{"id":"https://openalex.org/W2994731315","doi":"https://doi.org/10.1137/1.9781611976137.8","title":"Scalable Resilience Against Node Failures for Communication-Hiding Preconditioned Conjugate Gradient and Conjugate Residual Methods","display_name":"Scalable Resilience Against Node Failures for Communication-Hiding Preconditioned Conjugate Gradient and Conjugate Residual Methods","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W2994731315","doi":"https://doi.org/10.1137/1.9781611976137.8","mag":"2994731315"},"language":"en","primary_location":{"id":"doi:10.1137/1.9781611976137.8","is_oa":true,"landing_page_url":"https://doi.org/10.1137/1.9781611976137.8","pdf_url":"https://epubs.siam.org/doi/pdf/10.1137/1.9781611976137.8","source":{"id":"https://openalex.org/S4306463922","display_name":"Society for Industrial and Applied Mathematics eBooks","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"ebook platform"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 SIAM Conference on Parallel Processing for Scientific Computing","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://epubs.siam.org/doi/pdf/10.1137/1.9781611976137.8","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021445517","display_name":"Markus Levonyak","orcid":"https://orcid.org/0000-0002-5131-6318"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Markus Levonyak","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046065987","display_name":"Christina Pacher","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christina Pacher","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5021065276","display_name":"Wilfried N. Gansterer","orcid":"https://orcid.org/0000-0001-5170-1251"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wilfried N. Gansterer","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5021445517"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0987,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.78796277,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"81","last_page":"92"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10720","display_name":"Complexity and Algorithms in Graphs","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/scalability","display_name":"Scalability","score":0.8603599071502686},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7953990697860718},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6903638243675232},{"id":"https://openalex.org/keywords/conjugate-gradient-method","display_name":"Conjugate gradient method","score":0.6861817836761475},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.6646748781204224},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.6335455179214478},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5489148497581482},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5328711867332458},{"id":"https://openalex.org/keywords/resilience","display_name":"Resilience (materials science)","score":0.5311236381530762},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5086880326271057},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.45405513048171997},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.36807623505592346},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3486735224723816},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.26133865118026733},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07285645604133606}],"concepts":[{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8603599071502686},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7953990697860718},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6903638243675232},{"id":"https://openalex.org/C81184566","wikidata":"https://www.wikidata.org/wiki/Q1191895","display_name":"Conjugate gradient method","level":2,"score":0.6861817836761475},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.6646748781204224},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.6335455179214478},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5489148497581482},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5328711867332458},{"id":"https://openalex.org/C2779585090","wikidata":"https://www.wikidata.org/wiki/Q3457762","display_name":"Resilience (materials science)","level":2,"score":0.5311236381530762},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5086880326271057},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.45405513048171997},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.36807623505592346},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3486735224723816},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26133865118026733},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07285645604133606},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1137/1.9781611976137.8","is_oa":true,"landing_page_url":"https://doi.org/10.1137/1.9781611976137.8","pdf_url":"https://epubs.siam.org/doi/pdf/10.1137/1.9781611976137.8","source":{"id":"https://openalex.org/S4306463922","display_name":"Society for Industrial and Applied Mathematics eBooks","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"ebook platform"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 SIAM Conference on Parallel Processing for Scientific Computing","raw_type":"book-chapter"},{"id":"pmh:oai:arXiv.org:1912.09230","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1912.09230","pdf_url":"https://arxiv.org/pdf/1912.09230","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1137/1.9781611976137.8","is_oa":true,"landing_page_url":"https://doi.org/10.1137/1.9781611976137.8","pdf_url":"https://epubs.siam.org/doi/pdf/10.1137/1.9781611976137.8","source":{"id":"https://openalex.org/S4306463922","display_name":"Society for Industrial and Applied Mathematics eBooks","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"ebook platform"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 SIAM Conference on Parallel Processing for Scientific Computing","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2994731315.pdf","grobid_xml":"https://content.openalex.org/works/W2994731315.