{"id":"https://openalex.org/W2137192690","doi":"https://doi.org/10.1145/1375527.1375567","title":"Performance portable optimizations for loops containing communication operations","display_name":"Performance portable optimizations for loops containing communication operations","publication_year":2008,"publication_date":"2008-06-07","ids":{"openalex":"https://openalex.org/W2137192690","doi":"https://doi.org/10.1145/1375527.1375567","mag":"2137192690"},"language":"en","primary_location":{"id":"doi:10.1145/1375527.1375567","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1375527.1375567","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd annual international conference on Supercomputing","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/A5023233400","display_name":"Costin Iancu","orcid":"https://orcid.org/0000-0001-7845-2427"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Costin Iancu","raw_affiliation_strings":["LBNL, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"LBNL, Berkeley, CA, USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wei Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Chen","raw_affiliation_strings":["UC Berkeley, Berkeley, USA","UC-Berkeley, Berkeley, USA"],"affiliations":[{"raw_affiliation_string":"UC Berkeley, Berkeley, USA","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]},{"raw_affiliation_string":"UC-Berkeley, Berkeley, USA","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091741596","display_name":"Katherine Yelick","orcid":"https://orcid.org/0000-0003-0957-701X"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Katherine Yelick","raw_affiliation_strings":["UC Berkeley, Berkeley, USA","UC-Berkeley, Berkeley, USA"],"affiliations":[{"raw_affiliation_string":"UC Berkeley, Berkeley, USA","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]},{"raw_affiliation_string":"UC-Berkeley, Berkeley, USA","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5023233400"],"corresponding_institution_ids":["https://openalex.org/I148283060"],"apc_list":null,"apc_paid":null,"fwci":0.6907,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.77192717,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"266","last_page":"276"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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":0.9997000098228455,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9994999766349792,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8929488658905029},{"id":"https://openalex.org/keywords/programmer","display_name":"Programmer","score":0.7176704406738281},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.682184100151062},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.63873690366745},{"id":"https://openalex.org/keywords/compile-time","display_name":"Compile time","score":0.6041868329048157},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.5747789144515991},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.5070507526397705},{"id":"https://openalex.org/keywords/partitioned-global-address-space","display_name":"Partitioned global address space","score":0.5000793933868408},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4852878749370575},{"id":"https://openalex.org/keywords/runtime-system","display_name":"Runtime system","score":0.4610418975353241},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4136589467525482},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.32265418767929077},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.30012282729148865},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.19570425152778625}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8929488658905029},{"id":"https://openalex.org/C2778514511","wikidata":"https://www.wikidata.org/wiki/Q1374194","display_name":"Programmer","level":2,"score":0.7176704406738281},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.682184100151062},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.63873690366745},{"id":"https://openalex.org/C200833197","wikidata":"https://www.wikidata.org/wiki/Q333707","display_name":"Compile time","level":3,"score":0.6041868329048157},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.5747789144515991},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.5070507526397705},{"id":"https://openalex.org/C60832428","wikidata":"https://www.wikidata.org/wiki/Q945818","display_name":"Partitioned global address space","level":3,"score":0.5000793933868408},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4852878749370575},{"id":"https://openalex.org/C2780870223","wikidata":"https://www.wikidata.org/wiki/Q1004415","display_name":"Runtime