{"id":"https://openalex.org/W2945580137","doi":"https://doi.org/10.1109/access.2019.2918851","title":"Performance Evaluation of cuDNN Convolution Algorithms on NVIDIA Volta GPUs","display_name":"Performance Evaluation of cuDNN Convolution Algorithms on NVIDIA Volta GPUs","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2945580137","doi":"https://doi.org/10.1109/access.2019.2918851","mag":"2945580137"},"language":"en","primary_location":{"id":"doi:10.1109/access.2019.2918851","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2918851","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2019.2918851","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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 Jorda","raw_affiliation_strings":["Barcelona Supercomputing Center, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083524237","display_name":"Pedro Valero\u2010Lara","orcid":"https://orcid.org/0000-0002-1479-4310"},"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":"Pedro Valero-Lara","raw_affiliation_strings":["Barcelona Supercomputing Center, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000573036","display_name":"Antonio J. Pe\u00f1a","orcid":"https://orcid.org/0000-0002-3575-4617"},"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":"Antonio J. Pena","raw_affiliation_strings":["Barcelona Supercomputing Center, Barcelona, Spain"],"raw_orcid":"https://orcid.org/0000-0002-3575-4617","affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":4.3671,"has_fulltext":false,"cited_by_count":74,"citation_normalized_percentile":{"value":0.95602627,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"7","issue":null,"first_page":"70461","last_page":"70473"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9990000128746033,"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":0.9990000128746033,"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/T11019","display_name":"Image Enhancement Techniques","score":0.9961000084877014,"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/T13918","display_name":"Advanced Data and IoT Technologies","score":0.9932000041007996,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7891345024108887},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.699964702129364},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6783833503723145},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3847252130508423},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3615007996559143},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.14623981714248657}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7891345024108887},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.699964702129364},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6783833503723145},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3847252130508423},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3615007996559143},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.14623981714248657},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/access.2019.2918851","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2918851","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:dnet:upcommonspor::b3e83e38f2c6c4bbf0db915b79b2f0bf","is_oa":false,"landing_page_url":"http://hdl.handle.net/2117/167384","pdf_url":null,"source":{"id":"https://openalex.org/S4306402641","display_name":"LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Cient\u00edficas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4383465926","host_organization_name":"LA Referencia","host_organization_lineage":["https://openalex.org/I4383465926"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:doaj.org/article:fd2494dd399b4415915f067ef36ec90f","is_oa":true,"landing_page_url":"https://doaj.org/article/fd2494dd399b4415915f067ef36ec90f","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 7, Pp 70461-70473 (2019)","raw_type":"article"},{"id":"pmh:oai:upcommons.upc.edu:2117/167384","is_oa":true,"landing_page_url":"https://hdl.handle.net/2117/167384","pdf_url":null,"source":{"id":"https://openalex.org/S4377196262","display_name":"UPCommons institutional repository (Universitat Polit\u00e8cnica de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9617848","host_organization_name":"Universitat Polit\u00e8cnica de Catalunya","host_organization_lineage":["https://openalex.org/I9617848"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1109/access.2019.2918851","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2918851","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3989486137","display_name":"Advanced Ecosystem for Broad