{"id":"https://openalex.org/W2146924779","doi":"https://doi.org/10.1145/1504176.1504227","title":"A tunable holistic resiliency approach for high-performance computing systems","display_name":"A tunable holistic resiliency approach for high-performance computing systems","publication_year":2009,"publication_date":"2009-02-14","ids":{"openalex":"https://openalex.org/W2146924779","doi":"https://doi.org/10.1145/1504176.1504227","mag":"2146924779"},"language":"en","primary_location":{"id":"doi:10.1145/1504176.1504227","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1504176.1504227","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM SIGPLAN symposium on Principles and practice of parallel programming","raw_type":"proceedings-article"},"type":"article","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/A5109843869","display_name":"Stephen L. Scott","orcid":null},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephen L. Scott","raw_affiliation_strings":["Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019453159","display_name":"Christian Engelmann","orcid":"https://orcid.org/0000-0003-4365-6416"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christian Engelmann","raw_affiliation_strings":["Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091569195","display_name":"Geoffroy Vall\u00e9e","orcid":null},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Geoffroy R. Vall\u00e9e","raw_affiliation_strings":["Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065914106","display_name":"Thomas J. Naughton","orcid":"https://orcid.org/0000-0002-3546-2382"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas Naughton","raw_affiliation_strings":["Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038715601","display_name":"Anand Tikotekar","orcid":null},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anand Tikotekar","raw_affiliation_strings":["Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062363588","display_name":"George Ostrouchov","orcid":"https://orcid.org/0000-0002-2043-6026"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George Ostrouchov","raw_affiliation_strings":["Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110325179","display_name":"Chokchai Leangsuksun","orcid":null},"institutions":[{"id":"https://openalex.org/I919208787","display_name":"Louisiana Tech University","ror":"https://ror.org/04q9esz89","country_code":"US","type":"education","lineage":["https://openalex.org/I2799628689","https://openalex.org/I919208787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chokchai Leangsuksun","raw_affiliation_strings":["Louisiana Tech University, Ruston, LA, USA","(Louisiana Tech University, Ruston, LA, USA)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Louisiana Tech University, Ruston, LA, USA","institution_ids":["https://openalex.org/I919208787"]},{"raw_affiliation_string":"(Louisiana Tech University, Ruston, LA, USA)","institution_ids":["https://openalex.org/I919208787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029063905","display_name":"Nichamon Naksinehaboon","orcid":null},"institutions":[{"id":"https://openalex.org/I919208787","display_name":"Louisiana Tech University","ror":"https://ror.org/04q9esz89","country_code":"US","type":"education","lineage":["https://openalex.org/I2799628689","https://openalex.org/I919208787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nichamon Naksinehaboon","raw_affiliation_strings":["Louisiana Tech University, Ruston, LA, USA","(Louisiana Tech University, Ruston, LA, USA)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Louisiana Tech University, Ruston, LA, USA","institution_ids":["https://openalex.org/I919208787"]},{"raw_affiliation_string":"(Louisiana Tech University, Ruston, LA, USA)","institution_ids":["https://openalex.org/I919208787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114093464","display_name":"Raja Nassar","orcid":null},"institutions":[{"id":"https://openalex.org/I919208787","display_name":"Louisiana Tech University","ror":"https://ror.org/04q9esz89","country_code":"US","type":"education","lineage":["https://openalex.org/I2799628689","https://openalex.org/I919208787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Raja Nassar","raw_affiliation_strings":["Louisiana Tech University, Ruston, LA, USA","(Louisiana Tech University, Ruston, LA, USA)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Louisiana Tech University, Ruston, LA, USA","institution_ids":["https://openalex.org/I919208787"]},{"raw_affiliation_string":"(Louisiana Tech University, Ruston, LA, USA)","institution_ids":["https://openalex.org/I919208787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005550984","display_name":"Mihaela P\u0103un","orcid":"https://orcid.org/0000-0002-3342-9140"},"institutions":[{"id":"https://openalex.org/I919208787","display_name":"Louisiana Tech University","ror":"https://ror.org/04q9esz89","country_code":"US","type":"education","lineage":["https://openalex.org/I2799628689","https://openalex.org/I919208787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mihaela Paun","raw_affiliation_strings":["Louisiana Tech University, Ruston, LA, USA","(Louisiana Tech University, Ruston, LA, USA)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Louisiana Tech University, Ruston, LA, USA","institution_ids":["https://openalex.org/I919208787"]},{"raw_affiliation_string":"(Louisiana Tech University, Ruston, LA, USA)","institution_ids":["https://openalex.org/I919208787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031749427","display_name":"Frank Mueller","orcid":"https://orcid.org/0000-0002-0258-0294"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Frank Mueller","raw_affiliation_strings":["North Carolina State