{"id":"https://openalex.org/W2016340785","doi":"https://doi.org/10.1145/2716282.2716286","title":"GPU-SM: shared memory multi-GPU programming","display_name":"GPU-SM: shared memory multi-GPU programming","publication_year":2015,"publication_date":"2015-02-03","ids":{"openalex":"https://openalex.org/W2016340785","doi":"https://doi.org/10.1145/2716282.2716286","mag":"2016340785"},"language":"en","primary_location":{"id":"doi:10.1145/2716282.2716286","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2716282.2716286","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th Workshop on General Purpose Processing using GPUs","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/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":true,"raw_author_name":"Javier Cabezas","raw_affiliation_strings":["Barcelona Supercomputing Center, Spain","Barcelona Supercomputing Center (Spain)"],"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center, Spain","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]},{"raw_affiliation_string":"Barcelona Supercomputing Center (Spain)","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087802498","display_name":"Marc Jord\u00e0","orcid":"https://orcid.org/0000-0003-1458-7706"},"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":"Marc Jord\u00e0","raw_affiliation_strings":["Barcelona Supercomputing Center, Spain","Barcelona Supercomputing Center (Spain)"],"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center, Spain","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]},{"raw_affiliation_string":"Barcelona Supercomputing Center (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/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]},{"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":["GB","US"],"is_corresponding":false,"raw_author_name":"Isaac Gelado","raw_affiliation_strings":["NVIDIA, USA","[NVIDIA, USA]"],"affiliations":[{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"[NVIDIA, USA]","institution_ids":["https://openalex.org/I1304085615"]}]},{"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, Spain / Barcelona Supercomputing Center, Spain","Universitat Politecnica de Catalunya, Spain; Barcelona Supercomputing Center, Spain#TAB#"],"affiliations":[{"raw_affiliation_string":"Universitat Polit\u00e8cnica de Catalunya, Spain / Barcelona Supercomputing Center, Spain","institution_ids":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"raw_affiliation_string":"Universitat Politecnica de Catalunya, Spain; Barcelona Supercomputing Center, Spain#TAB#","institution_ids":["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, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"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":0.9689,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.75533928,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"13","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9994999766349792,"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":0.9984999895095825,"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":0.8932920694351196},{"id":"https://openalex.org/keywords/pci-express","display_name":"PCI Express","score":0.8732538819313049},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6774519085884094},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.48048296570777893},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.45894303917884827},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.45285090804100037},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4495741128921509},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4332354962825775},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.411778062582016},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3201187252998352},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.273017942905426},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.21473610401153564},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10932514071464539}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8932920694351196},{"id":"https://openalex.org/C64270927","wikidata":"https://www.wikidata.org/wiki/Q206924","display_name":"PCI Express","level":3,"score":0.8732538819313049},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6774519085884094},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.48048296570777893},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.45894303917884827},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.45285090804100037},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4495741128921509},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4332354962825775},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.411778062582016},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3201187252998352},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.273017942905426},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.21473610401153564},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10932514071464539},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2716282.2716286","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2716282.2716286","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th Workshop on General Purpose Processing using GPUs","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":19,"referenced_works":["https://openalex.org/W1850405760","https://openalex.org/W1987873989","https://openalex.org/W2005818856","https://openalex.org/W2029764709","https://openalex.org/W2076279664","https://openalex.org/W2106500842","https://openalex.org/W2110195531","https://openalex.org/W2113190809","https://openalex.org/W2127547524","https://openalex.org/W2130561688","https://openalex.org/W2147743629","https://openalex.org/W2150606860","https://openalex.org/W2152496451","https://openalex.org/W2153644244","https://openalex.org/W2154786353","https://openalex.org/W2157632164","https://openalex.org/W2157802978","https://openalex.org/W2160454978","https://openalex.org/W4250814284"],"related_works":["https://openalex.org/W4385894176","https://openalex.org/W2347371119","https://openalex.org/W2612768808","https://openalex.org/W3131402800","https://openalex.org/W2388965158","https://openalex.org/W2366201982","https://openalex.org/W2808480228","https://openalex.org/W2593071546","https://openalex.org/W3062287","https://openalex.org/W2805641962"],"abstract_inverted_index":{"Discrete":[0],"GPUs":[1,35,135],"in":[2,51,228],"modern":[3],"multi-GPU":[4,43,90],"systems":[5,17,44,50,91,96],"can":[6,105,190],"transparently":[7],"access":[8,33],"each":[9,53],"other's":[10],"memories":[11,111],"through":[12,123],"the":[13,62,65,124,131,155,159,178,185,220,229],"PCIe":[14,156,168],"interconnect.":[15,126],"Future":[16],"will":[18],"improve":[19],"this":[20,79],"capability":[21],"by":[22],"including":[23],"better":[24],"GPU":[25,54,76,110,119,180,187],"interconnects":[26],"such":[27],"as":[28,68],"NVLink.":[29],"However,":[30],"remote":[31,162],"memory":[32,95],"across":[34,75,108],"has":[36,173],"gone":[37],"largely":[38],"unnoticed":[39],"among":[40],"programmers,":[41],"and":[42,112,142,158,172,199],"are":[45,136],"still":[46],"programmed":[47],"like":[48,92],"distributed":[49],"which":[52],"only":[55],"accesses":[56,163],"its":[57,193],"own":[58],"memory.":[59],"This":[60],"increases":[61],"complexity":[63],"of":[64,86,130,154,161,196,232],"host":[66,230],"code":[67,218,231],"programmers":[69],"need":[70],"to":[71,88,177,206],"explicitly":[72],"communicate":[73],"data":[74,103,113],"memories.":[77],"In":[78],"paper":[80],"we":[81,182],"present":[82,149],"GPU-SM,":[83,102],"a":[84,117,139,150,210,224],"set":[85],"guidelines":[87],"program":[89],"NUMA":[93],"shared":[94],"with":[97,212,215],"minimal":[98],"performance":[99,152],"overheads.":[100],"Using":[101],"structures":[104],"be":[106],"decomposed":[107],"several":[109],"that":[114,184],"resides":[115],"on":[116,134,164,209],"different":[118],"is":[120],"accessed":[121],"remotely":[122],"PCI":[125],"The":[127],"programmability":[128],"benefits":[129],"shared-memory":[132],"model":[133,189],"shown":[137],"using":[138],"finite":[140,197,233],"difference":[141,198],"an":[143],"image":[144,200],"filtering":[145,201],"applications.":[146],"We":[147],"also":[148],"detailed":[151],"analysis":[153],"interconnect":[157],"impact":[160],"kernel":[165],"performance.":[166],"While":[167],"imposes":[169],"long":[170],"latency":[171],"limited":[174],"bandwidth":[175],"compared":[176],"local":[179],"memory,":[181],"show":[183],"highly-multithreaded":[186],"execution":[188],"help":[191],"reducing":[192],"costs.":[194],"Evaluation":[195],"GPU-SM":[202],"implementations":[203,222],"shows":[204],"close":[205],"linear":[207],"speedups":[208],"system":[211],"4":[213],"GPUs,":[214],"much":[216],"simpler":[217],"than":[219],"original":[221],"(e.g.":[223],"40%":[225],"SLOC":[226],"reduction":[227],"difference).":[234]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}