{"id":"https://openalex.org/W1980321276","doi":"https://doi.org/10.1145/2503210.2503226","title":"Rethinking algorithm-based fault tolerance with a cooperative software-hardware approach","display_name":"Rethinking algorithm-based fault tolerance with a cooperative software-hardware approach","publication_year":2013,"publication_date":"2013-10-30","ids":{"openalex":"https://openalex.org/W1980321276","doi":"https://doi.org/10.1145/2503210.2503226","mag":"1980321276"},"language":"en","primary_location":{"id":"doi:10.1145/2503210.2503226","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2503210.2503226","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"type":"article","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/A5100407453","display_name":"Dong Li","orcid":"https://orcid.org/0000-0002-5084-3781"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dong Li","raw_affiliation_strings":["Oak Ridge National Laboratory"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061737717","display_name":"Zizhong Chen","orcid":"https://orcid.org/0000-0003-2578-4940"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zizhong Chen","raw_affiliation_strings":["University of California, Riverside"],"affiliations":[{"raw_affiliation_string":"University of California, Riverside","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020822198","display_name":"Panruo Wu","orcid":"https://orcid.org/0000-0003-1859-3580"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Panruo Wu","raw_affiliation_strings":["University of California, Riverside"],"affiliations":[{"raw_affiliation_string":"University of California, Riverside","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061838490","display_name":"Jeffrey S. Vetter","orcid":"https://orcid.org/0000-0002-2449-6720"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]},{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeffrey S. Vetter","raw_affiliation_strings":["Oak Ridge National Laboratory and Georgia Institute of Technology","Oak Ridge National Laboratory and Georgia Institute of Technology#TAB#"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory and Georgia Institute of Technology","institution_ids":["https://openalex.org/I1289243028","https://openalex.org/I130701444"]},{"raw_affiliation_string":"Oak Ridge National Laboratory and Georgia Institute of Technology#TAB#","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100407453"],"corresponding_institution_ids":["https://openalex.org/I1289243028"],"apc_list":null,"apc_paid":null,"fwci":4.7119,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.95107812,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9994000196456909,"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":0.9994000196456909,"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/T11005","display_name":"Radiation Effects in Electronics","score":0.9994000196456909,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9976000189781189,"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/fault-tolerance","display_name":"Fault tolerance","score":0.8062522411346436},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7943804264068604},{"id":"https://openalex.org/keywords/resilience","display_name":"Resilience (materials science)","score":0.7641969919204712},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5830814242362976},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5206997990608215},{"id":"https://openalex.org/keywords/software-fault-tolerance","display_name":"Software fault tolerance","score":0.485113263130188},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.44721439480781555},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4417416751384735},{"id":"https://openalex.org/keywords/fault-injection","display_name":"Fault injection","score":0.43623197078704834},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3679220676422119},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3542613685131073},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.33886122703552246},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.20692971348762512}],"concepts":[{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.8062522411346436},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7943804264068604},{"id":"https://openalex.org/C2779585090","wikidata":"https://www.wikidata.org/wiki/Q3457762","display_name":"Resilience (materials science)","level":2,"score":0.7641969919204712},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5830814242362976},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5206997990608215},{"id":"https://openalex.org/C50712370","wikidata":"https://www.wikidata.org/wiki/Q4269346","display_name":"Software fault tolerance","level":3,"score":0.485113263130188},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.44721439480781555},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4417416751384735},{"id":"https://openalex.org/C2775928411","wikidata":"https://www.wikidata.org/wiki/Q2041312","display_name":"Fault