{"id":"https://openalex.org/W2159642127","doi":"https://doi.org/10.1145/2133173.2133179","title":"Soft error resilient QR factorization for hybrid system with GPGPU","display_name":"Soft error resilient QR factorization for hybrid system with GPGPU","publication_year":2011,"publication_date":"2011-11-14","ids":{"openalex":"https://openalex.org/W2159642127","doi":"https://doi.org/10.1145/2133173.2133179","mag":"2159642127"},"language":"en","primary_location":{"id":"doi:10.1145/2133173.2133179","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2133173.2133179","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the second workshop on Scalable algorithms for large-scale systems","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/A5100620408","display_name":"Peng Du","orcid":"https://orcid.org/0000-0002-8257-8230"},"institutions":[{"id":"https://openalex.org/I2802706902","display_name":"Knoxville College","ror":"https://ror.org/02bxrp522","country_code":"US","type":"education","lineage":["https://openalex.org/I2802706902"]},{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peng Du","raw_affiliation_strings":["University of Tennessee, Knoxville, Knoxville, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee, Knoxville, Knoxville, USA","institution_ids":["https://openalex.org/I2802706902","https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073990539","display_name":"Piotr \u0141uszczek","orcid":"https://orcid.org/0000-0002-0089-6965"},"institutions":[{"id":"https://openalex.org/I2802706902","display_name":"Knoxville College","ror":"https://ror.org/02bxrp522","country_code":"US","type":"education","lineage":["https://openalex.org/I2802706902"]},{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Piotr Luszczek","raw_affiliation_strings":["University of Tennessee, Knoxville, Knoxville, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee, Knoxville, Knoxville, USA","institution_ids":["https://openalex.org/I2802706902","https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083604741","display_name":"Stanimire Tomov","orcid":"https://orcid.org/0000-0002-5937-7959"},"institutions":[{"id":"https://openalex.org/I2802706902","display_name":"Knoxville College","ror":"https://ror.org/02bxrp522","country_code":"US","type":"education","lineage":["https://openalex.org/I2802706902"]},{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stan Tomov","raw_affiliation_strings":["University of Tennessee, Knoxville, Knoxville, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee, Knoxville, Knoxville, USA","institution_ids":["https://openalex.org/I2802706902","https://openalex.org/I75027704"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075517045","display_name":"Jack Dongarra","orcid":"https://orcid.org/0000-0003-3247-1782"},"institutions":[{"id":"https://openalex.org/I2802706902","display_name":"Knoxville College","ror":"https://ror.org/02bxrp522","country_code":"US","type":"education","lineage":["https://openalex.org/I2802706902"]},{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jack Dongarra","raw_affiliation_strings":["University of Tennessee, Knoxville, Knoxville, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee, Knoxville, Knoxville, USA","institution_ids":["https://openalex.org/I2802706902","https://openalex.org/I75027704"]}]}],"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":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11","last_page":"14"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9991999864578247,"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"}},{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.9986000061035156,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.8307408690452576},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8182932138442993},{"id":"https://openalex.org/keywords/qr-decomposition","display_name":"QR decomposition","score":0.7196670770645142},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6585180759429932},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5944271087646484},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.5845615863800049},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5775363445281982},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.5738509893417358},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.4690050780773163},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.46304255723953247},{"id":"https://openalex.org/keywords/soft-computing","display_name":"Soft computing","score":0.41469651460647583},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.41314369440078735},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.20938724279403687},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.12045636773109436},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.09544086456298828}],"concepts":[{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.8307408690452576},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8182932138442993},{"id":"https://openalex.org/C188060507","wikidata":"https://www.wikidata.org/wiki/Q653242","display_name":"QR