{"id":"https://openalex.org/W4388581172","doi":"https://doi.org/10.1145/3624062.3624117","title":"Dynamic Selective Protection of Sparse Iterative Solvers via ML Prediction of Soft Error Impacts","display_name":"Dynamic Selective Protection of Sparse Iterative Solvers via ML Prediction of Soft Error Impacts","publication_year":2023,"publication_date":"2023-11-10","ids":{"openalex":"https://openalex.org/W4388581172","doi":"https://doi.org/10.1145/3624062.3624117"},"language":"en","primary_location":{"id":"doi:10.1145/3624062.3624117","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3624062.3624117","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3624062.3624117","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3624062.3624117","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102989092","display_name":"Zizhao Chen","orcid":"https://orcid.org/0009-0007-0364-9146"},"institutions":[{"id":"https://openalex.org/I146416000","display_name":"University of Kansas","ror":"https://ror.org/001tmjg57","country_code":"US","type":"education","lineage":["https://openalex.org/I146416000"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zizhao Chen","raw_affiliation_strings":["University of Kansas, United States of America"],"raw_orcid":"https://orcid.org/0009-0007-0364-9146","affiliations":[{"raw_affiliation_string":"University of Kansas, United States of America","institution_ids":["https://openalex.org/I146416000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093240756","display_name":"Thomas Verrecchia","orcid":"https://orcid.org/0009-0005-1131-769X"},"institutions":[{"id":"https://openalex.org/I201181511","display_name":"\u00c9cole Nationale Sup\u00e9rieure de Techniques Avanc\u00e9es","ror":"https://ror.org/0309cs235","country_code":"FR","type":"education","lineage":["https://openalex.org/I201181511","https://openalex.org/I4210145102"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Thomas Verrecchia","raw_affiliation_strings":["National Institute of Advanced Technology (ENSTA Paris), France"],"raw_orcid":"https://orcid.org/0009-0005-1131-769X","affiliations":[{"raw_affiliation_string":"National Institute of Advanced Technology (ENSTA Paris), France","institution_ids":["https://openalex.org/I201181511"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076659753","display_name":"Hongyang Sun","orcid":"https://orcid.org/0000-0002-4379-4467"},"institutions":[{"id":"https://openalex.org/I146416000","display_name":"University of Kansas","ror":"https://ror.org/001tmjg57","country_code":"US","type":"education","lineage":["https://openalex.org/I146416000"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongyang Sun","raw_affiliation_strings":["University of Kansas, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-4379-4467","affiliations":[{"raw_affiliation_string":"University of Kansas, United States of America","institution_ids":["https://openalex.org/I146416000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045644763","display_name":"Joshua Dennis Booth","orcid":"https://orcid.org/0000-0001-7269-6367"},"institutions":[{"id":"https://openalex.org/I82495205","display_name":"University of Alabama in Huntsville","ror":"https://ror.org/02zsxwr40","country_code":"US","type":"education","lineage":["https://openalex.org/I82495205"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joshua Booth","raw_affiliation_strings":["University of Alabama in Huntsville, United States of America"],"raw_orcid":"https://orcid.org/0000-0001-7269-6367","affiliations":[{"raw_affiliation_string":"University of Alabama in Huntsville, United States of America","institution_ids":["https://openalex.org/I82495205"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102868534","display_name":"Padma Raghavan","orcid":"https://orcid.org/0009-0002-6785-2112"},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Padma Raghavan","raw_affiliation_strings":["Vanderbilt University, United States of America"],"raw_orcid":"https://orcid.org/0009-0002-6785-2112","affiliations":[{"raw_affiliation_string":"Vanderbilt University, United States of America","institution_ids":["https://openalex.org/I200719446"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102989092"],"corresponding_institution_ids":["https://openalex.org/I146416000"],"apc_list":null,"apc_paid":null,"fwci":0.3408,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.66889438,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"488","last_page":"491"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9986000061035156,"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":0.9986000061035156,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9940999746322632,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9868999719619751,"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":0.7979944944381714},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.6936859488487244},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6853788495063782},{"id":"https://openalex.org/keywords/resilience","display_name":"Resilience (materials science)","score":0.660616397857666},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6398428678512573},{"id":"https://openalex.org/keywords/soft-error","display_name":"Soft