{"id":"https://openalex.org/W4243160333","doi":"https://doi.org/10.1109/dsn.2010.5544426","title":"1&lt;sup&gt;st&lt;/sup&gt; workshop on fault-tolerance for HPC at extreme scale FTXS 2010","display_name":"1&lt;sup&gt;st&lt;/sup&gt; workshop on fault-tolerance for HPC at extreme scale FTXS 2010","publication_year":2010,"publication_date":"2010-06-01","ids":{"openalex":"https://openalex.org/W4243160333","doi":"https://doi.org/10.1109/dsn.2010.5544426"},"language":"en","primary_location":{"id":"doi:10.1109/dsn.2010.5544426","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsn.2010.5544426","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE/IFIP International Conference on Dependable Systems &amp; Networks (DSN)","raw_type":"proceedings-article"},"type":"conference-abstract","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/A5105303824","display_name":"John W. Daly","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"John Daly","raw_affiliation_strings":["Department of Defense, Center for Exceptional Computing, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Defense, Center for Exceptional Computing, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056569157","display_name":"Nathan DeBardeleben","orcid":"https://orcid.org/0000-0002-5593-9205"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nathan DeBardeleben","raw_affiliation_strings":["Department of Defense, Center for Exceptional Computing, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Defense, Center for Exceptional Computing, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":"615","last_page":"615"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.998199999332428,"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":0.998199999332428,"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":0.9962000250816345,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.994700014591217,"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/fault-tolerance","display_name":"Fault tolerance","score":0.7440638542175293},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.6348834037780762},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5983092188835144},{"id":"https://openalex.org/keywords/interrupt","display_name":"Interrupt","score":0.5202640295028687},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4554758071899414},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4373801350593567},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4053269028663635},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.32482683658599854},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.28107404708862305},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.2425956428050995},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16840919852256775},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11657842993736267},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09150862693786621}],"concepts":[{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.7440638542175293},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.6348834037780762},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5983092188835144},{"id":"https://openalex.org/C41661131","wikidata":"https://www.wikidata.org/wiki/Q220764","display_name":"Interrupt","level":3,"score":0.5202640295028687},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4554758071899414},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4373801350593567},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4053269028663635},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.32482683658599854},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.28107404708862305},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2425956428050995},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16840919852256775},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11657842993736267},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09150862693786621},{"id":"https://openalex.org/C173018170","wikidata":"https://www.wikidata.org/wiki/Q165678","display_name":"Microcontroller","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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":1,"locations":[{"id":"doi:10.1109/dsn.2010.5544426","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsn.2010.5544426","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE/IFIP International Conference on Dependable Systems &amp; Networks (DSN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.8299999833106995,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4288898221","https://openalex.org/W2358308054","https://openalex.org/W2391783641","https://openalex.org/W2109690896","https://openalex.org/W4231875098","https://openalex.org/W4230529130","https://openalex.org/W2391365542","https://openalex.org/W2361731841","https://openalex.org/W2386367690","https://openalex.org/W4243198198"],"abstract_inverted_index":{"With":[0],"the":[1,10,26,100],"emergence":[2],"of":[3,21,29,51,60,65,86],"many-core":[4],"processors,":[5],"accelerators,":[6],"and":[7,62,69,103],"alternative/heterogeneous":[8],"architectures,":[9],"HPC":[11,52],"community":[12],"faces":[13],"a":[14,17,83],"new":[15],"challenge:":[16],"scaling":[18,30],"in":[19,31,37],"number":[20],"processing":[22],"elements":[23],"that":[24],"supersedes":[25],"historical":[27],"trend":[28],"processor":[32],"frequencies.":[33],"The":[34],"attendant":[35],"increase":[36],"system":[38,88,111],"complexity":[39],"has":[40],"first-order":[41],"implications":[42],"for":[43],"fault":[44,53],"tolerance.":[45],"Mounting":[46],"evidence":[47],"invalidates":[48],"traditional":[49],"assumptions":[50],"tolerance:":[54],"faults":[55],"are":[56,73,107],"increasingly":[57],"multiple-point":[58],"instead":[59,64],"single-point":[61],"interdependent":[63],"independent;":[66],"silent":[67,70],"failures":[68],"data":[71],"corruption":[72],"no":[74],"longer":[75],"rare":[76],"enough":[77],"to":[78,94],"discount;":[79],"stabilization":[80],"time":[81],"consumes":[82],"larger":[84],"fraction":[85],"useful":[87],"lifetime,":[89],"with":[90],"failure":[91,112],"rates":[92,106],"projected":[93],"exceed":[95],"one":[96],"per":[97],"hour":[98],"on":[99],"largest":[101],"systems;":[102],"application":[104],"interrupt":[105],"apparently":[108],"diverging":[109],"from":[110],"rates.":[113]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
