{"id":"https://openalex.org/W1583519197","doi":"https://doi.org/10.1109/ipdps.2010.5470473","title":"A high-performance fault-tolerant software framework for memory on commodity GPUs","display_name":"A high-performance fault-tolerant software framework for memory on commodity GPUs","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W1583519197","doi":"https://doi.org/10.1109/ipdps.2010.5470473","mag":"1583519197"},"language":"en","primary_location":{"id":"doi:10.1109/ipdps.2010.5470473","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2010.5470473","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Symposium on Parallel &amp; Distributed Processing (IPDPS)","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/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"]},{"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":"Naoya Maruyama","raw_affiliation_strings":["GSIC, National Institute of Informatics, JST-CREST, Japan","GSIC, Tokyo Institute of Technology, JST Crest"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GSIC, National Institute of Informatics, JST-CREST, Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"GSIC, Tokyo Institute of Technology, JST Crest","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006972521","display_name":"Akira Nukada","orcid":"https://orcid.org/0000-0001-7959-6975"},"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":"Akira Nukada","raw_affiliation_strings":["GSIC, National Institute of Informatics, JST-CREST, Japan","GSIC, Tokyo Institute of Technology, JST Crest"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GSIC, National Institute of Informatics, JST-CREST, Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"GSIC, Tokyo Institute of Technology, JST Crest","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103252086","display_name":"Satoshi Matsuoka","orcid":"https://orcid.org/0000-0003-2126-2926"},"institutions":[{"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":["GSIC, National Institute of Informatics, JST-CREST, Japan","GSIC, Tokyo Institute of Technology, National Institute of Informatics, JST Crest"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GSIC, National Institute of Informatics, JST-CREST, Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"GSIC, Tokyo Institute of Technology, National Institute of Informatics, JST Crest","institution_ids":["https://openalex.org/I184597095"]}]}],"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":42,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11005","display_name":"Radiation Effects in Electronics","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11005","display_name":"Radiation Effects in Electronics","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9995999932289124,"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":0.9994999766349792,"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":0.8355543613433838},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6398733854293823},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.6294074058532715},{"id":"https://openalex.org/keywords/dram","display_name":"Dram","score":0.5766865611076355},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.4416763186454773},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.41632938385009766},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.39481765031814575},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.27076542377471924},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.19798043370246887}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8355543613433838},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6398733854293823},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.6294074058532715},{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.5766865611076355},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.4416763186454773},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.41632938385009766},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.39481765031814575},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.27076542377471924},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.19798043370246887}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ipdps.2010.5470473","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2010.5470473","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Symposium on Parallel &amp; Distributed Processing (IPDPS)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.383.1623","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.383.1623","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://matsu-www.is.titech.ac.jp/~naoya/publications/ipdps10.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337392","display_name":"Division of Electrical, Communications and Cyber Systems","ror":"https://ror.org/01krpsy48"},{"id":"https://openalex.org/F4320338075","display_name":"Core Research for Evolutional Science and Technology","ror":"https://ror.org/00097mb19"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1508198331","https://openalex.org/W1558516248","https://openalex.org/W1992851788","https://openalex.org/W2004749420","https://openalex.org/W2020634604","https://openalex.org/W2023856022","https://openalex.org/W2025474944","https://openalex.org/W2028499920","https://openalex.org/W2034593585","https://openalex.org/W2035486547","https://openalex.org/W2052348620","https://openalex.org/W2053352232","https://openalex.org/W2053578304","https://openalex.org/W2083613288","https://openalex.org/W2084402884","https://openalex.org/W2114927422","https://openalex.org/W2116097016","https://openalex.org/W2118033476","https://openalex.org/W2118582701","https://openalex.org/W2122249806","https://openalex.org/W2128022558","https://openalex.org/W2151845324","https://openalex.org/W2152407222","https://openalex.org/W2152652532","https://openalex.org/W2155503253","https://openalex.org/W2159497832","https://openalex.org/W2162546540","https://openalex.org/W2166621589","https://openalex.org/W2167435539","https://openalex.org/W2256188683","https://openalex.org/W3138798301","https://openalex.org/W3145767355","https://openalex.org/W4246578358","https://openalex.org/W4248445118","https://openalex.org/W6692224182"],"related_works":["https://openalex.org/W2384867379","https://openalex.org/W3120961607","https://openalex.org/W4400094300","https://openalex.org/W4401568740","https://openalex.org/W2329539859","https://openalex.org/W2227905990","https://openalex.org/W2765823764","https://openalex.org/W3214280620","https://openalex.org/W2098207691","https://openalex.org/W1599154403"],"abstract_inverted_index":{"As":[0],"GPUs":[1,71,101],"are":[2,92],"increasingly":[3],"used":[4,28],"to":[5,67],"accelerate":[6],"HPC":[7,59],"applications":[8,136],"by":[9],"allowing":[10],"more":[11,21],"flexibility":[12],"and":[13,44,84,102,121,141,144],"programmability,":[14],"their":[15],"fault":[16,74],"tolerance":[17],"is":[18,54],"becoming":[19],"much":[20],"important":[22],"than":[23],"before":[24],"when":[25,89],"they":[26],"were":[27],"only":[29],"for":[30,51,80,86],"graphics.":[31],"The":[32],"current":[33],"generation":[34],"of":[35,97,114,118],"GPUs,":[36],"however,":[37],"does":[38],"not":[39],"have":[40],"standard":[41],"error":[42],"detection":[43],"correction":[45],"capabilities,":[46],"such":[47,90,137],"as":[48,138,145,147],"SEC-DED":[49],"ECC":[50],"DRAM,":[52],"which":[53],"almost":[55],"always":[56],"exercised":[57],"in":[58,100,133,149],"servers.":[60],"We":[61,94,110],"present":[62,103,111],"a":[63,150],"high-performance":[64],"software":[65],"framework":[66,120,126],"enhance":[68],"commodity":[69],"off-the-shelf":[70],"with":[72,130],"DRAM":[73],"tolerance.":[75],"It":[76],"combines":[77],"data":[78,98],"coding":[79,99],"detecting":[81],"bit-flip":[82],"errors":[83,91],"checkpointing":[85],"recovering":[87],"computations":[88],"detected.":[93],"analyze":[95],"performance":[96,112],"optimizations":[104],"geared":[105],"toward":[106],"memory-intensive":[107],"GPU":[108],"applications.":[109],"studies":[113],"the":[115,119,124],"prototype":[116],"implementation":[117],"show":[122],"that":[123],"proposed":[125],"can":[127],"be":[128],"realized":[129],"negligible":[131],"overheads":[132],"compute":[134],"intensive":[135,153],"N-body":[139],"problem":[140],"matrix":[142],"multiplication,":[143],"low":[146],"35%":[148],"highly-efficient":[151],"memory":[152],"3-D":[154],"FFT":[155],"kernel.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":9}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
