{"id":"https://openalex.org/W3084185164","doi":"https://doi.org/10.1109/tcad.2020.3022330","title":"nZESPA: A Near-3D-Memory Zero Skipping Parallel Accelerator for CNNs","display_name":"nZESPA: A Near-3D-Memory Zero Skipping Parallel Accelerator for CNNs","publication_year":2020,"publication_date":"2020-09-08","ids":{"openalex":"https://openalex.org/W3084185164","doi":"https://doi.org/10.1109/tcad.2020.3022330","mag":"3084185164"},"language":"en","primary_location":{"id":"doi:10.1109/tcad.2020.3022330","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2020.3022330","pdf_url":null,"source":{"id":"https://openalex.org/S100835903","display_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","issn_l":"0278-0070","issn":["0278-0070","1937-4151"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits 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/A5021176902","display_name":"Palash Das","orcid":"https://orcid.org/0000-0002-1979-0298"},"institutions":[{"id":"https://openalex.org/I1317621060","display_name":"Indian Institute of Technology Guwahati","ror":"https://ror.org/0022nd079","country_code":"IN","type":"education","lineage":["https://openalex.org/I1317621060"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Palash Das","raw_affiliation_strings":["Department of Computer Science and Engineering, Indian Institute of Technology Guwahati, Guwahati, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology Guwahati, Guwahati, India","institution_ids":["https://openalex.org/I1317621060"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070605948","display_name":"Hemangee K. Kapoor","orcid":"https://orcid.org/0000-0002-9376-7686"},"institutions":[{"id":"https://openalex.org/I1317621060","display_name":"Indian Institute of Technology Guwahati","ror":"https://ror.org/0022nd079","country_code":"IN","type":"education","lineage":["https://openalex.org/I1317621060"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hemangee K. Kapoor","raw_affiliation_strings":["Department of Computer Science and Engineering, Indian Institute of Technology Guwahati, Guwahati, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology Guwahati, Guwahati, India","institution_ids":["https://openalex.org/I1317621060"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5021176902"],"corresponding_institution_ids":["https://openalex.org/I1317621060"],"apc_list":null,"apc_paid":null,"fwci":0.3925,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.62245085,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"40","issue":"8","first_page":"1573","last_page":"1585"},"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9988999962806702,"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9986000061035156,"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/dataflow","display_name":"Dataflow","score":0.9600410461425781},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8604828119277954},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6475527286529541},{"id":"https://openalex.org/keywords/dataflow-architecture","display_name":"Dataflow architecture","score":0.6329025626182556},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6304092407226562},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5925146341323853},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5499337911605835},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4616576135158539},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4375155568122864},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.41647422313690186},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3204677402973175},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22593456506729126},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.20000120997428894}],"concepts":[{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.9600410461425781},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8604828119277954},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6475527286529541},{"id":"https://openalex.org/C176727019","wikidata":"https://www.wikidata.org/wiki/Q1172415","display_name":"Dataflow architecture","level":3,"score":0.6329025626182556},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6304092407226562},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5925146341323853},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5499337911605835},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4616576135158539},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4375155568122864},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.41647422313690186},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3204677402973175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22593456506729126},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.20000120997428894},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcad.2020.3022330","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2020.3022330","pdf_url