{"id":"https://openalex.org/W2097493498","doi":"https://doi.org/10.1109/ipdps.2008.4536141","title":"Scaling alltoall collective on multi-core systems","display_name":"Scaling alltoall collective on multi-core systems","publication_year":2008,"publication_date":"2008-04-01","ids":{"openalex":"https://openalex.org/W2097493498","doi":"https://doi.org/10.1109/ipdps.2008.4536141","mag":"2097493498"},"language":"en","primary_location":{"id":"doi:10.1109/ipdps.2008.4536141","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2008.4536141","pdf_url":null,"source":{"id":"https://openalex.org/S4210174069","display_name":"Proceedings - IEEE International Parallel and Distributed Processing Symposium","issn_l":"1530-2075","issn":["1530-2075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Symposium on Parallel and Distributed Processing","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/A5067689068","display_name":"Rahul Kumar","orcid":"https://orcid.org/0000-0001-6887-7106"},"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":"Rahul Kumar","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State Uinversity, USA","Department of Computer Science and Engineering Ohio State University, Columbus OH"],"raw_orcid":null,"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 Ohio State University, Columbus OH","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109965519","display_name":"Amith R. Mamidala","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":"Amith Mamidala","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State Uinversity, USA","Department of Computer Science and Engineering Ohio State University, Columbus OH"],"raw_orcid":null,"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 Ohio State University, Columbus OH","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112459975","display_name":"D.K. Panda","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":"D. K. Panda","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State Uinversity, USA","Department of Computer Science and Engineering Ohio State University, Columbus OH"],"raw_orcid":null,"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 Ohio State University, Columbus OH","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":2.8004,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.91537089,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9986000061035156,"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":0.9986000061035156,"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":0.9976000189781189,"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"}},{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9975000023841858,"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/infiniband","display_name":"InfiniBand","score":0.9653662443161011},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8872745037078857},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.6621174812316895},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5688675045967102},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5670934915542603},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5376405119895935},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.525874137878418},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.48883503675460815},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.48371651768684387},{"id":"https://openalex.org/keywords/protocol-stack","display_name":"Protocol stack","score":0.4614807963371277},{"id":"https://openalex.org/keywords/protocol","display_name":"Protocol (science)","score":0.4273514449596405},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3383655250072479},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.325907826423645},{"id":"https://openalex.org/keywords/stack","display_name":"Stack (abstract data type)","score":0.28562039136886597},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.26801395416259766}],"concepts":[{"id":"https://openalex.org/C2781030343","wikidata":"https://www.wikidata.org/wiki/Q922437","display_name":"InfiniBand","level":2,"score":0.9653662443161011},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8872745037078857},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.6621174812316895},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5688675045967102},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5670934915542603},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5376405119895935},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.525874137878418},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.48883503675460815},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.48371651768684387},{"id":"https://openalex.org/C38601921","wikidata":"https://www.wikidata.org/wiki/Q1757693","display_name":"Protocol