{"id":"https://openalex.org/W3023485717","doi":"https://doi.org/10.1109/socc46988.2019.1570558495","title":"An Operation-Minimized FPGA Accelerator Design by Dynamically Exploiting Sparsity in CNN Winograd Transform","display_name":"An Operation-Minimized FPGA Accelerator Design by Dynamically Exploiting Sparsity in CNN Winograd Transform","publication_year":2019,"publication_date":"2019-09-01","ids":{"openalex":"https://openalex.org/W3023485717","doi":"https://doi.org/10.1109/socc46988.2019.1570558495","mag":"3023485717"},"language":"en","primary_location":{"id":"doi:10.1109/socc46988.2019.1570558495","is_oa":false,"landing_page_url":"https://doi.org/10.1109/socc46988.2019.1570558495","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 32nd IEEE International System-on-Chip Conference (SOCC)","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/A5009566154","display_name":"Xinkai Di","orcid":"https://orcid.org/0000-0002-6534-1995"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xinkai Di","raw_affiliation_strings":["University of Chinese Academy of Sciences,Beijing,China,100049","University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,Beijing,China,100049","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087392088","display_name":"Haigang Yang","orcid":"https://orcid.org/0000-0002-6471-9730"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haigang Yang","raw_affiliation_strings":["University of Chinese Academy of Sciences,Beijing,China,100049","University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,Beijing,China,100049","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102845279","display_name":"Zhihong Huang","orcid":"https://orcid.org/0000-0002-4235-2587"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihong Huang","raw_affiliation_strings":["University of Chinese Academy of Sciences,Beijing,China,100049","University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,Beijing,China,100049","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101805642","display_name":"Ning Mao","orcid":"https://orcid.org/0000-0001-8460-8168"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ning Mao","raw_affiliation_strings":["University of Chinese Academy of Sciences,Beijing,China,100049","University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,Beijing,China,100049","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5009566154"],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.2024,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.57299853,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"50","last_page":"55"},"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9997000098228455,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9975000023841858,"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":0.8341905474662781},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.7045754194259644},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6851717233657837},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5553737878799438},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.551079511642456},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4713413417339325},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.47068291902542114},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.44139859080314636},{"id":"https://openalex.org/keywords/virtex","display_name":"Virtex","score":0.42189884185791016},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.41910502314567566},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.41899892687797546},{"id":"https://openalex.org/keywords/application-specific-integrated-circuit","display_name":"Application-specific integrated circuit","score":0.4126688539981842},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.36028414964675903},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35935625433921814},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.34324049949645996},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18551334738731384}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8341905474662781},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7045754194259644},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6851717233657837},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5553737878799438},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.551079511642456},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4713413417339325},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.47068291902542114},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.44139859080314636},{"id":"https://openalex.org/C2777674469","wikidata":"https://www.wikidata.org/wiki/Q20741011","display_name":"Virtex","level":3,"score":0.42189884185791016},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.41910502314567566},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.41899892687797546},{"id":"https://openalex.org/C77390884","wikidata":"https://www.wikidata.org/wiki/Q217302","display_name":"Application-specific integrated