":null,"source":{"id":"https://openalex.org/S100835903","display_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","issn_l":"0278-0070","issn":["0278-0070","1937-4151"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.9100000262260437}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1598866093","https://openalex.org/W1686810756","https://openalex.org/W1903029394","https://openalex.org/W1981220134","https://openalex.org/W2048266589","https://openalex.org/W2067523571","https://openalex.org/W2097117768","https://openalex.org/W2117539524","https://openalex.org/W2125203716","https://openalex.org/W2152839228","https://openalex.org/W2162390675","https://openalex.org/W2163605009","https://openalex.org/W2167868137","https://openalex.org/W2170382128","https://openalex.org/W2194775991","https://openalex.org/W2270723299","https://openalex.org/W2285660444","https://openalex.org/W2289252105","https://openalex.org/W2331143823","https://openalex.org/W2442974303","https://openalex.org/W2474451066","https://openalex.org/W2489529491","https://openalex.org/W2516141709","https://openalex.org/W2517869808","https://openalex.org/W2518511512","https://openalex.org/W2529546376","https://openalex.org/W2530879419","https://openalex.org/W2565851976","https://openalex.org/W2582737986","https://openalex.org/W2605347906","https://openalex.org/W2606722458","https://openalex.org/W2612076670","https://openalex.org/W2625457103","https://openalex.org/W2795177683","https://openalex.org/W2798317693","https://openalex.org/W2809295488","https://openalex.org/W2899771611","https://openalex.org/W2963674932","https://openalex.org/W2964080840","https://openalex.org/W2964174152","https://openalex.org/W3105314253","https://openalex.org/W4212788319","https://openalex.org/W4236868170","https://openalex.org/W4240168186","https://openalex.org/W4248799209","https://openalex.org/W6683722107","https://openalex.org/W6684191040","https://openalex.org/W6693960836","https://openalex.org/W6701947533","https://openalex.org/W6756040250"],"related_works":["https://openalex.org/W1998949396","https://openalex.org/W2968111836","https://openalex.org/W1968046689","https://openalex.org/W1572523360","https://openalex.org/W2118306988","https://openalex.org/W2113002027","https://openalex.org/W1530954637","https://openalex.org/W2133923912","https://openalex.org/W2899363804","https://openalex.org/W4289362026"],"abstract_inverted_index":{"Convolutional":[0],"neural":[1],"networks":[2],"(CNNs)":[3],"are":[4,130],"one":[5],"of":[6,41,105,113,127,136,147,154,193],"the":[7,39,55,75,82,84,102,122,133,137,152,158,189],"most":[8],"popular":[9],"machine":[10],"learning":[11],"tools":[12],"for":[13,30],"computer":[14],"vision.":[15],"The":[16,67,125,185],"ubiquitous":[17],"use":[18],"in":[19,191],"several":[20],"applications":[21],"with":[22,161],"its":[23],"high":[24],"computation-cost":[25],"has":[26,36],"made":[27],"it":[28],"lucrative":[29],"optimization":[31],"through":[32,46],"accelerated":[33],"architecture.":[34],"State-of-the-art":[35],"either":[37,166],"exploited":[38],"parallelism":[40],"CNNs,":[42],"or":[43,48,96,172,179],"eliminated":[44],"computations":[45,112],"sparsity":[47,170],"used":[49],"near-memory":[50],"processing":[51],"(NMP)":[52],"to":[53],"accelerate":[54],"CNNs.":[56,114],"We":[57,115,156],"introduce":[58],"NMP-fully":[59],"sparse":[60],"architecture,":[61],"which":[62,120,165],"acquires":[63],"all":[64,109],"three":[65,162],"capabilities.":[66],"proposed":[68,85,159,186],"architecture":[69,160],"is":[70],"parallel":[71],"and":[72,195],"hence":[73],"processes":[74],"independent":[76],"CNN":[77,200],"tasks":[78],"concurrently.":[79],"To":[80],"exploit":[81,169],"sparsity,":[83],"system":[86,187],"employs":[87,121],"a":[88,117,144],"dataflow,":[89],"namely,":[90],"Near-3D-Memory":[91],"Zero":[92],"Skipping":[93],"Parallel":[94],"dataflow":[95,100],"nZESPA":[97,123,128],"dataflow.":[98,124],"This":[99,141],"maintains":[101],"compressed-sparse":[103],"encoding":[104],"data":[106],"that":[107],"skips":[108],"ineffectual":[110],"zero-valued":[111],"design":[116],"custom":[118],"accelerator":[119],"grids":[126],"modules":[129],"integrated":[131],"into":[132],"logic":[134],"layer":[135],"hybrid":[138],"memory":[139],"cube.":[140],"integration":[142],"saves":[143],"significant":[145],"amount":[146],"off-chip":[148],"communications":[149],"while":[150,198],"implementing":[151],"concept":[153],"NMP.":[155],"compare":[157],"other":[163],"architectures":[164],"do":[167,173,180],"not":[168,174,181],"(NMP-dense)":[171],"employ":[175],"NMP":[176],"(traditional-fully":[177],"sparse)":[178],"include":[182],"both":[183],"(traditional-dense).":[184],"outperforms":[188],"baselines":[190],"terms":[192],"performance":[194],"energy":[196],"consumption":[197],"executing":[199],"inference.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3}],"updated_date":"2026-03-25T14:56:36.534964","created_date":"2025-10-10T00:00:00"}