{"id":"https://openalex.org/W1997195086","doi":"https://doi.org/10.1145/2656342","title":"Hardware Fault Recovery for I/O Intensive Applications","display_name":"Hardware Fault Recovery for I/O Intensive Applications","publication_year":2014,"publication_date":"2014-10-27","ids":{"openalex":"https://openalex.org/W1997195086","doi":"https://doi.org/10.1145/2656342","mag":"1997195086"},"language":"en","primary_location":{"id":"doi:10.1145/2656342","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2656342","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2656342","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/2656342","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101419530","display_name":"Pradeep Ramachandran","orcid":"https://orcid.org/0000-0002-1844-609X"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Pradeep Ramachandran","raw_affiliation_strings":["Intel Corporation, Sarjapur Outner Ring Road, Bangalore"],"affiliations":[{"raw_affiliation_string":"Intel Corporation, Sarjapur Outner Ring Road, Bangalore","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054590774","display_name":"Siva Kumar Sastry Hari","orcid":"https://orcid.org/0000-0001-8346-7981"},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]},{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Siva Kumar Sastry Hari","raw_affiliation_strings":["NVIDIA, San Tomas Expy, Santa Clara, CA","NVIDIA, San Tomas Expy, Santa Clara, CA#TAB#"],"affiliations":[{"raw_affiliation_string":"NVIDIA, San Tomas Expy, Santa Clara, CA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA, San Tomas Expy, Santa Clara, CA#TAB#","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087543093","display_name":"Man-Lap Li","orcid":null},"institutions":[{"id":"https://openalex.org/I196151661","display_name":"Latham & Watkins (United States)","ror":"https://ror.org/03084a880","country_code":"US","type":"company","lineage":["https://openalex.org/I196151661"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manlap Li","raw_affiliation_strings":["Latham and Watkins LLP, San Francisco, CA"],"affiliations":[{"raw_affiliation_string":"Latham and Watkins LLP, San Francisco, CA","institution_ids":["https://openalex.org/I196151661"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086111967","display_name":"Sarita V. Adve","orcid":"https://orcid.org/0000-0002-3403-5119"},"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":"Sarita V. Adve","raw_affiliation_strings":["University of Illinois at Urbana Champaign, Urbana, Illinois"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana Champaign, Urbana, Illinois","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101419530"],"corresponding_institution_ids":["https://openalex.org/I1343180700"],"apc_list":null,"apc_paid":null,"fwci":1.2764,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.82235136,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"11","issue":"3","first_page":"1","last_page":"25"},"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9990000128746033,"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/T10933","display_name":"Real-Time Systems Scheduling","score":0.9947999715805054,"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":0.8279975652694702},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.6824400424957275},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.5937447547912598},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.5120609402656555},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4685294032096863},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4147277772426605},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.4022446870803833},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.317829966545105},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.27863579988479614}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8279975652694702},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6824400424957275},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.5937447547912598},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.5120609402656555},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4685294032096863},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4147277772426605},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.4022446870803833},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.317829966545105},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.27863579988479614},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2656342","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2656342","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2656342","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/2656342","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2656342","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2656342","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G498354251","display_name":null,"funder_award_id":"NSF CCF 0541383 and CCF 0811693","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5520775069","display_name":null,"funder_award_id":"NSF CCF 0541383 and CCF 0811693","funder_id":"https://openalex.org/F4320337387","funder_display_name":"Division of Computing and Communication