{"id":"https://openalex.org/W2902747167","doi":"https://doi.org/10.1631/fitee.1601450","title":"FTRP: a new fault tolerance framework using process replication and prefetching for high-performance computing","display_name":"FTRP: a new fault tolerance framework using process replication and prefetching for high-performance computing","publication_year":2018,"publication_date":"2018-10-01","ids":{"openalex":"https://openalex.org/W2902747167","doi":"https://doi.org/10.1631/fitee.1601450","mag":"2902747167"},"language":"en","primary_location":{"id":"doi:10.1631/fitee.1601450","is_oa":false,"landing_page_url":"https://doi.org/10.1631/fitee.1601450","pdf_url":null,"source":{"id":"https://openalex.org/S4210189857","display_name":"Frontiers of Information Technology & Electronic Engineering","issn_l":"2095-9184","issn":["2095-9184","2095-9230"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers of Information Technology & Electronic Engineering","raw_type":"journal-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/A5100727081","display_name":"Wei Hu","orcid":"https://orcid.org/0000-0002-8839-7748"},"institutions":[{"id":"https://openalex.org/I4210165734","display_name":"National Supercomputing Center of Tianjin","ror":"https://ror.org/05tngxm14","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210165734"]},{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wei Hu","raw_affiliation_strings":["College of Computer, National University of Defense Technology, Changsha, 410073, China","National Supercomputer Center in Tianjin, Tianjin, 300457, China"],"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha, 410073, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National Supercomputer Center in Tianjin, Tianjin, 300457, China","institution_ids":["https://openalex.org/I4210165734"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101657812","display_name":"Guangming Liu","orcid":"https://orcid.org/0000-0003-0379-3934"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]},{"id":"https://openalex.org/I4210165734","display_name":"National Supercomputing Center of Tianjin","ror":"https://ror.org/05tngxm14","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210165734"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guang-Ming Liu","raw_affiliation_strings":["College of Computer, National University of Defense Technology, Changsha, 410073, China","National Supercomputer Center in Tianjin, Tianjin, 300457, China"],"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha, 410073, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National Supercomputer Center in Tianjin, Tianjin, 300457, China","institution_ids":["https://openalex.org/I4210165734"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016311803","display_name":"Yanhuang Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan-Huang Jiang","raw_affiliation_strings":["College of Computer, National University of Defense Technology, Changsha, 410073, China"],"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha, 410073, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100727081"],"corresponding_institution_ids":["https://openalex.org/I170215575","https://openalex.org/I4210165734"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16592651,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"19","issue":"10","first_page":"1273","last_page":"1290"},"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/T12127","display_name":"Software System Performance and Reliability","score":0.9936000108718872,"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":0.9926000237464905,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/replication","display_name":"Replication (statistics)","score":0.8056919574737549},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7584176063537598},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.6452211737632751},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5827001929283142},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.505115807056427},{"id":"https://openalex.org/keywords/process-migration","display_name":"Process migration","score":0.4265231490135193},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4173538088798523},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2529967129230499},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.09721383452415466}],"concepts":[{"id":"https://openalex.org/C12590798","wikidata":"https://www.wikidata.org/wiki/Q3933199","display_name":"Replication (statistics)","level":2,"score":0.8056919574737549},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7584176063537598},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.6452211737632751},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5827001929283142},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.505115807056427},{"id":"https://openalex.org/C36351404","wikidata":"https://www.wikidata.org/wiki/Q7247295","display_name":"Process migration","level":3,"score":0.4265231490135193},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4173538088798523},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2529967129230499},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.09721383452415466},{"id":"https://openalex.org/C159047783","wikidata":"https://www.wikidata.org/wiki/Q7215","display_name":"Virology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1631/fitee.1601450","is_oa":false,"landing_page_url":"https://doi.org/10.1631/fitee.1601450","pdf_url":null,"source":{"id":"https://openalex.org/S4210189857","display_name":"Frontiers