{"id":"https://openalex.org/W2399192584","doi":"https://doi.org/10.1177/1094342017694946","title":"Application-based fault tolerance techniques for sparse matrix solvers","display_name":"Application-based fault tolerance techniques for sparse matrix solvers","publication_year":2017,"publication_date":"2017-05-10","ids":{"openalex":"https://openalex.org/W2399192584","doi":"https://doi.org/10.1177/1094342017694946","mag":"2399192584"},"language":"en","primary_location":{"id":"doi:10.1177/1094342017694946","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342017694946","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research-information.bris.ac.uk/en/publications/2c2896b8-0cfa-438d-8d85-8f947bbdfbf9","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020200003","display_name":"Simon McIntosh\u2010Smith","orcid":"https://orcid.org/0000-0002-5312-0378"},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Simon McIntosh\u2013Smith","raw_affiliation_strings":["University of Bristol, UK"],"affiliations":[{"raw_affiliation_string":"University of Bristol, UK","institution_ids":["https://openalex.org/I36234482"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048520638","display_name":"Rob Hunt","orcid":null},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Rob Hunt","raw_affiliation_strings":["University of Bristol, UK"],"affiliations":[{"raw_affiliation_string":"University of Bristol, UK","institution_ids":["https://openalex.org/I36234482"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061141810","display_name":"James Price","orcid":"https://orcid.org/0000-0002-9439-9731"},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"James Price","raw_affiliation_strings":["University of Bristol, UK"],"affiliations":[{"raw_affiliation_string":"University of Bristol, UK","institution_ids":["https://openalex.org/I36234482"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049323096","display_name":"Alex Warwick Vesztrocy","orcid":"https://orcid.org/0000-0002-4074-4261"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alex Warwick Vesztrocy","raw_affiliation_strings":["University College London, UK"],"affiliations":[{"raw_affiliation_string":"University College London, UK","institution_ids":["https://openalex.org/I45129253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5020200003"],"corresponding_institution_ids":["https://openalex.org/I36234482"],"apc_list":null,"apc_paid":null,"fwci":0.4631,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.58826939,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"32","issue":"5","first_page":"627","last_page":"640"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9995999932289124,"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/T11005","display_name":"Radiation Effects in Electronics","score":0.9994999766349792,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9958000183105469,"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":0.7789711952209473},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.7395094633102417},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6751828193664551},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6011621356010437},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.5780534744262695},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5155637264251709},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4660540521144867},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.45902925729751587},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.43936747312545776},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4275902211666107},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.32716408371925354},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11058998107910156},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08628121018409729}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7789711952209473},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.7395094633102417},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6751828193664551},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6011621356010437},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.5780534744262695},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5155637264251709},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4660540521144867},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.45902925729751587},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.43936747312545776},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4275902211666107},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.32716408371925354},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11058998107910156},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08628121018409729},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"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/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1177/1094342017694946","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342017694946","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},{"id":"pmh:oai:research-information.bris.ac.uk:openaire_cris_publications/2c2896b8-0cfa-438d-8d85-8f947bbdfbf9","is_oa":true,"landing_page_url":"https://research-information.bris.ac.uk/en/publications/2c2896b8-0cfa-438d-8d85-8f947bbdfbf9","pdf_url":null,"source":{"id":"https://openalex.org/S4306400895","display_name":"Bristol Research (University of Bristol)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I36234482","host_organization_name":"University of