{"id":"https://openalex.org/W2295268382","doi":"https://doi.org/10.1007/978-3-319-20119-1_31","title":"Designing Non-blocking Personalized Collectives with Near Perfect Overlap for RDMA-Enabled Clusters","display_name":"Designing Non-blocking Personalized Collectives with Near Perfect Overlap for RDMA-Enabled Clusters","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2295268382","doi":"https://doi.org/10.1007/978-3-319-20119-1_31","mag":"2295268382"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-319-20119-1_31","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319965","https://openalex.org/P4310319900"],"host_organization_lineage_names":["Springer Nature","Springer Science+Business Media"],"type":"book series"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"book-chapter","type_crossref":"book-chapter","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/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":true,"raw_author_name":"Hari Subramoni","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004330728","display_name":"Ammar Ahmad Awan","orcid":"https://orcid.org/0000-0002-6272-3760"},"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":"Ammar Ahmad Awan","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048039700","display_name":"Khaled Hamidouche","orcid":"https://orcid.org/0000-0003-4836-5335"},"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":"Khaled Hamidouche","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072395879","display_name":"Dmitry Pekurovsky","orcid":"https://orcid.org/0000-0003-0505-7404"},"institutions":[{"id":"https://openalex.org/I181653535","display_name":"San Diego Supercomputer Center","ror":"https://ror.org/04mg3nk07","country_code":"US","type":"facility","lineage":["https://openalex.org/I181653535","https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dmitry Pekurovsky","raw_affiliation_strings":["San Diego Supercomputer Center, San Diego, California"],"affiliations":[{"raw_affiliation_string":"San Diego Supercomputer Center, San Diego, California","institution_ids":["https://openalex.org/I181653535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112002767","display_name":"Akshay Venkatesh","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":"Akshay Venkatesh","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101626747","display_name":"Sourav Chakraborty","orcid":"https://orcid.org/0000-0001-9518-6204"},"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":"Sourav Chakraborty","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040711735","display_name":"Karen Tomko","orcid":"https://orcid.org/0000-0002-6542-853X"},"institutions":[{"id":"https://openalex.org/I34077533","display_name":"Ohio Supercomputer Center","ror":"https://ror.org/01apna436","country_code":"US","type":"facility","lineage":["https://openalex.org/I34077533"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karen Tomko","raw_affiliation_strings":["Ohio Supercomputer Center, Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"Ohio Supercomputer Center, Columbus, OH, USA","institution_ids":["https://openalex.org/I34077533"]}]},{"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, The Ohio State University, Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5034293705"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392,"provenance":"doaj"},"apc_paid":null,"fwci":3.369,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":13,"citation_normalized_percentile":{"value":0.920966,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":89},"biblio":{"volume":null,"issue":null,"first_page":"434","last_page":"453"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Performance Optimization","score":0.9971,"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 Performance Optimization","score":0.9971,"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 Grid Computing Systems","score":0.9968,"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/T11612","display_name":"Optimization Methods in Machine Learning","score":0.9953,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.7833142},{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.65981174},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel Computing","score":0.564154},{"id":"https://openalex.org/keywords/high-performance-computing","display_name":"High-Performance Computing","score":0.557172},{"id":"https://openalex.org/keywords/task-scheduling","display_name":"Task Scheduling","score":0.545742},{"id":"https://openalex.org/keywords/multicore-architectures","display_name":"Multicore Architectures","score":0.541792},{"id":"https://openalex.org/keywords/gpu-computing","display_name":"GPU Computing","score":0.537491}],"concepts":[{"id":"https://openalex.org/C130795937","wikidata":"https://www.wikidata.org/wiki/Q2561570","display_name":"Remote direct memory