{"id":"https://openalex.org/W3214560281","doi":"https://doi.org/10.1109/vdat53777.2021.9600988","title":"Hardware Acceleration of SpMV Multiplier for Deep Learning","display_name":"Hardware Acceleration of SpMV Multiplier for Deep Learning","publication_year":2021,"publication_date":"2021-09-16","ids":{"openalex":"https://openalex.org/W3214560281","doi":"https://doi.org/10.1109/vdat53777.2021.9600988","mag":"3214560281"},"language":"en","primary_location":{"id":"doi:10.1109/vdat53777.2021.9600988","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vdat53777.2021.9600988","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 25th International Symposium on VLSI Design and Test (VDAT)","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/A5087107789","display_name":"M.N. Mahesh","orcid":null},"institutions":[{"id":"https://openalex.org/I26072440","display_name":"Indian Institute of Information Technology Allahabad","ror":"https://ror.org/03rgjt374","country_code":"IN","type":"education","lineage":["https://openalex.org/I26072440"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"M Mahesh","raw_affiliation_strings":["Indian Institute of Information Technology, Kottayam, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Information Technology, Kottayam, India","institution_ids":["https://openalex.org/I26072440"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022529362","display_name":"S. Nalesh","orcid":null},"institutions":[{"id":"https://openalex.org/I20497027","display_name":"Cochin University of Science and Technology","ror":"https://ror.org/00a4kqq17","country_code":"IN","type":"education","lineage":["https://openalex.org/I20497027"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"S Nalesh","raw_affiliation_strings":["Cochin University of Science And Technology, Kerala, India"],"affiliations":[{"raw_affiliation_string":"Cochin University of Science And Technology, Kerala, India","institution_ids":["https://openalex.org/I20497027"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075824154","display_name":"S Kala","orcid":null},"institutions":[{"id":"https://openalex.org/I26072440","display_name":"Indian Institute of Information Technology Allahabad","ror":"https://ror.org/03rgjt374","country_code":"IN","type":"education","lineage":["https://openalex.org/I26072440"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"S Kala","raw_affiliation_strings":["Indian Institute of Information Technology, Kottayam, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Information Technology, Kottayam, India","institution_ids":["https://openalex.org/I26072440"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5087107789"],"corresponding_institution_ids":["https://openalex.org/I26072440"],"apc_list":null,"apc_paid":null,"fwci":0.1003,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.44992546,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9970999956130981,"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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":0.8633068203926086},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6612489819526672},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6201050281524658},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.568365752696991},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.5432009696960449},{"id":"https://openalex.org/keywords/edge-computing","display_name":"Edge computing","score":0.5122503638267517},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.48223838210105896},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.4745267927646637},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.47189056873321533},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44846707582473755},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.41243910789489746},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3844963312149048},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.35082244873046875},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3350682258605957},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.1708415448665619},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.15103289484977722}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8633068203926086},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6612489819526672},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6201050281524658},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.568365752696991},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.5432009696960449},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.5122503638267517},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.48223838210105896},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.4745267927646637},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.47189056873321533},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44846707582473755},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.41243910789489746},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3844963312149048},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.35082244873046875},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3350682258605957},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.1708415448665619},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.15103289484977722},{"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:10.1109/vdat53777.2021.9600988","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vdat53777.2021.9600988","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 