{"id":"https://openalex.org/W4312979995","doi":"https://doi.org/10.1109/iscas48785.2022.9937266","title":"An Efficient Hardware Architecture for DNN Training by Exploiting Triple Sparsity","display_name":"An Efficient Hardware Architecture for DNN Training by Exploiting Triple Sparsity","publication_year":2022,"publication_date":"2022-05-28","ids":{"openalex":"https://openalex.org/W4312979995","doi":"https://doi.org/10.1109/iscas48785.2022.9937266"},"language":"en","primary_location":{"id":"doi:10.1109/iscas48785.2022.9937266","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas48785.2022.9937266","pdf_url":null,"source":{"id":"https://openalex.org/S4363604393","display_name":"2022 IEEE International Symposium on Circuits and Systems (ISCAS)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Symposium on Circuits and Systems (ISCAS)","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/A5005380910","display_name":"Jian Huang","orcid":"https://orcid.org/0000-0002-1125-671X"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jian Huang","raw_affiliation_strings":["Nanjing University,School of Electronic Science and Engineering,Nanjing,China","School of Electronic Science and Engineering, Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University,School of Electronic Science and Engineering,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"School of Electronic Science and Engineering, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059107361","display_name":"Jinming Lu","orcid":"https://orcid.org/0000-0002-7134-6514"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinming Lu","raw_affiliation_strings":["Nanjing University,School of Electronic Science and Engineering,Nanjing,China","School of Electronic Science and Engineering, Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University,School of Electronic Science and Engineering,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"School of Electronic Science and Engineering, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100696999","display_name":"Zhongfeng Wang","orcid":"https://orcid.org/0000-0002-7227-4786"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongfeng Wang","raw_affiliation_strings":["Nanjing University,School of Electronic Science and Engineering,Nanjing,China","School of Electronic Science and Engineering, Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University,School of Electronic Science and Engineering,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"School of Electronic Science and Engineering, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5005380910"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":0.1199,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.44959361,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"27","issue":null,"first_page":"2802","last_page":"2805"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9991000294685364,"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":0.9991000294685364,"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/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9919999837875366,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12676","display_name":"Machine Learning and ELM","score":0.984499990940094,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8250281810760498},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.6996058821678162},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.6584597229957581},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.606031060218811},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5830709934234619},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.5577031970024109},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.48584648966789246},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.4668341875076294},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.46315282583236694},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.39484110474586487},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3580858111381531},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3526003062725067}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8250281810760498},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6996058821678162},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.6584597229957581},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.606031060218811},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5830709934234619},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.5577031970024109},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.48584648966789246},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.4668341875076294},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.46315282583236694},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.39484110474586487},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3580858111381531},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3526003062725067},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscas48785.2022.9937266","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas48785.2022.9937266","pdf_url":null,"source":{"id":"https://openalex.org/S4363604393","display_name":"2022 IEEE International Symposium on Circuits and Systems (ISCAS)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Symposium on Circuits and Systems (ISCAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.8799999952316284,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2119144962","https://openalex.org/W2285660444","https://openalex.org/W2464177207","https://openalex.org/W2884360532","https://openalex.org/W3015729306","https://openalex.org/W3047872496","https://openalex.org/W3092357178","https://openalex.org/W3105802176","https://openalex.org/W3107472389","https://openalex.org/W3109309915","https://openalex.org/W3174469560","https://openalex.org/W4236868170","https://openalex.org/W4240168186","https://openalex.org/W6677580257","https://openalex.org/W6719768283"],"related_works":["https://openalex.org/W1002902646","https://openalex.org/W2320205417","https://openalex.org/W2047588290","https://openalex.org/W2995926156","https://openalex.org/W2163403354","https://openalex.org/W2524802307","https://openalex.org/W2996827035","https://openalex.org/W2028686533","https://openalex.org/W4312979995","https://openalex.org/W1515021801"],"abstract_inverted_index":{"Recently,":[0],"on-device":[1],"DNN":[2,29,58,148],"training":[3,30,90,186,189],"has":[4],"attracted":[5],"much":[6],"attention":[7],"due":[8],"to":[9,19,50,66,118,131,159],"its":[10],"high":[11,25],"performance":[12],"on":[13,99,136,193],"edge":[14],"devices":[15],"and":[16,24,162,169,206,213],"great":[17],"ability":[18],"protect":[20],"user":[21],"privacy.":[22],"Low-power":[23],"throughput":[26,168],"implementations":[27],"of":[28,54,167,176,200],"are":[31,73,116],"highly":[32],"desired":[33],"for":[34,83,147],"resource-limited":[35],"devices.":[36],"In":[37],"this":[38],"paper,":[39],"we":[40,142],"present":[41],"an":[42,93,144],"efficient":[43,94,145],"hardware":[44],"accelerator":[45],"that":[46,153],"exploits":[47],"triple":[48],"sparsity":[49,95,139],"reduce":[51],"the":[52,100,120,137,184,194,197,210],"number":[53],"unnecessary":[55],"operations":[56],"during":[57],"training.":[59,149],"The":[60,173],"gradients":[61],"pruning":[62],"algorithm":[63],"is":[64,81,105,179],"employed":[65],"bring":[67],"error":[68],"sparsity.":[69],"Firstly,":[70],"sparse":[71,77],"data":[72,102],"represented":[74],"in":[75,88,165,209],"compressed":[76],"block":[78],"format,":[79],"which":[80,107],"suitable":[82],"different":[84],"memory":[85],"access":[86],"patterns":[87],"all":[89],"phases.":[91],"Secondly,":[92],"detection":[96,140],"logic":[97],"based":[98,135],"aforementioned":[101],"storage":[103],"format":[104],"proposed,":[106],"adopts":[108],"a":[109,190],"2-level":[110],"grained":[111],"mechanism.":[112],"Coarse-grained":[113],"mask-matching":[114,125],"units":[115,126],"reused":[117],"improve":[119],"energy":[121,170,174,198],"efficiency,":[122,171],"while":[123],"fine-grained":[124],"make":[127],"PEs":[128],"work":[129],"independently":[130],"enhance":[132],"throughput.":[133],"Thirdly,":[134],"above":[138],"logic,":[141],"propose":[143],"architecture":[146],"Experimental":[150],"results":[151],"show":[152],"our":[154,177,201],"design":[155,178,202],"can":[156],"achieve":[157],"up":[158],"42.1":[160],"TOPS":[161],"174.0":[163],"TOPS/W":[164,208],"terms":[166],"respectively.":[172,216],"efficiency":[175,199],"$2.12\\times":[180],"$":[181],"higher":[182],"than":[183],"state-of-the-art":[185],"processor.":[187],"For":[188],"ResNet-50":[191],"model":[192],"CIFAR10":[195],"dataset,":[196],"achieves":[203],"14.10,":[204],"96.57,":[205],"84.43":[207],"FP,":[211],"BP,":[212],"WG":[214],"phases,":[215]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}