access","level":2,"score":0.9771221},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.88802266},{"id":"https://openalex.org/C2781030343","wikidata":"https://www.wikidata.org/wiki/Q922437","display_name":"InfiniBand","level":2,"score":0.7833142},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.65981174},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.65158176},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5517103},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.48529452},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.47191006},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.43484986},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.4206879},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.4119869},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.20001036},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.100082755},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0885528}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-319-20119-1_31","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319965","https://openalex.org/P4310319900"],"host_organization_lineage_names":["Springer Nature","Springer Science+Business Media"],"type":"book series"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.43,"display_name":"Industry, innovation and infrastructure"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":25,"referenced_works":["https://openalex.org/W1485112544","https://openalex.org/W1530542361","https://openalex.org/W1568002392","https://openalex.org/W1591363587","https://openalex.org/W1626137763","https://openalex.org/W1803873461","https://openalex.org/W1979796968","https://openalex.org/W2024336888","https://openalex.org/W2091780466","https://openalex.org/W2111580991","https://openalex.org/W2112103101","https://openalex.org/W2115020004","https://openalex.org/W2126509165","https://openalex.org/W2129691304","https://openalex.org/W2131940306","https://openalex.org/W2134439087","https://openalex.org/W2135183195","https://openalex.org/W2151445386","https://openalex.org/W2153580423","https://openalex.org/W2158452341","https://openalex.org/W2165102815","https://openalex.org/W2165808215","https://openalex.org/W2166097017","https://openalex.org/W2276147136","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4390917331","https://openalex.org/W4282599985","https://openalex.org/W4253931064","https://openalex.org/W4245217724","https://openalex.org/W3166154920","https://openalex.org/W2751263050","https://openalex.org/W2154082760","https://openalex.org/W1984788566","https://openalex.org/W1978254186","https://openalex.org/W1964981582"],"abstract_inverted_index":{"Several":[0],"techniques":[1],"have":[2,102],"been":[3,103],"proposed":[4,164,192],"in":[5,197],"the":[6,29,47,55,66,70,89,92,105,120,128,154,188,191,216,230,237],"past":[7],"for":[8,76,177,204,208,213,229],"designing":[9],"non-blocking":[10,131,148],"collective":[11,30,132,149,179],"operations":[12,150,180],"on":[13,151,181,236],"high-performance":[14],"clusters.":[15],"While":[16],"some":[17],"of":[18,49,69,107,130,146,153,173,199,224],"them":[19],"required":[20],"a":[21],"dedicated":[22],"process/thread":[23],"or":[24],"periodic":[25],"probing":[26],"to":[27,41,74,110,127,168,201,226],"progress":[28],"others":[31],"needed":[32],"specialized":[33,77],"hardware":[34,78],"solutions.":[35],"The":[36,58],"former":[37],"technique,":[38],"while":[39],"applicable":[40],"any":[42],"generic":[43],"HPC":[44,71,108,183],"cluster,":[45],"had":[46,81],"drawback":[48],"stealing":[50],"CPU":[51],"cycles":[52],"away":[53],"from":[54],"compute":[56],"task.":[57],"latter":[59],"gave":[60],"near":[61,170],"perfect":[62,171],"overlap":[63,172],"but":[64],"increased":[65],"total":[67],"cost":[68],"installation":[72],"due":[73],"need":[75],"and":[79,98,142,175],"also":[80,220],"other":[82,90],"drawbacks":[83],"that":[84,118,162],"limited":[85],"its":[86],"applicability.":[87],"On":[88],"hand,":[91],"Remote":[93],"Direct":[94],"Memory":[95],"Access":[96],"technology":[97,124],"high":[99],"performance":[100,109],"networks":[101],"pushing":[104],"envelope":[106],"multi-petaflop":[111],"levels.":[112],"However,":[113],"no":[114],"scholarly":[115],"work":[116],"exists":[117],"explores":[119],"impact":[121],"such":[122],"RDMA":[123,156],"can":[125],"bring":[126],"design":[129],"primitives.":[133,157],"In":[134],"this":[135,140],"paper,":[136],"we":[137],"take":[138],"up":[139,200,225],"challenge":[141],"propose":[143],"efficient":[144],"designs":[145,165],"personalized":[147,178],"top":[152],"basic":[155],"Our":[158],"experimental":[159],"evaluation":[160],"shows":[161],"our":[163],"are":[166],"able":[167],"deliver":[169,195],"computation":[174],"communication":[176],"modern":[182],"systems":[184],"at":[185,233,241],"scale.":[186],"At":[187],"microbenchmark":[189],"level,":[190],"RDMA-Aware":[193],"collectives":[194],"improvements":[196],"latency":[198],"89":[202],"times":[203,207,212],"MPI_Igatherv,":[205],"3.71":[206],"MPI_Ialltoall":[209],"and,":[210],"3.23":[211],"MPI_Iscatter":[214],"over":[215],"state-of-the-art":[217],"designs.":[218],"We":[219],"observe":[221],"an":[222],"improvement":[223],"19":[227],"%":[228],"P3DFFT":[231],"kernel":[232],"8,192":[234],"cores":[235],"Stampede":[238],"supercomputing":[239],"system":[240],"TACC.":[242]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2295268382","counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":6}],"updated_date":"2024-10-19T05:04:24.663277","created_date":"2016-06-24"}
