{"id":"https://openalex.org/W2100431052","doi":"https://doi.org/10.1145/1378533.1378554","title":"Leveraging non-blocking collective communication in high-performance applications","display_name":"Leveraging non-blocking collective communication in high-performance applications","publication_year":2008,"publication_date":"2008-06-14","ids":{"openalex":"https://openalex.org/W2100431052","doi":"https://doi.org/10.1145/1378533.1378554","mag":"2100431052"},"language":"en","primary_location":{"id":"doi:10.1145/1378533.1378554","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1378533.1378554","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the twentieth annual symposium on Parallelism in algorithms and architectures","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/A5026990786","display_name":"Torsten Hoefler","orcid":"https://orcid.org/0000-0002-1333-9797"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Torsten Hoefler","raw_affiliation_strings":["Indiana University, Bloomington, IN, USA"],"affiliations":[{"raw_affiliation_string":"Indiana University, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051793103","display_name":"Peter Gottschling","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Gottschling","raw_affiliation_strings":["Indiana University, Bloomington, IN, USA"],"affiliations":[{"raw_affiliation_string":"Indiana University, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074260102","display_name":"Andrew Lumsdaine","orcid":"https://orcid.org/0000-0002-9153-6622"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Lumsdaine","raw_affiliation_strings":["Indiana University, Bloomington, IN, USA"],"affiliations":[{"raw_affiliation_string":"Indiana University, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5026990786"],"corresponding_institution_ids":["https://openalex.org/I4210119109"],"apc_list":null,"apc_paid":null,"fwci":4.1593,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.94367404,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"113","last_page":"115"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9984999895095825,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9973000288009644,"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/computer-science","display_name":"Computer science","score":0.8824403285980225},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.7633540630340576},{"id":"https://openalex.org/keywords/programmer","display_name":"Programmer","score":0.7421168088912964},{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.6841902732849121},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.6486971378326416},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6463444232940674},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5321292877197266},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.41043156385421753},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.33214646577835083},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.19044598937034607},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.1823124885559082},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13569343090057373}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8824403285980225},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.7633540630340576},{"id":"https://openalex.org/C2778514511","wikidata":"https://www.wikidata.org/wiki/Q1374194","display_name":"Programmer","level":2,"score":0.7421168088912964},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.6841902732849121},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6486971378326416},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6463444232940674},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5321292877197266},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.41043156385421753},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.33214646577835083},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.19044598937034607},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.1823124885559082},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13569343090057373}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1378533.1378554","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1378533.1378554","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the twentieth annual symposium on Parallelism in algorithms and architectures","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","score":0.4300000071525574,"display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W9649600","https://openalex.org/W27311811","https://openalex.org/W86735328","https://openalex.org/W1497413785","https://openalex.org/W1530542361","https://openalex.org/W1534291736","https://openalex.org/W1547502462","https://openalex.org/W1550062991","https://openalex.org/W1555915743","https://openalex.org/W1825216778","https://openalex.org/W1981753901","https://openalex.org/W2013299585","https://openalex.org/W2018899347","https://openalex.org/W2046526098","https://openalex.org/W2049004373","https://openalex.org/W2057303472","https://openalex.org/W2068975988","https://openalex.org/W2079579585","https://openalex.org/W2091521529","https://openalex.org/W2098815550","https://openalex.org/W2102182691","https://openalex.org/W2110194283","https://openalex.org/W2116507456","https://openalex.org/W2120827897","https://openalex.org/W2122814645","https://openalex.org/W2131940306","https://openalex.org/W2132777761","https://openalex.org/W2135342109","https://openalex.org/W2148744369","https://openalex.org/W2152719989","https://openalex.org/W2161708191","https://openalex.org/W2165102815","https://openalex.org/W2165808215","https://openalex.org/W2170902912","https://openalex.org/W2396414264","https://openalex.org/W2912686856","https://openalex.org/W3007497337"],"related_works":["https://openalex.org/W2379153735","https://openalex.org/W2046172023","https://openalex.org/W2170146914","https://openalex.org/W2972896947","https://openalex.org/W2083974823","https://openalex.org/W2355105570","https://openalex.org/W2072751097","https://openalex.org/W4237177615","https://openalex.org/W2289257917","https://openalex.org/W2015567081"],"abstract_inverted_index":{"Although":[0],"overlapping":[1,60],"communication":[2,47,62,66,93,106,124],"with":[3,87,113],"computation":[4,68,95,104],"is":[5],"an":[6,97],"important":[7],"mechanism":[8],"for":[9],"achieving":[10],"high":[11],"performance":[12,130],"in":[13,48,70,96,123,127],"parallel":[14,49],"programs,":[15],"developing":[16],"applications":[17],"that":[18],"actually":[19],"achieve":[20,108],"good":[21],"overlap":[22],"can":[23],"be":[24],"difficult.":[25],"Existing":[26],"approaches":[27],"are":[28,74],"typically":[29],"based":[30,52],"on":[31,53],"manual":[32],"or":[33],"compiler-based":[34],"transformations.":[35],"This":[36],"paper":[37],"presents":[38],"a":[39,114,120],"pattern":[40],"and":[41,63,67,94,105],"library-based":[42],"approach":[43,83],"to":[44,58,76,90,107],"optimizing":[45],"collective":[46,56],"high-performance":[50],"applications,":[51],"using":[54],"non-blocking":[55],"operations":[57],"enable":[59],"of":[61],"computation.":[64],"Common":[65],"patterns":[69],"iterative":[71],"SPMD":[72],"computations":[73],"used":[75],"motivate":[77],"the":[78,85,88,101],"transformations":[79],"we":[80],"present.":[81],"Our":[82],"provides":[84],"programmer":[86],"capability":[89],"separately":[91],"optimize":[92],"application,":[98],"while":[99],"automating":[100],"interaction":[102],"between":[103],"maximum":[109],"overlap.":[110],"Performance":[111],"results":[112],"model":[115],"application":[116],"show":[117],"more":[118],"than":[119],"90%":[121],"decrease":[122],"overhead,":[125],"resulting":[126],"21%":[128],"overall":[129],"improvements.":[131]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}