases":[102],"with":[103,131],"greater":[104],"solver":[105],"scale":[106],"complexity,":[108],"becoming":[109],"no":[110],"more":[111],"than":[112],"a":[113],"few":[114],"percent":[115],"in":[116,133],"some":[117],"cases.":[118],"A":[119],"key":[120],"advantage":[121],"is":[122],"can":[127],"be":[128],"handled":[129],"transparently":[130],"cache,":[134],"reducing":[135],"cost":[137],"false-positive":[139],"detections":[140],"compared":[141],"rollback":[143],"approaches.":[144]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-20T07:46:08.049788","created_date":"2025-10-10T00:00:00"}
