{"id":"https://openalex.org/W2170551503","doi":"https://doi.org/10.1109/dsn.2003.1209930","title":"Low overhead fault tolerant networking in Myrinet","display_name":"Low overhead fault tolerant networking in Myrinet","publication_year":2004,"publication_date":"2004-06-22","ids":{"openalex":"https://openalex.org/W2170551503","doi":"https://doi.org/10.1109/dsn.2003.1209930","mag":"2170551503"},"language":"en","primary_location":{"id":"doi:10.1109/dsn.2003.1209930","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsn.2003.1209930","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 International Conference on Dependable Systems and Networks, 2003. Proceedings.","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://scholarworks.umass.edu/ece_faculty_pubs/840","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069610773","display_name":"Vijay Lakamraju","orcid":null},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"V. Lakamraju","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Massachusetts, Amherst, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Massachusetts, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055210733","display_name":"Israel Koren","orcid":"https://orcid.org/0000-0003-2741-7108"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"I. Koren","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Massachusetts, Amherst, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Massachusetts, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065555691","display_name":"C.M. Krishna","orcid":"https://orcid.org/0000-0002-6019-9125"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C.M. Krishna","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Massachusetts, Amherst, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Massachusetts, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":0.824,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.69730692,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"1388","issue":null,"first_page":"193","last_page":"202"},"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9998000264167786,"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/T11005","display_name":"Radiation Effects in Electronics","score":0.9997000098228455,"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/myrinet","display_name":"Myrinet","score":0.9571628570556641},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.6815345287322998},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6647787690162659},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6506931781768799},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.5358676910400391},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3594592213630676},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3495386242866516},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.2416352927684784},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.06795057654380798}],"concepts":[{"id":"https://openalex.org/C2780601250","wikidata":"https://www.wikidata.org/wiki/Q1863181","display_name":"Myrinet","level":3,"score":0.9571628570556641},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.6815345287322998},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6647787690162659},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6506931781768799},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.5358676910400391},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3594592213630676},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3495386242866516},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.2416352927684784},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.06795057654380798}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/dsn.2003.1209930","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsn.2003.1209930","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 International Conference on Dependable Systems and Networks, 2003. Proceedings.","raw_type":"proceedings-article"},{"id":"pmh:oai:scholarworks.umass.edu:ece_faculty_pubs-1765","is_oa":false,"landing_page_url":"https://scholarworks.umass.edu/ece_faculty_pubs/766","pdf_url":null,"source":{"id":"https://openalex.org/S4306402057","display_name":"Scholarworks (University of Massachusetts Amherst)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I24603500","host_organization_name":"University of Massachusetts Amherst","host_organization_lineage":["https://openalex.org/I24603500"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Electrical and Computer Engineering Faculty Publication Series","raw_type":"text"},{"id":"pmh:oai:scholarworks.umass.edu:ece_faculty_pubs-1839","is_oa":true,"landing_page_url":"https://scholarworks.umass.edu/ece_faculty_pubs/840","pdf_url":null,"source":{"id":"https://openalex.org/S4306402240","display_name":"ScholarWorks@UMassAmherst (University of Massachusetts Amherst)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I24603500","host_organization_name":"University of Massachusetts Amherst","host_organization_lineage":["https://openalex.org/I24603500"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Electrical and Computer Engineering Faculty Publication Series","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.13.3887","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.13.3887","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ecs.umass.edu/ece/realtime/publications/vijay-dsn03.ps","raw_type":"text"},{"id":"pmh:oai:scholarworks.umass.edu:20.500.14394/21464","is_oa":false,"landing_page_url":"https://hdl.handle.net/20.500.14394/21464","pdf_url":null,"source":{"id":"https://openalex.org/S4306402057","display_name":"Scholarworks (University of Massachusetts Amherst)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I24603500","host_organization_name":"University of Massachusetts Amherst","host_organization_lineage":["https://openalex.org/I24603500"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"published","raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:scholarworks.umass.edu:ece_faculty_pubs-1839","is_oa":true,"landing_page_url":"https://scholarworks.umass.edu/ece_faculty_pubs/840","pdf_url":null,"source":{"id":"https://openalex.org/S4306402240","display_name":"ScholarWorks@UMassAmherst (University of Massachusetts Amherst)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I24603500","host_organization_name":"University of Massachusetts Amherst","host_organization_lineage":["https://openalex.org/I24603500"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Electrical and Computer Engineering Faculty Publication Series","raw_type":"text"},"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1521734293","https://openalex.org/W2011979817","https://openalex.org/W2041406071","https://openalex.org/W2095793442","https://openalex.org/W2102061396","https://openalex.org/W2109369875","https://openalex.org/W2114728910","https://openalex.org/W2146986710","https://openalex.org/W2171000060","https://openalex.org/W3138410280","https://openalex.org/W4251681643"],"related_works":["https://openalex.org/W2095736716","https://openalex.org/W3129203603","https://openalex.org/W2016613184","https://openalex.org/W1862835629","https://openalex.org/W600313189","https://openalex.org/W2099111379","https://openalex.org/W2136799148","https://openalex.org/W2897533804","https://openalex.org/W2890506991","https://openalex.org/W1974101162"],"abstract_inverted_index":{"Emerging":[0],"networking":[1],"technologies":[2],"have":[3,8],"complex":[4],"network":[5,12,28,33,55,84],"interfaces":[6],"that":[7,82,93],"renewed":[9],"concerns":[10],"about":[11],"reliability.":[13],"In":[14],"this":[15,120],"paper,":[16],"we":[17],"present":[18],"an":[19],"effective":[20],"low-overhead":[21],"fault":[22,74,96,121],"tolerance":[23],"technique":[24,39],"to":[25,128],"recover":[26],"from":[27],"interface":[29,56],"failures,":[30],"more":[31],"particularly":[32],"processor":[34,85],"hangs.":[35,86],"We":[36],"demonstrate":[37],"the":[38,41,51,54,64,89,94,129],"in":[40,101],"context":[42],"of":[43,53,67,109],"Myrinet.":[44],"Fault":[45],"recovery":[46,97,122],"is":[47,76],"achieved":[48,100],"by":[49],"restoring":[50],"state":[52],"using":[57],"a":[58,79,106],"small":[59],"backup":[60],"copy":[61],"containing":[62],"just":[63,110],"right":[65],"amount":[66],"information":[68],"required":[69],"for":[70],"complete":[71,95],"recovery.":[72],"Our":[73],"detection":[75],"based":[77],"on":[78,88],"software":[80],"watchdog":[81],"detects":[83],"Results":[87],"Myrinet":[90],"platform":[91],"show":[92],"can":[98,123],"be":[99,124],"under":[102],"2sec":[103],"while":[104],"incurring":[105],"latency":[107],"overhead":[108],"1:5s":[111],"during":[112],"normal":[113],"operation.":[114],"The":[115],"paper":[116],"also":[117],"shows":[118],"how":[119],"made":[125],"completely":[126],"transparent":[127],"user.":[130]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}