{"id":"https://openalex.org/W3008010570","doi":"https://doi.org/10.1145/3366428.3380771","title":"Automatic generation of specialized direct convolutions for mobile GPUs","display_name":"Automatic generation of specialized direct convolutions for mobile GPUs","publication_year":2020,"publication_date":"2020-02-19","ids":{"openalex":"https://openalex.org/W3008010570","doi":"https://doi.org/10.1145/3366428.3380771","mag":"3008010570"},"language":"en","primary_location":{"id":"doi:10.1145/3366428.3380771","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3366428.3380771","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th Annual Workshop on General Purpose Processing using Graphics Processing Unit","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/files/133591458/Automatic_Generation_of_Specialized_MOGERS_DOA20012020_AFV.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086175397","display_name":"Naums Mogers","orcid":"https://orcid.org/0000-0002-8789-8268"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Naums Mogers","raw_affiliation_strings":["University of Edinburgh, Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007676144","display_name":"Valentin Radu","orcid":"https://orcid.org/0000-0003-3502-4355"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Valentin Radu","raw_affiliation_strings":["University of Edinburgh, Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100386366","display_name":"Lu Li","orcid":"https://orcid.org/0009-0002-8665-0612"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Lu Li","raw_affiliation_strings":["University of Edinburgh, Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049917315","display_name":"Jack Turner","orcid":"https://orcid.org/0000-0003-4470-1805"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jack Turner","raw_affiliation_strings":["University of Edinburgh, Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027001025","display_name":"Michael O\u2019Boyle","orcid":"https://orcid.org/0000-0003-1619-5052"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Michael O'Boyle","raw_affiliation_strings":["University of Edinburgh, Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050229154","display_name":"Christophe Dubach","orcid":"https://orcid.org/0000-0003-4811-2469"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Christophe Dubach","raw_affiliation_strings":["University of Edinburgh, Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":1.025,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.83487781,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"41","last_page":"50"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":1.0,"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":1.0,"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9990000128746033,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9980000257492065,"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":0.8697751760482788},{"id":"https://openalex.org/keywords/vendor","display_name":"Vendor","score":0.7220652103424072},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.5881773233413696},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5692585706710815},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5433628559112549},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4895404279232025},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4885495603084564},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4480389952659607},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.43757399916648865},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.42331764101982117},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3973616361618042},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2712763845920563},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.21871796250343323}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8697751760482788},{"id":"https://openalex.org/C2777338717","wikidata":"https://www.wikidata.org/wiki/Q1762621","display_name":"Vendor","level":2,"score":0.7220652103424072},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.5881773233413696},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5692585706710815},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5433628559112549},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4895404279232025},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4885495603084564},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4480389952659607},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.43757399916648865},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.42331764101982117},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3973616361618042},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2712763845920563},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.21871796250343323},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3366428.3380771","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3366428.3380771","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th Annual Workshop on General Purpose Processing