25th International Symposium on VLSI Design and Test (VDAT)","raw_type":"proceedings-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":23,"referenced_works":["https://openalex.org/W1935978687","https://openalex.org/W1969102784","https://openalex.org/W1981252059","https://openalex.org/W1994515555","https://openalex.org/W2119144962","https://openalex.org/W2294458850","https://openalex.org/W2782757393","https://openalex.org/W2915106038","https://openalex.org/W2941763154","https://openalex.org/W2945913827","https://openalex.org/W2950064373","https://openalex.org/W2977634443","https://openalex.org/W3011253470","https://openalex.org/W3038041907","https://openalex.org/W3040024858","https://openalex.org/W3089060714","https://openalex.org/W3093571597","https://openalex.org/W4245683599","https://openalex.org/W4287208846","https://openalex.org/W4287828539","https://openalex.org/W6677580257","https://openalex.org/W6774302960","https://openalex.org/W6794457956"],"related_works":["https://openalex.org/W4322761281","https://openalex.org/W4238233472","https://openalex.org/W3111395152","https://openalex.org/W4313526662","https://openalex.org/W4313463218","https://openalex.org/W4312996489","https://openalex.org/W3106131444","https://openalex.org/W3216099748","https://openalex.org/W4205963435","https://openalex.org/W3214037210"],"abstract_inverted_index":{"Deep":[0,18,37],"Learning":[1],"techniques":[2],"are":[3,12,126,141],"widely":[4],"adopted":[5],"in":[6,15,74,180],"many":[7],"computer":[8],"vision":[9],"tasks":[10],"and":[11,79,86,92,121,205,224],"practically":[13],"implemented":[14,213],"real-world":[16],"systems.":[17],"learning":[19,38,59,106,171,185],"is":[20],"a":[21,161],"promising":[22],"method":[23],"for":[24,43,50,72,104,145,168],"machine":[25],"learning,":[26],"where":[27],"complex":[28],"functions":[29],"can":[30,189],"be":[31],"learned":[32],"directly":[33],"from":[34],"the":[35,54,98,191,197,201],"data.":[36],"algorithms":[39],"provide":[40],"high":[41,133],"accuracy":[42],"recognition":[44],"tasks,":[45],"while":[46],"consuming":[47],"significant":[48,226],"resources":[49],"computation,":[51],"compared":[52,230],"to":[53,96],"conventional":[55],"algorithms.":[56,186],"State-of-the-art":[57],"deep":[58,105,170,184],"networks":[60],"have":[61],"hundreds":[62],"of":[63,65,101,183,196,221],"millions":[64],"parameters,":[66],"which":[67,148],"makes":[68],"them":[69],"less":[70],"suitable":[71,142],"adoption":[73],"devices":[75,85],"with":[76,153,217,231],"constrained":[77],"memory":[78,194],"power":[80,151],"requirements":[81],"like":[82,90,116],"edge":[83,146],"computing":[84,114,198],"mobile":[87],"devices.":[88],"Techniques":[89],"quantization":[91],"inducing":[93],"sparsity,":[94],"aims":[95],"reduce":[97],"total":[99],"number":[100],"computations":[102],"needed":[103],"inference.":[107,172],"For":[108],"portable":[109],"embedded":[110],"applications,":[111],"general":[112],"purpose":[113],"hardware":[115,143,181],"GPPs":[117],"(General":[118],"Purpose":[119],"Processors)":[120],"GPUs":[122],"(Graphic":[123],"Processing":[124],"Units)":[125],"not":[127],"preferred":[128],"as":[129],"these":[130],"applications":[131],"demand":[132],"energy":[134],"efficiency.":[135],"Field":[136],"Programmable":[137],"Gate":[138],"Arrays":[139],"(FPGAs)":[140],"solutions":[144],"computing,":[147],"gives":[149],"better":[150],"consumption":[152],"increased":[154],"flexibility.":[155],"In":[156],"this":[157],"paper":[158],"we":[159],"propose":[160],"bandwidth-efficient":[162],"sparse":[163],"matrix-vector":[164],"(SpMV)":[165],"multiplier":[166],"architecture":[167,174,188,210],"faster":[169],"Our":[173],"also":[175],"reduces":[176],"memory-bandwidth":[177],"bottleneck":[178],"present":[179],"realization":[182],"Proposed":[187],"use":[190],"maximum":[192],"available":[193],"bandwidth":[195],"device,":[199],"using":[200],"multiple":[202],"MAC":[203],"(multiply":[204],"accumulate)":[206],"channels.":[207],"The":[208],"proposed":[209],"has":[211],"been":[212],"on":[214],"Kintex-7":[215],"FPGA":[216],"an":[218],"operating":[219],"frequency":[220],"270":[222],"MHz":[223],"gave":[225],"performance":[227],"gain":[228],"when":[229],"existing":[232],"implementation.":[233]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}