{"id":"https://openalex.org/W4300846918","doi":"https://doi.org/10.1145/3546000.3546011","title":"Performance Optimization of Sparse Deep Neural Networks Based on GPU","display_name":"Performance Optimization of Sparse Deep Neural Networks Based on GPU","publication_year":2022,"publication_date":"2022-06-23","ids":{"openalex":"https://openalex.org/W4300846918","doi":"https://doi.org/10.1145/3546000.3546011"},"language":"en","primary_location":{"id":"doi:10.1145/3546000.3546011","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3546000.3546011","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th International Conference on High Performance Compilation, Computing and Communications","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/A5003219096","display_name":"yucheng shi","orcid":null},"institutions":[{"id":"https://openalex.org/I116265982","display_name":"Qinghai University","ror":"https://ror.org/05h33bt13","country_code":"CN","type":"education","lineage":["https://openalex.org/I116265982"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"yucheng shi","raw_affiliation_strings":["Department of Computer Technology and Applications, Qinghai university, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Technology and Applications, Qinghai university, China","institution_ids":["https://openalex.org/I116265982"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089181435","display_name":"Longyun Ren","orcid":null},"institutions":[{"id":"https://openalex.org/I116265982","display_name":"Qinghai University","ror":"https://ror.org/05h33bt13","country_code":"CN","type":"education","lineage":["https://openalex.org/I116265982"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"long ren","raw_affiliation_strings":["Informationization Technolog, Qinghai university, China"],"affiliations":[{"raw_affiliation_string":"Informationization Technolog, Qinghai university, China","institution_ids":["https://openalex.org/I116265982"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5003219096"],"corresponding_institution_ids":["https://openalex.org/I116265982"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09178159,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"72","last_page":"76"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9965000152587891,"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":0.9965000152587891,"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/T10320","display_name":"Neural Networks and Applications","score":0.9887999892234802,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9876999855041504,"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/cuda","display_name":"CUDA","score":0.9146355986595154},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.817396879196167},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.7593665719032288},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.7460329532623291},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6102391481399536},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.6050854921340942},{"id":"https://openalex.org/keywords/matlab","display_name":"MATLAB","score":0.5881083011627197},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5669192671775818},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.52176433801651},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.42011114954948425}],"concepts":[{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.9146355986595154},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.817396879196167},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.7593665719032288},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.7460329532623291},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6102391481399536},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.6050854921340942},{"id":"https://openalex.org/C2780365114","wikidata":"https://www.wikidata.org/wiki/Q169478","display_name":"MATLAB","level":2,"score":0.5881083011627197},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5669192671775818},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.52176433801651},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.42011114954948425},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3546000.3546011","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3546000.3546011","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th International Conference on High Performance Compilation, Computing and Communications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2003840611","https://openalex.org/W2088866486","https://openalex.org/W2111669132","https://openalex.org/W2121492601","https://openalex.org/W2482957168","https://openalex.org/W2523437372","https://openalex.org/W2551895583","https://openalex.org/W2554342856","https://openalex.org/W2564583780","https://openalex.org/W2990007648","https://openalex.org/W2998966531","https://openalex.org/W3000280594","https://openalex.org/W3014399784","https://openalex.org/W3019166713","https://openalex.org/W4299996258"],"related_works":["https://openalex.org/W3189307731","https://openalex.org/W2949962288","https://openalex.org/W2364686214","https://openalex.org/W1428699136","https://openalex.org/W1998560227","https://openalex.org/W4377865163","https://openalex.org/W3193857078","https://openalex.org/W2568266861","https://openalex.org/W2888956734","https://openalex.org/W3000197790"],"abstract_inverted_index":{"Deep":[0],"neural":[1,19,28,40,54,86,110],"networks":[2,29],"are":[3],"widely":[4],"used":[5],"in":[6],"various":[7],"fields.":[8],"However,":[9],"due":[10],"to":[11,69],"the":[12,16,21,24,37,47,59,63,70,74,79,83,92,96,104,108,116],"large":[13],"scale":[14],"of":[15,26,36,50,58,62,73,82,95],"latest":[17],"deep":[18,27,39,53,85,109],"networks,":[20],"research":[22],"on":[23,42,89],"sparsity":[25],"is":[30,66,99],"constantly":[31],"carried":[32],"out.":[33],"The":[34,56],"implementation":[35,88],"sparse":[38,52,84],"network":[41,87,111],"GPU":[43,60,93],"can":[44],"further":[45],"accelerate":[46],"computing":[48],"speed":[49],"a":[51],"network.":[55],"performance":[57],"code":[61,94],"CUDA":[64,97],"version":[65,98,106],"far":[67],"superior":[68],"CPU":[71],"codes":[72],"Matlab":[75],"version,":[76],"which":[77],"confirms":[78],"great":[80],"superiority":[81],"GPU.":[90],"And":[91],"up":[100],"x1.61":[101],"faster":[102],"than":[103],"CUSPARSE":[105],"when":[107],"has":[112],"1024":[113],"neurons":[114],"and":[115],"1920":[117],"layers.":[118]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}