{"id":"https://openalex.org/W2031699282","doi":"https://doi.org/10.1145/2628071.2628109","title":"Automatic execution of single-GPU computations across multiple GPUs","display_name":"Automatic execution of single-GPU computations across multiple GPUs","publication_year":2014,"publication_date":"2014-08-21","ids":{"openalex":"https://openalex.org/W2031699282","doi":"https://doi.org/10.1145/2628071.2628109","mag":"2031699282"},"language":"en","primary_location":{"id":"doi:10.1145/2628071.2628109","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2628071.2628109","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd international conference on Parallel architectures and compilation","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/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":true,"raw_author_name":"Javier Cabezas","raw_affiliation_strings":["Barcelona Supercomputing Center, Barcelona, Spain"],"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"],"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 Corporation, Santa Clara, CA, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation, 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"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","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/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]},{"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"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Nacho Navarro","raw_affiliation_strings":["Universitat Polit\u00e8cnica de Catalunya & Barcelona Supercomputing Center, Barcelona, Spain"],"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 Hwu","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5077201715"],"corresponding_institution_ids":["https://openalex.org/I2799803557","https://openalex.org/I9617848"],"apc_list":null,"apc_paid":null,"fwci":2.4518,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.88939152,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"467","last_page":"468"},"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":0.9998000264167786,"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":0.998199999332428,"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":0.8985642194747925},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7957581281661987},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.689681887626648},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.6324639320373535},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5536521077156067},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5352485775947571},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.4847092628479004},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4587576389312744},{"id":"https://openalex.org/keywords/data-access","display_name":"Data access","score":0.45359864830970764},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.4530496299266815},{"id":"https://openalex.org/keywords/runtime-system","display_name":"Runtime system","score":0.426483690738678},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.41815781593322754},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.18766245245933533},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.12751713395118713},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11929410696029663},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11098971962928772}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8985642194747925},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7957581281661987},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.689681887626648},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6324639320373535},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5536521077156067},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5352485775947571},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.4847092628479004},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4587576389312744},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.45359864830970764},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.4530496299266815},{"id":"https://openalex.org/C2780870223","wikidata":"https://www.wikidata.org/wiki/Q1004415","display_name":"Runtime system","level":2,"score":0.426483690738678},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.41815781593322754},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.18766245245933533},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12751713395118713},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11929410696029663},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11098971962928772},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2628071.2628109","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2628071.2628109","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd international conference on Parallel architectures and compilation","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.4000000059604645}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1966344015","https://openalex.org/W2016939324","https://openalex.org/W2095894588","https://openalex.org/W2167101788","https://openalex.org/W4241790656"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2080146221","https://openalex.org/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W2792081825"],"abstract_inverted_index":{"We":[0],"present":[1],"AMGE,":[2],"a":[3,56,114,126],"programming":[4],"framework":[5],"and":[6,12,15,47,78,104,110],"runtime":[7,68],"system":[8],"to":[9,32,44,59,72,121],"decompose":[10,46],"data":[11,34,79],"GPU":[13,51,65,86],"kernels":[14],"execute":[16],"them":[17],"on":[18,125],"multiple":[19],"GPUs":[20,31,112],"concurrently.":[21],"AMGE":[22,43,53,88],"exploits":[23],"the":[24,75,95,122],"remote":[25],"memory":[26],"access":[27,62],"capability":[28],"of":[29,37,85,94,117],"recent":[30],"guarantee":[33],"accessibility":[35],"regardless":[36],"its":[38],"physical":[39],"location,":[40],"thus":[41],"allowing":[42],"safely":[45],"distribute":[48],"arrays":[49],"across":[50],"memories.":[52],"also":[54],"includes":[55],"compiler":[57],"analysis":[58],"detect":[60],"array":[61],"patterns":[63],"in":[64,92],"kernels.":[66],"The":[67],"uses":[69],"this":[70],"information":[71],"automatically":[73],"choose":[74],"best":[76],"computation":[77],"distribution":[80],"configuration.":[81],"Through":[82],"effective":[83],"use":[84],"caches,":[87],"achieves":[89],"good":[90],"scalability":[91],"spite":[93],"limited":[96],"interconnect":[97],"bandwidth":[98],"between":[99],"GPUs.":[100],"Results":[101],"show":[102],"1.95x":[103],"3.73x":[105],"execution":[106],"speedups":[107],"for":[108,113],"2":[109],"4":[111],"wide":[115],"range":[116],"dense":[118],"computations":[119],"compared":[120],"original":[123],"versions":[124],"single":[127],"GPU.":[128]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}