{"id":"https://openalex.org/W2158272436","doi":"https://doi.org/10.1109/ipdps.2004.1302982","title":"On the feasibility of incremental checkpointing for scienti .c computing","display_name":"On the feasibility of incremental checkpointing for scienti .c computing","publication_year":2004,"publication_date":"2004-06-10","ids":{"openalex":"https://openalex.org/W2158272436","doi":"https://doi.org/10.1109/ipdps.2004.1302982","mag":"2158272436"},"language":"en","primary_location":{"id":"doi:10.1109/ipdps.2004.1302982","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2004.1302982","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"18th International Parallel and Distributed Processing Symposium, 2004. Proceedings.","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/A5008026936","display_name":"Jos\u00e9 Carlos Sancho","orcid":"https://orcid.org/0000-0002-6917-9155"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"J.C. Sancho","raw_affiliation_strings":["Computer and Computational Sciences (CCS), Performance and Architecture Laboratory (PAL), NM, USA"],"affiliations":[{"raw_affiliation_string":"Computer and Computational Sciences (CCS), Performance and Architecture Laboratory (PAL), NM, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066195314","display_name":"Fabrizio Petrini","orcid":"https://orcid.org/0000-0002-4977-7107"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"F. Petrini","raw_affiliation_strings":["Computer and Computational Sciences (CCS), Performance and Architecture Laboratory (PAL), NM, USA"],"affiliations":[{"raw_affiliation_string":"Computer and Computational Sciences (CCS), Performance and Architecture Laboratory (PAL), NM, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111377647","display_name":"Greg Johnson","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"G. Johnson","raw_affiliation_strings":["Computer and Computational Sciences (CCS), Performance and Architecture Laboratory (PAL), NM, USA"],"affiliations":[{"raw_affiliation_string":"Computer and Computational Sciences (CCS), Performance and Architecture Laboratory (PAL), NM, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101542945","display_name":"Jos\u00e9 Fern\u00e1ndez","orcid":"https://orcid.org/0000-0002-9774-9055"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"J. Fernandez","raw_affiliation_strings":["Computer and Computational Sciences (CCS), Performance and Architecture Laboratory (PAL), NM, USA"],"affiliations":[{"raw_affiliation_string":"Computer and Computational Sciences (CCS), Performance and Architecture Laboratory (PAL), NM, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054975473","display_name":"Eitan Frachtenberg","orcid":"https://orcid.org/0000-0002-3709-1829"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"E. Frachtenberg","raw_affiliation_strings":["Computer and Computational Sciences (CCS), Performance and Architecture Laboratory (PAL), NM, USA"],"affiliations":[{"raw_affiliation_string":"Computer and Computational Sciences (CCS), Performance and Architecture Laboratory (PAL), NM, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5008026936"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.2444,"has_fulltext":false,"cited_by_count":62,"citation_normalized_percentile":{"value":0.93158452,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"58","last_page":"67"},"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":0.9994000196456909,"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":0.9983000159263611,"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/computer-science","display_name":"Computer science","score":0.8363608121871948},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.790024995803833},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.75632643699646},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.7086583375930786},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5794519782066345},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.5690520405769348},{"id":"https://openalex.org/keywords/transparency","display_name":"Transparency (behavior)","score":0.5168285965919495},{"id":"https://openalex.org/keywords/computer-cluster","display_name":"Computer cluster","score":0.4991621971130371},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.49424079060554504},{"id":"https://openalex.org/keywords/autonomic-computing","display_name":"Autonomic