{"id":"https://openalex.org/W2139702875","doi":"https://doi.org/10.1109/ipdps.2009.5160896","title":"Designing multi-leader-based Allgather algorithms for multi-core clusters","display_name":"Designing multi-leader-based Allgather algorithms for multi-core clusters","publication_year":2009,"publication_date":"2009-05-01","ids":{"openalex":"https://openalex.org/W2139702875","doi":"https://doi.org/10.1109/ipdps.2009.5160896","mag":"2139702875"},"language":"en","primary_location":{"id":"doi:10.1109/ipdps.2009.5160896","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2009.5160896","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Symposium on Parallel &amp; Distributed Processing","raw_type":"proceedings-article"},"type":"article","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/A5010923189","display_name":"Krishna Kandalla","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Krishna Kandalla","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State Uinversity, USA","Department of Computer Science and Engineering, The Ohio State University, USA;"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State Uinversity, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, USA;","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034293705","display_name":"Hari Subramoni","orcid":"https://orcid.org/0000-0002-1200-2754"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hari Subramoni","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State Uinversity, USA","Department of Computer Science and Engineering, The Ohio State University, USA;"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State Uinversity, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, USA;","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109866672","display_name":"Gopal Santhanaraman","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gopal Santhanaraman","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State Uinversity, USA","Department of Computer Science and Engineering, The Ohio State University, USA;"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State Uinversity, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, USA;","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033901219","display_name":"Matthew J. Koop","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Koop","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State Uinversity, USA","Department of Computer Science and Engineering, The Ohio State University, USA;"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State Uinversity, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, USA;","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024879682","display_name":"Dhabaleswar K. Panda","orcid":"https://orcid.org/0000-0002-0356-1781"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dhabaleswar K. Panda","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State Uinversity, USA","Department of Computer Science and Engineering, The Ohio State University, USA;"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State Uinversity, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, USA;","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5010923189"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":5.0918,"has_fulltext":false,"cited_by_count":48,"citation_normalized_percentile":{"value":0.95958353,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"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":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9994000196456909,"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/infiniband","display_name":"InfiniBand","score":0.9271981120109558},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.9044219255447388},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7092148661613464},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.6213964223861694},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6063450574874878},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6025392413139343},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5439068078994751},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5268762707710266},{"id":"https://openalex.org/keywords/message-passing-interface","display_name":"Message Passing Interface","score":0.49810242652893066},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.4782068729400635},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.4563165605068207},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.43951547145843506},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.4185773730278015},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.41713768243789673},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.22973310947418213}],"concepts":[{"id":"https://openalex.org/C2781030343","wikidata":"https://www.wikidata.org/wiki/Q922437","display_name":"InfiniBand","level":2,"score":0.9271981120109558},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9044219255447388},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7092148661613464},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.6213964223861694},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6063450574874878},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6025392413139343},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5439068078994751},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5268762707710266},{"id":"https://openalex.org/C166782233","wikidata":"https://www.wikidata.org/wiki/Q127879","display_name":"Message Passing Interface","level":3,"score":0.49810242652893066},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.4782068729400635},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.4563165605068207},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.43951547145843506},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.4185773730278015},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.41713768243789673},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.22973310947418213},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ipdps.2009.5160896","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2009.5160896","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Symposium on Parallel &amp; Distributed Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.145.5421","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.145.5421","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://nowlab.cse.ohio-state.edu/publications/conf-papers/2009/kandalla-cac09.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W134816542","https://openalex.org/W1487927419","https://openalex.org/W1498011047","https://openalex.org/W1540787490","https://openalex.org/W1558115001","https://openalex.org/W1574750619","https://openalex.org/W2012652661","https://openalex.org/W2097493498","https://openalex.org/W2111144707","https://openalex.org/W3134910092"],"related_works":["https://openalex.org/W2124048060","https://openalex.org/W1902983110","https://openalex.org/W2246013950","https://openalex.org/W2378910916","https://openalex.org/W4386915331","https://openalex.org/W2116006827","https://openalex.org/W2119634093","https://openalex.org/W2045442757","https://openalex.org/W2086666199","https://openalex.org/W1970720081"],"abstract_inverted_index":{"The":[0,31,48,63,133],"increasing":[1],"demand":[2],"for":[3,60,66,71,111,145,150],"computational":[4],"cycles":[5],"is":[6,36],"being":[7],"met":[8],"by":[9],"the":[10,28,37,57,85,122],"use":[11,120],"of":[12,18,56,87,121,141],"multi-core":[13,23],"processors.":[14],"Having":[15],"large":[16],"number":[17,86],"cores":[19,88],"per":[20,89],"node":[21,90],"necessitates":[22],"aware":[24],"designs":[25],"to":[26,74,143],"extract":[27],"best":[29],"performance.":[30,76],"Message":[32],"Passing":[33],"Interface":[34],"(MPI)":[35],"dominant":[38],"parallel":[39],"programming":[40],"model":[41],"on":[42],"modern":[43],"high":[44,127],"performance":[45,128,139],"computing":[46],"clusters.":[47],"MPI":[49],"collective":[50],"operations":[51],"take":[52],"a":[53,97,138],"significant":[54],"portion":[55],"communication":[58,73],"time":[59],"an":[61],"application.":[62],"existing":[64],"optimizations":[65],"collectives":[67],"exploit":[68],"shared":[69],"memory":[70],"intra-node":[72],"improve":[75],"However,":[77],"it":[78],"still":[79],"would":[80],"not":[81],"scale":[82],"well":[83],"as":[84,131],"increase.":[91],"In":[92],"this":[93],"work,":[94],"we":[95],"propose":[96],"novel":[98],"and":[99,117,148],"scalable":[100],"multi-leader-based":[101,135],"hierarchical":[102],"Allgather":[103],"design.":[104],"This":[105],"design":[106],"allows":[107],"better":[108,119],"cache":[109],"sharing":[110],"Non-Uniform":[112],"Memory":[113],"Access":[114],"(NUMA)":[115],"machines":[116],"makes":[118],"network":[123],"speed":[124],"available":[125],"with":[126],"interconnects":[129],"such":[130],"InfiniBand.":[132],"new":[134],"scheme":[136],"achieves":[137],"improvement":[140],"up":[142],"58%":[144],"small":[146],"messages":[147],"70%":[149],"medium":[151],"sized":[152],"messages.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":5}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