Heterogeneous Memory Usage","funder_award_id":"749516","funder_id":"https://openalex.org/F4320338337","funder_display_name":"H2020 Marie Sk\u0142odowska-Curie Actions"}],"funders":[{"id":"https://openalex.org/F4320338337","display_name":"H2020 Marie Sk\u0142odowska-Curie Actions","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1487564550","https://openalex.org/W1533861849","https://openalex.org/W1686810756","https://openalex.org/W1789336918","https://openalex.org/W1841592590","https://openalex.org/W1975818677","https://openalex.org/W2097117768","https://openalex.org/W2108598243","https://openalex.org/W2160815625","https://openalex.org/W2163605009","https://openalex.org/W2172654076","https://openalex.org/W2194775991","https://openalex.org/W2265127172","https://openalex.org/W2271840356","https://openalex.org/W2279098554","https://openalex.org/W2611453176","https://openalex.org/W2622428623","https://openalex.org/W2753032179","https://openalex.org/W2763421725","https://openalex.org/W2765439756","https://openalex.org/W2791673912","https://openalex.org/W2809624076","https://openalex.org/W2899771611","https://openalex.org/W2962949934","https://openalex.org/W2963340555","https://openalex.org/W3101543398","https://openalex.org/W4294371482","https://openalex.org/W4300537377","https://openalex.org/W4302296459","https://openalex.org/W4320930577","https://openalex.org/W6631943919","https://openalex.org/W6637151318","https://openalex.org/W6637373629","https://openalex.org/W6638020065","https://openalex.org/W6638783484","https://openalex.org/W6638839971","https://openalex.org/W6640442106","https://openalex.org/W6684191040","https://openalex.org/W6685315510","https://openalex.org/W6694517276","https://openalex.org/W6737185050","https://openalex.org/W6745245109","https://openalex.org/W6746023985","https://openalex.org/W6753069482","https://openalex.org/W6756040250"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2051487156","https://openalex.org/W2073681303","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109"],"abstract_inverted_index":{"Convolutional":[0],"neural":[1,34],"networks":[2,35],"(CNNs)":[3],"have":[4],"recently":[5],"attracted":[6],"considerable":[7],"attention":[8],"due":[9,77],"to":[10,78,100,220],"their":[11,37,143],"outstanding":[12],"accuracy":[13],"in":[14,87,102,114],"applications,":[15],"such":[16],"as":[17],"image":[18],"recognition":[19],"and":[20,49,63,90,160,175,188],"natural":[21],"language":[22],"processing.":[23],"While":[24],"one":[25],"advantage":[26],"of":[27,33,56,70,74,82,105,126,191],"the":[28,57,68,79,88,91,106,111,127,132,134,151,158,169,185,189,194,222],"CNNs":[29,89,159],"over":[30],"other":[31],"types":[32],"is":[36,43,97,218],"reduced":[38],"computational":[39],"cost,":[40],"faster":[41],"execution":[42,58],"still":[44],"desired":[45],"for":[46,142,172,204],"both":[47,173],"training":[48],"inference.":[50],"Since":[51],"convolution":[52,83,128,152,170,202],"operations":[53],"pose":[54],"most":[55,138,195],"time,":[59],"multiple":[60],"algorithms":[61,108,129,163],"were":[62],"are":[64,164,193],"being":[65],"developed":[66],"with":[67],"aim":[69],"accelerating":[71],"this":[72,119],"type":[73,94],"operations.":[75,145],"However,":[76],"wide":[80],"range":[81],"parameter":[84,153],"configurations":[85,154],"used":[86,136,157],"possible":[92],"data":[93,179],"representations,":[95],"it":[96],"not":[98],"straightforward":[99],"assess":[101],"advance":[103],"which":[104,162],"available":[107],"will":[109],"be":[110],"best":[112,223],"performing":[113],"each":[115],"particular":[116],"case.":[117],"In":[118,146],"paper,":[120],"we":[121,149],"present":[122],"a":[123,200],"performance":[124],"evaluation":[125],"provided":[130],"by":[131,137],"cuDNN,":[133],"library":[135],"deep":[139],"learning":[140],"frameworks":[141],"GPU":[144,201],"our":[147],"analysis,":[148],"leverage":[150],"from":[155],"widely":[156],"discuss":[161],"better":[165],"suited":[166],"depending":[167],"on":[168],"parameters":[171,197],"32":[174],"16-bit":[176,209],"floating-point":[177],"(FP)":[178],"representations.":[180],"Our":[181],"results":[182],"show":[183],"that":[184],"filter":[186],"size":[187],"number":[190],"inputs":[192],"significant":[196],"when":[198],"selecting":[199],"algorithm":[203],"32-bit":[205],"FP":[206],"data.":[207],"For":[208],"FP,":[210],"leveraging":[211],"specialized":[212],"arithmetic":[213],"units":[214],"(NVIDIA":[215],"Tensor":[216],"Cores)":[217],"key":[219],"obtain":[221],"performance.":[224]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":18},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}