{"id":"https://openalex.org/W4413147049","doi":"https://doi.org/10.1109/ipdpsw66978.2025.00071","title":"Using Checkpoint Alteration to Gauge Fault Sensitivity of HPC Scientific Applications","display_name":"Using Checkpoint Alteration to Gauge Fault Sensitivity of HPC Scientific Applications","publication_year":2025,"publication_date":"2025-06-03","ids":{"openalex":"https://openalex.org/W4413147049","doi":"https://doi.org/10.1109/ipdpsw66978.2025.00071"},"language":"en","primary_location":{"id":"doi:10.1109/ipdpsw66978.2025.00071","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdpsw66978.2025.00071","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)","raw_type":"proceedings-article"},"type":"article","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/A5052774129","display_name":"Elvis Rojas","orcid":"https://orcid.org/0000-0002-4238-0908"},"institutions":[{"id":"https://openalex.org/I198243066","display_name":"Universidad Nacional","ror":"https://ror.org/01t466c14","country_code":"CR","type":"education","lineage":["https://openalex.org/I198243066"]}],"countries":["CR"],"is_corresponding":true,"raw_author_name":"Elvis Rojas","raw_affiliation_strings":["National University of Costa Rica"],"affiliations":[{"raw_affiliation_string":"National University of Costa Rica","institution_ids":["https://openalex.org/I198243066"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119282118","display_name":"Luis Carlos N. Todd","orcid":null},"institutions":[{"id":"https://openalex.org/I145372079","display_name":"Instituto Tecnol\u00f3gico de Costa Rica","ror":"https://ror.org/04zhrfn38","country_code":"CR","type":"education","lineage":["https://openalex.org/I145372079"]}],"countries":["CR"],"is_corresponding":false,"raw_author_name":"Luis Carlos N. Todd","raw_affiliation_strings":["Costa Rica Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Costa Rica Institute of Technology","institution_ids":["https://openalex.org/I145372079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046704108","display_name":"Esteban Meneses","orcid":"https://orcid.org/0000-0002-4307-6000"},"institutions":[{"id":"https://openalex.org/I145372079","display_name":"Instituto Tecnol\u00f3gico de Costa Rica","ror":"https://ror.org/04zhrfn38","country_code":"CR","type":"education","lineage":["https://openalex.org/I145372079"]}],"countries":["CR"],"is_corresponding":false,"raw_author_name":"Esteban Meneses","raw_affiliation_strings":["Costa Rica Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Costa Rica Institute of Technology","institution_ids":["https://openalex.org/I145372079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5052774129"],"corresponding_institution_ids":["https://openalex.org/I198243066"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27178996,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"453","last_page":"462"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.963100016117096,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.963100016117096,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.9563000202178955,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T11005","display_name":"Radiation Effects in Electronics","score":0.9541000127792358,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.6789140701293945},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5746961832046509},{"id":"https://openalex.org/keywords/gauge","display_name":"Gauge (firearms)","score":0.4589494466781616},{"id":"https://openalex.org/keywords/fault","display_name":"Fault (geology)","score":0.4570072591304779},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.37326768040657043},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.1826448142528534},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.1454494297504425},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14206603169441223},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.09691914916038513}],"concepts":[{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.6789140701293945},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5746961832046509},{"id":"https://openalex.org/C40976572","wikidata":"https://www.wikidata.org/wiki/Q2330873","display_name":"Gauge (firearms)","level":2,"score":0.4589494466781616},{"id":"https://openalex.org/C175551986","wikidata":"https://www.wikidata.org/wiki/Q47089","display_name":"Fault (geology)","level":2,"score":0.4570072591304779},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.37326768040657043},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.1826448142528534},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.1454494297504425},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14206603169441223},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.09691914916038513},{"id":"https://openalex.org/C165205528","wikidata":"https://www.wikidata.org/wiki/Q83371","display_name":"Seismology","level":1,"score":0.0},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipdpsw66978.2025.00071","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdpsw66978.2025.00071","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","score":0.7900000214576721,"display_name":"Climate action"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"The":[0,9,33,86,171],"impact":[1],"of":[2,12,46,63,82,89,129,139,158,184],"High":[3],"Performance":[4],"Computing":[5],"(HPC)":[6],"is":[7,56,84],"ubiquitous.":[8],"main":[10],"techniques":[11],"HPC":[13,64,122,159,175],"(advanced":[14],"computer":[15],"simulation,":[16],"sophisticated":[17],"generative":[18],"artificial":[19],"intelligence,":[20],"and":[21,31,119],"big-data":[22],"analytics)":[23],"have":[24,59],"been":[25],"successfully":[26],"applied":[27],"to":[28,42,58,71,74,114,161,179,189],"science,":[29],"engineering,":[30],"business.":[32],"rapid":[34],"progress":[35,62],"in":[36],"those":[37,101],"fields":[38],"permits":[39],"the":[40,79,92,95,137,140,151,156,185,190],"solution":[41],"highly":[43],"complex":[44],"problems":[45],"our":[47],"society.":[48],"To":[49],"maintain":[50],"a":[51,60,90,106,126,165],"fast-moving":[52],"innovation":[53],"rate,":[54],"it":[55],"fundamental":[57],"sustainable":[61],"infrastructure.":[65],"However,":[66,193],"large-scale":[67],"computers":[68],"are":[69,103,177,196],"prone":[70],"fail":[72],"due":[73],"several":[75],"factors.":[76],"For":[77,99],"one,":[78],"stark":[80],"number":[81],"components":[83,88,102],"gigantic.":[85],"more":[87,93,112],"system,":[91,141],"likely":[94],"system":[96],"will":[97,124],"fail.":[98],"another,":[100],"built":[104],"using":[105,164],"shrinking":[107],"feature":[108],"size,":[109],"making":[110],"them":[111],"sensitive":[113],"voltage":[115],"fluctuations,":[116],"high-energy":[117],"radiation,":[118],"temperature.":[120],"Future":[121],"systems":[123],"experiment":[125],"higher":[127],"rate":[128],"silent":[130],"data":[131],"corruption":[132],"(SDC),":[133],"faults":[134],"that":[135,174],"corrupt":[136],"state":[138],"but":[142],"does":[143],"not":[144],"necessarily":[145],"provoke":[146],"an":[147],"abrupt":[148],"error":[149],"on":[150],"system.":[152],"This":[153],"paper":[154],"examines":[155],"sensitivity":[157],"codes":[160],"bitflips":[162],"by":[163],"portable":[166],"mechanism":[167],"called":[168],"checkpoint":[169],"alteration.":[170],"results":[172],"show":[173],"applications":[176],"resilient":[178],"single-bit":[180],"errors,":[181],"showing":[182],"most":[183],"time":[186],"no":[187],"alteration":[188],"expected":[191],"results.":[192],"multiple-bit":[194],"errors":[195],"often":[197],"times":[198],"disastrous":[199],"for":[200],"executions.":[201]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}