injection","level":3,"score":0.43623197078704834},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3679220676422119},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3542613685131073},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.33886122703552246},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.20692971348762512},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2503210.2503226","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2503210.2503226","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.8899999856948853,"id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G2713955069","display_name":null,"funder_award_id":"CNS-1304969, CCF-1305622, OCI-1305624","funder_id":"https://openalex.org/F4320337387","funder_display_name":"Division of Computing and Communication Foundations"},{"id":"https://openalex.org/G3958220316","display_name":null,"funder_award_id":"CNS-1304969, CCF-1305622, OCI-1305624","funder_id":"https://openalex.org/F4320337388","funder_display_name":"Division of Computer and Network Systems"},{"id":"https://openalex.org/G8106743005","display_name":null,"funder_award_id":"CNS-1304969, CCF-1305622, OCI-1305624","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"}],"funders":[{"id":"https://openalex.org/F4320337377","display_name":"Office of Advanced Cyberinfrastructure","ror":"https://ror.org/04nh1dc89"},{"id":"https://openalex.org/F4320337387","display_name":"Division of Computing and Communication Foundations","ror":"https://ror.org/01mng8331"},{"id":"https://openalex.org/F4320337388","display_name":"Division of Computer and Network Systems","ror":"https://ror.org/02rdzmk74"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1522102036","https://openalex.org/W1963637299","https://openalex.org/W1981493666","https://openalex.org/W1988070283","https://openalex.org/W1989773959","https://openalex.org/W2007958367","https://openalex.org/W2016481757","https://openalex.org/W2021708499","https://openalex.org/W2037523067","https://openalex.org/W2040379684","https://openalex.org/W2061887253","https://openalex.org/W2063924830","https://openalex.org/W2065132365","https://openalex.org/W2088943630","https://openalex.org/W2089344916","https://openalex.org/W2091180845","https://openalex.org/W2096504919","https://openalex.org/W2098809490","https://openalex.org/W2100866260","https://openalex.org/W2105372251","https://openalex.org/W2118231788","https://openalex.org/W2119296805","https://openalex.org/W2120591095","https://openalex.org/W2122249806","https://openalex.org/W2123500455","https://openalex.org/W2125640880","https://openalex.org/W2128511938","https://openalex.org/W2135382555","https://openalex.org/W2136799148","https://openalex.org/W2146065717","https://openalex.org/W2151917022","https://openalex.org/W2152211247","https://openalex.org/W2159216681","https://openalex.org/W2162639668","https://openalex.org/W2170310381","https://openalex.org/W3004493283","https://openalex.org/W4213043702","https://openalex.org/W4245880889","https://openalex.org/W6677946485"],"related_works":["https://openalex.org/W2146400304","https://openalex.org/W3101271453","https://openalex.org/W3014207222","https://openalex.org/W4385585346","https://openalex.org/W2123309364","https://openalex.org/W2024608029","https://openalex.org/W4285820867","https://openalex.org/W2895044751","https://openalex.org/W2987257786","https://openalex.org/W3143484911"],"abstract_inverted_index":{"Algorithm-based":[0],"fault":[1],"tolerance":[2],"(ABFT)":[3],"is":[4,25],"a":[5,35],"highly":[6],"efficient":[7],"resilience":[8,22,32,110],"solution":[9],"for":[10,96,111,126,133],"many":[11],"widely-used":[12],"scientific":[13],"computing":[14],"kernels.":[15],"However,":[16],"in":[17,51],"the":[18,21,73,101],"context":[19],"of":[20,53,75,81,103,146],"ecosystem,":[23],"ABFT":[24,43,62,91,147],"completely":[26],"opaque":[27],"to":[28,48,89,124,131,139],"any":[29],"underlying":[30],"hardware":[31,71],"mechanisms.":[33],"As":[34],"result,":[36],"some":[37],"data":[38],"structures":[39],"are":[40],"over-protected":[41],"by":[42],"and":[44,55,70,78,92,99,109,116],"hardware,":[45],"which":[46],"leads":[47],"redundant":[49],"costs":[50],"terms":[52],"performance":[54,77,141],"energy.":[56],"In":[57,84],"this":[58,104],"paper,":[59],"we":[60,86],"rethink":[61],"using":[63],"an":[64],"integrated":[65],"view":[66],"including":[67],"both":[68],"software":[69],"with":[72,137,148],"goal":[74],"improving":[76],"energy":[79,128],"efficiency":[80],"ABFT-enabled":[82,112],"applications.":[83,113],"particular,":[85],"study":[87],"how":[88],"coordinate":[90],"error-correcting":[93],"code":[94],"(ECC)":[95],"main":[97],"memory,":[98],"investigate":[100],"impact":[102],"coordination":[105],"on":[106],"performance,":[107],"energy,":[108],"Scaling":[114],"tests":[115],"analysis":[117],"indicate":[118],"that":[119],"our":[120],"approach":[121],"saves":[122],"up":[123,130,138],"25%":[125],"system":[127],"(and":[129],"40%":[132],"dynamic":[134],"memory":[135],"energy)":[136],"18%":[140],"improvement":[142],"over":[143],"traditional":[144],"approaches":[145],"ECC.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":11},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
