{"id":"https://openalex.org/W2067280503","doi":"https://doi.org/10.1145/2751205.2751218","title":"Automatic Parallelization of Kernels in Shared-Memory Multi-GPU Nodes","display_name":"Automatic Parallelization of Kernels in Shared-Memory Multi-GPU Nodes","publication_year":2015,"publication_date":"2015-06-02","ids":{"openalex":"https://openalex.org/W2067280503","doi":"https://doi.org/10.1145/2751205.2751218","mag":"2067280503"},"language":"en","primary_location":{"id":"doi:10.1145/2751205.2751218","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2751205.2751218","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM on International Conference on Supercomputing","raw_type":"proceedings-article"},"type":"conference-paper","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/A5077201715","display_name":"Javier Cabezas","orcid":"https://orcid.org/0000-0003-3335-8036"},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Javier Cabezas","raw_affiliation_strings":["Barcelona Supercomputing Center, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024693147","display_name":"Llu\u00eds Vilanova","orcid":"https://orcid.org/0000-0002-1452-840X"},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Llu\u00eds Vilanova","raw_affiliation_strings":["Barcelona Supercomputing Center, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034214277","display_name":"Isaac Gelado","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Isaac Gelado","raw_affiliation_strings":["NVIDIA Research, Santa Clara, CA, USA",", NVIDIA Research, Santa Clara, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Research, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":", NVIDIA Research, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081352952","display_name":"Thomas B. Jablin","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":false,"raw_author_name":"Thomas B. Jablin","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, USA","University of Illinois at Urbana/Champaign, Urbana, IL, USA#TAB#"],"raw_orcid":null,"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":"middle","author":{"id":"https://openalex.org/A5113528111","display_name":"Nacho Navarro","orcid":null},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Nacho Navarro","raw_affiliation_strings":["Universitat Polit\u00e8cnica de Catalunya/Barcelona Supercomputing Center, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat Polit\u00e8cnica de Catalunya/Barcelona Supercomputing Center, Barcelona, Spain","institution_ids":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040404999","display_name":"Wen\u2010mei Hwu","orcid":"https://orcid.org/0000-0003-2532-5349"},"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":"Wen-mei W. Hwu","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, USA","University of Illinois at Urbana/Champaign, Urbana, IL, USA#TAB#"],"raw_orcid":null,"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":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3","last_page":"13"},"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/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":0.9993000030517578,"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":0.9059776663780212},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.793110191822052},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.643641471862793},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5638637542724609},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.556217610836029},{"id":"https://openalex.org/keywords/runtime-system","display_name":"Runtime system","score":0.48516184091567993},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4844372570514679},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.444867879152298},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.43942055106163025},{"id":"https://openalex.org/keywords/data-access","display_name":"Data access","score":0.4191358983516693},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4173811674118042},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2164558470249176},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12698698043823242}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9059776663780212},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.793110191822052},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.643641471862793},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5638637542724609},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.556217610836029},{"id":"https://openalex.org/C2780870223","wikidata":"https://www.wikidata.org/wiki/Q1004415","display_name":"Runtime system","level":2,"score":0.48516184091567993},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4844372570514679},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.444867879152298},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.43942055106163025},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.4191358983516693},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4173811674118042},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2164558470249176},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12698698043823242},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2751205.2751218","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2751205.2751218","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM on International Conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1521571223","https://openalex.org/W1966344015","https://openalex.org/W1977899806","https://openalex.org/W1987873989","https://openalex.org/W1991602131","https://openalex.org/W2005818856","https://openalex.org/W2014033064","https://openalex.org/W2016939324","https://openalex.org/W2024122052","https://openalex.org/W2065963893","https://openalex.org/W2076279664","https://openalex.org/W2085118703","https://openalex.org/W2092309910","https://openalex.org/W2095894588","https://openalex.org/W2109065830","https://openalex.org/W2117293168","https://openalex.org/W2146852595","https://openalex.org/W2149788502","https://openalex.org/W2149970695","https://openalex.org/W2150446161","https://openalex.org/W2153644244","https://openalex.org/W2156275124","https://openalex.org/W2157632164","https://openalex.org/W2167101788","https://openalex.org/W4241790656"],"related_works":["https://openalex.org/W3062287","https://openalex.org/W2380390332","https://openalex.org/W2742145873","https://openalex.org/W4245975140","https://openalex.org/W1977763331","https://openalex.org/W2062253548","https://openalex.org/W4225414539","https://openalex.org/W4289522463","https://openalex.org/W2767298477","https://openalex.org/W2344299099"],"abstract_inverted_index":{"In":[0],"this":[1,74],"paper":[2],"we":[3],"present":[4],"AMGE,":[5],"a":[6,62,112,143,155],"programming":[7],"framework":[8],"and":[9,17,53,83,133,139],"runtime":[10,49,77],"system":[11],"that":[12,37,65,111,117],"transparently":[13],"decomposes":[14],"GPU":[15,57,71,91],"kernels":[16],"executes":[18],"them":[19],"on":[20,154],"multiple":[21],"GPUs":[22,34,141],"in":[23,32,70],"parallel.":[24],"AMGE":[25,95],"exploits":[26],"the":[27,76,98,122,151],"remote":[28,101,119],"memory":[29],"access":[30,68],"capability":[31],"modern":[33],"to":[35,50,96,150],"ensure":[36],"data":[38,84],"can":[39,78],"be":[40],"accessed":[41],"regardless":[42],"of":[43,100,146],"its":[44],"physical":[45],"location,":[46],"allowing":[47],"our":[48],"safely":[51],"decompose":[52],"distribute":[54],"arrays":[55],"across":[56],"memories.":[58],"It":[59],"optionally":[60],"performs":[61],"compiler":[63],"analysis":[64],"detects":[66],"array":[67],"patterns":[69],"kernels.":[72],"Using":[73],"information,":[75],"perform":[79],"more":[80],"efficient":[81],"computation":[82],"distribution":[85],"configurations":[86],"than":[87],"previous":[88],"works.":[89],"The":[90],"execution":[92,125,135],"model":[93],"allows":[94],"hide":[97],"cost":[99],"accesses":[102,120],"if":[103],"they":[104],"are":[105],"kept":[106],"below":[107],"5%.":[108],"We":[109],"demonstrate":[110],"thread":[113],"block":[114],"scheduling":[115],"policy":[116],"distributes":[118],"through":[121],"whole":[123],"kernel":[124],"further":[126],"reduces":[127],"their":[128],"overhead.":[129],"Results":[130],"show":[131],"1.98\u00d7":[132],"3.89\u00d7":[134],"speedups":[136],"for":[137,142],"2":[138],"4":[140],"wide":[144],"range":[145],"dense":[147],"computations":[148],"compared":[149],"original":[152],"versions":[153],"single":[156],"GPU.":[157]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}