{"id":"https://openalex.org/W4221037885","doi":"https://doi.org/10.1007/s11227-022-04336-3","title":"A batched GEMM optimization framework for deep learning","display_name":"A batched GEMM optimization framework for deep learning","publication_year":2022,"publication_date":"2022-03-19","ids":{"openalex":"https://openalex.org/W4221037885","doi":"https://doi.org/10.1007/s11227-022-04336-3"},"language":"en","primary_location":{"id":"doi:10.1007/s11227-022-04336-3","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11227-022-04336-3","pdf_url":null,"source":{"id":"https://openalex.org/S32326811","display_name":"The Journal of Supercomputing","issn_l":"0920-8542","issn":["0920-8542","1573-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of Supercomputing","raw_type":"journal-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/A5051367545","display_name":"Zhiwei Yang","orcid":"https://orcid.org/0000-0002-0534-158X"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwei Yang","raw_affiliation_strings":["School of Software Engineering, South China University of Technology, Guanzhou, 510006, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software Engineering, South China University of Technology, Guanzhou, 510006, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100366001","display_name":"Lu Lu","orcid":"https://orcid.org/0000-0001-6372-7088"},"institutions":[{"id":"https://openalex.org/I142066694","display_name":"ITRI International","ror":"https://ror.org/04wwsbd59","country_code":"US","type":"facility","lineage":["https://openalex.org/I142066694"]},{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN","US"],"is_corresponding":true,"raw_author_name":"Lu Lu","raw_affiliation_strings":["Modern Industrial Technology Research Institute, South China University of Technology, Zhongshan, 528400, Guangdong, China","School of Computer Science and Engineering, South China University of Technology, Guangzhou, 510006, Guangdong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Modern Industrial Technology Research Institute, South China University of Technology, Zhongshan, 528400, Guangdong, China","institution_ids":["https://openalex.org/I142066694"]},{"raw_affiliation_string":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, 510006, Guangdong, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101688784","display_name":"Ruimin Wang","orcid":"https://orcid.org/0009-0007-8349-0568"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruimin Wang","raw_affiliation_strings":["School of Computer Science and Engineering, South China University of Technology, Guangzhou, 510006, Guangdong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, 510006, Guangdong, China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100366001"],"corresponding_institution_ids":["https://openalex.org/I142066694","https://openalex.org/I90610280"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":0.783,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.70891849,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"78","issue":"11","first_page":"13393","last_page":"13408"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.995199978351593,"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":0.995199978351593,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9940000176429749,"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/T12303","display_name":"Tensor decomposition and applications","score":0.9923999905586243,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8754168748855591},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7102245092391968},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6370257139205933},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6256221532821655},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6237649917602539},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.5715342164039612},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.5509785413742065},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.498490571975708},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4361034631729126},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4109594225883484},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.40444427728652954},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34160247445106506}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8754168748855591},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7102245092391968},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6370257139205933},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6256221532821655},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6237649917602539},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.5715342164039612},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.5509785413742065},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.498490571975708},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4361034631729126},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4109594225883484},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.40444427728652954},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34160247445106506},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11227-022-04336-3","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11227-022-04336-3","pdf_url":null,"source":{"id":"https://openalex.org/S32326811","display_name":"The Journal of Supercomputing","issn_l":"0920-8542","issn":["0920-8542","1573-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of Supercomputing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1978642402","https://openalex.org/W2090593986","https://openalex.org/W2097117768","https://openalex.org/W2099021415","https://openalex.org/W2117539524","https://openalex.org/W2499931820","https://openalex.org/W2521727659","https://openalex.org/W2549139847","https://openalex.org/W2570467259","https://openalex.org/W2605739168","https://openalex.org/W2617819327","https://openalex.org/W2913790721","https://openalex.org/W2914926228","https://openalex.org/W2953264125","https://openalex.org/W2963674387","https://openalex.org/W2998957070","https://openalex.org/W3105696640","https://openalex.org/W6603092227"],"related_works":["https://openalex.org/W2983282793","https://openalex.org/W4287593139","https://openalex.org/W3099313426","https://openalex.org/W1506547947","https://openalex.org/W3189307731","https://openalex.org/W2086146848","https://openalex.org/W4206811032","https://openalex.org/W2995605830","https://openalex.org/W2949962288","https://openalex.org/W2364686214"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-19T15:47:20.252518","created_date":"2025-10-10T00:00:00"}