system","level":2,"score":0.4610418975353241},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4136589467525482},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.32265418767929077},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.30012282729148865},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.19570425152778625}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1375527.1375567","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1375527.1375567","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd annual international conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W179815580","https://openalex.org/W1494557862","https://openalex.org/W1519221062","https://openalex.org/W1559860755","https://openalex.org/W1861151562","https://openalex.org/W1974470587","https://openalex.org/W1980390491","https://openalex.org/W1994994277","https://openalex.org/W2007914110","https://openalex.org/W2008654264","https://openalex.org/W2041351581","https://openalex.org/W2065413511","https://openalex.org/W2068700702","https://openalex.org/W2069224457","https://openalex.org/W2076560273","https://openalex.org/W2077790567","https://openalex.org/W2078526874","https://openalex.org/W2102061396","https://openalex.org/W2102604868","https://openalex.org/W2116823855","https://openalex.org/W2117996251","https://openalex.org/W2122814645","https://openalex.org/W2124751742","https://openalex.org/W2127218465","https://openalex.org/W2132777761","https://openalex.org/W2135342109","https://openalex.org/W2140300123","https://openalex.org/W2142252451","https://openalex.org/W2154955271","https://openalex.org/W2165575435","https://openalex.org/W2166521388","https://openalex.org/W2753574770","https://openalex.org/W4250089307"],"related_works":["https://openalex.org/W2371266106","https://openalex.org/W2117382851","https://openalex.org/W3006505070","https://openalex.org/W2382449560","https://openalex.org/W2110432562","https://openalex.org/W2117864619","https://openalex.org/W2025344","https://openalex.org/W2090337950","https://openalex.org/W2163552442","https://openalex.org/W2767298477"],"abstract_inverted_index":{"Effective":[0],"use":[1],"of":[2,12,25,31,114,124,166,179,200],"communication":[3,48,97,117,122,130,168,171],"networks":[4,44],"is":[5,49,61,131,158],"critical":[6],"to":[7,53,67,160],"the":[8,23,54,63,76,112,115,121,125,170,176],"performance":[9,26,70,80,142],"and":[10,27,90,106,108,129,133,140,153,156,182,195],"scalability":[11],"parallel":[13],"applications.":[14],"Partitioned":[15],"Global":[16],"Address":[17],"Space":[18],"languages":[19,38],"like":[20],"UPC":[21],"bring":[22],"promise":[24],"programmer":[28,212],"productivity.":[29],"Studies":[30],"well-tuned":[32],"programs":[33],"have":[34],"suggested":[35],"that":[36,188,193,199],"PGAS":[37],"are":[39,127],"effective":[40],"at":[41],"utilizing":[42],"modern":[43],"because":[45],"their":[46],"one-sided":[47],"a":[50,79,88,163],"good":[51,69],"match":[52],"underlying":[55],"network":[56,139,150],"hardware.":[57],"An":[58],"open":[59],"question":[60],"whether":[62],"manual":[64],"optimizations":[65],"required":[66],"achieve":[68],"can":[71],"be":[72],"performed":[73],"automatically":[74],"by":[75],"compiler":[77,89],"in":[78],"portable":[81],"manner.":[82],"In":[83],"this":[84],"paper":[85],"we":[86],"present":[87],"runtime":[91,111,145],"optimization":[92],"framework":[93,100,190],"for":[94,175],"loops":[95],"containing":[96],"operations.":[98,118],"Our":[99,204],"performs":[101,196],"compile":[102],"time":[103],"message":[104],"vectorization":[105],"strip-mining":[107],"defers":[109],"until":[110],"selection":[113],"actual":[116],"At":[119],"runtime,":[120],"requirements":[123],"program":[126],"analyzed,":[128],"instantiated":[132],"scheduled":[134],"based":[135],"on":[136],"highly":[137],"tuned":[138],"application":[141],"models.":[143],"The":[144,185],"analysis":[146],"takes":[147],"into":[148],"account":[149],"flow":[151],"control":[152],"quality-of-service":[154],"restrictions,":[155],"it":[157],"able":[159],"select":[161],"from":[162],"large":[164],"class":[165],"available":[167],"primitives":[169],"schedule":[172],"best":[173],"suited":[174],"dynamic":[177],"combination":[178],"input":[180],"size":[181],"system":[183],"parameters.":[184],"results":[186],"indicate":[187],"our":[189],"produces":[191],"code":[192],"scales":[194],"better":[197],"than":[198],"manually":[201],"optimized":[202],"implementations.":[203],"approach":[205],"not":[206],"only":[207],"improves":[208],"performance,":[209],"but":[210],"increases":[211],"productivity":[213],"as":[214],"well.":[215]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}
