{"id":"https://openalex.org/W3156110668","doi":"https://doi.org/10.1142/s0218126621502662","title":"High Performance Kernel Architecture for Convolutional Neural Network Acceleration","display_name":"High Performance Kernel Architecture for Convolutional Neural Network Acceleration","publication_year":2021,"publication_date":"2021-04-19","ids":{"openalex":"https://openalex.org/W3156110668","doi":"https://doi.org/10.1142/s0218126621502662","mag":"3156110668"},"language":"en","primary_location":{"id":"doi:10.1142/s0218126621502662","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218126621502662","pdf_url":null,"source":{"id":"https://openalex.org/S167602672","display_name":"Journal of Circuits Systems and Computers","issn_l":"0218-1266","issn":["0218-1266","1793-6454"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Circuits, Systems and Computers","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/A5040486945","display_name":"Anakhi Hazarika","orcid":"https://orcid.org/0000-0003-0911-6627"},"institutions":[{"id":"https://openalex.org/I4210089896","display_name":"Indian Institute of Information Technology Guwahati","ror":"https://ror.org/00bb9ch64","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210089896"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Anakhi Hazarika","raw_affiliation_strings":["Department of Electronics and Communications, Indian Institute of Information Technology Guwahati, Guwahati 781015, Assam, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics and Communications, Indian Institute of Information Technology Guwahati, Guwahati 781015, Assam, India","institution_ids":["https://openalex.org/I4210089896"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018489725","display_name":"Soumyajit Poddar","orcid":"https://orcid.org/0000-0002-3476-2199"},"institutions":[{"id":"https://openalex.org/I4210089896","display_name":"Indian Institute of Information Technology Guwahati","ror":"https://ror.org/00bb9ch64","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210089896"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Soumyajit Poddar","raw_affiliation_strings":["Department of Electronics and Communications, Indian Institute of Information Technology Guwahati, Guwahati 781015, Assam, India"],"raw_orcid":"https://orcid.org/0000-0002-3476-2199","affiliations":[{"raw_affiliation_string":"Department of Electronics and Communications, Indian Institute of Information Technology Guwahati, Guwahati 781015, Assam, India","institution_ids":["https://openalex.org/I4210089896"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082934529","display_name":"Hafizur Rahaman","orcid":"https://orcid.org/0000-0001-9012-5437"},"institutions":[{"id":"https://openalex.org/I98365261","display_name":"Indian Institute of Engineering Science and Technology, Shibpur","ror":"https://ror.org/02ytfzr55","country_code":"IN","type":"education","lineage":["https://openalex.org/I98365261"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hafizur Rahaman","raw_affiliation_strings":["Indian Institute of Engineering Science and Technology, Shibpur 711103, West Bengal, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Engineering Science and Technology, Shibpur 711103, West Bengal, India","institution_ids":["https://openalex.org/I98365261"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5018489725"],"corresponding_institution_ids":["https://openalex.org/I4210089896"],"apc_list":null,"apc_paid":null,"fwci":0.3879,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.59504519,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"30","issue":"15","first_page":null,"last_page":null},"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/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9987999796867371,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9980000257492065,"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":0.8413519263267517},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7473363876342773},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.7053382396697998},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.626556932926178},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.6018853783607483},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5638869404792786},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.523733377456665},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.5146569013595581},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.49413564801216125},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.46884098649024963},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.45358920097351074},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4371696412563324},{"id":"https://openalex.org/keywords/microarchitecture","display_name":"Microarchitecture","score":0.4305221438407898},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.42526674270629883},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.4108915627002716},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.339563250541687},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3395025134086609},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3066837787628174},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.20738789439201355},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.17342910170555115},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.0957036018371582}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8413519263267517},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7473363876342773},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.7053382396697998},