{"id":"https://openalex.org/W2127089909","doi":"https://doi.org/10.1109/clustr.2007.4629229","title":"Efficient offloading of collective communications in large-scale systems","display_name":"Efficient offloading of collective communications in large-scale systems","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W2127089909","doi":"https://doi.org/10.1109/clustr.2007.4629229","mag":"2127089909"},"language":"en","primary_location":{"id":"doi:10.1109/clustr.2007.4629229","is_oa":false,"landing_page_url":"https://doi.org/10.1109/clustr.2007.4629229","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE International Conference on Cluster Computing","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/A5008026936","display_name":"Jos\u00e9 Carlos Sancho","orcid":"https://orcid.org/0000-0002-6917-9155"},"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":"Jose Carlos Sancho","raw_affiliation_strings":["Performance and Architecture Laboratory (PAL), Computer Science for HPC (CCS-1), Los Alamos National Laboratory, NM, USA","Performance & Archit. Lab. (PAL), Los Alamos Nat. Lab., Los Alamos, NM"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Performance and Architecture Laboratory (PAL), Computer Science for HPC (CCS-1), Los Alamos National Laboratory, NM, USA","institution_ids":["https://openalex.org/I1343871089"]},{"raw_affiliation_string":"Performance & Archit. Lab. (PAL), Los Alamos Nat. Lab., Los Alamos, NM","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064935199","display_name":"Darren J. Kerbyson","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":"Darren J. Kerbyson","raw_affiliation_strings":["Performance and Architecture Laboratory (PAL), Computer Science for HPC (CCS-1), Los Alamos National Laboratory, NM, USA","Performance & Archit. Lab. (PAL), Los Alamos Nat. Lab., Los Alamos, NM"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Performance and Architecture Laboratory (PAL), Computer Science for HPC (CCS-1), Los Alamos National Laboratory, NM, USA","institution_ids":["https://openalex.org/I1343871089"]},{"raw_affiliation_string":"Performance & Archit. Lab. (PAL), Los Alamos Nat. Lab., Los Alamos, NM","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038062469","display_name":"Kevin Barker","orcid":"https://orcid.org/0000-0003-4947-0559"},"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":"Kevin J. Barker","raw_affiliation_strings":["Performance and Architecture Laboratory (PAL), Computer Science for HPC (CCS-1), Los Alamos National Laboratory, NM, USA","Performance & Archit. Lab. (PAL), Los Alamos Nat. Lab., Los Alamos, NM"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Performance and Architecture Laboratory (PAL), Computer Science for HPC (CCS-1), Los Alamos National Laboratory, NM, USA","institution_ids":["https://openalex.org/I1343871089"]},{"raw_affiliation_string":"Performance & Archit. Lab. (PAL), Los Alamos Nat. Lab., Los Alamos, NM","institution_ids":["https://openalex.org/I1343871089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1343871089"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"169","last_page":"178"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.9995999932289124,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9995999932289124,"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":0.9987999796867371,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.7858058214187622},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.7016312479972839},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.657049298286438},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.6439017057418823},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6118819117546082},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5033761858940125},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.45278215408325195},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.40334513783454895},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.33943599462509155},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.23308086395263672},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.17161104083061218},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09474325180053711}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7858058214187622},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.7016312479972839},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.657049298286438},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.6439017057418823},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6118819117546082},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5033761858940125},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.45278215408325195},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.40334513783454895},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.33943599462509155},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.23308086395263672},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.17161104083061218},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09474325180053711},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/clustr.2007.4629229","is_oa":false,"landing_page_url":"https://doi.org/10.1109/clustr.2007.4629229","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE International Conference on Cluster Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1530542361","https://openalex.org/W1587378023","https://openalex.org/W1591363587","https://openalex.org/W1937799376","https://openalex.org/W1971952282","https://openalex.org/W2048075797","https://openalex.org/W2147870060","https://openalex.org/W2151511816","https://openalex.org/W2316564661","https://openalex.org/W2534577245","https://openalex.org/W2677178705","https://openalex.org/W2903691225","https://openalex.org/W3140467006","https://openalex.org/W4232225775","https://openalex.org/W6631718410","https://openalex.org/W6681756741"],"related_works":["https://openalex.org/W2120447654","https://openalex.org/W2977179488","https://openalex.org/W2144453115","https://openalex.org/W2128223750","https://openalex.org/W4238532390","https://openalex.org/W2188872161","https://openalex.org/W2961779879","https://openalex.org/W797688974","https://openalex.org/W2002978035","https://openalex.org/W2209382646"],"abstract_inverted_index":{"In":[0,28],"parallel":[1],"applications":[2],"communication":[3,16,83],"overheads":[4],"generally":[5],"increase":[6],"as":[7],"the":[8,45,52,60,72,82,128],"processor":[9,86],"count":[10],"increases":[11],"and":[12,54,80],"in":[13,24,44],"particular,":[14],"collective":[15,48,62,73,130],"operations":[17],"can":[18,75],"become":[19],"a":[20,33,65,109],"critical":[21],"limiting":[22],"factor":[23],"achieving":[25],"high":[26],"performance.":[27],"this":[29,57,116],"paper":[30],"we":[31],"explore":[32],"novel":[34],"technique":[35],"to":[36,47],"boost":[37],"application":[38,112],"performance":[39,101,121],"by":[40,78],"dedicating":[41],"some":[42],"processors":[43,124],"system":[46],"operations.":[49],"We":[50],"demonstrate":[51],"viability":[53],"efficiency":[55],"of":[56,98],"approach":[58,117],"for":[59],"allreduce":[61],"operation":[63],"on":[64,108,122],"state-of-the-art":[66],"cluster.":[67],"Experimental":[68],"results":[69,107],"show":[70,114],"that":[71,81,115],"latency":[74],"be":[76],"reduced":[77],"30%":[79],"overhead":[84],"per":[85],"is":[87],"also":[88],"very":[89],"low,":[90],"at":[91],"1.6":[92],"mus,":[93],"which":[94],"represents":[95],"one":[96],"order":[97],"magnitude":[99],"higher":[100,120],"than":[102,125],"with":[103],"conventional":[104],"implementations.":[105],"Moreover,":[106],"large-scale":[110],"scientific":[111],"(POP)":[113],"achieves":[118],"15%":[119],"640":[123],"when":[126],"using":[127],"default":[129],"implementation.":[131]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}