{"id":"https://openalex.org/W3090529387","doi":"https://doi.org/10.1109/iscas45731.2020.9180863","title":"Accelerating Depthwise Convolution and Pooling Operations on z-First Storage CNN Architectures","display_name":"Accelerating Depthwise Convolution and Pooling Operations on z-First Storage CNN Architectures","publication_year":2020,"publication_date":"2020-09-29","ids":{"openalex":"https://openalex.org/W3090529387","doi":"https://doi.org/10.1109/iscas45731.2020.9180863","mag":"3090529387"},"language":"en","primary_location":{"id":"doi:10.1109/iscas45731.2020.9180863","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas45731.2020.9180863","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Symposium on Circuits and Systems (ISCAS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5074864897","display_name":"Pramod Udupa","orcid":"https://orcid.org/0000-0003-4943-3643"},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Pramod Udupa","raw_affiliation_strings":["SAIT, Samsung R&D Institute India-Bangalore, India","SAIT, Samsung R&D Institute India-Bangalore, Bangalore, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SAIT, Samsung R&D Institute India-Bangalore, India","institution_ids":["https://openalex.org/I4210139030"]},{"raw_affiliation_string":"SAIT, Samsung R&D Institute India-Bangalore, Bangalore, India","institution_ids":["https://openalex.org/I4210139030"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041747019","display_name":"Gopinath Mahale","orcid":"https://orcid.org/0000-0002-6950-0834"},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Gopinath Mahale","raw_affiliation_strings":["SAIT, Samsung R&D Institute India-Bangalore, India","SAIT, Samsung R&D Institute India-Bangalore, Bangalore, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SAIT, Samsung R&D Institute India-Bangalore, India","institution_ids":["https://openalex.org/I4210139030"]},{"raw_affiliation_string":"SAIT, Samsung R&D Institute India-Bangalore, Bangalore, India","institution_ids":["https://openalex.org/I4210139030"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072829097","display_name":"Kiran Kolar Chandrasekharan","orcid":"https://orcid.org/0000-0002-0741-6696"},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Kiran Kolar Chandrasekharan","raw_affiliation_strings":["SAIT, Samsung R&D Institute India-Bangalore, India","SAIT, Samsung R&D Institute India-Bangalore, Bangalore, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SAIT, Samsung R&D Institute India-Bangalore, India","institution_ids":["https://openalex.org/I4210139030"]},{"raw_affiliation_string":"SAIT, Samsung R&D Institute India-Bangalore, Bangalore, India","institution_ids":["https://openalex.org/I4210139030"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032109382","display_name":"Sehwan Lee","orcid":"https://orcid.org/0000-0001-5504-974X"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sehwan Lee","raw_affiliation_strings":["SAIT, Samsung Electronics, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SAIT, Samsung Electronics, South Korea","institution_ids":["https://openalex.org/I2250650973"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1709,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.47535593,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9973000288009644,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.9127134084701538},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.8068768382072449},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.7943252325057983},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7915623188018799},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.6808282136917114},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6455906629562378},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5831711292266846},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5406327843666077},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.49902963638305664},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.4679837226867676},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4379413425922394},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.4114196002483368},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.38473016023635864},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.33383846282958984},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3321373462677002},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.25772109627723694},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.23509466648101807},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.19392737746238708},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08551591634750366}],"concepts":[{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.9127134084701538},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.8068768382072449},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.7943252325057983},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7915623188018799},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.6808282136917114},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6455906629562378},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5831711292266846},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5406327843666077},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.49902963638305664},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.4679837226867676},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4379413425922394},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.4114196002483368},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.38473016023635864},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.33383846282958984},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3321373462677002},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25772109627723694},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.23509466648101807},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.19392737746238708},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08551591634750366},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscas45731.2020.9180863","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas45731.2020.9180863","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Symposium on Circuits and Systems (ISCAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2097117768","https://openalex.org/W2108598243","https://openalex.org/W2163605009","https://openalex.org/W2531409750","https://openalex.org/W2604319603","https://openalex.org/W2612445135","https://openalex.org/W2955425717","https://openalex.org/W2963163009","https://openalex.org/W2963918968","https://openalex.org/W4297775537","https://openalex.org/W6762718338"],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W2626256601","https://openalex.org/W3034421924","https://openalex.org/W2982536526","https://openalex.org/W4386858688","https://openalex.org/W4380302312","https://openalex.org/W3008689640","https://openalex.org/W4385338604","https://openalex.org/W3081626085","https://openalex.org/W4391382578"],"abstract_inverted_index":{"Majority":[0],"of":[1,18,23,117,153],"the":[2,15,129],"present":[3],"day":[4],"applications":[5],"in":[6,70,78],"computer":[7],"vision":[8],"use":[9],"Convolutional":[10],"neural":[11],"networks":[12],"(CNN)":[13],"as":[14,56],"preferred":[16],"engine":[17],"computation.":[19],"For":[20],"hardware":[21],"acceleration":[22],"CNNs,":[24],"z-first":[25,106],"storage":[26,107],"architectures":[27,47,108],"like":[28,82],"NVDLA":[29],"have":[30,48,87],"gained":[31,76],"prominence":[32,77],"which":[33,86],"show":[34,72],"better":[35],"resource":[36,65],"utilization":[37],"and":[38,60,121,125],"effective":[39,50,134],"throughput":[40,51,135],"for":[41,52,100,123],"3-D":[42],"convolution":[43],"operation.":[44],"However,":[45],"these":[46],"low":[49],"2-D":[53,102],"operations":[54,103],"such":[55],"Depthwise":[57],"Convolution":[58],"(DWC)":[59],"Pooling":[61,126],"due":[62],"to":[63,91],"poor":[64],"utilization.":[66],"The":[67],"current":[68],"trend":[69],"CNNs":[71,81],"that":[73],"DWC":[74,124],"has":[75],"compact":[79],"mobile-first":[80],"MnasNet,":[83],"EfficientNet":[84],"etc.,":[85],"classification":[88],"accuracies":[89],"comparable":[90],"state-of-the-art":[92],"complex":[93],"CNNs.":[94],"In":[95],"this":[96],"work,":[97],"an":[98],"accelerator":[99,112],"accelerating":[101],"based":[104],"on":[105],"is":[109],"proposed.":[110],"Proposed":[111,138],"delivers":[113],"power":[114],"efficiency":[115],"improvement":[116],"at":[118,148],"least":[119,149],"1.46\u00d7":[120],"1.89\u00d7":[122],"respectively":[127],"over":[128],"baseline":[130],"architecture,":[131],"while":[132],"improving":[133],"by":[136,150],"4\u00d7.":[137],"IFM":[139,144],"reuse":[140],"scheme":[141],"also":[142],"reduces":[143],"reads":[145],"from":[146],"memory":[147],"a":[151],"factor":[152],"1.72\u00d7.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}