{"id":"https://openalex.org/W3157804741","doi":"https://doi.org/10.1007/s11227-021-03951-w","title":"Legio: fault resiliency for embarrassingly parallel MPI applications","display_name":"Legio: fault resiliency for embarrassingly parallel MPI applications","publication_year":2021,"publication_date":"2021-06-25","ids":{"openalex":"https://openalex.org/W3157804741","doi":"https://doi.org/10.1007/s11227-021-03951-w","mag":"3157804741"},"language":"en","primary_location":{"id":"doi:10.1007/s11227-021-03951-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11227-021-03951-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11227-021-03951-w.pdf","source":{"id":"https://openalex.org/S32326811","display_name":"The Journal of Supercomputing","issn_l":"0920-8542","issn":["0920-8542","1573-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of Supercomputing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11227-021-03951-w.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Roberto Rocco","orcid":"https://orcid.org/0000-0002-0223-2900"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Roberto Rocco","raw_affiliation_strings":["Dipartimento di Elettronica, Infomazione e Bioingegneria, Politecnico di Milano, Milan, Italy"],"affiliations":[{"raw_affiliation_string":"Dipartimento di Elettronica, Infomazione e Bioingegneria, Politecnico di Milano, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Davide Gadioli","orcid":null},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Davide Gadioli","raw_affiliation_strings":["Dipartimento di Elettronica, Infomazione e Bioingegneria, Politecnico di Milano, Milan, Italy"],"affiliations":[{"raw_affiliation_string":"Dipartimento di Elettronica, Infomazione e Bioingegneria, Politecnico di Milano, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"last","author":{"id":null,"display_name":"Gianluca Palermo","orcid":null},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Gianluca Palermo","raw_affiliation_strings":["Dipartimento di Elettronica, Infomazione e Bioingegneria, Politecnico di Milano, Milan, Italy"],"affiliations":[{"raw_affiliation_string":"Dipartimento di Elettronica, Infomazione e Bioingegneria, Politecnico di Milano, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I93860229"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":0.7964,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.73513361,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"78","issue":"2","first_page":"2175","last_page":"2195"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.8471999764442444,"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":0.8471999764442444,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.06849999725818634,"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":0.030300000682473183,"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/embarrassingly-parallel","display_name":"Embarrassingly parallel","score":0.7497000098228455},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6983000040054321},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6579999923706055},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5843999981880188},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.5285999774932861},{"id":"https://openalex.org/keywords/message-passing-interface","display_name":"Message Passing Interface","score":0.4447000026702881},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.4099000096321106},{"id":"https://openalex.org/keywords/computer-cluster","display_name":"Computer cluster","score":0.3779999911785126}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8860999941825867},{"id":"https://openalex.org/C126909462","wikidata":"https://www.wikidata.org/wiki/Q5369501","display_name":"Embarrassingly parallel","level":3,"score":0.7497000098228455},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6983000040054321},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6579999923706055},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5843999981880188},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5819000005722046},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5407999753952026},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.5285999774932861},{"id":"https://openalex.org/C166782233","wikidata":"https://www.wikidata.org/wiki/Q127879","display_name":"Message Passing Interface","level":3,"score":0.4447000026702881},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.4099000096321106},{"id":"https://openalex.org/C29140674","wikidata":"https://www.wikidata.org/wiki/Q206637","display_name":"Computer cluster","level":2,"score":0.3779999911785126},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.37439998984336853},{"id":"https://openalex.org/C175551986","wikidata":"https://www.wikidata.org/wiki/Q47089","display_name":"Fault (geology)","level":2,"score":0.33230000734329224},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.3052999973297119},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.29109999537467957},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.2849999964237213},{"id":"https://openalex.org/C19527686","wikidata":"https://www.wikidata.org/wiki/Q1665453","display_name":"System integration","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.25679999589920044},{"id":"https://openalex.org/C152745839","wikidata":"https://www.wikidata.org/wiki/Q5438153","display_name":"Fault detection and isolation","level":3,"score":0.2538999915122986}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/s11227-021-03951-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11227-021-03951-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11227-021-03951-w.pdf","source":{"id":"https://openalex.org/S32326811","display_name":"The Journal of Supercomputing","issn_l":"0920-8542","issn":["0920-8542","1573-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of Supercomputing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2104.14246","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.14246","pdf_url":"https://arxiv.org/pdf/2104.14246","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"},{"id":"pmh:oai:re.public.polimi.it:11311/1181619","is_oa":true,"landing_page_url":"http://hdl.handle.net/11311/1181619","pdf_url":"https://link.springer.com/article/10.1007/s11227-021-03951-w","source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1007/s11227-021-03951-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11227-021-03951-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11227-021-03951-w.pdf","source":{"id":"https://openalex.org/S32326811","display_name":"The Journal of Supercomputing","issn_l":"0920-8542","issn":["0920-8542","1573-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of Supercomputing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3157804741.pdf","grobid_xml":"https://content.openalex.org/works/W3157804741.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W31923072","https://openalex.org/W1576341769","https://openalex.org/W1592551687","https://openalex.org/W1972865626","https://openalex.org/W1978498449","https://openalex.org/W1986905947","https://openalex.org/W2017060126","https://openalex.org/W2021234574","https://openalex.org/W2031260715","https://openalex.org/W2105524676","https://openalex.org/W2117667603","https://openalex.org/W2128577831","https://openalex.org/W2170454619","https://openalex.org/W2285867394","https://openalex.org/W2403702746","https://openalex.org/W2488604781","https://openalex.org/W2643067049","https://openalex.org/W2891179284","https://openalex.org/W2963258975","https://openalex.org/W2964339509","https://openalex.org/W3002241702","https://openalex.org/W3006153736","https://openalex.org/W6638693640"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Due":[1],"to":[2,16,43,76],"the":[3,28,36,45,53,77,87,92,114,126,130,139],"increasing":[4],"size":[5],"of":[6,38,142],"HPC":[7],"machines,":[8],"dealing":[9],"with":[10,52,91,119],"faults":[11,24],"is":[12,41,132],"becoming":[13],"mandatory":[14],"due":[15],"their":[17],"high":[18],"frequency.":[19],"Natively,":[20],"MPI":[21,70],"cannot":[22],"handle":[23],"and":[25,121,134],"it":[26,32,40,48,135],"stops":[27],"execution":[29,88],"prematurely":[30],"when":[31],"finds":[33],"one.":[34],"With":[35],"introduction":[37],"ULFM,":[39],"possible":[42],"continue":[44],"execution,":[46],"but":[47],"requires":[49],"complex":[50],"integration":[51,82],"application.":[54],"In":[55],"this":[56],"paper":[57],"we":[58],"propose":[59,97],"Legio,":[60],"a":[61,85,98],"framework":[62],"that":[63,125],"introduces":[64],"fault":[65],"resiliency":[66],"in":[67],"embarrassingly":[68],"parallel":[69],"applications.":[71],"Legio":[72],"exposes":[73],"its":[74],"features":[75,102],"application":[78],"transparently,":[79],"removing":[80],"any":[81],"difficulty.":[83],"After":[84],"fault,":[86],"continues":[89],"only":[90],"non-failed":[93],"processes.":[94],"We":[95,109],"also":[96],"hierarchical":[99],"alternative,":[100],"which":[101],"lower":[103],"repair":[104],"costs":[105],"on":[106,113],"large":[107],"communicators.":[108],"evaluated":[110],"our":[111],"solutions":[112],"Marconi100":[115],"cluster":[116],"at":[117],"CINECA":[118],"benchmarks":[120],"real-world":[122],"applications,":[123],"showing":[124],"overhead":[127],"introduced":[128],"by":[129],"library":[131],"negligible":[133],"does":[136],"not":[137],"limit":[138],"scalability":[140],"properties":[141],"MPI.":[143]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2021-05-10T00:00:00"}
