{"id":"https://openalex.org/W4400230011","doi":"https://doi.org/10.1109/iscas58744.2024.10558092","title":"Efficient FFT-Based CNN Acceleration with Intra-Patch Parallelization and Flex-Stationary Dataflow","display_name":"Efficient FFT-Based CNN Acceleration with Intra-Patch Parallelization and Flex-Stationary Dataflow","publication_year":2024,"publication_date":"2024-05-19","ids":{"openalex":"https://openalex.org/W4400230011","doi":"https://doi.org/10.1109/iscas58744.2024.10558092"},"language":"en","primary_location":{"id":"doi:10.1109/iscas58744.2024.10558092","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iscas58744.2024.10558092","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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/A5041466078","display_name":"Shine Parekkadan Sunny","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113248","display_name":"Indian Institute of Technology Palakkad","ror":"https://ror.org/0264cg909","country_code":"IN","type":"facility","lineage":["https://openalex.org/I4210113248"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shine Parekkadan Sunny","raw_affiliation_strings":["Indian Institute of Technology Palakkad,Department of Computer Science and Engineering,Kerala,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Palakkad,Department of Computer Science and Engineering,Kerala,India","institution_ids":["https://openalex.org/I4210113248"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006643857","display_name":"Satyajit Das","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113248","display_name":"Indian Institute of Technology Palakkad","ror":"https://ror.org/0264cg909","country_code":"IN","type":"facility","lineage":["https://openalex.org/I4210113248"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Satyajit Das","raw_affiliation_strings":["Indian Institute of Technology Palakkad,Department of Computer Science and Engineering,Kerala,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Palakkad,Department of Computer Science and Engineering,Kerala,India","institution_ids":["https://openalex.org/I4210113248"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210113248"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07370107,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.9757999777793884,"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"}},"topics":[{"id":"https://openalex.org/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.9757999777793884,"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"}},{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.972100019454956,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"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/T10320","display_name":"Neural Networks and Applications","score":0.9520999789237976,"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/dataflow","display_name":"Dataflow","score":0.902902364730835},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7754573822021484},{"id":"https://openalex.org/keywords/flex","display_name":"FLEX","score":0.7742783427238464},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7422126531600952},{"id":"https://openalex.org/keywords/fast-fourier-transform","display_name":"Fast Fourier transform","score":0.7234045267105103},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.6940115094184875},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.33011552691459656},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.22475209832191467},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06979861855506897}],"concepts":[{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.902902364730835},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7754573822021484},{"id":"https://openalex.org/C2776252893","wikidata":"https://www.wikidata.org/wiki/Q1364836","display_name":"FLEX","level":2,"score":0.7742783427238464},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7422126531600952},{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.7234045267105103},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.6940115094184875},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.33011552691459656},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.22475209832191467},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06979861855506897},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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:10.1109/iscas58744.2024.10558092","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iscas58744.2024.10558092","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Symposium on Circuits and Systems (ISCAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1849277567","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2289252105","https://openalex.org/W2584616277","https://openalex.org/W2604319603","https://openalex.org/W2612076670","https://openalex.org/W2759684853","https://openalex.org/W3007444108","https://openalex.org/W3013215059","https://openalex.org/W3017521908","https://openalex.org/W4244024631","https://openalex.org/W4255681033","https://openalex.org/W4280600490","https://openalex.org/W4300273322","https://openalex.org/W6637373629","https://openalex.org/W6775520913","https://openalex.org/W6910690987"],"related_works":["https://openalex.org/W4250698707","https://openalex.org/W4244545186","https://openalex.org/W4247748223","https://openalex.org/W1008394927","https://openalex.org/W183173419","https://openalex.org/W4253292776","https://openalex.org/W2483231410","https://openalex.org/W2293118914","https://openalex.org/W4244549413","https://openalex.org/W4367355863"],"abstract_inverted_index":{"This":[0,43],"paper":[1],"presents":[2],"a":[3,119,127],"novel":[4],"Hadamard":[5],"Product":[6],"Generator":[7],"(HPG)":[8],"for":[9,90,94],"FFT-based":[10],"CNN":[11],"acceleration":[12],"that":[13],"effectively":[14],"addresses":[15],"computation":[16],"and":[17,30,35,92,118],"energy":[18],"bottlenecks.":[19],"The":[20,75],"proposed":[21,57],"block":[22],"uses":[23],"Intra-Patch":[24],"parallelization":[25],"to":[26,51,63,97],"optimize":[27],"Complex":[28],"Multiply":[29],"Accumulate":[31],"(CMAC)":[32],"unit":[33],"utilization":[34],"maintains":[36],"identical":[37],"reuse":[38,69],"behavior":[39],"across":[40],"patch":[41],"elements.":[42],"scheme":[44],"also":[45],"offers":[46],"multiple":[47],"spatial":[48],"unrolling":[49],"schemes":[50],"increase":[52],"resource":[53],"reuse.":[54],"Additionally,":[55],"the":[56,60,72,80,98],"HPG":[58],"leverages":[59],"Flex-Stationary":[61],"dataflow":[62],"adaptively":[64],"store":[65],"tensors":[66],"with":[67,103,126],"high":[68],"opportunities":[70],"in":[71,124],"on-chip":[73],"memory.":[74],"prototype":[76],"is":[77],"implemented":[78],"on":[79],"Zynq":[81],"MPSoC":[82],"(XCZU7CG).":[83],"It":[84,110],"showcases":[85],"throughput":[86],"gains":[87],"of":[88,107],"8.16\u00d7":[89],"VGG-16":[91],"9.30\u00d7":[93],"AlexNet":[95],"compared":[96],"state-of-the-art":[99],"frequency":[100],"domain":[101],"accelerator":[102],"an":[104,112],"area":[105],"overhead":[106],"only":[108],"28.51%.":[109],"achieves":[111],"8.82\u00d7":[113],"average":[114],"improvement":[115,121],"over":[116,122],"Eyeriss":[117],"7.87\u00d7":[120],"Flexflow":[123],"EDP":[125],"similar":[128],"hardware":[129],"configuration.":[130]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}