Foundations"},{"id":"https://openalex.org/G6507447573","display_name":null,"funder_award_id":"several","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6556314","display_name":"Lifetime Reliability Aware Microprocessors","funder_award_id":"0541383","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7741751233","display_name":"CPA-CSA-T:  Low Cost and Comprehensive Hardware Reliability","funder_award_id":"0811693","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320307102","display_name":"Intel Corporation","ror":"https://ror.org/01ek73717"},{"id":"https://openalex.org/F4320307762","display_name":"International Business Machines Corporation","ror":"https://ror.org/05hh8d621"},{"id":"https://openalex.org/F4320309370","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10"},{"id":"https://openalex.org/F4320337387","display_name":"Division of Computing and Communication Foundations","ror":"https://ror.org/01mng8331"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1997195086.pdf","grobid_xml":"https://content.openalex.org/works/W1997195086.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W1482451474","https://openalex.org/W1533195354","https://openalex.org/W1560055425","https://openalex.org/W1579215414","https://openalex.org/W1994759706","https://openalex.org/W2007925061","https://openalex.org/W2008482633","https://openalex.org/W2012035814","https://openalex.org/W2013280342","https://openalex.org/W2038366891","https://openalex.org/W2051694501","https://openalex.org/W2099123934","https://openalex.org/W2099828501","https://openalex.org/W2100866260","https://openalex.org/W2101580666","https://openalex.org/W2105372251","https://openalex.org/W2110908283","https://openalex.org/W2112752650","https://openalex.org/W2114100940","https://openalex.org/W2115081151","https://openalex.org/W2116613705","https://openalex.org/W2118033476","https://openalex.org/W2121579803","https://openalex.org/W2125169487","https://openalex.org/W2126869140","https://openalex.org/W2128941141","https://openalex.org/W2129673456","https://openalex.org/W2132362854","https://openalex.org/W2139727248","https://openalex.org/W2141365240","https://openalex.org/W2144382742","https://openalex.org/W2144512449","https://openalex.org/W2146065717","https://openalex.org/W2147280888","https://openalex.org/W2148162182","https://openalex.org/W2151845324","https://openalex.org/W2155851497","https://openalex.org/W2156204788","https://openalex.org/W2158382658","https://openalex.org/W2162351670","https://openalex.org/W2163890539","https://openalex.org/W2171882483","https://openalex.org/W2174598112","https://openalex.org/W3142506685","https://openalex.org/W3149940895","https://openalex.org/W4255519882"],"related_works":["https://openalex.org/W4306316843","https://openalex.org/W2040956888","https://openalex.org/W1483135751","https://openalex.org/W3102446781","https://openalex.org/W101888041","https://openalex.org/W2570560494","https://openalex.org/W2027487876","https://openalex.org/W2480447910","https://openalex.org/W2262841941","https://openalex.org/W3029473433"],"abstract_inverted_index":{"With":[0],"continued":[1],"process":[2],"scaling,":[3],"the":[4,81,91,165],"rate":[5],"of":[6,72],"hardware":[7,140,154],"failures":[8,32],"in":[9],"commodity":[10,16,64],"systems":[11,17],"is":[12,55,75,156],"increasing.":[13],"Because":[14],"these":[15,108],"are":[18,33,83],"highly":[19],"sensitive":[20],"to":[21,29,38,80,134,163],"cost,":[22],"traditional":[23],"solutions":[24,74],"that":[25,77,143,173],"employ":[26],"heavy":[27],"redundancy":[28],"handle":[30],"such":[31,44,73],"no":[34],"longer":[35],"acceptable":[36,149],"owing":[37],"their":[39],"high":[40,175],"associated":[41],"costs.":[42],"Detecting":[43],"faults":[45],"by":[46],"identifying":[47],"anomalous":[48],"software":[49],"execution":[50],"and":[51,141,168],"recovering":[52],"through":[53],"checkpoint-and-replay":[54],"emerging":[56],"as":[57,148],"a":[58,132,170],"viable":[59],"low-cost":[60],"alternative":[61],"for":[62,100,123],"future":[63],"systems.":[65],"An":[66],"important":[67],"but":[68],"commonly":[69],"ignored":[70,116],"aspect":[71],"ensuring":[76],"external":[78,136],"outputs":[79,86,137],"system":[82],"fault-free.":[84],"The":[85,98],"must":[87,102],"be":[88,104],"delayed":[89],"until":[90],"detectors":[92],"guarantee":[93],"this,":[94],"influencing":[95],"fault-free":[96],"performance.":[97],"overheads":[99,152],"resiliency":[101,176],"thus":[103],"evaluated":[105],"while":[106,177],"taking":[107],"delays":[109],"into":[110],"consideration;":[111],"prior":[112],"work":[113],"has":[114],"largely":[115],"this":[117],"relationship.":[118],"This":[119],"article":[120],"concerns":[121],"recovery":[122],"I/O":[124],"intensive":[125],"applications":[126],"from":[127],"in-core":[128],"faults.":[129],"We":[130,158],"present":[131,160],"strategy":[133],"buffer":[135],"using":[138],"dedicated":[139],"show":[142],"checkpoint":[144,166],"intervals":[145],"previously":[146],"considered":[147],"incur":[150],"exorbitant":[151],"when":[153],"buffering":[155],"considered.":[157],"then":[159],"two":[161],"techniques":[162],"reduce":[164],"interval":[167],"demonstrate":[169],"practical":[171],"solution":[172],"provides":[174],"incurring":[178],"low":[179],"overheads.":[180]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-03-15T09:29:46.208133","created_date":"2025-10-10T00:00:00"}