Bristol","host_organization_lineage":["https://openalex.org/I36234482"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"McIntosh\u2013Smith, S, Hunt, R, Price, J & Vesztrocy, A W 2018, 'Application-based fault tolerance techniques for sparse matrix solvers', International Journal of High Performance Computing Applications, vol. 32, no. 5, pp. 627-640. https://doi.org/10.1177/1094342017694946","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:research-information.bris.ac.uk:publications/2c2896b8-0cfa-438d-8d85-8f947bbdfbf9","is_oa":false,"landing_page_url":"https://hdl.handle.net/1983/2c2896b8-0cfa-438d-8d85-8f947bbdfbf9","pdf_url":null,"source":{"id":"https://openalex.org/S4306400895","display_name":"Bristol Research (University of Bristol)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I36234482","host_organization_name":"University of Bristol","host_organization_lineage":["https://openalex.org/I36234482"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:research-information.bris.ac.uk:openaire_cris_publications/2c2896b8-0cfa-438d-8d85-8f947bbdfbf9","is_oa":true,"landing_page_url":"https://research-information.bris.ac.uk/en/publications/2c2896b8-0cfa-438d-8d85-8f947bbdfbf9","pdf_url":null,"source":{"id":"https://openalex.org/S4306400895","display_name":"Bristol Research (University of Bristol)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I36234482","host_organization_name":"University of Bristol","host_organization_lineage":["https://openalex.org/I36234482"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"McIntosh\u2013Smith, S, Hunt, R, Price, J & Vesztrocy, A W 2018, 'Application-based fault tolerance techniques for sparse matrix solvers', International Journal of High Performance Computing Applications, vol. 32, no. 5, pp. 627-640. https://doi.org/10.1177/1094342017694946","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.8999999761581421,"display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G6581378985","display_name":null,"funder_award_id":"610402","funder_id":"https://openalex.org/F4320334960","funder_display_name":"Seventh Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"},{"id":"https://openalex.org/F4320334960","display_name":"Seventh Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1506342804","https://openalex.org/W1583519197","https://openalex.org/W1897941323","https://openalex.org/W1967835393","https://openalex.org/W1980073965","https://openalex.org/W1981194937","https://openalex.org/W1981432246","https://openalex.org/W2031260715","https://openalex.org/W2033346530","https://openalex.org/W2033943015","https://openalex.org/W2035080386","https://openalex.org/W2074673023","https://openalex.org/W2104679543","https://openalex.org/W2105524676","https://openalex.org/W2117485913","https://openalex.org/W2120591095","https://openalex.org/W2122249806","https://openalex.org/W2162457113","https://openalex.org/W2187348494","https://openalex.org/W2342204193","https://openalex.org/W2471965769","https://openalex.org/W2751243270","https://openalex.org/W4300557244"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W4312814274","https://openalex.org/W1862835629","https://openalex.org/W2099111379","https://openalex.org/W2136799148","https://openalex.org/W2897533804","https://openalex.org/W2890506991"],"abstract_inverted_index":{"High-performance":[0],"computing":[1,58],"systems":[2,43],"continue":[3,103],"to":[4,34,47,102,104,152,173,187],"increase":[5],"in":[6,8,25,40,55,161,182],"size":[7],"the":[9,23,29,61,80,155,177,189,197],"quest":[10],"for":[11],"ever":[12],"higher":[13],"performance.":[14],"The":[15],"resulting":[16],"increased":[17,83],"electronic":[18],"component":[19],"count,":[20],"coupled":[21],"with":[22,133],"decrease":[24],"feature":[26],"sizes":[27],"of":[28,63,73,82,117,122,124,154,159,176,179,196],"silicon":[30],"manufacturing":[31],"processes":[32],"used":[33],"build":[35],"these":[36,74,100,112],"components,":[37],"may":[38],"result":[39],"future":[41],"exascale":[42],"being":[44],"more":[45,134],"susceptible":[46],"soft":[48],"errors":[49],"caused":[50],"by":[51],"cosmic":[52],"radiation":[53],"than":[54],"current":[56],"high-performance":[57,162],"systems.":[59],"Through":[60],"use":[62],"techniques":[64,147,170],"such":[65,183],"as":[66,93,95,186],"hardware-based":[67],"error-correcting":[68],"codes":[69],"and":[70,87,120,193],"checkpoint-restart,":[71],"many":[72],"faults":[75],"can":[76,91,149],"be":[77,92,131,150],"mitigated":[78],"at":[79],"cost":[81],"hardware":[84,126],"overhead,":[85],"run-time,":[86],"energy":[88,191],"consumption":[89,119],"that":[90,148],"much":[94],"10\u201320%.":[96],"Some":[97],"predictions":[98],"expect":[99],"overheads":[101,113],"grow":[105],"over":[106],"time.":[107],"For":[108],"extreme":[109],"scale":[110],"systems,":[111],"will":[114],"represent":[115],"megawatts":[116],"power":[118],"millions":[121],"dollars":[123],"additional":[125],"costs,":[127],"which":[128],"could":[129],"potentially":[130],"avoided":[132],"sophisticated":[135],"fault-tolerance":[136],"techniques.":[137],"In":[138],"this":[139],"paper":[140],"we":[141],"present":[142],"new":[143,169],"software-based":[144],"fault":[145,194],"tolerance":[146,195],"applied":[151],"one":[153],"most":[156],"important":[157],"classes":[158],"software":[160],"computing:":[163],"iterative":[164],"sparse":[165,180],"matrix":[166],"solvers.":[167],"Our":[168],"enables":[171],"us":[172],"exploit":[174],"knowledge":[175],"structure":[178],"matrices":[181],"a":[184],"way":[185],"improve":[188],"performance,":[190],"efficiency,":[192],"overall":[198],"solution.":[199]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
