{"id":"https://openalex.org/W2141492514","doi":"https://doi.org/10.1109/pccc.2011.6108098","title":"Evaluation of process level redundant checkpointing/restart for HPC systems","display_name":"Evaluation of process level redundant checkpointing/restart for HPC systems","publication_year":2011,"publication_date":"2011-11-01","ids":{"openalex":"https://openalex.org/W2141492514","doi":"https://doi.org/10.1109/pccc.2011.6108098","mag":"2141492514"},"language":"en","primary_location":{"id":"doi:10.1109/pccc.2011.6108098","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pccc.2011.6108098","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"30th IEEE International Performance Computing and Communications Conference","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/A5063909341","display_name":"Ifeanyi P. Egwutuoha","orcid":null},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Ifeanyi P. Egwutuoha","raw_affiliation_strings":["Electrical & Information Engineering, University of Sydney, NSW, Australia","Electrical & Information Engineering, The University of Sydney, NSW 2006, Australia"],"affiliations":[{"raw_affiliation_string":"Electrical & Information Engineering, University of Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]},{"raw_affiliation_string":"Electrical & Information Engineering, The University of Sydney, NSW 2006, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062521849","display_name":"David Levy","orcid":"https://orcid.org/0000-0002-2490-8318"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"David Levy","raw_affiliation_strings":["Electrical & Information Engineering, University of Sydney, NSW, Australia","Electrical & Information Engineering, The University of Sydney, NSW 2006, Australia"],"affiliations":[{"raw_affiliation_string":"Electrical & Information Engineering, University of Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]},{"raw_affiliation_string":"Electrical & Information Engineering, The University of Sydney, NSW 2006, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052960440","display_name":"Bran Seli\u0107","orcid":"https://orcid.org/0000-0002-3703-8593"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Bran Selic","raw_affiliation_strings":["Electrical & Information Engineering, University of Sydney, NSW, Australia","Electrical & Information Engineering, The University of Sydney, NSW 2006, Australia"],"affiliations":[{"raw_affiliation_string":"Electrical & Information Engineering, University of Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]},{"raw_affiliation_string":"Electrical & Information Engineering, The University of Sydney, NSW 2006, Australia","institution_ids":["https://openalex.org/I129604602"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5063909341"],"corresponding_institution_ids":["https://openalex.org/I129604602"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19712863,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9976000189781189,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9905999898910522,"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":0.8500936031341553},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.7811050415039062},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.7090490460395813},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.6943099498748779},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.6816853880882263},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6694190502166748},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.6041824817657471},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5170953273773193},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4866641163825989},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3407559394836426},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.32696759700775146},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.27708083391189575}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8500936031341553},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.7811050415039062},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.7090490460395813},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.6943099498748779},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.6816853880882263},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6694190502166748},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.6041824817657471},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5170953273773193},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4866641163825989},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3407559394836426},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.32696759700775146},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.27708083391189575},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/pccc.2011.6108098","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pccc.2011.6108098","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"30th IEEE International Performance Computing and Communications Conference","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":2,"referenced_works":["https://openalex.org/W169659540","https://openalex.org/W2009994617"],"related_works":["https://openalex.org/W2073684863","https://openalex.org/W1599154403","https://openalex.org/W2023839151","https://openalex.org/W1774183074","https://openalex.org/W2057488824","https://openalex.org/W2334687145","https://openalex.org/W2178011914","https://openalex.org/W4235962491","https://openalex.org/W2061778832","https://openalex.org/W1513001507"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"High":[3],"Performance":[4],"Computing":[5],"(HPC)":[6],"systems":[7],"have":[8],"been":[9],"shifting":[10],"from":[11],"expensive":[12],"massively":[13],"parallel":[14],"custom":[15],"architectures":[16],"to":[17,23,34,52],"clusters":[18],"of":[19,26,40,65,73,89],"commodity":[20],"personal":[21],"computers":[22],"take":[24],"advantage":[25],"cost":[27],"and":[28],"performance":[29],"benefits.":[30],"To":[31],"avoid":[32],"having":[33],"restart":[35],"an":[36,58,66,90],"application":[37],"in":[38],"case":[39],"sudden":[41],"failure,":[42],"checkpointing/restart":[43,53,82],"fault":[44],"tolerance":[45],"mechanisms":[46],"are":[47],"commonly":[48],"implemented.":[49],"One":[50],"drawback":[51],"is":[54],"that":[55,79],"it":[56],"creates":[57],"overhead":[59],"which":[60],"increases":[61],"the":[62,80,86],"execution":[63],"time":[64],"application.":[67],"We":[68],"present":[69],"a":[70],"theoretical":[71],"analysis":[72],"our":[74],"technique.":[75],"The":[76],"results":[77],"show":[78],"PLR":[81],"can":[83],"significantly":[84],"improve":[85],"overall":[87],"reliability":[88],"HPC":[91],"system.":[92]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
