{"id":"https://openalex.org/W2026006942","doi":"https://doi.org/10.1145/2749246.2749260","title":"Exploring Failure Recovery for Stencil-based Applications at Extreme Scales","display_name":"Exploring Failure Recovery for Stencil-based Applications at Extreme Scales","publication_year":2015,"publication_date":"2015-06-08","ids":{"openalex":"https://openalex.org/W2026006942","doi":"https://doi.org/10.1145/2749246.2749260","mag":"2026006942"},"language":"en","primary_location":{"id":"doi:10.1145/2749246.2749260","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2749246.2749260","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/biblio/1246303","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027432313","display_name":"Marc Gamell","orcid":null},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marc Gamell","raw_affiliation_strings":["Rutgers University, Piscataway, NJ, USA","Rutgers University , Piscataway, NJ , USA ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers University, Piscataway, NJ, USA","institution_ids":["https://openalex.org/I102322142"]},{"raw_affiliation_string":"Rutgers University , Piscataway, NJ , USA ,","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019745966","display_name":"Keita Teranishi","orcid":"https://orcid.org/0000-0001-6647-2690"},"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":"Keita Teranishi","raw_affiliation_strings":["Sandia National Laboratories, Livermore, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories, Livermore, CA, USA","institution_ids":["https://openalex.org/I192454743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074276326","display_name":"Michael A. Heroux","orcid":"https://orcid.org/0000-0002-5893-0273"},"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":"Michael A. Heroux","raw_affiliation_strings":["Sandia National Laboratories, Albuquerque, NM, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories, Albuquerque, NM, USA","institution_ids":["https://openalex.org/I4210104735"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103336291","display_name":"Jackson 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 Mayo","raw_affiliation_strings":["Sandia National Laboratories, Livermore, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories, Livermore, CA, USA","institution_ids":["https://openalex.org/I192454743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012593852","display_name":"Hemanth Kolla","orcid":"https://orcid.org/0000-0003-4969-5870"},"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":"Hemanth Kolla","raw_affiliation_strings":["Sandia National Laboratories, Livermore, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories, Livermore, CA, USA","institution_ids":["https://openalex.org/I192454743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103362304","display_name":"Jacqueline Chen","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":"Jacqueline Chen","raw_affiliation_strings":["Sandia National Laboratories, Livermore, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories, Livermore, CA, USA","institution_ids":["https://openalex.org/I192454743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060153432","display_name":"Manish Parashar","orcid":"https://orcid.org/0000-0003-0983-7408"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manish Parashar","raw_affiliation_strings":["Rutgers University, Piscataway, NJ, USA","Rutgers University , Piscataway, NJ , USA ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers University, Piscataway, NJ, USA","institution_ids":["https://openalex.org/I102322142"]},{"raw_affiliation_string":"Rutgers University , Piscataway, NJ , USA ,","institution_ids":["https://openalex.org/I102322142"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"279","last_page":"282"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9952999949455261,"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/T11005","display_name":"Radiation Effects in Electronics","score":0.9944999814033508,"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/stencil","display_name":"Stencil","score":0.8915746212005615},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8339922428131104},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.7506116628646851},{"id":"https://openalex.org/keywords/resilience","display_name":"Resilience (materials science)","score":0.7470065355300903},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5567184686660767},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5416849255561829},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.35284480452537537},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.14980652928352356},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.13358652591705322},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.09586650133132935}],"concepts":[{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.8915746212005615},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8339922428131104},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.7506116628646851},{"id":"https://openalex.org/C2779585090","wikidata":"https://www.wikidata.org/wiki/Q3457762","display_name":"Resilience (materials science)","level":2,"score":0.7470065355300903},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5567184686660767},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5416849255561829},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.35284480452537537},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.14980652928352356},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.13358652591705322},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.09586650133132935},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2749246.2749260","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2749246.2749260","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"},{"id":"pmh:oai:osti.gov:1246303","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1246303","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:1246303","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1246303","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},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W141129880","https://openalex.org/W1978347128","https://openalex.org/W1981432246","https://openalex.org/W1984564341","https://openalex.org/W1986905947","https://openalex.org/W1993660990","https://openalex.org/W2014332384","https://openalex.org/W2017060126","https://openalex.org/W2018060613","https://openalex.org/W2021234574","https://openalex.org/W2031260715","https://openalex.org/W2105524676","https://openalex.org/W2116115793","https://openalex.org/W2167259479","https://openalex.org/W6646916258"],"related_works":["https://openalex.org/W3105129168","https://openalex.org/W2804920739","https://openalex.org/W4316371992","https://openalex.org/W2186216222","https://openalex.org/W2392765154","https://openalex.org/W2008005532","https://openalex.org/W1971603802","https://openalex.org/W2564509292","https://openalex.org/W1795008753","https://openalex.org/W4255540064"],"abstract_inverted_index":{"Application":[0],"resilience":[1],"is":[2],"a":[3,28],"key":[4],"challenge":[5],"that":[6,21],"must":[7],"be":[8,76,110],"addressed":[9],"in":[10,27],"order":[11],"to":[12,44,83,88,112,121],"realize":[13],"the":[14,38,45,51,57,85,93,115,118],"exascale":[15],"vision.":[16],"Previous":[17],"work":[18],"has":[19],"shown":[20],"online":[22],"recovery,":[23],"even":[24],"when":[25,42],"done":[26],"global":[29],"manner":[30],"(i.e.,":[31],"involving":[32],"all":[33],"processes),":[34],"can":[35,75,109],"dramatically":[36],"reduce":[37,84,114],"overhead":[39],"of":[40,49,81,95],"failures":[41,108],"compared":[43],"more":[46],"traditional":[47],"approach":[48],"terminating":[50],"job":[52],"and":[53,70,102],"restarting":[54],"it":[55],"from":[56],"last":[58],"stored":[59],"checkpoint.":[60],"In":[61],"this":[62],"paper":[63],"we":[64,91,103],"suggest":[65],"going":[66],"one":[67],"step":[68],"further,":[69],"explore":[71],"how":[72,105],"local":[73,96],"recovery":[74,97],"used":[77],"for":[78,98],"certain":[79],"classes":[80],"applications":[82,101],"overheads":[86],"due":[87],"failures.":[89],"Specifically":[90],"study":[92],"feasibility":[94],"stencil-based":[99],"parallel":[100],"show":[104],"multiple":[106],"independent":[107],"masked":[111],"effectively":[113],"impact":[116],"on":[117],"total":[119],"time":[120],"solution.":[122]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
