{"id":"https://openalex.org/W1981432246","doi":"https://doi.org/10.1145/2063384.2063427","title":"FTI","display_name":"FTI","publication_year":2011,"publication_date":"2011-11-08","ids":{"openalex":"https://openalex.org/W1981432246","doi":"https://doi.org/10.1145/2063384.2063427","mag":"1981432246"},"language":"en","primary_location":{"id":"doi:10.1145/2063384.2063427","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2063384.2063427","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis","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/A5013543252","display_name":"Leonardo Bautista-Gomez","orcid":"https://orcid.org/0000-0002-0814-5779"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR","JP"],"is_corresponding":false,"raw_author_name":"Leonardo Bautista-Gomez","raw_affiliation_strings":["Tokyo Institute of Technology, INRIA","Tokyo Institute of Technology, INRIA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, INRIA","institution_ids":["https://openalex.org/I114531698","https://openalex.org/I1326498283"]},{"raw_affiliation_string":"Tokyo Institute of Technology, INRIA#TAB#","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026810720","display_name":"Seiji Tsuboi","orcid":"https://orcid.org/0000-0003-3422-6879"},"institutions":[{"id":"https://openalex.org/I1315852903","display_name":"Japan Agency for Marine-Earth Science and Technology","ror":"https://ror.org/059qg2m13","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1315852903"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Seiji Tsuboi","raw_affiliation_strings":["JAMSTEC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JAMSTEC","institution_ids":["https://openalex.org/I1315852903"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001988181","display_name":"Dimitri Komatitsch","orcid":"https://orcid.org/0000-0003-2309-8269"},"institutions":[{"id":"https://openalex.org/I17866349","display_name":"Universit\u00e9 F\u00e9d\u00e9rale de Toulouse Midi-Pyr\u00e9n\u00e9es","ror":"https://ror.org/004raaa70","country_code":"FR","type":"education","lineage":["https://openalex.org/I17866349"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Dimitri Komatitsch","raw_affiliation_strings":["University of Toulouse"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toulouse","institution_ids":["https://openalex.org/I17866349"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046613458","display_name":"Franck Cappello","orcid":"https://orcid.org/0000-0002-7890-3934"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Franck Cappello","raw_affiliation_strings":["INRIA, University of Illinois"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA, University of Illinois","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035025604","display_name":"Naoya Maruyama","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naoya Maruyama","raw_affiliation_strings":["Tokyo Institute of Technology","Tokyo Institute of Technology, Naoya"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Tokyo Institute of Technology, Naoya","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100634486","display_name":"Satoshi Matsuoka","orcid":"https://orcid.org/0000-0003-1910-8532"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]},{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Matsuoka","raw_affiliation_strings":["Tokyo Institute of Technology","Tokyo Institute of Technology / National Institute of Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Tokyo Institute of Technology / National Institute of Informatics","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":296,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"32"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9987000226974487,"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"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9980999827384949,"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":0.8736502528190613},{"id":"https://openalex.org/keywords/petascale-computing","display_name":"Petascale computing","score":0.7728840708732605},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.6483426094055176},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.6247419118881226},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5543663501739502},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5119167566299438},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5028693079948425},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.4583614766597748},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.4575352966785431},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.43310436606407166},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.3790995478630066},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3578720986843109},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.33759093284606934},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.08311814069747925}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8736502528190613},{"id":"https://openalex.org/C185410017","wikidata":"https://www.wikidata.org/wiki/Q7171778","display_name":"Petascale