circuit","level":2,"score":0.4126688539981842},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.36028414964675903},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35935625433921814},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.34324049949645996},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18551334738731384},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"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/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/socc46988.2019.1570558495","is_oa":false,"landing_page_url":"https://doi.org/10.1109/socc46988.2019.1570558495","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 32nd IEEE International System-on-Chip Conference (SOCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.4000000059604645}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W1537260300","https://openalex.org/W1903029394","https://openalex.org/W2004455575","https://openalex.org/W2048266589","https://openalex.org/W2094756095","https://openalex.org/W2097117768","https://openalex.org/W2117539524","https://openalex.org/W2172654076","https://openalex.org/W2294282016","https://openalex.org/W2520083297","https://openalex.org/W2592875630","https://openalex.org/W2616014673","https://openalex.org/W2617247391","https://openalex.org/W2625457103","https://openalex.org/W2727238169","https://openalex.org/W2729080111","https://openalex.org/W2895394565","https://openalex.org/W2919115771","https://openalex.org/W2963037989","https://openalex.org/W2963163009","https://openalex.org/W2963403664","https://openalex.org/W2963416938","https://openalex.org/W3024621361","https://openalex.org/W4245683599","https://openalex.org/W6685214006","https://openalex.org/W6725896364","https://openalex.org/W6738105350","https://openalex.org/W6754888283"],"related_works":["https://openalex.org/W2293771254","https://openalex.org/W3121828480","https://openalex.org/W2039875226","https://openalex.org/W4221142455","https://openalex.org/W2032786851","https://openalex.org/W2914631005","https://openalex.org/W2123154672","https://openalex.org/W2952630098","https://openalex.org/W3132517792","https://openalex.org/W4285148873"],"abstract_inverted_index":{"To":[0,83],"address":[1],"the":[2,18,24,35,40,50,55,63,68,76,80,93,114,117,123,129,138,153,160,167,172,181,197,228,257],"challenges":[3],"of":[4,54,70,79,132,224,241],"high":[5],"computational":[6],"complexity":[7],"incurred":[8],"in":[9,31,75,103,194,239],"deep":[10],"convolutional":[11],"neural":[12],"networks":[13],"(CNNs),":[14],"implementations":[15],"by":[16,179],"both":[17],"Fast":[19],"Winograd":[20],"Transform":[21],"algorithm":[22],"and":[23,106,148,185,219],"sparsity":[25,52,72,251],"exploration":[26],"method":[27],"have":[28,43],"been":[29,44],"attempted":[30],"order":[32],"to":[33,150,176,187,235,256],"reduce":[34],"hardware":[36],"operation":[37],"overhead.":[38],"Yet,":[39],"previous":[41],"studies":[42],"mainly":[45],"concentrated":[46],"on":[47,122,211],"dealing":[48],"with":[49,92,152,248],"fixed":[51],"patterns":[53,73],"weight":[56,134,191],"filter.":[57],"In":[58,166],"this":[59,84],"paper,":[60],"we":[61],"focus":[62],"effort":[64],"specifically":[65],"towards":[66],"exploiting":[67],"characteristics":[69],"varying":[71],"existing":[74],"input/output":[77],"Activations":[78],"Winograd-transformed":[81],"network.":[82],"end,":[85],"a":[86,99,133,141,205],"dynamically":[87,111],"compressing":[88],"approach":[89],"for":[90,157,217],"multiplication":[91],"sparsity-changing":[94],"matrix":[95,135,155],"is":[96,146],"proposed.":[97],"Such":[98],"processing":[100],"flow":[101],"features":[102],"data":[104,125,174],"indexing":[105],"restoring.":[107],"Because":[108],"they":[109],"are":[110,119],"generated":[112],"during":[113],"inference":[115],"process,":[116],"inputs/outputs":[118,161],"highly":[120],"dependent":[121],"actual":[124],"being":[126],"processed.":[127],"Unlike":[128],"static":[130],"pattern":[131,156],"just":[136],"requiring":[137],"offline":[139],"compression,":[140],"real-time":[142],"compression":[143],"processor":[144],"module":[145],"devised":[147],"employed":[149],"deal":[151],"dynamic":[154],"updating":[158],"online":[159],"within":[162],"FPGAs":[163],"Block":[164,246],"RAMs.":[165],"next":[168,198],"layer":[169],"computation,":[170],"only":[171],"valid":[173],"needs":[175],"be":[177],"restored":[178],"following":[180],"necessary":[182],"index":[183],"information":[184],"broadcasting":[186],"those":[188],"corresponding":[189],"sparse":[190],"matrices,":[192],"which":[193],"turn":[195],"generates":[196],"batch":[199],"inputs/outputs.":[200],"The":[201],"design":[202],"has":[203],"realized":[204],"typical":[206],"CNN":[207],"such":[208],"as":[209],"VGG":[210],"Xilinx":[212],"Virtex":[213],"7":[214],"FPGA":[215],"device":[216],"verification":[218],"achieves":[220],"an":[221],"overall":[222],"performance":[223],"629.4":[225],"GOPS.":[226],"Meanwhile,":[227],"preliminary":[229],"experimental":[230],"results":[231],"demonstrate":[232],"2.2":[233],"(up":[234],"5.5)":[236],"times":[237],"improvement":[238],"terms":[240],"equivalent":[242],"GOPS":[243],"per":[244],"DSP":[245],"achieved":[247],"our":[249],"adaptive":[250],"exploitation":[252],"approach,":[253],"when":[254],"compared":[255],"other":[258],"conventional":[259],"counterparts.":[260]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}