{"id":"https://openalex.org/W2412349256","doi":"https://doi.org/10.1145/2907294.2907315","title":"Towards Practical Algorithm Based Fault Tolerance in Dense Linear Algebra","display_name":"Towards Practical Algorithm Based Fault Tolerance in Dense Linear Algebra","publication_year":2016,"publication_date":"2016-05-31","ids":{"openalex":"https://openalex.org/W2412349256","doi":"https://doi.org/10.1145/2907294.2907315","mag":"2412349256"},"language":"en","primary_location":{"id":"doi:10.1145/2907294.2907315","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2907294.2907315","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2907315&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=2907315&type=pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","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":true,"raw_author_name":"Panruo Wu","raw_affiliation_strings":["University of California Riverside, Riverside, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102787759","display_name":"Qiang Guan","orcid":"https://orcid.org/0000-0002-3804-8945"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qiang Guan","raw_affiliation_strings":["Los Alamos National Laboratory, Los Alamos, NM, USA"],"affiliations":[{"raw_affiliation_string":"Los Alamos National Laboratory, Los Alamos, NM, USA","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056569157","display_name":"Nathan DeBardeleben","orcid":"https://orcid.org/0000-0002-5593-9205"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nathan DeBardeleben","raw_affiliation_strings":["Los Alamos National Laboratory, Los Alamos, NM, USA"],"affiliations":[{"raw_affiliation_string":"Los Alamos National Laboratory, Los Alamos, NM, USA","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036921385","display_name":"Sean Blanchard","orcid":"https://orcid.org/0000-0002-1119-7828"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sean Blanchard","raw_affiliation_strings":["Los Alamos National Laboratory, Los Alamos, NM, USA"],"affiliations":[{"raw_affiliation_string":"Los Alamos National Laboratory, Los Alamos, NM, USA","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063703614","display_name":"Dingwen Tao","orcid":"https://orcid.org/0000-0001-5422-4497"},"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":"Dingwen Tao","raw_affiliation_strings":["University of California Riverside, Riverside, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057011942","display_name":"Xin Liang","orcid":"https://orcid.org/0000-0002-7219-1809"},"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":"Xin Liang","raw_affiliation_strings":["University of California Riverside, Riverside, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","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":["University of California Riverside, Riverside, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California Riverside, Riverside, CA, USA","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":["University of California Riverside, Riverside, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5020822198"],"corresponding_institution_ids":["https://openalex.org/I103635307"],"apc_list":null,"apc_paid":null,"fwci":2.4167,"has_fulltext":true,"cited_by_count":39,"citation_normalized_percentile":{"value":0.89560811,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"31","last_page":"42"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11005","display_name":"Radiation Effects in Electronics","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994000196456909,"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/T10472","display_name":"Semiconductor materials and devices","score":0.9937000274658203,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.8190086483955383},{"id":"https://openalex.org/keywords/checksum","display_name":"Checksum","score":0.8043195009231567},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7369611263275146},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7349810600280762},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.7171660661697388},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6313490867614746},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5478416085243225},{"id":"https://openalex.org/keywords/software-fault-tolerance","display_name":"Software fault tolerance","score":0.504520058631897},{"id":"https://openalex.org/keywords/fault-coverage","display_name":"Fault coverage","score":0.46568647027015686},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4544454514980316},{"id":"https://openalex.org/keywords/factor","display_name":"Factor (programming language)","score":0.4193272590637207},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4068431258201599},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.4029988646507263},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11420083045959473},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09753528237342834},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09323981404304504},{"id":"https://openalex.org/keywords/electronic-circuit","display_name":"Electronic circuit","score":0.07891041040420532},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06265276670455933}],"concepts":[{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.8190086483955383},{"id":"https://openalex.org/C162372511","wikidata":"https://www.wikidata.org/wiki/Q218341","display_name":"Checksum","level":2,"score":0.8043195009231567},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7369611263275146},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7349810600280762},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.7171660661697388},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6313490867614746},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5478416085243225},{"id":"https://openalex.org/C50712370","wikidata":"https://www.wikidata.org/wiki/Q4269346","display_name":"Software fault tolerance","level":3,"score":0.504520058631897},{"id":"https://openalex.org/C126953365","wikidata":"https://www.wikidata.org/wiki/Q5438152","display_name":"Fault