{"id":"https://openalex.org/W2108882057","doi":"https://doi.org/10.1109/clustr.2008.4663790","title":"Environmental-aware optimization of MPI checkpointing intervals","display_name":"Environmental-aware optimization of MPI checkpointing intervals","publication_year":2008,"publication_date":"2008-09-01","ids":{"openalex":"https://openalex.org/W2108882057","doi":"https://doi.org/10.1109/clustr.2008.4663790","mag":"2108882057"},"language":"en","primary_location":{"id":"doi:10.1109/clustr.2008.4663790","is_oa":false,"landing_page_url":"https://doi.org/10.1109/clustr.2008.4663790","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Cluster Computing","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/A5028835323","display_name":"Hideyuki Jitsumoto","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":"Hideyuki Jitsumoto","raw_affiliation_strings":["Tokyo Institute of Technology, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011254074","display_name":"Toshio Endo","orcid":"https://orcid.org/0000-0001-7297-6211"},"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":"Toshio Endo","raw_affiliation_strings":["Tokyo Institute of Technology, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, Japan","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":["National Institute of Information, Tokyo, Japan","Tokyo Institute of Technology, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"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":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"326","last_page":"329"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","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/T10715","display_name":"Distributed and Parallel Computing Systems","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/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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9995999932289124,"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":0.8591651916503906},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.7653356790542603},{"id":"https://openalex.org/keywords/rollback","display_name":"Rollback","score":0.6071114540100098},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5923317670822144},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5370686650276184},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5170639157295227},{"id":"https://openalex.org/keywords/interval","display_name":"Interval (graph theory)","score":0.46880772709846497},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4249938130378723},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10779500007629395}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8591651916503906},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.7653356790542603},{"id":"https://openalex.org/C174220543","wikidata":"https://www.wikidata.org/wiki/Q395307","display_name":"Rollback","level":3,"score":0.6071114540100098},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5923317670822144},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5370686650276184},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5170639157295227},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.46880772709846497},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4249938130378723},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10779500007629395},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C75949130","wikidata":"https://www.wikidata.org/wiki/Q848010","display_name":"Database transaction","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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"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":2,"locations":[{"id":"doi:10.1109/clustr.2008.4663790","is_oa":false,"landing_page_url":"https://doi.org/10.1109/clustr.2008.4663790","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Cluster Computing","raw_type":"proceedings-article"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:50062987","is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100576078","pdf_url":null,"source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land","score":0.4300000071525574}],"awards":[],"funders":[{"id":"https://openalex.org/F4320313934","display_name":"Institut national de recherche en informatique et en automatique (INRIA)","ror":"https://ror.org/02kvxyf05"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W57243869","https://openalex.org/W182304672","https://openalex.org/W1527754331","https://openalex.org/W2004885674","https://openalex.org/W2099796457","https://openalex.org/W2112121929","https://openalex.org/W2113181808","https://openalex.org/W2154983209"],"related_works":["https://openalex.org/W2075454349","https://openalex.org/W2145855242","https://openalex.org/W2010356481","https://openalex.org/W2016184125","https://openalex.org/W4236084769","https://openalex.org/W2621536082","https://openalex.org/W2152640076","https://openalex.org/W4313728343","https://openalex.org/W1599154403","https://openalex.org/W2103295733"],"abstract_inverted_index":{"Fault-tolerance":[0],"for":[1],"HPC":[2],"systems":[3],"with":[4,17],"long-running":[5],"applications":[6],"of":[7,39,46,74],"massive":[8],"and":[9,61,67],"growing":[10],"scale":[11],"is":[12,20,26,50,71],"now":[13],"essential.":[14],"Although":[15],"checkpointing":[16,25],"rollback":[18],"recovery":[19],"a":[21,30],"popular":[22],"technique,":[23],"automated":[24,44],"becoming":[27],"troublesome":[28],"in":[29],"real":[31],"system,":[32],"due":[33],"to":[34],"the":[35,47,53,78],"extremely":[36],"large":[37],"size":[38],"collective":[40],"application":[41],"memory.":[42],"Therefore,":[43],"optimization":[45],"checkpoint":[48],"interval":[49],"essential,":[51],"but":[52],"optimal":[54],"point":[55],"depends":[56],"on":[57,88],"hardware":[58],"failure":[59],"rates":[60],"I/O":[62],"bandwidth.":[63],"Our":[64],"new":[65],"model":[66],"an":[68,72],"algorithm,":[69],"which":[70],"extension":[73],"Vaidyapsilas":[75],"model,":[76],"solve":[77],"problem":[79],"by":[80],"taking":[81],"such":[82],"parameters":[83],"into":[84],"account.":[85],"Prototype":[86],"implementation":[87],"our":[89],"fault-tolerant":[90],"MPI":[91],"framework":[92],"ABARIS":[93],"showed":[94],"approximately":[95],"5.5%":[96],"improvement":[97],"over":[98],"statically":[99],"user-determined":[100],"cases.":[101]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