computing","level":3,"score":0.7728840708732605},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.6483426094055176},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.6247419118881226},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5543663501739502},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5119167566299438},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5028693079948425},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.4583614766597748},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.4575352966785431},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.43310436606407166},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.3790995478630066},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3578720986843109},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.33759093284606934},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.08311814069747925},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2063384.2063427","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2063384.2063427","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-00721216v1","is_oa":false,"landing_page_url":"https://inria.hal.science/hal-00721216","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"SC'11: Proceedings of the 2011 ACM/IEEE conference on Supercomputing, 2011, New York, United States. pp.32:1-32:12, &#x27E8;10.1145/2063384.2063427&#x27E9;","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:HAL:hal-01298430v1","is_oa":false,"landing_page_url":"https://hal.science/hal-01298430","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the ACM / IEEE Supercomputing SC'2011 conference, Nov 2011, Seattle, United States. pp.1-12, &#x27E8;10.1145/2063384.2063427&#x27E9;","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5125938736","display_name":"Fault Tolerant Infrastructure Toward Billion of Parallelization and Exa-scale Supercomputer","funder_award_id":"23220003","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W8726371","https://openalex.org/W28511425","https://openalex.org/W130792636","https://openalex.org/W156943659","https://openalex.org/W1498586823","https://openalex.org/W1537929875","https://openalex.org/W1558516248","https://openalex.org/W1881933307","https://openalex.org/W1973963067","https://openalex.org/W1984564341","https://openalex.org/W1997021720","https://openalex.org/W2001495258","https://openalex.org/W2021261510","https://openalex.org/W2031086351","https://openalex.org/W2033656974","https://openalex.org/W2045879521","https://openalex.org/W2050033223","https://openalex.org/W2057630513","https://openalex.org/W2066529295","https://openalex.org/W2075665712","https://openalex.org/W2089536264","https://openalex.org/W2091396517","https://openalex.org/W2097946733","https://openalex.org/W2101650420","https://openalex.org/W2103113534","https://openalex.org/W2104129492","https://openalex.org/W2112512905","https://openalex.org/W2122249806","https://openalex.org/W2124439663","https://openalex.org/W2125169487","https://openalex.org/W2131645490","https://openalex.org/W2131894525","https://openalex.org/W2155521027","https://openalex.org/W2159416784","https://openalex.org/W2163295644","https://openalex.org/W2164590718","https://openalex.org/W2165231728","https://openalex.org/W2165751385","https://openalex.org/W2168743256","https://openalex.org/W2170196949","https://openalex.org/W2183928100","https://openalex.org/W2275750751","https://openalex.org/W2296772319","https://openalex.org/W2333836441","https://openalex.org/W2914685418","https://openalex.org/W4246550866","https://openalex.org/W4251384337","https://openalex.org/W6638807542"],"related_works":["https://openalex.org/W2021702679","https://openalex.org/W3038449658","https://openalex.org/W1582746211","https://openalex.org/W3129378740","https://openalex.org/W2607572736","https://openalex.org/W2266027327","https://openalex.org/W2278366184","https://openalex.org/W1486544172","https://openalex.org/W4206324154","https://openalex.org/W1978931242"],"abstract_inverted_index":{"Large":[0],"scientific":[1],"applications":[2],"deployed":[3],"on":[4,120,131],"current":[5],"petascale":[6],"systems":[7],"expend":[8],"a":[9,39,49,55,92,108,124],"significant":[10],"amount":[11],"of":[12,86,94,97,104,111],"their":[13],"execution":[14],"time":[15,64],"dumping":[16],"checkpoint":[17,43,57,125],"files":[18],"to":[19,29],"remote":[20],"storage.":[21],"New":[22],"fault":[23],"tolerant":[24],"techniques":[25],"will":[26],"be":[27],"critical":[28],"efficiently":[30,60],"exploit":[31],"post-petascale":[32],"systems.":[33],"In":[34],"this":[35],"work,":[36],"we":[37,47,106],"propose":[38],"low-overhead":[40],"high-frequency":[41],"multi-level":[42],"technique":[44,75],"in":[45,54,76],"which":[46],"integrate":[48],"highly-reliable":[50],"topology-aware":[51],"Reed-Solomon":[52],"encoding":[53,63],"three-level":[56],"scheme.":[58],"We":[59,72,82,122],"hide":[61],"the":[62,77,84,95,102,112],"using":[65],"one":[66],"Fault-Tolerance":[67],"dedicated":[68],"thread":[69],"per":[70],"node.":[71],"implement":[73],"our":[74,87,98],"Fault":[78],"Tolerance":[79],"Interface":[80],"FTI.":[81],"evaluate":[83],"correctness":[85],"performance":[88,103],"model":[89],"and":[90],"conduct":[91],"study":[93,110],"reliability":[96],"library.":[99],"To":[100],"demonstrate":[101,123],"FTI,":[105],"present":[107],"case":[109],"Mw9.0":[113],"Tohoku":[114],"Japan":[115],"earthquake":[116],"simulation":[117],"with":[118],"SPECFEM3D":[119],"TSUBAME2.0.":[121],"overhead":[126],"as":[127,129],"low":[128],"8%":[130],"sustained":[132],"0.1":[133],"petaflops":[134],"runs":[135],"(1152":[136],"GPUs)":[137],"while":[138],"checkpointing":[139],"at":[140],"high":[141],"frequency.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":19},{"year":2020,"cited_by_count":25},{"year":2019,"cited_by_count":26},{"year":2018,"cited_by_count":36},{"year":2017,"cited_by_count":30},{"year":2016,"cited_by_count":27},{"year":2015,"cited_by_count":35},{"year":2014,"cited_by_count":19},{"year":2013,"cited_by_count":21},{"year":2012,"cited_by_count":15}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2016-06-24T00:00:00"}