of Information Technology & Electronic Engineering","issn_l":"2095-9184","issn":["2095-9184","2095-9230"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers of Information Technology & Electronic Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Climate action","id":"https://metadata.un.org/sdg/13","score":0.5299999713897705}],"awards":[{"id":"https://openalex.org/G150812581","display_name":null,"funder_award_id":"61120106005","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7607406252","display_name":null,"funder_award_id":"61272141","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8142093687","display_name":null,"funder_award_id":"61303068","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W28511425","https://openalex.org/W63848143","https://openalex.org/W1530427892","https://openalex.org/W1537929875","https://openalex.org/W1728583482","https://openalex.org/W1976029653","https://openalex.org/W1984564341","https://openalex.org/W1987482957","https://openalex.org/W1988099502","https://openalex.org/W2003214215","https://openalex.org/W2010172047","https://openalex.org/W2015853171","https://openalex.org/W2016411419","https://openalex.org/W2033656974","https://openalex.org/W2042506452","https://openalex.org/W2045152180","https://openalex.org/W2053691501","https://openalex.org/W2063924830","https://openalex.org/W2066159013","https://openalex.org/W2072672002","https://openalex.org/W2074787299","https://openalex.org/W2088552220","https://openalex.org/W2091250014","https://openalex.org/W2095157729","https://openalex.org/W2096121981","https://openalex.org/W2097833816","https://openalex.org/W2100970777","https://openalex.org/W2116115793","https://openalex.org/W2121288477","https://openalex.org/W2122249806","https://openalex.org/W2125165932","https://openalex.org/W2133046454","https://openalex.org/W2136797898","https://openalex.org/W2137512117","https://openalex.org/W2146854584","https://openalex.org/W2155118768","https://openalex.org/W2158272436","https://openalex.org/W2158907675","https://openalex.org/W2163785249","https://openalex.org/W2164463086","https://openalex.org/W2167138189","https://openalex.org/W2208101261","https://openalex.org/W2296772319","https://openalex.org/W2677178705","https://openalex.org/W2791753912","https://openalex.org/W4246134203","https://openalex.org/W4249923483","https://openalex.org/W6638221552","https://openalex.org/W6658448701","https://openalex.org/W6678803342","https://openalex.org/W7033776944"],"related_works":["https://openalex.org/W2144438995","https://openalex.org/W1577886464","https://openalex.org/W2164896586","https://openalex.org/W2087385017","https://openalex.org/W1593559483","https://openalex.org/W2108334564","https://openalex.org/W2111125783","https://openalex.org/W2100367016","https://openalex.org/W2357064441","https://openalex.org/W2152632384"],"abstract_inverted_index":{"As":[0],"the":[1,7,11,48,70,79,112,119,123,138,146,162],"scale":[2],"of":[3,50,94,149],"supercomputers":[4,117],"rapidly":[5],"grows,":[6],"reliability":[8],"problem":[9],"dominates":[10],"system":[12],"availability.":[13],"Existing":[14],"fault":[15,38,65,95,126,167],"tolerance":[16,39,66,96,127,168],"mechanisms,":[17],"such":[18],"as":[19],"periodic":[20],"checkpointing":[21],"and":[22,44,52,61,103,183,189],"process":[23,42,129,132],"redundancy,":[24],"cannot":[25],"effectively":[26],"fix":[27],"this":[28,32],"problem.":[29],"To":[30],"address":[31],"issue,":[33],"we":[34,110],"present":[35],"a":[36,57,62,92],"new":[37,63,124],"framework":[40,164],"using":[41],"replication":[43,130],"prefetching":[45,133],"(FTRP),":[46],"combining":[47],"benefits":[49],"proactive":[51,64,125],"reactive":[53],"mechanisms.":[54],"FTRP":[55,163],"incorporates":[56],"novel":[58,75],"cost":[59,76],"model":[60],"mechanism":[67],"to":[68,86,107,172],"improve":[69],"application":[71,104,176],"execution":[72],"efficiency.":[73],"The":[74],"model,":[77,82],"called":[78],"\u2018work-most\u2019":[80],"(WM)":[81],"makes":[83],"runtime":[84],"decisions":[85],"adaptively":[87],"choose":[88],"an":[89],"action":[90],"from":[91],"set":[93],"mechanisms":[97,169],"based":[98,136],"on":[99,137],"failure":[100,113,139,158,180],"prediction":[101,181],"results":[102],"status.":[105],"Similar":[106],"program":[108],"locality,":[109,140],"observe":[111],"locality":[114],"phenomenon":[115],"in":[116,175],"for":[118,178,186],"first":[120],"time.":[121],"In":[122],"mechanism,":[128],"with":[131,156,170],"is":[134,184],"proposed":[135],"significantly":[141],"avoiding":[142],"losses":[143],"caused":[144],"by":[145],"failures":[147],"regardless":[148],"whether":[150],"they":[151],"have":[152],"been":[153],"predicted.":[154],"Simulations":[155],"real":[157],"traces":[159],"demonstrate":[160],"that":[161],"outperforms":[165],"existing":[166],"up":[171],"10%":[173],"improvement":[174],"efficiency":[177],"common":[179],"accuracy,":[182],"effective":[185],"petascale":[187],"systems":[188],"beyond.":[190]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}