{"id":"https://openalex.org/W2888193973","doi":"https://doi.org/10.1109/snpd.2018.8441056","title":"Performance of Convolution Neural Network based on Multiple GPUs with Different Data Communication Models","display_name":"Performance of Convolution Neural Network based on Multiple GPUs with Different Data Communication Models","publication_year":2018,"publication_date":"2018-06-01","ids":{"openalex":"https://openalex.org/W2888193973","doi":"https://doi.org/10.1109/snpd.2018.8441056","mag":"2888193973"},"language":"en","primary_location":{"id":"doi:10.1109/snpd.2018.8441056","is_oa":false,"landing_page_url":"https://doi.org/10.1109/snpd.2018.8441056","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 19th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD)","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/A5003302169","display_name":"Che\u2010Lun Hung","orcid":"https://orcid.org/0000-0002-8906-9367"},"institutions":[{"id":"https://openalex.org/I177918364","display_name":"Providence University","ror":"https://ror.org/03fcpsq87","country_code":"TW","type":"education","lineage":["https://openalex.org/I177918364"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Che-Lun Hung","raw_affiliation_strings":["Department of Computer Science and Communication Engineering, Providence University, Taichung City, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Communication Engineering, Providence University, Taichung City, Taiwan","institution_ids":["https://openalex.org/I177918364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083716563","display_name":"Yiyang Lin","orcid":"https://orcid.org/0000-0001-8572-649X"},"institutions":[{"id":"https://openalex.org/I177918364","display_name":"Providence University","ror":"https://ror.org/03fcpsq87","country_code":"TW","type":"education","lineage":["https://openalex.org/I177918364"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Yang Lin","raw_affiliation_strings":["Department of Computer Science and Information Engineering, Providence University, Taichung City, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, Providence University, Taichung City, Taiwan","institution_ids":["https://openalex.org/I177918364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101474162","display_name":"Chuan Yi Tang","orcid":"https://orcid.org/0000-0003-0729-1624"},"institutions":[{"id":"https://openalex.org/I177918364","display_name":"Providence University","ror":"https://ror.org/03fcpsq87","country_code":"TW","type":"education","lineage":["https://openalex.org/I177918364"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chuan Yi Tang","raw_affiliation_strings":["Department of Computer Science and Information Engineering, Providence University, Taichung City, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, Providence University, Taichung City, Taiwan","institution_ids":["https://openalex.org/I177918364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040330532","display_name":"Chilung Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chilung Wang","raw_affiliation_strings":["Information and Communications Research Laboratories, Technology Research Institute, Zhudong Township, Taiwan"],"affiliations":[{"raw_affiliation_string":"Information and Communications Research Laboratories, Technology Research Institute, Zhudong Township, Taiwan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054287076","display_name":"Ming-Chiang Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ming-Chiang Chen","raw_affiliation_strings":["Information and Communications Research Laboratories, Technology Research Institute, Zhudong Township, Taiwan"],"affiliations":[{"raw_affiliation_string":"Information and Communications Research Laboratories, Technology Research Institute, Zhudong Township, Taiwan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5003302169"],"corresponding_institution_ids":["https://openalex.org/I177918364"],"apc_list":null,"apc_paid":null,"fwci":0.1045,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.44201337,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"87","last_page":"92"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8851989507675171},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.6959296464920044},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6893399357795715},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5957943797111511},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5765990018844604},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.5735368132591248},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5524736642837524},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.5248851180076599},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5202699899673462},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4749608039855957},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4729991555213928},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.42008838057518005},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4115602374076843},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3966783285140991},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3604316711425781},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.34640225768089294},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1619354784488678},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1510714292526245},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.1375828981399536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8851989507675171},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.6959296464920044},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6893399357795715},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5957943797111511},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5765990018844604},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.5735368132591248},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5524736642837524},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.5248851180076599},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5202699899673462},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4749608039855957},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4729991555213928},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.42008838057518005},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4115602374076843},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3966783285140991},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3604316711425781},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.34640225768089294},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1619354784488678},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1510714292526245},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.1375828981399536},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/snpd.2018.8441056","is_oa":false,"landing_page_url":"https://doi.org/10.1109/snpd.2018.8441056","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 19th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W753012316","https://openalex.org/W1510052597","https://openalex.org/W1572016165","https://openalex.org/W1606347560","https://openalex.org/W1686810756","https://openalex.org/W2016323639","https://openalex.org/W2097117768","https://openalex.org/W2105549957","https://openalex.org/W2143031615","https://openalex.org/W2155893237","https://openalex.org/W2163605009","https://openalex.org/W2171278097","https://openalex.org/W2186615578","https://openalex.org/W2194775991","https://openalex.org/W2266822037","https://openalex.org/W2271840356","https://openalex.org/W2405883473","https://openalex.org/W2524428287","https://openalex.org/W2750150650","https://openalex.org/W2950094539","https://openalex.org/W6622239757","https://openalex.org/W6634263594","https://openalex.org/W6687483927","https://openalex.org/W6693270258"],"related_works":["https://openalex.org/W2140186469","https://openalex.org/W4280563792","https://openalex.org/W4318719684","https://openalex.org/W4318559728","https://openalex.org/W3183136280","https://openalex.org/W2775233965","https://openalex.org/W3114716045","https://openalex.org/W4360995913","https://openalex.org/W2609418570","https://openalex.org/W3114025147"],"abstract_inverted_index":{"Recently,":[0],"deep":[1,40],"learning":[2,41],"technologies":[3],"have":[4],"been":[5],"utilized":[6],"in":[7,18],"many":[8],"scientific":[9],"domains":[10],"successfully.":[11],"Convolution":[12],"neural":[13,27],"networks":[14],"are":[15],"common":[16],"used":[17],"image":[19],"understanding":[20],"problems.":[21],"However,":[22],"to":[23,55],"train":[24,56],"a":[25],"convolution":[26],"network":[28],"model":[29,57],"with":[30,90],"huge":[31],"amount":[32],"of":[33,39,73,76],"images":[34],"is":[35],"time-consuming":[36],"task.":[37],"Most":[38],"frameworks,":[42],"such":[43],"as":[44],"Caffe,":[45],"TensorFlow,":[46],"Torch,":[47],"Keras,":[48],"MxNet,":[49],"and":[50,82],"so":[51],"forth,":[52],"support":[53],"GPU":[54,80,88],"fast;":[58],"especially":[59],"executing":[60],"these":[61],"models":[62],"on":[63],"multiple":[64],"GPUs.":[65],"In":[66],"this":[67],"work,":[68],"we":[69],"present":[70],"the":[71],"comparison":[72],"computation":[74],"performance":[75,98],"AlexNet":[77],"among":[78],"different":[79],"servers":[81,89],"hyperparameters.":[83],"The":[84],"results":[85],"shows":[86],"that":[87],"high":[91],"bandwidth":[92],"rate,":[93],"NVLINK,":[94],"can":[95],"achieve":[96],"better":[97],"than":[99],"others.":[100]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