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W9532344","https://openalex.org/W90568776","https://openalex.org/W138506437","https://openalex.org/W1506342804","https://openalex.org/W1507702133","https://openalex.org/W1565402953","https://openalex.org/W1569090332","https://openalex.org/W1907157228","https://openalex.org/W1968131776","https://openalex.org/W1985923806","https://openalex.org/W2029023406","https://openalex.org/W2035080386","https://openalex.org/W2037523067","https://openalex.org/W2038238534","https://openalex.org/W2039631162","https://openalex.org/W2066692739","https://openalex.org/W2080225225","https://openalex.org/W2084402884","https://openalex.org/W2096714979","https://openalex.org/W2128577831","https://openalex.org/W2138660187","https://openalex.org/W2148039812","https://openalex.org/W2155934041","https://openalex.org/W2179059335","https://openalex.org/W2316564661","https://openalex.org/W2399595040","https://openalex.org/W2466095195","https://openalex.org/W2520594231","https://openalex.org/W2559846188","https://openalex.org/W2561069372","https://openalex.org/W2562413630","https://openalex.org/W2577617996","https://openalex.org/W2658150166","https://openalex.org/W2783685059","https://openalex.org/W2792956195","https://openalex.org/W2888491088","https://openalex.org/W2897248362","https://openalex.org/W2905376222","https://openalex.org/W2914726413","https://openalex.org/W2920482256","https://openalex.org/W2924321664","https://openalex.org/W2945267784","https://openalex.org/W2963483698","https://openalex.org/W2964082713","https://openalex.org/W3000330907"],"related_works":["https://openalex.org/W2186864281","https://openalex.org/W2544771389","https://openalex.org/W2034060070","https://openalex.org/W4229957265","https://openalex.org/W4255427455","https://openalex.org/W2386899346","https://openalex.org/W3082608044","https://openalex.org/W2131505227","https://openalex.org/W2375597358","https://openalex.org/W1966025497"],"abstract_inverted_index":{"The":[0,124],"observed":[1],"and":[2,33,98,120],"expected":[3],"continued":[4],"growth":[5],"in":[6,11,49,180],"the":[7,34,50,63,78,88,95,108,165,169,174,181,199],"number":[8],"of":[9,36,52,80,100,110,135,168,187],"nodes":[10,141],"large-scale":[12],"parallel":[13,175],"computers":[14],"gives":[15],"rise":[16],"to":[17,29,74,94,128,139,198],"two":[18,99],"major":[19,26],"challenges:":[20],"global":[21],"communication":[22],"operations":[23],"are":[24,154],"becoming":[25],"bottlenecks":[27],"due":[28],"their":[30,117,122],"limited":[31],"scalability,":[32],"likelihood":[35],"node":[37,113,149],"failures":[38],"is":[39,127],"increasing.":[40],"We":[41,91],"study":[42],"an":[43],"approach":[44,189],"for":[45],"addressing":[46],"these":[47,81,151],"challenges":[48],"context":[51],"solving":[53],"large":[54],"sparse":[55],"linear":[56],"systems.":[57],"In":[58,83,146],"particular,":[59],"we":[60,86],"focus":[61],"on":[62,191],"pipelined":[64],"preconditioned":[65],"conjugate":[66],"gradient":[67],"(PPCG)":[68],"method,":[69],"which":[70,103,160],"has":[71],"been":[72],"shown":[73],"successfully":[75],"deal":[76],"with":[77,142],"first":[79],"challenges.":[82],"this":[84],"paper,":[85],"address":[87],"second":[89],"challenge.":[90],"present":[92],"extensions":[93],"PPCG":[96],"solver":[97,176],"its":[101],"variants":[102],"make":[104],"them":[105],"resilient":[106],"against":[107],"failure":[109,182],"a":[111,131,148,157],"compute":[112],"while":[114],"fully":[115],"preserving":[116],"communication-hiding":[118],"properties":[119],"thus":[121],"scalability.":[123],"basic":[125],"idea":[126],"efficiently":[129],"communicate":[130],"few":[132],"redundant":[133,152],"copies":[134,153],"local":[136],"vector":[137],"elements":[138],"neighboring":[140],"very":[143,193],"little":[144],"overhead.":[145],"case":[147],"fails,":[150],"gathered":[155],"at":[156,212],"replacement":[158],"node,":[159],"can":[161,177,209],"then":[162],"accurately":[163],"reconstruct":[164],"lost":[166],"parts":[167],"solver's":[170],"state.":[171],"After":[172],"that,":[173],"continue":[178],"as":[179],"free":[183],"scenario.":[184],"Experimental":[185],"evaluations":[186],"our":[188],"illustrate":[190],"average":[192],"low":[194,213],"runtime":[195],"overheads":[196],"compared":[197],"standard":[200],"non-resilient":[201],"algorithms.":[202],"This":[203],"shows":[204],"that":[205],"scalable":[206],"algorithmic":[207],"resilience":[208],"be":[210],"achieved":[211],"extra":[214],"cost.":[215]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2019-12-26T00:00:00"}