{"id":"https://openalex.org/W4206472295","doi":"https://doi.org/10.1109/ipccc51483.2021.9679435","title":"Differential Shadowing: A Resilience Framework for Extreme-scale, Heterogeneous Environments with Non-Uniform Node Failure Distribution","display_name":"Differential Shadowing: A Resilience Framework for Extreme-scale, Heterogeneous Environments with Non-Uniform Node Failure Distribution","publication_year":2021,"publication_date":"2021-10-29","ids":{"openalex":"https://openalex.org/W4206472295","doi":"https://doi.org/10.1109/ipccc51483.2021.9679435"},"language":"en","primary_location":{"id":"doi:10.1109/ipccc51483.2021.9679435","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipccc51483.2021.9679435","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Performance, Computing, and Communications Conference (IPCCC)","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/A5111803498","display_name":"Longhao Li","orcid":"https://orcid.org/0009-0007-6280-6973"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Longhao Li","raw_affiliation_strings":["University of Pittsburgh,Department of Computer Science,Pittsburgh,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pittsburgh,Department of Computer Science,Pittsburgh,USA","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051806341","display_name":"Taieb Znati","orcid":"https://orcid.org/0000-0002-9389-3033"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Taieb Znati","raw_affiliation_strings":["University of Pittsburgh,Department of Computer Science,Pittsburgh,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pittsburgh,Department of Computer Science,Pittsburgh,USA","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038997010","display_name":"Rami Melhem","orcid":"https://orcid.org/0000-0001-6403-5446"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rami Melhem","raw_affiliation_strings":["University of Pittsburgh,Department of Computer Science,Pittsburgh,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pittsburgh,Department of Computer Science,Pittsburgh,USA","institution_ids":["https://openalex.org/I170201317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170201317"],"apc_list":null,"apc_paid":null,"fwci":0.1604,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.56370589,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9997000098228455,"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":0.9997000098228455,"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/T13553","display_name":"Age of Information Optimization","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"}},{"id":"https://openalex.org/T12288","display_name":"Optimization and Search Problems","score":0.9840999841690063,"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/resilience","display_name":"Resilience (materials science)","score":0.7255639433860779},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.6646599769592285},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.589367687702179},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5690908432006836},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4613044857978821},{"id":"https://openalex.org/keywords/differential","display_name":"Differential (mechanical device)","score":0.4593982398509979},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1288021206855774},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11546748876571655},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.11049529910087585},{"id":"https://openalex.org/keywords/aerospace-engineering","display_name":"Aerospace engineering","score":0.09988296031951904},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.07517692446708679}],"concepts":[{"id":"https://openalex.org/C2779585090","wikidata":"https://www.wikidata.org/wiki/Q3457762","display_name":"Resilience (materials science)","level":2,"score":0.7255639433860779},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.6646599769592285},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.589367687702179},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5690908432006836},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4613044857978821},{"id":"https://openalex.org/C93226319","wikidata":"https://www.wikidata.org/wiki/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.4593982398509979},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1288021206855774},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11546748876571655},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.11049529910087585},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.09988296031951904},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.07517692446708679},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipccc51483.2021.9679435","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipccc51483.2021.9679435","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Performance, Computing, and Communications Conference (IPCCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.9100000262260437,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W63848143","https://openalex.org/W1578105119","https://openalex.org/W1978807861","https://openalex.org/W1998221613","https://openalex.org/W2001219263","https://openalex.org/W2045271686","https://openalex.org/W2048085362","https://openalex.org/W2108434125","https://openalex.org/W2128577831","https://openalex.org/W2152465173","https://openalex.org/W2160779498","https://openalex.org/W2340533753","https://openalex.org/W2891179284","https://openalex.org/W2961595369","https://openalex.org/W2972188323","https://openalex.org/W3037298866","https://openalex.org/W4233976225"],"related_works":["https://openalex.org/W2284759612","https://openalex.org/W4402320089","https://openalex.org/W4378555281","https://openalex.org/W2953081822","https://openalex.org/W2752145644","https://openalex.org/W1887981150","https://openalex.org/W4229446828","https://openalex.org/W2016027324","https://openalex.org/W2884088167","https://openalex.org/W2004641193"],"abstract_inverted_index":{"Achieving":[0],"resilience":[1,37],"in":[2,125,132],"extreme-scale":[3,41],"environments,":[4,42,104],"while":[5,91],"minimizing":[6],"energy":[7,89,126],"consumption,":[8],"is":[9,61,65],"a":[10,33,62,66,87,135],"daunting":[11],"challenge.":[12],"At":[13],"extreme":[14],"scale,":[15],"however,":[16],"the":[17,148,151,155],"classic":[18],"checkpoint-restart":[19],"approach":[20],"or":[21],"replication":[22,52],"for":[23,40],"recovery":[24],"techniques":[25],"become":[26],"inadequate.":[27],"In":[28],"this":[29,59],"paper,":[30],"we":[31],"propose":[32],"novel":[34],"application-aware":[35],"elastic":[36],"model,":[38],"dShadowing,":[39],"as":[43],"an":[44],"efficient":[45],"and":[46,53,75,128,154,163],"scalable":[47],"alternative":[48],"to":[49,80,84,94,98,134,157],"checkpointing,":[50],"pure":[51],"re-execution.":[54],"The":[55,111,144],"basic":[56],"tenet":[57],"of":[58,68,150],"model":[60,117,138,153],"dShadow,":[63],"which":[64],"derivative":[67],"its":[69],"associated":[70],"main":[71],"process,":[72],"whose":[73],"functional":[74],"non-functional":[76],"attributes":[77],"are":[78],"derived":[79],"achieve":[81,119],"high":[82],"tolerance":[83],"failure,":[85],"at":[86,160],"minimum":[88],"cost,":[90],"closely":[92],"adhering":[93],"QoS":[95],"requirements.":[96],"Contrary":[97],"current":[99],"schemes,":[100],"dShadowing":[101,116,152],"assumes":[102],"heterogeneous":[103],"where":[105],"cores":[106,141],"fail":[107,142],"independently,":[108],"but":[109],"non-identically.":[110],"experiment\u2019s":[112],"results":[113,145],"show":[114],"that":[115,139],"can":[118],"on":[120],"average":[121],"over":[122],"20%":[123],"reduction":[124],"consumption":[127],"expected":[129],"completion":[130],"time,":[131],"comparison":[133],"baseline":[136],"shadowing":[137],"considers":[140],"uniformly.":[143],"also":[146],"demonstrate":[147],"flexibility":[149],"ability":[156],"tolerate":[158],"failure":[159],"scale":[161],"adaptively":[162],"efficiently.":[164]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}
