{"id":"https://openalex.org/W2011443595","doi":"https://doi.org/10.1145/2145816.2145823","title":"Faster topology-aware collective algorithms through non-minimal communication","display_name":"Faster topology-aware collective algorithms through non-minimal communication","publication_year":2012,"publication_date":"2012-02-25","ids":{"openalex":"https://openalex.org/W2011443595","doi":"https://doi.org/10.1145/2145816.2145823","mag":"2011443595"},"language":"en","primary_location":{"id":"doi:10.1145/2145816.2145823","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2145816.2145823","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM SIGPLAN symposium on Principles and Practice of Parallel Programming","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/A5091821862","display_name":"Paul Sack","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Paul Sack","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, USA","University of Illinois at Urbana/Champaign, Urbana, IL, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois at Urbana/Champaign, Urbana, IL, USA#TAB#","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017241944","display_name":"William Gropp","orcid":"https://orcid.org/0000-0003-2905-3029"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William Gropp","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, USA","University of Illinois at Urbana/Champaign, Urbana, IL, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois at Urbana/Champaign, Urbana, IL, USA#TAB#","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5091821862"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":3.7708,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.9330148,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"45","last_page":"54"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9994999766349792,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8303514719009399},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.6280664205551147},{"id":"https://openalex.org/keywords/porting","display_name":"Porting","score":0.5550372004508972},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5322211980819702},{"id":"https://openalex.org/keywords/network-topology","display_name":"Network topology","score":0.4893280863761902},{"id":"https://openalex.org/keywords/ibm","display_name":"IBM","score":0.4888309836387634},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4426640272140503},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.43155214190483093},{"id":"https://openalex.org/keywords/semaphore","display_name":"Semaphore","score":0.42715543508529663},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.4201720356941223},{"id":"https://openalex.org/keywords/topology","display_name":"Topology (electrical circuits)","score":0.35853925347328186},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.34847384691238403},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.2290467917919159},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10920727252960205},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09705513715744019}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8303514719009399},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.6280664205551147},{"id":"https://openalex.org/C106251023","wikidata":"https://www.wikidata.org/wiki/Q851989","display_name":"Porting","level":3,"score":0.5550372004508972},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5322211980819702},{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.4893280863761902},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.4888309836387634},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4426640272140503},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.43155214190483093},{"id":"https://openalex.org/C95203288","wikidata":"https://www.wikidata.org/wiki/Q221682","display_name":"Semaphore","level":2,"score":0.42715543508529663},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4201720356941223},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.35853925347328186},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.34847384691238403},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2290467917919159},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10920727252960205},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09705513715744019},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2145816.2145823","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2145816.2145823","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM SIGPLAN symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1556769401","https://openalex.org/W1558115001","https://openalex.org/W1825216778","https://openalex.org/W1978516206","https://openalex.org/W1997674404","https://openalex.org/W2053663473","https://openalex.org/W2081612620","https://openalex.org/W2096811399","https://openalex.org/W2105549957","https://openalex.org/W2128543830","https://openalex.org/W2131613942","https://openalex.org/W2133557963","https://openalex.org/W2144594679","https://openalex.org/W2166399120","https://openalex.org/W2245435529","https://openalex.org/W4206687892"],"related_works":["https://openalex.org/W3003341543","https://openalex.org/W2049762404","https://openalex.org/W2390878321","https://openalex.org/W60162714","https://openalex.org/W1739793394","https://openalex.org/W1990738635","https://openalex.org/W2740134768","https://openalex.org/W2072951017","https://openalex.org/W1966628122","https://openalex.org/W2005937251"],"abstract_inverted_index":{"Known":[0],"algorithms":[1,47,66],"for":[2,67],"two":[3],"important":[4],"collective":[5,114],"communication":[6],"operations,":[7,34],"allgather":[8,83,109],"and":[9,38,70,89,103,112],"reduce-scatter,":[10],"are":[11],"minimal-communication":[12],"algorithms;":[13],"no":[14],"process":[15],"sends":[16],"or":[17,72,110],"receives":[18],"more":[19],"than":[20],"the":[21,29,33,36,53,97,120],"minimum":[22],"amount":[23,59],"of":[24,32,40,55,60,85,92,108,122],"data.":[25],"This,":[26],"combined":[27],"with":[28,52],"data-ordering":[30],"semantics":[31],"limits":[35],"flexibility":[37],"performance":[39,51,121],"these":[41,123],"algorithms.":[42,124],"Our":[43],"novel":[44,65],"non-minimal,":[45],"topology-aware":[46],"deliver":[48],"far":[49],"better":[50],"addition":[54],"a":[56,78],"very":[57],"small":[58],"redundant":[61],"communication.":[62],"We":[63],"develop":[64],"Clos":[68],"networks":[69],"single":[71],"multi-ported":[73],"torus":[74],"networks.":[75],"Tests":[76],"on":[77],"32k-node":[79],"BlueGene/P":[80],"result":[81],"in":[82],"speedups":[84,91],"up":[86],"to":[87,96],"6x":[88],"reduce-scatter":[90,111],"over":[93],"11x":[94],"compared":[95],"native":[98],"IBM":[99],"algorithm.":[100],"Broadcast,":[101],"reduce,":[102],"allreduce":[104],"can":[105],"be":[106],"composed":[107],"other":[113],"operations;":[115],"our":[116],"techniques":[117],"also":[118],"improve":[119]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