error","score":0.5502526760101318},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.5122891664505005},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4859134256839752},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4811374247074127},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.4540442228317261},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.4478505551815033},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.42585843801498413},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3403892517089844},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.29900407791137695},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.14096596837043762},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09085461497306824},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07316550612449646}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7979944944381714},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.6936859488487244},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6853788495063782},{"id":"https://openalex.org/C2779585090","wikidata":"https://www.wikidata.org/wiki/Q3457762","display_name":"Resilience (materials science)","level":2,"score":0.660616397857666},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6398428678512573},{"id":"https://openalex.org/C154474529","wikidata":"https://www.wikidata.org/wiki/Q1658917","display_name":"Soft error","level":2,"score":0.5502526760101318},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.5122891664505005},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4859134256839752},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4811374247074127},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.4540442228317261},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.4478505551815033},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.42585843801498413},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3403892517089844},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29900407791137695},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.14096596837043762},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09085461497306824},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07316550612449646},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3624062.3624117","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3624062.3624117","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3624062.3624117","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3624062.3624117","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3624062.3624117","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3624062.3624117","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5534893117","display_name":null,"funder_award_id":"2135310","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/F4320309151","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4388581172.pdf","grobid_xml":"https://content.openalex.org/works/W4388581172.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W1506342804","https://openalex.org/W1584278023","https://openalex.org/W1965069357","https://openalex.org/W2004675401","https://openalex.org/W2035080386","https://openalex.org/W2128511938","https://openalex.org/W2148039812","https://openalex.org/W4233783938","https://openalex.org/W4298304654"],"related_works":["https://openalex.org/W2041615232","https://openalex.org/W975040225","https://openalex.org/W2186864281","https://openalex.org/W233983175","https://openalex.org/W2355089277","https://openalex.org/W2312486021","https://openalex.org/W1927459197","https://openalex.org/W2554735846","https://openalex.org/W2394408226","https://openalex.org/W3041678444"],"abstract_inverted_index":{"Soft":[0],"errors":[1,35,100],"occur":[2],"frequently":[3],"on":[4,120],"large":[5,141],"computing":[6],"platforms":[7],"due":[8],"to":[9,29,81,94,131,160,166],"the":[10,49,71,78,83,96,117,121,124,162],"increasing":[11],"scale":[12],"and":[13,24],"complexity":[14],"of":[15,98,105,116,123],"HPC":[16],"systems.":[17],"Various":[18],"resilience":[19,56,84,163],"techniques":[20],"(e.g.,":[21],"checkpointing,":[22],"ABFT,":[23],"replication)":[25],"have":[26],"been":[27],"proposed":[28],"protect":[30,133],"scientific":[31],"applications":[32],"from":[33],"soft":[34,99,147],"at":[36,77,113],"different":[37,103,114],"levels.":[38],"Among":[39],"them,":[40],"system-level":[41],"replication":[42],"often":[43],"involves":[44],"duplicating":[45],"or":[46],"even":[47],"triplicating":[48],"entire":[50],"computation,":[51],"thus":[52],"resulting":[53],"in":[54,68,139],"high":[55],"overhead.":[57,85],"This":[58],"paper":[59],"proposes":[60],"dynamic":[61,129,155],"selective":[62],"protection":[63,156],"for":[64,70],"sparse":[65,110],"iterative":[66],"solvers,":[67],"particular":[69],"Preconditioned":[72],"Conjugate":[73],"Gradient":[74],"(PCG)":[75],"solver,":[76],"system":[79],"level":[80],"reduce":[82,161],"For":[86],"this":[87],"method,":[88],"we":[89,126],"leverage":[90],"machine":[91],"learning":[92],"(ML)":[93],"predict":[95],"impact":[97],"that":[101,136,153],"strike":[102],"elements":[104,135],"a":[106,128,140],"key":[107],"computation":[108],"(i.e.,":[109],"matrix-vector":[111],"multiplication)":[112],"iterations":[115],"solver.":[118],"Based":[119],"result":[122,138],"prediction,":[125],"design":[127],"strategy":[130,157],"selectively":[132],"those":[134],"would":[137],"performance":[142],"degradation":[143],"if":[144],"struck":[145],"by":[146],"errors.":[148],"An":[149],"experimental":[150],"evaluation":[151],"demonstrates":[152],"our":[154],"is":[158],"able":[159],"overhead":[164],"compared":[165],"existing":[167],"algorithms.":[168]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}