{"id":"https://openalex.org/W2108095339","doi":"https://doi.org/10.1109/ipdps.2004.1302920","title":"Architecture of LA-MPI, a network-fault-tolerant MPI","display_name":"Architecture of LA-MPI, a network-fault-tolerant MPI","publication_year":2004,"publication_date":"2004-06-10","ids":{"openalex":"https://openalex.org/W2108095339","doi":"https://doi.org/10.1109/ipdps.2004.1302920","mag":"2108095339"},"language":"en","primary_location":{"id":"doi:10.1109/ipdps.2004.1302920","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2004.1302920","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"18th International Parallel and Distributed Processing Symposium, 2004. Proceedings.","raw_type":"proceedings-article"},"type":"conference-paper","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/A5024254559","display_name":"Rob Aulwes","orcid":"https://orcid.org/0000-0001-7291-1135"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"R.T. Aulwes","raw_affiliation_strings":["Advanced Computing Laboratory, Los Alamos National Laboratory, Los Alamos, NM, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Computing Laboratory, Los Alamos National Laboratory, Los Alamos, NM, USA","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089304007","display_name":"David Daniel","orcid":"https://orcid.org/0000-0002-4873-6856"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"D.J. Daniel","raw_affiliation_strings":["Advanced Computing Laboratory, Los Alamos National Laboratory, Los Alamos, NM, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Computing Laboratory, Los Alamos National Laboratory, Los Alamos, NM, USA","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008466703","display_name":"Nehal Desai","orcid":null},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"N.N. Desai","raw_affiliation_strings":["Advanced Computing Laboratory, Los Alamos National Laboratory, Los Alamos, NM, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Computing Laboratory, Los Alamos National Laboratory, Los Alamos, NM, USA","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109559556","display_name":"Richard L. Graham","orcid":null},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"R.L. Graham","raw_affiliation_strings":["Advanced Computing Laboratory, Los Alamos National Laboratory, Los Alamos, NM, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Computing Laboratory, Los Alamos National Laboratory, Los Alamos, NM, USA","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024290404","display_name":"L. Dean Risinger","orcid":null},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"L.D. Risinger","raw_affiliation_strings":["Advanced Computing Laboratory, Los Alamos National Laboratory, Los Alamos, NM, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Computing Laboratory, Los Alamos National Laboratory, Los Alamos, NM, USA","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022737320","display_name":"Mark A. Taylor","orcid":"https://orcid.org/0000-0002-9267-2554"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M.A. Taylor","raw_affiliation_strings":["Advanced Computing Laboratory, Los Alamos National Laboratory, Los Alamos, NM, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Computing Laboratory, Los Alamos National Laboratory, Los Alamos, NM, USA","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111792288","display_name":"T.S. Woodall","orcid":null},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"T.S. Woodall","raw_affiliation_strings":["Advanced Computing Laboratory, Los Alamos National Laboratory, Los Alamos, NM, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Computing Laboratory, Los Alamos National Laboratory, Los Alamos, NM, USA","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051893100","display_name":"Mitchel W. Sukalski","orcid":null},"institutions":[{"id":"https://openalex.org/I192454743","display_name":"Sandia National Laboratories California","ror":"https://ror.org/058m7ey48","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1330989302","https://openalex.org/I192454743","https://openalex.org/I198811213","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M.W. Sukalski","raw_affiliation_strings":["High Performance Computing and Networking Research, Sandia National Laboratories, Livermore, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"High Performance Computing and Networking Research, Sandia National Laboratories, Livermore, CA, USA","institution_ids":["https://openalex.org/I192454743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.1199,"has_fulltext":false,"cited_by_count":59,"citation_normalized_percentile":{"value":0.94947696,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"la ur 3 939","issue":null,"first_page":"15","last_page":"24"},"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/T10715","display_name":"Distributed and Parallel Computing 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/T10772","display_name":"Distributed systems and fault tolerance","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.871637761592865},{"id":"https://openalex.org/keywords/message-passing-interface","display_name":"Message