coverage","level":3,"score":0.46568647027015686},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4544454514980316},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.4193272590637207},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4068431258201599},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.4029988646507263},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11420083045959473},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09753528237342834},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09323981404304504},{"id":"https://openalex.org/C134146338","wikidata":"https://www.wikidata.org/wiki/Q1815901","display_name":"Electronic circuit","level":2,"score":0.07891041040420532},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06265276670455933},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2907294.2907315","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2907294.2907315","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2907315&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/2907294.2907315","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2907294.2907315","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2907315&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.4300000071525574}],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1477544716","display_name":null,"funder_award_id":"Guangdong","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2240610671","display_name":null,"funder_award_id":"CCF-1305622, ACI-1305624, CCF-1513201","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2273800250","display_name":null,"funder_award_id":"NSFC-","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3442558166","display_name":null,"funder_award_id":"ACI-1305624","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3757194791","display_name":null,"funder_award_id":"JCYJ20","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G527974540","display_name":"SHF: Medium: Energy Efficient Computing on GPU-based Heterogeneous Systems","funder_award_id":"1513201","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G536053718","display_name":"SHF: Small: FTLA: Fault Tolerant Linear Algebra Software for Massively Parallel Architectures","funder_award_id":"1305622","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5402090779","display_name":null,"funder_award_id":"F-130","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7117328668","display_name":null,"funder_award_id":"CCF-1513201","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8160623262","display_name":"CAREER: Dependable High Performance Scientific Computing at Extreme Scale  via Algorithmic Fault Tolerance","funder_award_id":"1305624","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/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320336213","display_name":"National Natural Science Foundation of China-Guangdong Joint Fund","ror":null},{"id":"https://openalex.org/F4320338304","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2412349256.pdf","grobid_xml":"https://content.openalex.org/works/W2412349256.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W160422864","https://openalex.org/W1522250664","https://openalex.org/W1584278023","https://openalex.org/W1750504612","https://openalex.org/W1981493666","https://openalex.org/W1983303752","https://openalex.org/W1986905947","https://openalex.org/W1993660990","https://openalex.org/W1995746640","https://openalex.org/W2000882268","https://openalex.org/W2023856022","https://openalex.org/W2046607737","https://openalex.org/W2054176560","https://openalex.org/W2056109788","https://openalex.org/W2083606889","https://openalex.org/W2083613288","https://openalex.org/W2091180845","https://openalex.org/W2116097016","https://openalex.org/W2118582701","https://openalex.org/W2128511938","https://openalex.org/W2130076536","https://openalex.org/W2134864637","https://openalex.org/W2171007672","https://openalex.org/W2497735908","https://openalex.org/W2798909945","https://openalex.org/W3182208082","https://openalex.org/W4213043702","https://openalex.org/W4312258136"],"related_works":["https://openalex.org/W2971479921","https://openalex.org/W2412349256","https://openalex.org/W3145923041","https://openalex.org/W2946906624","https://openalex.org/W841176518","https://openalex.org/W2101077206","https://openalex.org/W2157727563","https://openalex.org/W2470343202","https://openalex.org/W2123437881","https://openalex.org/W2098626762"],"abstract_inverted_index":{"Algorithm":[0],"based":[1],"fault":[2,18,48,85,126,137],"tolerance":[3,138],"(ABFT)":[4],"attracts":[5],"renewed":[6],"interest":[7],"for":[8],"its":[9,136],"extremely":[10],"low":[11],"overhead":[12,142],"and":[13,41,87,129,139],"good":[14],"scalability.":[15],"However":[16],"the":[17,38,43,47,51,60,77,104,115,141],"model":[19,49,86],"used":[20],"to":[21,75,113,133],"design":[22],"ABFT":[23,62,91,106],"has":[24],"been":[25],"either":[26],"abstract,":[27],"simplistic,":[28],"or":[29],"both,":[30],"leaving":[31],"a":[32,82,89],"gap":[33,78],"between":[34],"what":[35,42],"occurs":[36],"at":[37],"architecture":[39],"level":[40],"algorithm":[44],"expects.":[45],"As":[46],"is":[50],"deciding":[52],"factor":[53],"in":[54,68,117],"choosing":[55],"an":[56],"effective":[57],"checksum":[58],"scheme,":[59],"resulting":[61],"techniques":[63],"have":[64],"seen":[65],"limited":[66],"impact":[67],"practice.":[69],"In":[70],"this":[71],"paper":[72],"we":[73],"seek":[74],"close":[76],"by":[79],"directly":[80],"using":[81],"comprehensive":[83,90],"architectural":[84,97,125],"devise":[88],"scheme":[92,107],"that":[93],"can":[94],"tolerate":[95],"multiple":[96],"faults":[98],"of":[99,143],"various":[100],"kinds.":[101],"We":[102,123],"implement":[103],"new":[105],"into":[108],"high":[109,120],"performance":[110,121],"linpack":[111],"(HPL)":[112],"demonstrate":[114,140],"feasibility":[116],"large":[118,130],"scale":[119,131],"benchmark.":[122],"conduct":[124],"injection":[127],"experiments":[128,132],"empirically":[134],"validate":[135],"error":[144],"handling,":[145],"respectively.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":5}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}