computing","score":0.4777457118034363},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3961970806121826},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2588670253753662},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.2369873821735382},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.1775539219379425},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.10808336734771729}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8363608121871948},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.790024995803833},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.75632643699646},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.7086583375930786},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5794519782066345},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.5690520405769348},{"id":"https://openalex.org/C2780233690","wikidata":"https://www.wikidata.org/wiki/Q535347","display_name":"Transparency (behavior)","level":2,"score":0.5168285965919495},{"id":"https://openalex.org/C29140674","wikidata":"https://www.wikidata.org/wiki/Q206637","display_name":"Computer cluster","level":2,"score":0.4991621971130371},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.49424079060554504},{"id":"https://openalex.org/C558632462","wikidata":"https://www.wikidata.org/wiki/Q788172","display_name":"Autonomic computing","level":3,"score":0.4777457118034363},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3961970806121826},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2588670253753662},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.2369873821735382},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.1775539219379425},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.10808336734771729},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipdps.2004.1302982","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2004.1302982","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"18th International Parallel and Distributed Processing Symposium, 2004. Proceedings.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320338304","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W169659540","https://openalex.org/W307918303","https://openalex.org/W1537929875","https://openalex.org/W1538291993","https://openalex.org/W1555915743","https://openalex.org/W1571582830","https://openalex.org/W1971952282","https://openalex.org/W1987608073","https://openalex.org/W2043522772","https://openalex.org/W2047117506","https://openalex.org/W2081413727","https://openalex.org/W2100970777","https://openalex.org/W2109739361","https://openalex.org/W2114035455","https://openalex.org/W2126071114","https://openalex.org/W2127416886","https://openalex.org/W2129399119","https://openalex.org/W2151080836","https://openalex.org/W2156204788","https://openalex.org/W2162351670","https://openalex.org/W2168475458","https://openalex.org/W2169167780","https://openalex.org/W2181301067","https://openalex.org/W2296772319","https://openalex.org/W2533204039","https://openalex.org/W3022806736","https://openalex.org/W4246310005","https://openalex.org/W4247060036","https://openalex.org/W4250644124","https://openalex.org/W6643050054","https://openalex.org/W6676932180","https://openalex.org/W6682033297","https://openalex.org/W6695275532"],"related_works":["https://openalex.org/W2384867379","https://openalex.org/W2525033434","https://openalex.org/W4280533024","https://openalex.org/W4300992253","https://openalex.org/W1942762218","https://openalex.org/W1985270856","https://openalex.org/W1833720599","https://openalex.org/W3101274117","https://openalex.org/W1966875563","https://openalex.org/W2386343905"],"abstract_inverted_index":{"Summary":[0],"form":[1],"only":[2],"given.":[3],"In":[4,19],"the":[5,53,64],"near":[6],"future":[7],"large-scale":[8],"parallel":[9],"computers":[10],"will":[11,28],"feature":[12],"hundreds":[13],"of":[14,16,67,82],"thousands":[15],"processing":[17],"nodes.":[18],"such":[20],"systems,":[21],"fault":[22,45],"tolerance":[23],"is":[24,110],"critical":[25],"as":[26,40],"failures":[27],"occur":[29],"very":[30],"often.":[31],"Checkpointing":[32],"and":[33,56,75,106],"rollback":[34],"recovery":[35],"has":[36],"been":[37],"extensively":[38],"studied":[39],"an":[41,79],"attempt":[42],"to":[43,62,73],"provide":[44,52,78],"tolerance.":[46],"However,":[47],"current":[48,114],"implementations":[49],"do":[50],"not":[51],"total":[54],"transparency":[55],"full":[57],"flexibility":[58],"that":[59,102],"are":[60],"necessary":[61],"support":[63],"new":[65],"paradigm":[66],"autonomic":[68],"computing":[69],"-":[70],"systems":[71],"able":[72],"self-heal":[74],"self-repair.":[76],"We":[77],"in-depth":[80],"evaluation":[81],"incremental":[83,108],"checkpointing":[84,109],"for":[85],"scientific":[86,99],"computing.":[87],"The":[88],"experimental":[89],"results,":[90],"obtained":[91],"on":[92],"a":[93],"state-of-the":[94],"art":[95],"cluster":[96],"running":[97],"several":[98],"applications,":[100],"show":[101],"efficient,":[103],"scalable,":[104],"automatic":[105],"user-transparent":[107],"within":[111],"reach":[112],"with":[113],"technology.":[115]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":10},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
