{"id":"https://openalex.org/W2530879419","doi":"https://doi.org/10.1145/2968456.2968476","title":"Zero and data reuse-aware fast convolution for deep neural networks on GPU","display_name":"Zero and data reuse-aware fast convolution for deep neural networks on GPU","publication_year":2016,"publication_date":"2016-10-01","ids":{"openalex":"https://openalex.org/W2530879419","doi":"https://doi.org/10.1145/2968456.2968476","mag":"2530879419"},"language":"en","primary_location":{"id":"doi:10.1145/2968456.2968476","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2968456.2968476","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Eleventh IEEE/ACM/IFIP International Conference on Hardware/Software Codesign and System Synthesis","raw_type":"proceedings-article"},"type":"conference-paper","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/A5026159722","display_name":"Hyunsun Park","orcid":"https://orcid.org/0000-0003-1338-654X"},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]},{"id":"https://openalex.org/I2799891827","display_name":"Korea Post","ror":"https://ror.org/00p45d091","country_code":"KR","type":"government","lineage":["https://openalex.org/I2799891827","https://openalex.org/I2801339556","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyunsun Park","raw_affiliation_strings":["POSTECH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"POSTECH","institution_ids":["https://openalex.org/I123900574","https://openalex.org/I2799891827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100357419","display_name":"Dongyoung Kim","orcid":"https://orcid.org/0000-0002-1441-9254"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dongyoung Kim","raw_affiliation_strings":["Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029188471","display_name":"Junwhan Ahn","orcid":"https://orcid.org/0000-0001-7613-0571"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Junwhan Ahn","raw_affiliation_strings":["Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063521444","display_name":"Sungjoo Yoo","orcid":"https://orcid.org/0000-0002-5853-0675"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sungjoo Yoo","raw_affiliation_strings":["Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7122,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":{"value":0.93493238,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9987999796867371,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9983999729156494,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/titan","display_name":"Titan (rocket family)","score":0.8092395067214966},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7940467596054077},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7096098065376282},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.675333559513092},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6570546627044678},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5902049541473389},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.5072376728057861},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.49758628010749817},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.48185762763023376},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4371027946472168},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.37764155864715576},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.34908080101013184},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.33084607124328613},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.26779264211654663},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26057296991348267},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08321502804756165}],"concepts":[{"id":"https://openalex.org/C50805821","wikidata":"https://www.wikidata.org/wiki/Q1136670","display_name":"Titan (rocket family)","level":2,"score":0.8092395067214966},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7940467596054077},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7096098065376282},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.675333559513092},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6570546627044678},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5902049541473389},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.5072376728057861},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.49758628010749817},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.48185762763023376},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4371027946472168},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37764155864715576},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.34908080101013184},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.33084607124328613},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.26779264211654663},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26057296991348267},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08321502804756165},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2968456.2968476","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2968456.2968476","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Eleventh IEEE/ACM/IFIP International Conference on Hardware/Software Codesign and System Synthesis","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":32,"referenced_works":["https://openalex.org/W1487564550","https://openalex.org/W1667652561","https://openalex.org/W1686810756","https://openalex.org/W1789336918","https://openalex.org/W1902041153","https://openalex.org/W1922123711","https://openalex.org/W1974078116","https://openalex.org/W1979527452","https://openalex.org/W1996901117","https://openalex.org/W1998917233","https://openalex.org/W2093043622","https://openalex.org/W2097117768","https://openalex.org/W2104636679","https://openalex.org/W2131524184","https://openalex.org/W2152839228","https://openalex.org/W2155893237","https://openalex.org/W2161388792","https://openalex.org/W2167215970","https://openalex.org/W2172654076","https://openalex.org/W2194775991","https://openalex.org/W2291160084","https://openalex.org/W2300242332","https://openalex.org/W2618530766","https://openalex.org/W2963674932","https://openalex.org/W2964299589","https://openalex.org/W3023154643","https://openalex.org/W4234833047","https://openalex.org/W6600336938","https://openalex.org/W6601031873","https://openalex.org/W6672970576","https://openalex.org/W6819060087","https://openalex.org/W6836035380"],"related_works":["https://openalex.org/W2408545863","https://openalex.org/W643179351","https://openalex.org/W2905265805","https://openalex.org/W2740469715","https://openalex.org/W2162805293","https://openalex.org/W2064207836","https://openalex.org/W2025174650","https://openalex.org/W2478963093","https://openalex.org/W2013629274","https://openalex.org/W3001496181"],"abstract_inverted_index":{"Convolution":[0],"operations":[1,110],"dominate":[2],"the":[3,20,23,31,49,100,118,143,155],"total":[4],"execution":[5],"time":[6],"of":[7,22,52,91,120],"deep":[8,133],"convolutional":[9],"neural":[10],"networks":[11],"(CNNs).":[12],"In":[13,66,96],"this":[14],"paper,":[15],"we":[16,73,103],"aim":[17],"at":[18],"enhancing":[19],"performance":[21,50,153,170],"state-of-the-art":[24],"convolution":[25,54,113,152],"algorithm":[26],"(called":[27,94,114],"Winograd":[28,53,112,157],"convolution)":[29],"on":[30,37,136,171],"GPU.":[32],"Our":[33,128],"work":[34],"is":[35,55],"based":[36],"two":[38],"observations:":[39],"(1)":[40],"CNNs":[41],"often":[42],"have":[43],"abundant":[44,70],"zero":[45,71,88],"weights":[46],"and":[47,77,138,147],"(2)":[48],"benefit":[51],"limited":[56],"mainly":[57],"due":[58],"to":[59,68,98],"extra":[60],"additions":[61],"incurred":[62],"during":[63],"data":[64,93,105],"transformation.":[65],"order":[67],"exploit":[69],"weights,":[72],"propose":[74],"a":[75,131,172],"low-overhead":[76],"efficient":[78],"hardware":[79,163,174],"mechanism":[80],"that":[81,84,142],"skips":[82],"multiplications":[83],"will":[85],"always":[86],"give":[87],"results":[89],"regardless":[90],"input":[92],"ZeroSkip).":[95],"addition,":[97],"leverage":[99],"second":[101],"observation,":[102],"present":[104],"reuse":[106],"optimization":[107],"for":[108],"addition":[109],"in":[111],"AddOpt),":[115],"which":[116],"improves":[117],"utilization":[119],"local":[121],"registers,":[122],"thereby":[123],"reducing":[124],"on-chip":[125],"cache":[126],"accesses.":[127],"experiments":[129],"with":[130],"real-world":[132],"CNN,":[134],"VGG-16,":[135],"GPGPU-Sim":[137],"Titan":[139,176],"X":[140],"show":[141],"proposed":[144],"methods,":[145],"ZeroSkip":[146],"AddOpt,":[148],"achieve":[149],"51.8%":[150],"higher":[151,169],"than":[154],"baseline":[156],"convolution.":[158],"Moreover,":[159],"even":[160],"without":[161],"any":[162],"modification,":[164],"AddOpt":[165],"alone":[166],"gives":[167],"35.6%":[168],"real":[173],"platform,":[175],"X.":[177]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":10}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}