{"id":"https://openalex.org/W2515526980","doi":"https://doi.org/10.1109/nas.2016.7549404","title":"GPU-ABFT: Optimizing Algorithm-Based Fault Tolerance for Heterogeneous Systems with GPUs","display_name":"GPU-ABFT: Optimizing Algorithm-Based Fault Tolerance for Heterogeneous Systems with GPUs","publication_year":2016,"publication_date":"2016-08-01","ids":{"openalex":"https://openalex.org/W2515526980","doi":"https://doi.org/10.1109/nas.2016.7549404","mag":"2515526980"},"language":"en","primary_location":{"id":"doi:10.1109/nas.2016.7549404","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nas.2016.7549404","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Networking, Architecture and Storage (NAS)","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/A5063649910","display_name":"Jieyang Chen","orcid":"https://orcid.org/0000-0002-1905-9171"},"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":"Jieyang Chen","raw_affiliation_strings":["Department of Computer Science and Engineering, University of California, Riverside"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of California, Riverside","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103179545","display_name":"Sihuan Li","orcid":"https://orcid.org/0000-0001-7315-7955"},"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":"Sihuan Li","raw_affiliation_strings":["Department of Computer Science and Engineering, University of California, Riverside"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of California, Riverside","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"last","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":["Department of Computer Science and Engineering, University of California, Riverside"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of California, Riverside","institution_ids":["https://openalex.org/I103635307"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I103635307"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9991000294685364,"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":0.9988999962806702,"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":0.8429280519485474},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.8058332800865173},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.7212039232254028},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6320302486419678},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5540338754653931},{"id":"https://openalex.org/keywords/cholesky-decomposition","display_name":"Cholesky decomposition","score":0.5275934338569641},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.5049737095832825},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.4894922971725464},{"id":"https://openalex.org/keywords/triple-modular-redundancy","display_name":"Triple modular redundancy","score":0.44987618923187256},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.39895379543304443},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3349180221557617},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.26098018884658813},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10351201891899109}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8429280519485474},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.8058332800865173},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.7212039232254028},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6320302486419678},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5540338754653931},{"id":"https://openalex.org/C34727166","wikidata":"https://www.wikidata.org/wiki/Q515375","display_name":"Cholesky decomposition","level":3,"score":0.5275934338569641},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.5049737095832825},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.4894922971725464},{"id":"https://openalex.org/C196371267","wikidata":"https://www.wikidata.org/wiki/Q3998979","display_name":"Triple modular redundancy","level":3,"score":0.44987618923187256},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.39895379543304443},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3349180221557617},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26098018884658813},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10351201891899109},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/nas.2016.7549404","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nas.2016.7549404","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Networking, Architecture and Storage (NAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1995746640","https://openalex.org/W2031533321","https://openalex.org/W2083613288","https://openalex.org/W2151984682","https://openalex.org/W6671166405","https://openalex.org/W6682626600"],"related_works":["https://openalex.org/W58658798","https://openalex.org/W3114375939","https://openalex.org/W3008821054","https://openalex.org/W2797678940","https://openalex.org/W2759696718","https://openalex.org/W2359816675","https://openalex.org/W2000379092","https://openalex.org/W2153096481","https://openalex.org/W2148616436","https://openalex.org/W4245453130"],"abstract_inverted_index":{"For":[0],"matrix":[1],"operations,":[2],"the":[3,15,41,65],"algorithm-based":[4],"fault":[5,11,115],"tolerance":[6,12,116],"(ABFT)":[7],"brings":[8,63],"much":[9],"lower":[10],"overhead":[13,117,147],"than":[14],"traditional":[16],"Triple":[17],"Modular":[18,22],"Redundancy":[19,23],"or":[20],"Double":[21],"approaches.":[24],"Many":[25],"works":[26],"have":[27],"been":[28],"done":[29],"to":[30,102,136],"develop":[31,113],"and":[32,53,76,94,141,148],"optimize":[33],"ABFT":[34,42,57,80,89,132],"schemes":[35,43,58],"on":[36,44,105],"general":[37],"purpose":[38],"microprocessors.":[39],"However,":[40],"heterogeneous":[45,106,122],"systems":[46,107,123],"with":[47,91,108,124,145],"GPUs":[48,125],"are":[49],"not":[50],"fully":[51],"developed":[52],"optimized.":[54],"Moreover,":[55],"existing":[56],"can":[59],"correct":[60,137],"computing":[61,93,139],"errors":[62,72],"by":[64,78],"logic":[66],"parts,":[67],"however,":[68],"many":[69],"memory":[70,95,142],"storage":[71,96,143],"cannot":[73],"be":[74],"detected":[75],"corrected":[77],"current":[79],"schemes.":[81],"In":[82,110],"this":[83],"work,":[84],"we":[85,99,112],"designed":[86],"a":[87],"new":[88],"scheme":[90,133],"both":[92,138],"protection.":[97],"Then,":[98],"apply":[100],"it":[101],"Cholesky":[103],"decomposition":[104],"GPUs.":[109],"addition,":[111],"several":[114],"reduction":[118],"techniques":[119],"specifically":[120],"for":[121],"accelerators.":[126],"Experimental":[127],"results":[128],"show":[129],"that":[130],"our":[131],"is":[134],"able":[135],"error":[140,144],"low":[146],"comparable":[149],"overall":[150],"performance.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}