{"id":"https://openalex.org/W1984692061","doi":"https://doi.org/10.1145/2370816.2370856","title":"Runtime detection and optimization of collective communication patterns","display_name":"Runtime detection and optimization of collective communication patterns","publication_year":2012,"publication_date":"2012-09-19","ids":{"openalex":"https://openalex.org/W1984692061","doi":"https://doi.org/10.1145/2370816.2370856","mag":"1984692061"},"language":"en","primary_location":{"id":"doi:10.1145/2370816.2370856","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2370816.2370856","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st international conference on Parallel architectures and compilation techniques","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/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Torsten Hoefler","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland","Department of Computer Science ETH Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"Department of Computer Science ETH Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"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/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":"Timo Schneider","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":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5026990786"],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":2.3205,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.87642871,"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":"263","last_page":"272"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9986000061035156,"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":0.9986000061035156,"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":0.8808521628379822},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.8268740177154541},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.5420267581939697},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5342326164245605},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.48107457160949707},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4533296823501587},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.4289036989212036},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.4288784861564636},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.4156056046485901},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.39007917046546936},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3852728009223938},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.22406375408172607}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8808521628379822},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.8268740177154541},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.5420267581939697},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5342326164245605},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.48107457160949707},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4533296823501587},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.4289036989212036},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.4288784861564636},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.4156056046485901},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.39007917046546936},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3852728009223938},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.22406375408172607},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2370816.2370856","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2370816.2370856","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st international conference on Parallel architectures and compilation techniques","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W122364089","https://openalex.org/W563453116","https://openalex.org/W590105139","https://openalex.org/W1429771687","https://openalex.org/W1535569416","https://openalex.org/W1575350781","https://openalex.org/W1966889169","https://openalex.org/W1980670496","https://openalex.org/W1985565667","https://openalex.org/W1994691947","https://openalex.org/W2002571766","https://openalex.org/W2018346931","https://openalex.org/W2049459394","https://openalex.org/W2053738729","https://openalex.org/W2063799188","https://openalex.org/W2078637295","https://openalex.org/W2084379367","https://openalex.org/W2097982440","https://openalex.org/W2099148634","https://openalex.org/W2109065830","https://openalex.org/W2110147070","https://openalex.org/W2115331279","https://openalex.org/W2124583046","https://openalex.org/W2136041296","https://openalex.org/W2140300123","https://openalex.org/W2146412016","https://openalex.org/W2149960335","https://openalex.org/W2160054705","https://openalex.org/W2166301347","https://openalex.org/W2169816952","https://openalex.org/W4285719527","https://openalex.org/W6685054132"],"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":{"Parallelism":[0],"is":[1,75,89],"steadily":[2],"growing,":[3],"remote-data":[4],"access":[5],"will":[6,195],"soon":[7],"dominate":[8],"the":[9,98,102,132],"execution":[10],"time":[11],"of":[12,97,134,141],"large-scale":[13,16,172],"applications.":[14],"Many":[15],"communication":[17,36,55,93,123,173,191],"patterns":[18,37],"expose":[19],"significant":[20],"structure":[21],"that":[22,74,88,127,151,189],"can":[23,130],"be":[24],"used":[25],"to":[26,41,77,91,121],"schedule":[27],"communications":[28],"accordingly.":[29],"In":[30],"this":[31],"work,":[32],"we":[33,148],"identify":[34],"concurrent":[35],"and":[38,57,62,100,118,185,193,205],"transform":[39],"them":[40],"semantically":[42],"equivalent":[43],"but":[44],"faster":[45],"communications.":[46],"We":[47,80,187],"show":[48,126,150],"a":[49,82,166],"directed":[50],"acyclic":[51],"graph":[52,99],"formulation":[53],"for":[54,85,181,209],"schedules":[56],"concisely":[58],"define":[59],"their":[60],"synchronization":[61],"data":[63],"movement":[64],"semantics.":[65],"Our":[66,175],"dataflow":[67],"solver":[68],"computes":[69],"an":[70,115],"internal":[71],"representation":[72],"(IR)":[73],"amenable":[76],"pattern":[78,200],"detection.":[79],"demonstrate":[81],"detection":[83,117,154],"algorithm":[84],"our":[86,128],"IR":[87],"guaranteed":[90],"detect":[92],"kernels":[94],"on":[95,143,156],"subsets":[96,158],"replace":[101],"subgraph":[103],"with":[104],"hardware":[105],"accelerated":[106],"or":[107],"hand-tuned":[108],"kernels.":[109],"Those":[110],"techniques":[111,129,164,177],"are":[112,159,165,207],"implemented":[113],"in":[114],"open-source":[116],"transformation":[119,183],"framework":[120],"optimize":[122],"patterns.":[124],"Experiments":[125],"improve":[131],"performance":[133],"representative":[135],"example":[136],"codes":[137],"by":[138],"several":[139,179],"orders":[140],"magnitude":[142],"two":[144],"different":[145],"systems.":[146],"However,":[147],"also":[149],"some":[152],"collective":[153],"problems":[155],"process":[157],"NP-hard.":[160],"The":[161],"developed":[162,176],"analysis":[163],"first":[167],"important":[168],"step":[169],"towards":[170],"automatic":[171],"transformations.":[174],"open":[178],"avenues":[180],"additional":[182],"heuristics":[184],"analyses.":[186],"expect":[188],"such":[190],"analyses":[192],"transformations":[194],"become":[196],"as":[197,199],"natural":[198],"detection,":[201],"just-in-time":[202],"compiler":[203],"optimizations,":[204],"autotuning":[206],"today":[208],"serial":[210],"codes.":[211]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
