{"id":"https://openalex.org/W2110147070","doi":"https://doi.org/10.1145/2145816.2145866","title":"Communication-centric optimizations by dynamically detecting collective operations","display_name":"Communication-centric optimizations by dynamically detecting collective operations","publication_year":2012,"publication_date":"2012-02-25","ids":{"openalex":"https://openalex.org/W2110147070","doi":"https://doi.org/10.1145/2145816.2145866","mag":"2110147070"},"language":"en","primary_location":{"id":"doi:10.1145/2145816.2145866","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2145816.2145866","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/A5026990786","display_name":"Torsten Hoefler","orcid":"https://orcid.org/0000-0002-1333-9797"},"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":"Torsten Hoefler","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/A5066066810","display_name":"Timo Schneider","orcid":"https://orcid.org/0000-0002-4884-3934"},"institutions":[{"id":"https://openalex.org/I2610724","display_name":"Chemnitz University of Technology","ror":"https://ror.org/00a208s56","country_code":"DE","type":"education","lineage":["https://openalex.org/I2610724"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Timo Schneider","raw_affiliation_strings":["University of Technology Chemnitz, Chemnitz, Germany"],"affiliations":[{"raw_affiliation_string":"University of Technology Chemnitz, Chemnitz, Germany","institution_ids":["https://openalex.org/I2610724"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5026990786"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":0.5855,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.69012301,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"305","last_page":"306"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9995999932289124,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9980000257492065,"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/computer-science","display_name":"Computer science","score":0.8744760155677795},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.8651574850082397},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7553174495697021},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.6712060570716858},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6552121639251709},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.628537654876709},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.554542064666748},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.525363564491272},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.46432632207870483},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4362054765224457},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3069860339164734},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.11331760883331299},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10549551248550415}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8744760155677795},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.8651574850082397},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7553174495697021},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.6712060570716858},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6552121639251709},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.628537654876709},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.554542064666748},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.525363564491272},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.46432632207870483},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4362054765224457},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3069860339164734},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.11331760883331299},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10549551248550415},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2145816.2145866","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2145816.2145866","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.298.7815","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.298.7815","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.unixer.de/publications//img/goal_colldetect_ppopp.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W122364089","https://openalex.org/W2063799188","https://openalex.org/W2112103101","https://openalex.org/W2115331279","https://openalex.org/W2140300123","https://openalex.org/W2166301347"],"related_works":["https://openalex.org/W2293118914","https://openalex.org/W2998381397","https://openalex.org/W4236419692","https://openalex.org/W3167919718","https://openalex.org/W4251718783","https://openalex.org/W2171015181","https://openalex.org/W4239447582","https://openalex.org/W1484403103","https://openalex.org/W2521947294","https://openalex.org/W2320820360"],"abstract_inverted_index":{"The":[0,88],"steady":[1],"increase":[2],"of":[3,26,29,75,90,125,127,145,160],"parallelism":[4],"in":[5,16,55,69,135,148,164],"high-performance":[6],"computing":[7],"platforms":[8],"implies":[9],"that":[10,63,116,149],"communication":[11,31,80,86,162],"will":[12],"be":[13],"most":[14],"important":[15],"large-scale":[17,30],"applications.":[18],"In":[19],"this":[20],"work,":[21],"we":[22],"tackle":[23],"the":[24,39,76,78,97,143,150,157],"problem":[25],"transparent":[27],"optimization":[28],"patterns":[32,99],"using":[33],"online":[34],"compilation":[35],"techniques.":[36],"We":[37,59],"utilize":[38],"Group":[40],"Operation":[41],"Assembly":[42],"Language":[43],"(GOAL),":[44],"an":[45],"abstract":[46],"parallel":[47,146],"dataflow":[48,65],"definition":[49],"language,":[50],"to":[51,95,121,155,166],"specify":[52],"our":[53,117],"transformations":[54],"a":[56,83,122],"device-independent":[57],"manner.":[58],"develop":[60],"fast":[61],"schemes":[62],"analyze":[64],"and":[66,71,108,169],"synchronization":[67],"semantics":[68,159],"GOAL":[70],"detect":[72],"if":[73],"parts":[74],"(or":[77],"whole)":[79],"pattern":[81],"express":[82],"known":[84],"collective":[85,91,139],"operation.":[87],"detection":[89],"operations":[92,140,163],"allows":[93],"us":[94],"replace":[96],"detected":[98],"with":[100,130],"highly":[101],"optimized":[102,132],"algorithms":[103,133],"or":[104],"low-level":[105],"hardware":[106],"calls":[107],"thus":[109],"improve":[110],"performance":[111,123],"significantly.":[112],"Benchmark":[113],"results":[114],"suggest":[115],"technique":[118],"can":[119],"lead":[120],"improvement":[124],"orders":[126],"magnitude":[128],"compared":[129],"various":[131],"written":[134],"Co-Array":[136],"Fortran.":[137],"Detecting":[138],"also":[141],"improves":[142],"programmability":[144],"languages":[147],"user":[151],"does":[152],"not":[153],"have":[154],"understand":[156],"detailed":[158],"high-level":[161],"order":[165],"generate":[167],"efficient":[168],"scalable":[170],"code.":[171]},"counts_by_year":[{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
