{"id":"https://openalex.org/W2079499440","doi":"https://doi.org/10.1145/2530268.2530271","title":"A study of application-level recovery methods for transient network faults","display_name":"A study of application-level recovery methods for transient network faults","publication_year":2013,"publication_date":"2013-10-29","ids":{"openalex":"https://openalex.org/W2079499440","doi":"https://doi.org/10.1145/2530268.2530271","mag":"2079499440"},"language":"en","primary_location":{"id":"doi:10.1145/2530268.2530271","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2530268.2530271","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/biblio/1113406","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033868370","display_name":"Ignacio Laguna","orcid":"https://orcid.org/0000-0002-9374-4433"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ignacio Laguna","raw_affiliation_strings":["Lawrence Livermore National Laboratory"],"affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005644355","display_name":"Edgar A. Le\u00f3n","orcid":"https://orcid.org/0000-0001-5805-9046"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Edgar A. Le\u00f3n","raw_affiliation_strings":["Lawrence Livermore National Laboratory"],"affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045289712","display_name":"Martin Schulz","orcid":"https://orcid.org/0000-0001-9013-435X"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Martin Schulz","raw_affiliation_strings":["Lawrence Livermore National Laboratory"],"affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015391591","display_name":"Mark W. Stephenson","orcid":"https://orcid.org/0000-0002-1350-0165"},"institutions":[{"id":"https://openalex.org/I4210156936","display_name":"IBM Research - Austin","ror":"https://ror.org/05gjbbg60","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210156936"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Stephenson","raw_affiliation_strings":["IBM Research Austin","IBM Research - Austin"],"affiliations":[{"raw_affiliation_string":"IBM Research Austin","institution_ids":["https://openalex.org/I4210156936"]},{"raw_affiliation_string":"IBM Research - Austin","institution_ids":["https://openalex.org/I4210156936"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5033868370"],"corresponding_institution_ids":["https://openalex.org/I1282311441"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13875969,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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/T11181","display_name":"Advanced Data Storage Technologies","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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9991999864578247,"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":0.7555969953536987},{"id":"https://openalex.org/keywords/network-packet","display_name":"Network packet","score":0.6406160593032837},{"id":"https://openalex.org/keywords/transient","display_name":"Transient (computer programming)","score":0.5872763991355896},{"id":"https://openalex.org/keywords/fast-fourier-transform","display_name":"Fast Fourier transform","score":0.5002009868621826},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4610307812690735},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.46023938059806824},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.45428773760795593},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3981148302555084},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3914961516857147},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.19130316376686096},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10992425680160522}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7555969953536987},{"id":"https://openalex.org/C158379750","wikidata":"https://www.wikidata.org/wiki/Q214111","display_name":"Network packet","level":2,"score":0.6406160593032837},{"id":"https://openalex.org/C2780799671","wikidata":"https://www.wikidata.org/wiki/Q17087362","display_name":"Transient (computer programming)","level":2,"score":0.5872763991355896},{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.5002009868621826},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4610307812690735},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.46023938059806824},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.45428773760795593},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3981148302555084},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3914961516857147},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.19130316376686096},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10992425680160522},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2530268.2530271","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2530268.2530271","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems","raw_type":"proceedings-article"},{"id":"pmh:info:ark/67531/metadc869207","is_oa":false,"landing_page_url":"https://digital.library.unt.edu/ark:/67531/metadc869207/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400792","display_name":"University of North Texas Digital Library (University of North Texas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I123534392","host_organization_name":"University of North Texas","host_organization_lineage":["https://openalex.org/I123534392"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Presented at: The International Conference for High Performance Computing, Networking, Storage and Analysis, Denver, CO, United States, Nov 17 - Nov 22, 2013","raw_type":"Article"},{"id":"pmh:oai:osti.gov:1113406","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1113406","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"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":null}],"best_oa_location":{"id":"pmh:oai:osti.gov:1113406","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1113406","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"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":null},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320338286","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W166766737","https://openalex.org/W775605853","https://openalex.org/W1486339539","https://openalex.org/W1573592400","https://openalex.org/W1884915318","https://openalex.org/W2002037063","https://openalex.org/W2012307454","https://openalex.org/W2019465613","https://openalex.org/W2036641664","https://openalex.org/W2042544282","https://openalex.org/W2048431618","https://openalex.org/W2061171222","https://openalex.org/W2076424788","https://openalex.org/W2082490936","https://openalex.org/W2083613288","https://openalex.org/W2097946733","https://openalex.org/W2102182691","https://openalex.org/W2106263082","https://openalex.org/W2115252128","https://openalex.org/W2122527617","https://openalex.org/W2123500455","https://openalex.org/W2126969025","https://openalex.org/W2130449268","https://openalex.org/W2158512617","https://openalex.org/W2168260026","https://openalex.org/W2952753488","https://openalex.org/W6639576536"],"related_works":["https://openalex.org/W4327521644","https://openalex.org/W2978884468","https://openalex.org/W3132558499","https://openalex.org/W2005846134","https://openalex.org/W2168413811","https://openalex.org/W2369237035","https://openalex.org/W2948041274","https://openalex.org/W4226515754","https://openalex.org/W2087878472","https://openalex.org/W2322333442"],"abstract_inverted_index":{"With":[0],"the":[1,31,62,94,107,130],"increasing":[2],"number":[3],"of":[4,33,96],"components":[5],"in":[6,100,136,141],"HPC":[7,87],"systems,":[8],"transient":[9,16,58],"faults":[10,60,125],"will":[11],"become":[12],"commonplace.":[13],"Today,":[14],"network":[15,23,59,81,124],"faults,":[17],"such":[18],"as":[19,116,118],"lost":[20],"or":[21,69],"corrupted":[22,70],"packets,":[24],"are":[25],"addressed":[26],"by":[27],"middleware":[28],"libraries":[29],"at":[30,61,129],"cost":[32],"high":[34],"memory":[35],"usage":[36],"and":[37,89],"packet":[38],"retransmissions.":[39],"These":[40,65],"costs,":[41],"however,":[42],"can":[43,114,126],"be":[44,115,127],"eliminated":[45],"using":[46,80],"application-level":[47],"fault":[48,78,82],"tolerance.":[49],"In":[50],"this":[51],"paper,":[52],"we":[53],"propose":[54],"recovery":[55],"methods":[56,66,99],"for":[57,111],"application":[63,131],"level.":[64],"reconstruct":[67],"missing":[68],"data":[71],"via":[72],"interpolation.":[73],"We":[74,104],"derive":[75],"a":[76,85],"realistic":[77],"model":[79],"rates":[83],"from":[84],"production":[86],"cluster":[88],"use":[90],"it":[91],"to":[92],"demonstrate":[93],"effectiveness":[95],"our":[97],"reconstruction":[98],"an":[101],"FFT":[102,112],"kernel.":[103],"found":[105],"that":[106,123,138],"normalized":[108],"root-mean-square":[109],"error":[110],"computations":[113],"low":[117,134],"0.1%":[119],"and,":[120],"thus,":[121],"demonstrates":[122],"handled":[128],"level":[132],"with":[133],"perturbation":[135],"applications":[137],"have":[139],"smoothness":[140],"their":[142],"computed":[143],"data.":[144]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}