{"id":"https://openalex.org/W2172257066","doi":"https://doi.org/10.1109/hipc.2011.6152427","title":"A multi-GPU algorithm for communication in neuronal network simulations","display_name":"A multi-GPU algorithm for communication in neuronal network simulations","publication_year":2011,"publication_date":"2011-12-01","ids":{"openalex":"https://openalex.org/W2172257066","doi":"https://doi.org/10.1109/hipc.2011.6152427","mag":"2172257066"},"language":"en","primary_location":{"id":"doi:10.1109/hipc.2011.6152427","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hipc.2011.6152427","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 18th International Conference on High Performance Computing","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/A5012679482","display_name":"Raphael Y. de Camargo","orcid":"https://orcid.org/0000-0001-6021-747X"},"institutions":[{"id":"https://openalex.org/I71715416","display_name":"Universidade Federal do ABC","ror":"https://ror.org/028kg9j04","country_code":"BR","type":"education","lineage":["https://openalex.org/I71715416"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Raphael Y. de Camargo","raw_affiliation_strings":["Center for Mathematics, Computation and Cognition, Universidade Federal do ABC, Brazil"],"affiliations":[{"raw_affiliation_string":"Center for Mathematics, Computation and Cognition, Universidade Federal do ABC, Brazil","institution_ids":["https://openalex.org/I71715416"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5012679482"],"corresponding_institution_ids":["https://openalex.org/I71715416"],"apc_list":null,"apc_paid":null,"fwci":0.265,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.64778121,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"3994","issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10581","display_name":"Neural dynamics and brain function","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11601","display_name":"Neuroscience and Neural Engineering","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/2804","display_name":"Cellular and Molecular Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8364620804786682},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.7472528219223022},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6405826807022095},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.4826991558074951},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.44205543398857117},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.4338739514350891},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.43336474895477295},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4165041148662567},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3932148218154907},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.2457398772239685}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8364620804786682},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.7472528219223022},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6405826807022095},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.4826991558074951},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.44205543398857117},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.4338739514350891},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.43336474895477295},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4165041148662567},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3932148218154907},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.2457398772239685},{"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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":1,"locations":[{"id":"doi:10.1109/hipc.2011.6152427","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hipc.2011.6152427","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 18th International Conference on High Performance Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W206482553","https://openalex.org/W622828751","https://openalex.org/W1532842753","https://openalex.org/W1608524095","https://openalex.org/W1985940938","https://openalex.org/W1993792073","https://openalex.org/W2048895682","https://openalex.org/W2058443342","https://openalex.org/W2071007053","https://openalex.org/W2078391824","https://openalex.org/W2134224856","https://openalex.org/W2152502378","https://openalex.org/W2155677028","https://openalex.org/W2164653071","https://openalex.org/W2169377408","https://openalex.org/W2482214201","https://openalex.org/W4285719527","https://openalex.org/W6636515797"],"related_works":["https://openalex.org/W3189307731","https://openalex.org/W1428699136","https://openalex.org/W2949962288","https://openalex.org/W2364686214","https://openalex.org/W1998560227","https://openalex.org/W2031026393","https://openalex.org/W2473478803","https://openalex.org/W2063611263","https://openalex.org/W2729363167","https://openalex.org/W2331916929"],"abstract_inverted_index":{"Graphical":[0],"Processing":[1],"Units":[2],"(GPUs)":[3],"are":[4,17],"frequently":[5],"used":[6],"for":[7,106,116,120],"simulations":[8,121],"of":[9,20,62,82,91,113],"physical":[10],"and":[11,80,98,125],"biological":[12],"systems.":[13],"The":[14],"simulated":[15],"systems":[16],"often":[18],"composed":[19],"simple":[21],"elements":[22],"that":[23,58,71],"communicate":[24,41],"only":[25],"with":[26,42,122,132,136,142],"their":[27],"neighbors.":[28],"But":[29],"in":[30,46,84,102,162,166],"some":[31],"systems,":[32],"such":[33],"as":[34],"large-scale":[35,107],"neuronal":[36,108,152],"networks,":[37],"each":[38],"element":[39,45],"can":[40,73],"any":[43],"other":[44],"the":[47,76,85,88,117,150,163,167],"simulation.":[48],"In":[49],"this":[50,60,100],"work,":[51],"we":[52,148],"present":[53],"an":[54],"efficient":[55],"CUDA":[56],"algorithm":[57,101],"enables":[59],"type":[61],"communication,":[63],"even":[64],"when":[65,140],"using":[66,128],"multiple":[67],"GPUs.":[68],"We":[69,96,110],"show":[70],"it":[72],"benefit":[74],"from":[75],"large":[77],"memory":[78],"bandwidth":[79],"number":[81,90],"cores":[83],"GPU,":[86],"despite":[87],"small":[89],"required":[92],"floating":[93],"point":[94],"operations.":[95],"implemented":[97],"evaluated":[99],"a":[103,129,143],"GPU":[104,164],"simulator":[105],"networks.":[109],"obtained":[111],"speedups":[112],"over":[114],"10":[115],"communication":[118],"steps":[119],"50k":[123],"neurons":[124],"50M":[126],"connections,":[127],"single":[130],"computer":[131],"2":[133,137],"graphic":[134],"boards":[135],"GPUs":[138],"each,":[139],"compared":[141],"modern":[144],"quad-core":[145],"CPU.":[146,168],"When":[147],"consider":[149],"complete":[151],"network":[153],"simulation,":[154],"its":[155],"execution":[156],"was":[157],"nearly":[158],"40":[159],"times":[160],"faster":[161],"than":[165]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}