decomposition","level":3,"score":0.7196670770645142},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6585180759429932},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5944271087646484},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.5845615863800049},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5775363445281982},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.5738509893417358},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.4690050780773163},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.46304255723953247},{"id":"https://openalex.org/C140073362","wikidata":"https://www.wikidata.org/wiki/Q738759","display_name":"Soft computing","level":3,"score":0.41469651460647583},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.41314369440078735},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.20938724279403687},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.12045636773109436},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.09544086456298828},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2133173.2133179","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2133173.2133179","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the second workshop on Scalable algorithms for large-scale systems","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.637.6380","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.637.6380","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.netlib.org/lapack/lawnspdf/lawn252.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.818.4187","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.818.4187","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://web.eecs.utk.edu/%7Elibrary/TechReports/2011/ut-cs-11-675.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W179067477","https://openalex.org/W1560267277","https://openalex.org/W1569825195","https://openalex.org/W1583519197","https://openalex.org/W1750504612","https://openalex.org/W1760551737","https://openalex.org/W1969399184","https://openalex.org/W1981745143","https://openalex.org/W1982165439","https://openalex.org/W2004050974","https://openalex.org/W2016279572","https://openalex.org/W2031032655","https://openalex.org/W2039778940","https://openalex.org/W2042806004","https://openalex.org/W2061771449","https://openalex.org/W2073216164","https://openalex.org/W2073260424","https://openalex.org/W2083606889","https://openalex.org/W2083613288","https://openalex.org/W2087064525","https://openalex.org/W2087723190","https://openalex.org/W2089536264","https://openalex.org/W2091180845","https://openalex.org/W2099084006","https://openalex.org/W2117293168","https://openalex.org/W2123475473","https://openalex.org/W2123500455","https://openalex.org/W2146351362","https://openalex.org/W2150679822","https://openalex.org/W2152211247","https://openalex.org/W2162322364","https://openalex.org/W2167502740","https://openalex.org/W2256188683","https://openalex.org/W2260078122","https://openalex.org/W2296772319","https://openalex.org/W2798909945","https://openalex.org/W6692508180","https://openalex.org/W6750968397"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2080146221","https://openalex.org/W2945737145","https://openalex.org/W2370314112","https://openalex.org/W1912958759"],"abstract_inverted_index":{"The":[0],"general":[1],"purpose":[2],"graphics":[3,41],"processing":[4],"units":[5],"(GPGPU)":[6],"are":[7],"increasingly":[8],"deployed":[9],"for":[10,40,80,96,126],"scientific":[11],"computing":[12,51],"due":[13],"to":[14,32,114,121],"their":[15],"performance":[16,56,101],"advantages":[17],"over":[18],"CPUs.":[19],"As":[20],"a":[21,27,49,75,91,136],"result,":[22],"fault":[23,150],"tolerance":[24],"has":[25],"become":[26],"more":[28],"serious":[29],"concern":[30],"compared":[31],"the":[33,60,63,97,127,130,164],"period":[34],"when":[35],"GPGPUs":[36,113],"were":[37],"used":[38],"exclusively":[39],"applications.":[42],"Using":[43],"GPUs":[44],"and":[45,55,93,134,158],"CPUs":[46],"together":[47],"in":[48,163],"hybrid":[50,85,105,171],"system":[52],"increases":[53,59],"flexibility":[54],"but":[57],"also":[58],"possibility":[61],"of":[62,129],"computations":[64],"being":[65],"affected":[66],"by":[67],"soft":[68,76,161],"errors.":[69],"In":[70],"this":[71],"work,":[72],"we":[73],"propose":[74],"error":[77],"resilient":[78],"algorithm":[79,138],"QR":[81,141,152],"factorization":[82,153],"on":[83,104,112,140,143,170],"such":[84],"systems.":[86],"Our":[87],"contributions":[88],"include":[89],"(1)":[90],"checkpointing":[92],"recovery":[94,137],"mechanism":[95],"left-factor":[98],"Q":[99],"whose":[100],"is":[102],"scalable":[103],"systems;":[106],"(2)":[107],"optimized":[108],"Givens":[109],"rotation":[110],"utilities":[111],"efficiently":[115],"reduce":[116],"an":[117,122],"upper":[118,123],"Hessenberg":[119],"matrix":[120,166],"triangular":[124],"form":[125],"protection":[128],"right":[131],"factor":[132],"R,":[133],"(3)":[135],"based":[139],"update":[142],"GPGPUs.":[144,174],"Experimental":[145],"results":[146],"show":[147],"that":[148],"our":[149],"tolerant":[151],"can":[154],"success-":[155],"fully":[156],"detect":[157],"recover":[159],"from":[160],"errors":[162],"entire":[165],"with":[167,173],"little":[168],"overhead":[169],"systems":[172]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}