{"id":"https://openalex.org/W2003437216","doi":"https://doi.org/10.1145/2491661.2481432","title":"Evaluating the feasibility of using memory content similarity to improve system resilience","display_name":"Evaluating the feasibility of using memory content similarity to improve system resilience","publication_year":2013,"publication_date":"2013-06-10","ids":{"openalex":"https://openalex.org/W2003437216","doi":"https://doi.org/10.1145/2491661.2481432","mag":"2003437216"},"language":"en","primary_location":{"id":"doi:10.1145/2491661.2481432","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2491661.2481432","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Workshop on Runtime and Operating Systems for Supercomputers","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/A5018865548","display_name":"Scott Levy","orcid":"https://orcid.org/0000-0002-2232-3201"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Scott Levy","raw_affiliation_strings":["University of New Mexico","University of New Mexico;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New Mexico","institution_ids":[]},{"raw_affiliation_string":"University of New Mexico;","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052769561","display_name":"Patrick G. Bridges","orcid":"https://orcid.org/0000-0003-4801-0390"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Patrick G. Bridges","raw_affiliation_strings":["University of New Mexico","University of New Mexico;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New Mexico","institution_ids":[]},{"raw_affiliation_string":"University of New Mexico;","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020783484","display_name":"Kurt Brian Ferreira","orcid":"https://orcid.org/0000-0001-5607-5691"},"institutions":[{"id":"https://openalex.org/I4210104735","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kurt B. Ferreira","raw_affiliation_strings":["Sandia National Laboratories"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories","institution_ids":["https://openalex.org/I4210104735"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103072309","display_name":"Aidan P. Thompson","orcid":"https://orcid.org/0000-0002-0324-9114"},"institutions":[{"id":"https://openalex.org/I4210104735","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aidan P. Thompson","raw_affiliation_strings":["Sandia National Laboratories"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories","institution_ids":["https://openalex.org/I4210104735"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081085090","display_name":"Christian Robert Trott","orcid":"https://orcid.org/0000-0003-0661-5594"},"institutions":[{"id":"https://openalex.org/I4210104735","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christian Trott","raw_affiliation_strings":["Sandia National Laboratories"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories","institution_ids":["https://openalex.org/I4210104735"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9997000098228455,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12127","display_name":"Software System Performance and Reliability","score":0.9968000054359436,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7767671346664429},{"id":"https://openalex.org/keywords/resilience","display_name":"Resilience (materials science)","score":0.7500721216201782},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6019752025604248},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.5663185715675354},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5028359293937683},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4895354211330414},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.42070114612579346},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1908179521560669},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09242945909500122}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7767671346664429},{"id":"https://openalex.org/C2779585090","wikidata":"https://www.wikidata.org/wiki/Q3457762","display_name":"Resilience (materials science)","level":2,"score":0.7500721216201782},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6019752025604248},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.5663185715675354},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5028359293937683},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4895354211330414},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.42070114612579346},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1908179521560669},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09242945909500122},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2491661.2481432","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2491661.2481432","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Workshop on Runtime and Operating Systems for Supercomputers","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W39601649","https://openalex.org/W200233886","https://openalex.org/W1558516248","https://openalex.org/W1568101540","https://openalex.org/W2006816934","https://openalex.org/W2013592197","https://openalex.org/W2020115430","https://openalex.org/W2039789965","https://openalex.org/W2046124011","https://openalex.org/W2047484077","https://openalex.org/W2052116012","https://openalex.org/W2063924830","https://openalex.org/W2083415705","https://openalex.org/W2095954861","https://openalex.org/W2097946733","https://openalex.org/W2100970777","https://openalex.org/W2119018856","https://openalex.org/W2120591095","https://openalex.org/W2121542813","https://openalex.org/W2126658609","https://openalex.org/W2144071847","https://openalex.org/W2154509298","https://openalex.org/W2160424485","https://openalex.org/W2160779498","https://openalex.org/W2297093017"],"related_works":["https://openalex.org/W2284759612","https://openalex.org/W2375480909","https://openalex.org/W4402320089","https://openalex.org/W2353314428","https://openalex.org/W2012019886","https://openalex.org/W2166090428","https://openalex.org/W2381021552","https://openalex.org/W2354749003","https://openalex.org/W2892165056","https://openalex.org/W2098964748"],"abstract_inverted_index":{"Building":[0],"the":[1,17,25,32,64,76,92,95],"next-generation":[2],"of":[3,19,31,36,78,94],"extreme-scale":[4],"distributed":[5],"systems":[6,23,40],"will":[7],"require":[8],"overcoming":[9],"several":[10],"challenges":[11],"related":[12],"to":[13,58,71],"system":[14,60,113],"resilience.":[15],"As":[16],"number":[18],"processors":[20],"in":[21,38,100,115],"these":[22,101],"grows,":[24],"failure":[26,37],"rate":[27,65],"increases":[28],"proportionally.":[29],"One":[30],"most":[33],"common":[34],"sources":[35],"large-scale":[39,116],"is":[41],"memory":[42,55,68,83],"errors.":[43],"In":[44],"this":[45,79],"paper,":[46],"we":[47,98,103],"propose":[48],"a":[49],"novel":[50],"run-time":[51],"for":[52,111],"transparently":[53],"exploiting":[54],"content":[56],"similarity":[57,96],"improve":[59],"resilience":[61,114],"by":[62,81],"reducing":[63],"at":[66],"which":[67],"errors":[69],"lead":[70],"node":[72],"failure.":[73],"We":[74],"evaluate":[75],"feasibility":[77],"approach":[80,108],"examining":[82],"snapshots":[84],"collected":[85],"from":[86],"eight":[87],"HPC":[88],"applications.":[89],"Based":[90],"on":[91],"characteristics":[93],"that":[97,105],"uncover":[99],"applications,":[102],"conclude":[104],"our":[106],"proposed":[107],"shows":[109],"promise":[110],"addressing":[112],"systems.":[117]},"counts_by_year":[{"year":2016,"cited_by_count":4},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