Passing Interface","score":0.7241796851158142},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.7014527320861816},{"id":"https://openalex.org/keywords/retransmission","display_name":"Retransmission","score":0.6626169681549072},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.6615851521492004},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.4977848529815674},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4552553594112396},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.44997817277908325},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4492841064929962},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.44782814383506775},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.4377230405807495},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3188554048538208},{"id":"https://openalex.org/keywords/network-packet","display_name":"Network packet","score":0.11464187502861023}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.871637761592865},{"id":"https://openalex.org/C166782233","wikidata":"https://www.wikidata.org/wiki/Q127879","display_name":"Message Passing Interface","level":3,"score":0.7241796851158142},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.7014527320861816},{"id":"https://openalex.org/C180611318","wikidata":"https://www.wikidata.org/wiki/Q7316902","display_name":"Retransmission","level":3,"score":0.6626169681549072},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.6615851521492004},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.4977848529815674},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4552553594112396},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.44997817277908325},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4492841064929962},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.44782814383506775},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.4377230405807495},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3188554048538208},{"id":"https://openalex.org/C158379750","wikidata":"https://www.wikidata.org/wiki/Q214111","display_name":"Network packet","level":2,"score":0.11464187502861023}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ipdps.2004.1302920","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2004.1302920","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"18th International Parallel and Distributed Processing Symposium, 2004. Proceedings.","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.98.3586","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.98.3586","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://public.lanl.gov/lampi/LA-UR-03-0939.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320338304","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W31923072","https://openalex.org/W1575350781","https://openalex.org/W1576341769","https://openalex.org/W1674145689","https://openalex.org/W2005867208","https://openalex.org/W2094526959","https://openalex.org/W2105039796","https://openalex.org/W2114676697","https://openalex.org/W2126071114","https://openalex.org/W2140332639","https://openalex.org/W2158479991","https://openalex.org/W2171453084","https://openalex.org/W3085209527","https://openalex.org/W4236546623","https://openalex.org/W4239022315","https://openalex.org/W6634580932"],"related_works":["https://openalex.org/W2124048060","https://openalex.org/W1902983110","https://openalex.org/W2378910916","https://openalex.org/W4386915331","https://openalex.org/W2086666199","https://openalex.org/W1511717675","https://openalex.org/W2366325093","https://openalex.org/W2498758832","https://openalex.org/W2154020360","https://openalex.org/W2133825528"],"abstract_inverted_index":{"Summary":[0],"form":[1],"only":[2],"given.":[3],"We":[4,50],"discuss":[5],"the":[6,11,54],"unique":[7],"architectural":[8],"elements":[9],"of":[10,41],"Los":[12],"Alamos":[13],"message":[14,69,73,83],"passing":[15],"interface":[16],"(LA-MPI),":[17],"a":[18],"high-performance,":[19],"network-fault-tolerant,":[20],"thread-safe":[21],"MPI":[22],"library.":[23],"LA-MPI":[24],"is":[25],"designed":[26],"for":[27],"use":[28],"on":[29],"terascale":[30],"clusters":[31],"which":[32],"are":[33,98],"inherently":[34],"unreliable":[35],"due":[36],"to":[37,58],"their":[38],"sheer":[39],"number":[40],"system":[42],"components":[43],"and":[44,48,71,90,92],"trade-offs":[45],"between":[46],"cost":[47],"performance.":[49],"examine":[51],"in":[52],"detail":[53],"design":[55],"concepts":[56],"used":[57],"implement":[59],"LA-MPI.":[60],"These":[61],"include":[62],"reliability":[63],"features,":[64,79],"such":[65,80],"as":[66,81],"application-level":[67],"checksumming,":[68],"retransmission,":[70],"automatic":[72],"rerouting.":[74],"Other":[75],"key":[76],"performance":[77],"enhancing":[78],"concurrent":[82],"routing":[84],"over":[85],"multiple,":[86],"diverse":[87],"network":[88],"adapters":[89],"protocols,":[91],"communication-specific":[93],"optimizations":[94],"(e.g.,":[95],"shared":[96],"memory)":[97],"examined.":[99]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
