{"id":"https://openalex.org/W2007024473","doi":"https://doi.org/10.1145/2503210.2503249","title":"Parallel reduction to hessenberg form with algorithm-based fault tolerance","display_name":"Parallel reduction to hessenberg form with algorithm-based fault tolerance","publication_year":2013,"publication_date":"2013-10-30","ids":{"openalex":"https://openalex.org/W2007024473","doi":"https://doi.org/10.1145/2503210.2503249","mag":"2007024473"},"language":"en","primary_location":{"id":"doi:10.1145/2503210.2503249","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2503210.2503249","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":"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/A5108555267","display_name":"Yulu Jia","orcid":null},"institutions":[{"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":"Yulu Jia","raw_affiliation_strings":["University of Tennessee, Knoxville"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee, Knoxville","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010055736","display_name":"George Bosilca","orcid":"https://orcid.org/0000-0003-2411-8495"},"institutions":[{"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":"George Bosilca","raw_affiliation_strings":["University of Tennessee, Knoxville"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee, Knoxville","institution_ids":["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/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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee, Knoxville","institution_ids":["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/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/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 J. Dongarra","raw_affiliation_strings":["University of Tennessee, Knoxville, Oak Ridge National Laboratory and University of Manchester"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee, Knoxville, Oak Ridge National Laboratory and University of Manchester","institution_ids":["https://openalex.org/I1289243028","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":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9991000294685364,"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":0.9991000294685364,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9970999956130981,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9962999820709229,"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/computer-science","display_name":"Computer science","score":0.8319933414459229},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.7155194878578186},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.68109530210495},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5879490971565247},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.5674921274185181},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5656692385673523},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5631086230278015},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5064746141433716},{"id":"https://openalex.org/keywords/checksum","display_name":"Checksum","score":0.4813733398914337},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4686811566352844},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3948568105697632},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10481402277946472},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08389011025428772}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8319933414459229},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.7155194878578186},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.68109530210495},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5879490971565247},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.5674921274185181},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5656692385673523},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5631086230278015},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5064746141433716},{"id":"https://openalex.org/C162372511","wikidata":"https://www.wikidata.org/wiki/Q218341","display_name":"Checksum","level":2,"score":0.4813733398914337},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4686811566352844},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3948568105697632},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10481402277946472},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08389011025428772},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2503210.2503249","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2503210.2503249","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.421.7562","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.421.7562","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/utk/people/JackDongarra/PAPERS/ft_hess.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1198362632","display_name":null,"funder_award_id":"0904952, 1063019","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W28511425","https://openalex.org/W48112945","https://openalex.org/W94439627","https://openalex.org/W155647330","https://openalex.org/W1480928214","https://openalex.org/W1544423579","https://openalex.org/W1608412409","https://openalex.org/W1695243693","https://openalex.org/W1875298896","https://openalex.org/W1939822385","https://openalex.org/W1966287322","https://openalex.org/W1976169918","https://openalex.org/W1977847708","https://openalex.org/W1981265672","https://openalex.org/W1982165439","https://openalex.org/W1995854415","https://openalex.org/W1996934732","https://openalex.org/W2013737143","https://openalex.org/W2025631352","https://openalex.org/W2039778940","https://openalex.org/W2049790251","https://openalex.org/W2050873083","https://openalex.org/W2066636486","https://openalex.org/W2071237893","https://openalex.org/W2072072075","https://openalex.org/W2073216164","https://openalex.org/W2078152929","https://openalex.org/W2079925720","https://openalex.org/W2083613288","https://openalex.org/W2087263172","https://openalex.org/W2089536264","https://openalex.org/W2096504919","https://openalex.org/W2097178696","https://openalex.org/W2105524676","https://openalex.org/W2123500455","https://openalex.org/W2132914434","https://openalex.org/W2137787140","https://openalex.org/W2138660187","https://openalex.org/W2145670264","https://openalex.org/W2151801080","https://openalex.org/W2158344138","https://openalex.org/W2162739943","https://openalex.org/W2163295644","https://openalex.org/W2169631286","https://openalex.org/W2173738636","https://openalex.org/W2184298889","https://openalex.org/W2189441933","https://openalex.org/W2271295020","https://openalex.org/W2296772319","https://openalex.org/W2481759777","https://openalex.org/W2505619928","https://openalex.org/W2531455017","https://openalex.org/W2724752491","https://openalex.org/W2798909945","https://openalex.org/W2913825273","https://openalex.org/W3006153736","https://openalex.org/W3022136271","https://openalex.org/W4229666556","https://openalex.org/W4231150350","https://openalex.org/W4380434592","https://openalex.org/W6641625552","https://openalex.org/W6645511383","https://openalex.org/W6653932534","https://openalex.org/W6750968397"],"related_works":["https://openalex.org/W2064720525","https://openalex.org/W2567658269","https://openalex.org/W2111125783","https://openalex.org/W2123437881","https://openalex.org/W1862835629","https://openalex.org/W2136799148","https://openalex.org/W2897533804","https://openalex.org/W2890506991","https://openalex.org/W2412349256","https://openalex.org/W2098626762"],"abstract_inverted_index":{"This":[0],"paper":[1],"studies":[2],"the":[3,23,27,30,34,37,46,75,79,82,86,95,103,119,127,134,137,140,143],"resilience":[4],"of":[5,16,26,33,39,51,85,122,136,142],"a":[6,11,40,52,58,130],"two-sided":[7,18],"factorization":[8],"and":[9,29,44,48,81,90,117],"presents":[10],"generic":[12],"algorithm-based":[13],"approach":[14,35],"capable":[15],"making":[17],"factorizations":[19],"resilient.":[20],"We":[21,77,124],"establish":[22],"theoretical":[24],"proof":[25],"correctness":[28],"numerical":[31],"stability":[32],"in":[36,94],"context":[38],"Hessenberg":[41],"Reduction":[42],"(HR)":[43],"present":[45],"scalability":[47],"performance":[49],"results":[50],"practical":[53],"implementation.":[54],"Our":[55],"method":[56],"is":[57],"hybrid":[59],"algorithm":[60,112],"combining":[61],"an":[62],"Algorithm":[63],"Based":[64],"Fault":[65],"Tolerance":[66],"(ABFT)":[67],"technique":[68],"with":[69,88,98,102],"diskless":[70,99],"checkpointing":[71],"to":[72],"fully":[73],"protect":[74,78,91],"data.":[76],"trailing":[80],"initial":[83],"part":[84],"matrix":[87,138],"checksums,":[89],"finished":[92],"panels":[93],"panel":[96],"scope":[97],"checkpoints.":[100],"Compared":[101],"original":[104],"HR":[105],"(the":[106],"ScaLAPACK":[107],"PDGEHRD":[108],"routine)":[109],"our":[110],"fault-tolerant":[111],"introduces":[113],"very":[114],"little":[115],"overhead,":[116],"maintains":[118],"same":[120],"level":[121],"scalability.":[123],"prove":[125],"that":[126],"overhead":[128],"shows":[129],"decreasing":[131],"trend":[132],"as":[133],"size":[135,141],"or":[139],"process":[144],"grid":[145],"increases.":[146]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}