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.626556932926178},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.6018853783607483},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5638869404792786},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.523733377456665},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.5146569013595581},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.49413564801216125},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.46884098649024963},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.45358920097351074},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4371696412563324},{"id":"https://openalex.org/C107598950","wikidata":"https://www.wikidata.org/wiki/Q259864","display_name":"Microarchitecture","level":2,"score":0.4305221438407898},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.42526674270629883},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.4108915627002716},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.339563250541687},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3395025134086609},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3066837787628174},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.20738789439201355},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.17342910170555115},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0957036018371582},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0218126621502662","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218126621502662","pdf_url":null,"source":{"id":"https://openalex.org/S167602672","display_name":"Journal of Circuits Systems and Computers","issn_l":"0218-1266","issn":["0218-1266","1793-6454"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Circuits, Systems and Computers","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":0.8700000047683716}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2002555321","https://openalex.org/W2048266589","https://openalex.org/W2097117768","https://openalex.org/W2102631020","https://openalex.org/W2112796928","https://openalex.org/W2130416988","https://openalex.org/W2194775991","https://openalex.org/W2260498192","https://openalex.org/W2289252105","https://openalex.org/W2331737637","https://openalex.org/W2442974303","https://openalex.org/W2546366412","https://openalex.org/W2570343428","https://openalex.org/W2604272474","https://openalex.org/W2795915628","https://openalex.org/W2896983500","https://openalex.org/W2919115771","https://openalex.org/W2933917628","https://openalex.org/W2945146780","https://openalex.org/W2961882198","https://openalex.org/W2963037989","https://openalex.org/W3010819965","https://openalex.org/W3012178976","https://openalex.org/W3016542674","https://openalex.org/W3016904661","https://openalex.org/W3036743609","https://openalex.org/W4212788319","https://openalex.org/W4234863022","https://openalex.org/W4241197095"],"related_works":["https://openalex.org/W4255097844","https://openalex.org/W2567660513","https://openalex.org/W4319952061","https://openalex.org/W4280636456","https://openalex.org/W4388913998","https://openalex.org/W4310584535","https://openalex.org/W3154092384","https://openalex.org/W4295935044","https://openalex.org/W4307927141","https://openalex.org/W3159906349"],"abstract_inverted_index":{"Convolutional":[0],"neural":[1],"networks":[2],"(CNNs)":[3],"have":[4,19],"emerged":[5],"as":[6],"a":[7,82,96],"prominent":[8],"choice":[9],"in":[10,16,31,105,153],"artificial":[11],"intelligence":[12],"tasks.":[13],"Recent":[14],"advancements":[15],"CNN":[17,37,55,89,177],"designs":[18],"greatly":[20],"improved":[21],"the":[22,41,51,71,101,114,123,132,159,165,171],"performance":[23,130],"and":[24,48,65,75,175],"energy-efficiency":[25],"of":[26,36,43,53,107,122,125,131,148,155,186],"several":[27],"computation-intensive":[28],"applications.":[29],"However,":[30],"real-time":[32,54],"applications,":[33],"greater":[34],"accuracy":[35],"is":[38,59,135],"attained":[39],"at":[40],"expense":[42],"very":[44],"high":[45],"computational":[46,73,108],"cost":[47,104],"complexity.":[49],"Further,":[50],"implementation":[52],"on":[56],"embedded":[57],"platforms":[58],"highly":[60],"challenging":[61],"due":[62],"to":[63,86],"resource":[64],"power":[66],"constraints.":[67],"This":[68,118],"paper":[69],"addresses":[70],"aforesaid":[72],"complexity":[74],"presents":[76],"an":[77,146,184],"accelerator":[78,144,181],"architecture":[79,119,134,172,182],"accompanied":[80],"by":[81,112],"novel":[83],"kernel":[84,93],"design":[85,94],"improve":[87],"overall":[88],"performance.":[90],"The":[91,129,142,179],"proposed":[92,133,143,166,180],"introduces":[95],"computing":[97,161],"mechanism":[98],"that":[99],"reduces":[100],"data":[102],"movement":[103],"terms":[106],"cycle":[109],"count":[110],"(latency)":[111],"parallelizing":[113],"convolution":[115],"processing":[116],"elements.":[117],"takes":[120],"advantage":[121],"overlap":[124],"spatially":[126],"adjacent":[127],"data.":[128],"also":[136],"analyzed":[137],"for":[138],"multiple":[139],"hyper-parameter":[140],"configurations.":[141],"achieves":[145,183],"average":[147,185],"[Formula:":[149,187],"see":[150,188],"text]":[151,189],"improvement":[152,191],"reduction":[154],"execution":[156],"time":[157],"than":[158],"conventional":[160],"architecture.":[162],"To":[163],"analyze":[164],"architecture\u2019s":[167],"performance,":[168],"we":[169],"validate":[170],"with":[173],"AlexNet":[174],"VGG-16":[176],"models.":[178],"throughput":[190],"over":[192],"state-of-the-art":[193],"accelerators.":[194]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"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"}