{"id":"https://openalex.org/W2037523067","doi":"https://doi.org/10.1145/1996130.1996142","title":"Algorithm-based recovery for iterative methods without checkpointing","display_name":"Algorithm-based recovery for iterative methods without checkpointing","publication_year":2011,"publication_date":"2011-06-08","ids":{"openalex":"https://openalex.org/W2037523067","doi":"https://doi.org/10.1145/1996130.1996142","mag":"2037523067"},"language":"en","primary_location":{"id":"doi:10.1145/1996130.1996142","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1996130.1996142","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th international symposium on High performance distributed 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/A5061737717","display_name":"Zizhong Chen","orcid":"https://orcid.org/0000-0003-2578-4940"},"institutions":[{"id":"https://openalex.org/I167576493","display_name":"Colorado School of Mines","ror":"https://ror.org/04raf6v53","country_code":"US","type":"education","lineage":["https://openalex.org/I167576493"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zizhong Chen","raw_affiliation_strings":["Colorado School of Mines, Golden, CO, USA","Colorado School of Mines, Golden, CO, USA,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Colorado School of Mines, Golden, CO, USA","institution_ids":["https://openalex.org/I167576493"]},{"raw_affiliation_string":"Colorado School of Mines, Golden, CO, USA,","institution_ids":["https://openalex.org/I167576493"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5061737717"],"corresponding_institution_ids":["https://openalex.org/I167576493"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":107,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"73","last_page":"84"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9975000023841858,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9937999844551086,"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/computer-science","display_name":"Computer science","score":0.8629026412963867},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.845212996006012},{"id":"https://openalex.org/keywords/petascale-computing","display_name":"Petascale computing","score":0.7304470539093018},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.679888129234314},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.6781883239746094},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6532489657402039},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.6358473300933838},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.6147753000259399},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5544485449790955},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5441762208938599},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.4289943277835846},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.343514621257782},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.13909515738487244}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8629026412963867},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.845212996006012},{"id":"https://openalex.org/C185410017","wikidata":"https://www.wikidata.org/wiki/Q7171778","display_name":"Petascale computing","level":3,"score":0.7304470539093018},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.679888129234314},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.6781883239746094},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6532489657402039},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.6358473300933838},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.6147753000259399},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5544485449790955},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5441762208938599},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.4289943277835846},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.343514621257782},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.13909515738487244},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1996130.1996142","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1996130.1996142","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th international symposium on High performance distributed computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W155647330","https://openalex.org/W1539055682","https://openalex.org/W1558516248","https://openalex.org/W1569090332","https://openalex.org/W1569680480","https://openalex.org/W1575701986","https://openalex.org/W1585772192","https://openalex.org/W1607166357","https://openalex.org/W1782355304","https://openalex.org/W1825216778","https://openalex.org/W1847519410","https://openalex.org/W1973269641","https://openalex.org/W1974401809","https://openalex.org/W1997021720","https://openalex.org/W1997796448","https://openalex.org/W2001495258","https://openalex.org/W2022916138","https://openalex.org/W2023779315","https://openalex.org/W2036641664","https://openalex.org/W2068092015","https://openalex.org/W2081409107","https://openalex.org/W2083606889","https://openalex.org/W2083613288","https://openalex.org/W2092712520","https://openalex.org/W2097946733","https://openalex.org/W2100970777","https://openalex.org/W2102844000","https://openalex.org/W2104120668","https://openalex.org/W2105039796","https://openalex.org/W2105524676","https://openalex.org/W2108167744","https://openalex.org/W2114035455","https://openalex.org/W2125768532","https://openalex.org/W2128564847","https://openalex.org/W2128854702","https://openalex.org/W2130076109","https://openalex.org/W2138660187","https://openalex.org/W2150679822","https://openalex.org/W2151984682","https://openalex.org/W2152212524","https://openalex.org/W2156514327","https://openalex.org/W2157243803","https://openalex.org/W2158344138","https://openalex.org/W2161551433","https://openalex.org/W2165863720","https://openalex.org/W2170500888","https://openalex.org/W2170575069","https://openalex.org/W2171453084","https://openalex.org/W2246600761","https://openalex.org/W2296772319","https://openalex.org/W2501950392","https://openalex.org/W2798909945","https://openalex.org/W4233549502","https://openalex.org/W4285719527","https://openalex.org/W6600210833","https://openalex.org/W6750968397"],"related_works":["https://openalex.org/W4307656122","https://openalex.org/W2087210673","https://openalex.org/W2080435752","https://openalex.org/W4232104505","https://openalex.org/W2019484008","https://openalex.org/W1522862521","https://openalex.org/W1580237945","https://openalex.org/W2092071486","https://openalex.org/W2520782116","https://openalex.org/W2222431521"],"abstract_inverted_index":{"In":[0,44],"today's":[1],"high":[2],"performance":[3],"computing":[4],"practice,":[5],"fail-stop":[6],"failures":[7,132],"are":[8],"often":[9,22,32],"tolerated":[10],"by":[11],"checkpointing.":[12,82,105],"While":[13],"checkpointing":[14,162],"is":[15,110,116,127,139],"a":[16,26,34,96,135],"very":[17],"general":[18],"technique":[19],"and":[20,42,94],"can":[21],"be":[23],"applied":[24],"to":[25],"wide":[27],"range":[28],"of":[29,77],"applications,":[30],"it":[31,152],"introduces":[33,157],"considerable":[35],"overhead":[36,125,160],"especially":[37],"when":[38,142,151],"computations":[39],"reach":[40],"petascale":[41],"beyond.":[43],"this":[45,107],"paper,":[46],"we":[47],"show":[48],"that,":[49,150],"for":[50,73,91,99,118],"many":[51],"iterative":[52,64],"methods,":[53],"if":[54,129],"the":[55,63,74,78,85,101,119,122,154,164],"parallel":[56],"data":[57,80,88,103],"partitioning":[58,89],"scheme":[59,90,156],"satisfies":[60],"certain":[61],"conditions,":[62],"methods":[65],"themselves":[66],"will":[67],"maintain":[68],"enough":[69],"inherent":[70],"redundant":[71],"information":[72],"accurate":[75],"recovery":[76],"lost":[79],"without":[81,104],"We":[83],"analyze":[84],"block":[86],"row":[87],"sparse":[92],"matrices":[93],"derive":[95],"sufficient":[97,108],"condition":[98,109],"recovering":[100],"critical":[102],"When":[106],"satisfied,":[111],"neither":[112],"checkpoint":[113],"nor":[114],"roll-back":[115],"necessary":[117],"recovery.":[120],"Furthermore,":[121],"fault":[123],"tolerance":[124],"(time)":[126],"zero":[128],"no":[130],"actual":[131,144],"occur":[133],"during":[134],"program":[136],"execution.":[137],"Overhead":[138],"introduced":[140],"only":[141],"an":[143],"failure":[145],"occurs.":[146],"Experimental":[147],"results":[148],"demonstrate":[149],"works,":[153],"proposed":[155],"much":[158],"less":[159],"than":[161],"on":[163],"current":[165],"world's":[166],"eighth-fastest":[167],"supercomputer":[168],"Kraken.":[169]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":15},{"year":2016,"cited_by_count":16},{"year":2015,"cited_by_count":12},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":13},{"year":2012,"cited_by_count":7}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
