{"id":"https://openalex.org/W2005196107","doi":"https://doi.org/10.1145/2676870.2676894","title":"Fault Tolerance for OpenSHMEM","display_name":"Fault Tolerance for OpenSHMEM","publication_year":2014,"publication_date":"2014-10-06","ids":{"openalex":"https://openalex.org/W2005196107","doi":"https://doi.org/10.1145/2676870.2676894","mag":"2005196107"},"language":"en","primary_location":{"id":"doi:10.1145/2676870.2676894","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2676870.2676894","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th International Conference on Partitioned Global Address Space Programming Models","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/A5112704656","display_name":"Pengfei Hao","orcid":null},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pengfei Hao","raw_affiliation_strings":["University of Houston"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Houston","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071927802","display_name":"Pavel Shamis","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":"Pavel Shamis","raw_affiliation_strings":["Oak Ridge National Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067995943","display_name":"Manjunath Gorentla Venkata","orcid":"https://orcid.org/0000-0002-5282-1682"},"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":"Manjunath Gorentla Venkata","raw_affiliation_strings":["Oak Ridge National Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040363327","display_name":"Swaroop Pophale","orcid":"https://orcid.org/0000-0001-8544-6367"},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Swaroop Pophale","raw_affiliation_strings":["University of Houston"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Houston","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015354365","display_name":"Aaron Welch","orcid":"https://orcid.org/0000-0002-8988-3027"},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aaron Welch","raw_affiliation_strings":["University of Houston"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Houston","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043234330","display_name":"Stephen Poole","orcid":"https://orcid.org/0000-0002-4531-7453"},"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 Poole","raw_affiliation_strings":["Oak Ridge National Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053733660","display_name":"Barbara Chapman","orcid":"https://orcid.org/0000-0001-8449-8579"},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Barbara Chapman","raw_affiliation_strings":["University of Houston"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Houston","institution_ids":["https://openalex.org/I44461941"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"3"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9973999857902527,"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":0.9973000288009644,"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/fault-tolerance","display_name":"Fault tolerance","score":0.816918134689331},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7667359113693237},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7267971038818359},{"id":"https://openalex.org/keywords/software-fault-tolerance","display_name":"Software fault tolerance","score":0.6598901152610779},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.5619732141494751},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5138259530067444},{"id":"https://openalex.org/keywords/partitioned-global-address-space","display_name":"Partitioned global address space","score":0.4963417649269104},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4767818748950958},{"id":"https://openalex.org/keywords/fault-model","display_name":"Fault model","score":0.4320718050003052},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.41233256459236145},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.35095059871673584},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.34295180439949036},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.32008281350135803},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.28689175844192505},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13535961508750916},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10534635186195374}],"concepts":[{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.816918134689331},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7667359113693237},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7267971038818359},{"id":"https://openalex.org/C50712370","wikidata":"https://www.wikidata.org/wiki/Q4269346","display_name":"Software fault tolerance","level":3,"score":0.6598901152610779},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.5619732141494751},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5138259530067444},{"id":"https://openalex.org/C60832428","wikidata":"https://www.wikidata.org/wiki/Q945818","display_name":"Partitioned global address space","level":3,"score":0.4963417649269104},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4767818748950958},{"id":"https://openalex.org/C167391956","wikidata":"https://www.wikidata.org/wiki/Q1401211","display_name":"Fault model","level":3,"score":0.4320718050003052},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.41233256459236145},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.35095059871673584},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.34295180439949036},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.32008281350135803},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.28689175844192505},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13535961508750916},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10534635186195374},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C134146338","wikidata":"https://www.wikidata.org/wiki/Q1815901","display_name":"Electronic circuit","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2676870.2676894","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2676870.2676894","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th International Conference on Partitioned Global Address Space Programming Models","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320338287","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W170768260","https://openalex.org/W1965092590","https://openalex.org/W2105227455","https://openalex.org/W2156935376","https://openalex.org/W2157664008","https://openalex.org/W2730779250"],"related_works":["https://openalex.org/W2166185777","https://openalex.org/W2494227547","https://openalex.org/W2913497647","https://openalex.org/W2913919777","https://openalex.org/W2072270916","https://openalex.org/W2043059266","https://openalex.org/W2018988446","https://openalex.org/W2171525159","https://openalex.org/W2236289510","https://openalex.org/W3150557277"],"abstract_inverted_index":{"On":[0],"today's":[1],"supercomputing":[2],"systems,":[3,25,51],"faults":[4],"are":[5,35],"becoming":[6],"a":[7,40,76,82,85,91,110,116],"norm":[8],"rather":[9],"than":[10],"an":[11],"exception.":[12],"Given":[13],"the":[14,66,104,127],"complexity":[15],"required":[16],"for":[17,93,113],"achieving":[18],"expected":[19,29,36],"scalability":[20],"and":[21,58,73,121],"performance":[22],"on":[23,49],"future":[24],"this":[26,97,100],"situation":[27],"is":[28],"to":[30,37,60,63],"become":[31,90],"worse.":[32],"The":[33],"systems":[34],"function":[38],"in":[39,99],"nearly":[41],"constant":[42],"presence":[43],"of":[44,69,78,84,106],"faults.":[45,64],"To":[46],"be":[47,61],"productive":[48],"these":[50],"programming":[52,71],"models":[53],"will":[54],"require":[55],"both":[56],"hardware":[57],"software":[59,80],"resilient":[62],"With":[65],"growing":[67],"importance":[68],"PGAS":[70],"model":[72,88],"OpenSHMEM,":[74,114],"as":[75,109],"part":[77],"HPC":[79],"stack,":[81],"lack":[83],"fault":[86],"tolerance":[87],"may":[89],"liability":[92],"its":[94],"users.":[95],"Towards":[96],"end,":[98],"paper,":[101],"we":[102],"discuss":[103,122],"viability":[105],"using":[107],"checkpoint/restart":[108,118],"fault-tolerance":[111,119],"method":[112],"propose":[115],"selective":[117],"model,":[120],"challenges":[123],"associated":[124],"with":[125],"implementing":[126],"proposed":[128],"model.":[129]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
