{"id":"https://openalex.org/W3199348509","doi":"https://doi.org/10.1145/3467476","title":"BISWSRBS: A Winograd-based CNN Accelerator with a Fine-grained Regular Sparsity Pattern and Mixed Precision Quantization","display_name":"BISWSRBS: A Winograd-based CNN Accelerator with a Fine-grained Regular Sparsity Pattern and Mixed Precision Quantization","publication_year":2021,"publication_date":"2021-09-13","ids":{"openalex":"https://openalex.org/W3199348509","doi":"https://doi.org/10.1145/3467476","mag":"3199348509"},"language":"en","primary_location":{"id":"doi:10.1145/3467476","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3467476","pdf_url":null,"source":{"id":"https://openalex.org/S112809824","display_name":"ACM Transactions on Reconfigurable Technology and Systems","issn_l":"1936-7406","issn":["1936-7406","1936-7414"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Reconfigurable Technology and Systems","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/A5022287798","display_name":"Tao Yang","orcid":"https://orcid.org/0000-0001-8588-9483"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Yang","raw_affiliation_strings":["School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036755436","display_name":"Zhezhi He","orcid":"https://orcid.org/0000-0002-6357-236X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhezhi He","raw_affiliation_strings":["School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034182283","display_name":"Tengchuan Kou","orcid":"https://orcid.org/0009-0001-1510-027X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tengchuan Kou","raw_affiliation_strings":["School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063041785","display_name":"Qingzheng Li","orcid":"https://orcid.org/0009-0000-4857-4255"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingzheng Li","raw_affiliation_strings":["SenseTime Group Limited, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Group Limited, Shanghai, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100717224","display_name":"Qi Han","orcid":"https://orcid.org/0000-0002-2061-9367"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Han","raw_affiliation_strings":["SenseTime Group Limited, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Group Limited, Shanghai, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071406417","display_name":"Haibao Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haibao Yu","raw_affiliation_strings":["SenseTime Group Limited, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Group Limited, Shanghai, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017670541","display_name":"Fangxin Liu","orcid":"https://orcid.org/0000-0002-8769-293X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangxin Liu","raw_affiliation_strings":["School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100604860","display_name":"Yun Liang","orcid":"https://orcid.org/0000-0002-9076-7998"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Liang","raw_affiliation_strings":["School of EECS, Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of EECS, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053801300","display_name":"Li Jiang","orcid":"https://orcid.org/0000-0002-7353-8798"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Jiang","raw_affiliation_strings":["School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2827,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.55144532,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"14","issue":"4","first_page":"1","last_page":"28"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9987000226974487,"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":0.9962000250816345,"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":0.8116312623023987},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.7261378169059753},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7152324914932251},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.7039928436279297},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5952363610267639},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.5390071272850037},{"id":"https://openalex.org/keywords/gate-array","display_name":"Gate array","score":0.5280112624168396},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4904806315898895},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4729437828063965},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.42217540740966797},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4215134382247925},{"id":"https://openalex.org/keywords/stratix","display_name":"Stratix","score":0.4185606837272644},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.33106672763824463},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.2313489019870758},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2016516625881195}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8116312623023987},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.7261378169059753},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7152324914932251},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7039928436279297},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5952363610267639},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5390071272850037},{"id":"https://openalex.org/C114237110","wikidata":"https://www.wikidata.org/wiki/Q114901","display_name":"Gate