University, Raleigh, NC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North Carolina State University, Raleigh, NC, USA","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100407048","display_name":"Chao Wang","orcid":"https://orcid.org/0000-0002-8054-3472"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chao Wang","raw_affiliation_strings":["North Carolina State University, Raleigh, NC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North Carolina State University, Raleigh, NC, USA","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003059283","display_name":"Arun Babu Nagarajan","orcid":null},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arun B. Nagarajan","raw_affiliation_strings":["North Carolina State University, Raleigh, NC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North Carolina State University, Raleigh, NC, USA","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069911834","display_name":"Jyothish Varma","orcid":null},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jyothish Varma","raw_affiliation_strings":["North Carolina State University, Raleigh, NC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North Carolina State University, Raleigh, NC, USA","institution_ids":["https://openalex.org/I137902535"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":14,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.6586,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.95463338,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"305","last_page":"306"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9994999766349792,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.996399998664856,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9937000274658203,"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":0.7322763800621033},{"id":"https://openalex.org/keywords/resilience","display_name":"Resilience (materials science)","score":0.7098599076271057},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5743257403373718},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5589249730110168},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5579530000686646},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.5474947690963745},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5463464856147766},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5123614072799683},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.3711731433868408},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.35766851902008057},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.17188626527786255},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15964847803115845}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7322763800621033},{"id":"https://openalex.org/C2779585090","wikidata":"https://www.wikidata.org/wiki/Q3457762","display_name":"Resilience (materials science)","level":2,"score":0.7098599076271057},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5743257403373718},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5589249730110168},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5579530000686646},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.5474947690963745},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5463464856147766},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5123614072799683},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.3711731433868408},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.35766851902008057},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.17188626527786255},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15964847803115845},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1504176.1504227","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1504176.1504227","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM SIGPLAN symposium on Principles and practice of parallel programming","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":7,"referenced_works":["https://openalex.org/W2096611465","https://openalex.org/W2107559915","https://openalex.org/W2123646449","https://openalex.org/W2135895123","https://openalex.org/W2146306455","https://openalex.org/W2161551433","https://openalex.org/W2767510344"],"related_works":["https://openalex.org/W2384867379","https://openalex.org/W4400094300","https://openalex.org/W2329539859","https://openalex.org/W2227905990","https://openalex.org/W2765823764","https://openalex.org/W3214280620","https://openalex.org/W3191490922","https://openalex.org/W2794038527","https://openalex.org/W2327638088","https://openalex.org/W2151092287"],"abstract_inverted_index":{"In":[0],"order":[1],"to":[2],"address":[3],"anticipated":[4],"high":[5],"failure":[6,51],"rates,":[7],"resiliency":[8],"characteristics":[9],"have":[10],"become":[11],"an":[12],"urgent":[13],"priority":[14],"for":[15,35,61],"next-generation":[16],"extreme-scale":[17],"high-performance":[18],"computing":[19],"(HPC)":[20],"systems.":[21],"This":[22,67],"poster":[23,68],"describes":[24],"our":[25,70],"past":[26],"and":[27,45,49,55,58,72],"ongoing":[28],"efforts":[29],"in":[30],"novel":[31],"fault":[32,41,83],"resilience":[33,42,84],"technologies":[34,76],"HPC.":[36],"Presented":[37],"work":[38,71],"includes":[39],"proactive":[40],"techniques,":[43],"system":[44],"application":[46],"reliability":[47],"models":[48,60],"analyses,":[50],"prediction,":[52],"transparent":[53],"process-":[54],"virtual-machine-level":[56],"migration,":[57],"trade-off":[59],"combining":[62],"preemptive":[63],"migration":[64],"with":[65,79],"checkpoint/restart.":[66],"summarizes":[69],"puts":[73],"all":[74],"individual":[75],"into":[77],"context":[78],"a":[80],"proposed":[81],"holistic":[82],"framework.":[85]},"counts_by_year":[{"year":2015,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