stack","level":3,"score":0.4614807963371277},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.4273514449596405},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3383655250072479},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.325907826423645},{"id":"https://openalex.org/C9395851","wikidata":"https://www.wikidata.org/wiki/Q177929","display_name":"Stack (abstract data type)","level":2,"score":0.28562039136886597},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.26801395416259766},{"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/C204787440","wikidata":"https://www.wikidata.org/wiki/Q188504","display_name":"Alternative medicine","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ipdps.2008.4536141","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2008.4536141","pdf_url":null,"source":{"id":"https://openalex.org/S4210174069","display_name":"Proceedings - IEEE International Parallel and Distributed Processing Symposium","issn_l":"1530-2075","issn":["1530-2075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Symposium on Parallel and Distributed Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.145.2494","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.145.2494","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/2008/kumarra-cac08.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1907125365","https://openalex.org/W1937799376","https://openalex.org/W2047763672","https://openalex.org/W2071220401","https://openalex.org/W2081612620","https://openalex.org/W2131613942","https://openalex.org/W2133557963","https://openalex.org/W2158587304","https://openalex.org/W2164488397","https://openalex.org/W2167967054","https://openalex.org/W2168281730","https://openalex.org/W2170396259","https://openalex.org/W3138954289","https://openalex.org/W4231725297","https://openalex.org/W4238826819","https://openalex.org/W4241954130","https://openalex.org/W4285719527","https://openalex.org/W6662492315","https://openalex.org/W6684224193"],"related_works":["https://openalex.org/W2406331183","https://openalex.org/W2363988059","https://openalex.org/W2792231649","https://openalex.org/W2053215237","https://openalex.org/W1939358748","https://openalex.org/W1995426833","https://openalex.org/W159577597","https://openalex.org/W1597650818","https://openalex.org/W4287109558","https://openalex.org/W2025467172"],"abstract_inverted_index":{"MPI_Alltoall":[0,54,136,213],"is":[1,36,59,111],"one":[2,148],"of":[3,23,70,101,107,156,200],"the":[4,16,71,77,94,102,105,198,224],"most":[5],"communication":[6,116],"intense":[7,117],"collective":[8],"operation":[9,41,118],"used":[10,180],"in":[11,113,174,193,212],"many":[12],"parallel":[13],"applications.":[14],"Recently,":[15],"supercomputing":[17],"arena":[18],"has":[19],"witnessed":[20],"phenomenal":[21],"growth":[22],"commodity":[24],"clusters":[25,45],"built":[26],"using":[27],"InfiniBand":[28,64],"and":[29,131,173,196,221],"multi-core":[30,185,204],"systems.":[31,186,205],"In":[32,122],"this":[33,40,123],"context,":[34],"it":[35,89],"important":[37],"to":[38,46,83,138,168,181],"optimize":[39],"for":[42,48,67,135,217],"these":[43,56,108,128,139,157,194,201],"emerging":[44,57],"allow":[47],"good":[49],"application":[50,226],"scaling.":[51],"However,":[52],"optimizing":[53,114],"on":[55,154,184,203],"systems":[58],"not":[60],"a":[61,84,115,210],"trivial":[62],"task.":[63],"architecture":[65],"allows":[66],"varying":[68,158],"implementations":[69,110,163],"network":[72,171],"protocol":[73,78],"stack.":[74],"For":[75,160],"example,":[76,161],"can":[79,90,97,164,178],"be":[80,91,179],"totally":[81],"on-loaded":[82,162],"host":[85],"processing":[86],"core":[87],"or":[88,96],"off-loaded":[92],"onto":[93],"NIC":[95],"use":[98,147],"any":[99],"combination":[100],"two.":[103],"Understanding":[104],"characteristics":[106],"different":[109,129],"critical":[112],"such":[119],"as":[120],"MPI_Alltoall.":[121],"paper,":[124],"we":[125,142,145],"systematically":[126],"study":[127],"architectures":[130],"propose":[132],"new":[133],"schemes":[134,195,202],"tailored":[137],"architectures.":[140,159],"Specifically,":[141],"demonstrate":[143],"that":[144],"cannot":[146],"common":[149],"scheme":[150],"which":[151],"performs":[152],"optimally":[153],"each":[155],"exploit":[165],"multiple":[166],"cores":[167],"achieve":[169],"better":[170],"utilization,":[172],"offload":[175],"interfaces":[176],"aggregation":[177,191],"avoid":[182],"congestion":[183],"We":[187],"employ":[188],"shared":[189],"memory":[190],"techniques":[192],"elucidate":[197],"impact":[199],"The":[206],"proposed":[207],"design":[208],"achieves":[209],"reduction":[211],"time":[214],"by":[215,227],"55%":[216],"512":[218],"Byte":[219],"messages":[220],"speeds":[222],"up":[223],"CPMD":[225],"33%.":[228]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