array","level":3,"score":0.5280112624168396},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4904806315898895},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4729437828063965},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.42217540740966797},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4215134382247925},{"id":"https://openalex.org/C2776277307","wikidata":"https://www.wikidata.org/wiki/Q22074755","display_name":"Stratix","level":3,"score":0.4185606837272644},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.33106672763824463},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.2313489019870758},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2016516625881195},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3467476","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3467476","pdf_url":null,"source":{"id":"https://openalex.org/S112809824","display_name":"ACM Transactions on Reconfigurable Technology and Systems","issn_l":"1936-7406","issn":["1936-7406","1936-7414"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Reconfigurable Technology and Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.8999999761581421}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2106033855","https://openalex.org/W2117539524","https://openalex.org/W2172654076","https://openalex.org/W2285660444","https://openalex.org/W2469490737","https://openalex.org/W2565516711","https://openalex.org/W2592875630","https://openalex.org/W2736953746","https://openalex.org/W2755741562","https://openalex.org/W2786771851","https://openalex.org/W2793950911","https://openalex.org/W2809121165","https://openalex.org/W2883920103","https://openalex.org/W2910323801","https://openalex.org/W2915106038","https://openalex.org/W2940399336","https://openalex.org/W2951104886","https://openalex.org/W2962851801","https://openalex.org/W2963122961","https://openalex.org/W2964228333","https://openalex.org/W2982479999","https://openalex.org/W2997106510","https://openalex.org/W3012561096","https://openalex.org/W3108833523","https://openalex.org/W3143835353"],"related_works":["https://openalex.org/W1784146144","https://openalex.org/W2083695406","https://openalex.org/W2952735458","https://openalex.org/W2904876938","https://openalex.org/W2786216825","https://openalex.org/W2177578193","https://openalex.org/W2898755250","https://openalex.org/W4310614714","https://openalex.org/W4289086683","https://openalex.org/W3061070527"],"abstract_inverted_index":{"Field-programmable":[0],"Gate":[1],"Array":[2],"(FPGA)":[3],"is":[4],"a":[5,69,80,106,127,173],"high-performance":[6],"computing":[7],"platform":[8],"for":[9,73],"Convolution":[10],"Neural":[11],"Networks":[12],"(CNNs)":[13],"inference.":[14],"Winograd":[15,44,206,229],"algorithm,":[16],"weight":[17],"pruning,":[18],"and":[19,28,52,57,159,183,191,195],"quantization":[20,71,130,170],"are":[21,64],"widely":[22],"adopted":[23],"to":[24,38,54,67,94,111,131,155,171,189],"reduce":[25,133],"the":[26,40,43,86,96,99,113,117,122,134,149,152,160,167,203,226],"storage":[27],"arithmetic":[29],"overhead":[30],"of":[31,60,98,137,151,212],"CNNs":[32],"on":[33,121,179,232],"FPGAs.":[34],"Recent":[35],"studies":[36],"strive":[37],"prune":[39],"weights":[41],"in":[42,48,85],"domain,":[45],"however,":[46],"resulting":[47],"irregular":[49,100,161],"sparse":[50,82,101,228],"patterns":[51],"leading":[53],"low":[55],"parallelism":[56],"reduced":[58],"utilization":[59],"resources.":[61],"Besides,":[62],"there":[63],"few":[65],"works":[66],"discuss":[68],"suitable":[70],"scheme":[72],"Winograd.":[74],"In":[75],"this":[76],"article,":[77],"we":[78,104,125,141],"propose":[79],"regular":[81],"pruning":[83],"pattern":[84,154],"Winograd-based":[87],"CNN,":[88],"namely,":[89],"Sub-row-balanced":[90],"Sparsity":[91],"(SRBS)":[92],"pattern,":[93],"overcome":[95],"challenge":[97],"pattern.":[102,119],"Then,":[103],"develop":[105],"two-step":[107],"hardware":[108],"co-optimization":[109],"approach":[110],"improve":[112],"model":[114,213],"accuracy":[115],"using":[116],"SRBS":[118,153],"Based":[120],"pruned":[123],"model,":[124],"implement":[126],"mixed":[128,168],"precision":[129,169],"further":[132],"computational":[135],"complexity":[136],"bit":[138,175],"operations.":[139],"Finally,":[140],"design":[142,220],"an":[143],"FPGA":[144],"accelerator":[145,207,230],"that":[146,218],"takes":[147],"both":[148],"advantage":[150],"eliminate":[156],"low-parallelism":[157],"computation":[158],"memory":[162],"accesses,":[163],"as":[164,166],"well":[165],"get":[172],"layer-wise":[174],"width.":[176],"Experimental":[177],"results":[178],"VGG16/VGG-nagadomi":[180],"with":[181,185,202,209,225],"CIFAR-10":[182],"ResNet-18/34/50":[184],"ImageNet":[186],"show":[187,217],"up":[188],"11.8\u00d7/8.67\u00d7":[190],"8.17\u00d7/8.31\u00d7/10.6\u00d7":[192],"speedup,":[193],"12.74\u00d7/9.19\u00d7":[194],"8.75\u00d7/8.81\u00d7/11.1\u00d7":[196],"energy":[197],"efficiency":[198],"improvement,":[199],"respectively,":[200],"compared":[201,224],"state-of-the-art":[204,227],"dense":[205],"[20]":[208],"negligible":[210],"loss":[211],"accuracy.":[214],"We":[215],"also":[216],"our":[219],"has":[221],"4.11\u00d7":[222],"speedup":[223],"[19]":[231],"VGG16.":[233]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}