using Graphics Processing Unit","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/1cf41805-5447-424b-a724-75e180cf62ff","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/1cf41805-5447-424b-a724-75e180cf62ff","pdf_url":"https://www.research.ed.ac.uk/files/133591458/Automatic_Generation_of_Specialized_MOGERS_DOA20012020_AFV.pdf","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Mogers, N, Radu, V, Li, L, Turner, J, O'Boyle, M & Dubach, C 2020, Automatic Generation of Specialized Direct Convolutions for Mobile GPUs. in GPGPU '20: Proceedings of the 13th Annual Workshop on General Purpose Processing using Graphics Processing Unit. pp. 41-50, 13th Workshop on General Purpose Processing Using GPU (GPGPU 2020) , San Diego, California, United States, 23/02/20. https://doi.org/10.1145/3366428.3380771","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/1cf41805-5447-424b-a724-75e180cf62ff","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/1cf41805-5447-424b-a724-75e180cf62ff","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Mogers, N, Radu, V, Li, L, Turner, J, O'Boyle, M & Dubach, C 2020, Automatic Generation of Specialized Direct Convolutions for Mobile GPUs. in GPGPU '20: Proceedings of the 13th Annual Workshop on General Purpose Processing using Graphics Processing Unit. pp. 41-50, 13th Workshop on General Purpose Processing Using GPU (GPGPU 2020) , San Diego, California, United States, 23/02/20. https://doi.org/10.1145/3366428.3380771","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/1cf41805-5447-424b-a724-75e180cf62ff","is_oa":false,"landing_page_url":"http://hdl.handle.net/20.500.11820/1cf41805-5447-424b-a724-75e180cf62ff","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:publications/1cf41805-5447-424b-a724-75e180cf62ff","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/1cf41805-5447-424b-a724-75e180cf62ff","pdf_url":"https://www.research.ed.ac.uk/files/133591458/Automatic_Generation_of_Specialized_MOGERS_DOA20012020_AFV.pdf","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Mogers, N, Radu, V, Li, L, Turner, J, O'Boyle, M & Dubach, C 2020, Automatic Generation of Specialized Direct Convolutions for Mobile GPUs. in GPGPU '20: Proceedings of the 13th Annual Workshop on General Purpose Processing using Graphics Processing Unit. pp. 41-50, 13th Workshop on General Purpose Processing Using GPU (GPGPU 2020) , San Diego, California, United States, 23/02/20. https://doi.org/10.1145/3366428.3380771","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3276400090","display_name":"EPSRC Centre for Doctoral Training in Pervasive Parallelism","funder_award_id":"EP/L01503X/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G3739566937","display_name":null,"funder_award_id":"EP/R016690/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5811753289","display_name":null,"funder_award_id":"EP/M507258/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3008010570.pdf","grobid_xml":"https://content.openalex.org/works/W3008010570.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2163605009","https://openalex.org/W2172654076","https://openalex.org/W2531409750","https://openalex.org/W2752782242","https://openalex.org/W2772612468","https://openalex.org/W2913668833","https://openalex.org/W2951894856","https://openalex.org/W2963993763","https://openalex.org/W4240382083","https://openalex.org/W4242886852"],"related_works":["https://openalex.org/W4399354997","https://openalex.org/W3062287","https://openalex.org/W2380390332","https://openalex.org/W2742145873","https://openalex.org/W2023572661","https://openalex.org/W4245975140","https://openalex.org/W2532592438","https://openalex.org/W1977763331","https://openalex.org/W2062253548","https://openalex.org/W2076165488"],"abstract_inverted_index":{"Convolutional":[0],"Neural":[1],"Networks":[2],"(CNNs)":[3],"are":[4,43],"a":[5,76],"powerful":[6],"and":[7,20,92],"versatile":[8],"tool":[9],"for":[10,31,46,68],"performing":[11],"computer":[12],"vision":[13],"tasks":[14],"in":[15],"both":[16],"resource":[17],"constrained":[18],"settings":[19],"server-side":[21],"applications.":[22],"Most":[23],"GPU":[24],"hardware":[25,91],"vendors":[26],"provide":[27],"highly":[28],"tuned":[29],"libraries":[30,42],"CNNs":[32],"such":[33,51],"as":[34,52],"Nvidia's":[35],"cuDNN":[36],"or":[37,54],"ARM":[38],"Compute":[39],"Library.":[40],"Such":[41],"the":[44],"basis":[45],"higher-level,":[47],"commonly-used,":[48],"machine-learning":[49],"frameworks":[50],"PyTorch":[53],"Caffe,":[55],"abstracting":[56],"them":[57],"away":[58],"from":[59,72],"vendor-specific":[60],"implementation":[61],"details.":[62],"However,":[63],"writing":[64],"optimized":[65],"parallel":[66],"code":[67],"GPUs":[69],"is":[70],"far":[71],"trivial.":[73],"This":[74],"places":[75],"significant":[77],"burden":[78],"on":[79],"hardware-specific":[80],"library":[81],"writers":[82],"which":[83],"have":[84],"to":[85],"continually":[86],"play":[87],"catch-up":[88],"with":[89],"rapid":[90],"network":[93],"evolution.":[94]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}
