{"id":"https://openalex.org/W4319870530","doi":"https://doi.org/10.1145/3543622.3573141","title":"AoCStream: All-on-Chip CNN Accelerator With Stream-Based Line-Buffer Architecture","display_name":"AoCStream: All-on-Chip CNN Accelerator With Stream-Based Line-Buffer Architecture","publication_year":2023,"publication_date":"2023-02-10","ids":{"openalex":"https://openalex.org/W4319870530","doi":"https://doi.org/10.1145/3543622.3573141"},"language":"en","primary_location":{"id":"doi:10.1145/3543622.3573141","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3543622.3573141","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM/SIGDA International Symposium on Field Programmable Gate Arrays","raw_type":"proceedings-article"},"type":"conference-abstract","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/A5050847500","display_name":"Hyeong\u2010Ju Kang","orcid":"https://orcid.org/0000-0002-0408-661X"},"institutions":[{"id":"https://openalex.org/I35886859","display_name":"Korea University of Technology and Education","ror":"https://ror.org/053nycv62","country_code":"KR","type":"education","lineage":["https://openalex.org/I35886859"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Hyeong-Ju Kang","raw_affiliation_strings":["Korea University of Technology and Education, Cheonan-si, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-0408-661X","affiliations":[{"raw_affiliation_string":"Korea University of Technology and Education, Cheonan-si, South Korea","institution_ids":["https://openalex.org/I35886859"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5050847500"],"corresponding_institution_ids":["https://openalex.org/I35886859"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"48","last_page":"48"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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":0.9998000264167786,"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/T11992","display_name":"CCD and CMOS Imaging Sensors","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"}},{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9911999702453613,"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/computer-science","display_name":"Computer science","score":0.8465074896812439},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.5982764363288879},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.593969464302063},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.5216879844665527},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5193318128585815},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5077065229415894},{"id":"https://openalex.org/keywords/memory-architecture","display_name":"Memory architecture","score":0.47216886281967163},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.46451038122177124},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4543234407901764},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.34266605973243713},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1249290406703949},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08824655413627625}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8465074896812439},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.5982764363288879},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.593969464302063},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.5216879844665527},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5193318128585815},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5077065229415894},{"id":"https://openalex.org/C2779602883","wikidata":"https://www.wikidata.org/wiki/Q15544750","display_name":"Memory architecture","level":2,"score":0.47216886281967163},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.46451038122177124},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4543234407901764},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.34266605973243713},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1249290406703949},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08824655413627625},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3543622.3573141","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3543622.3573141","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM/SIGDA International Symposium on Field Programmable Gate Arrays","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.47999998927116394,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2293118914","https://openalex.org/W2998381397","https://openalex.org/W4236419692","https://openalex.org/W2171015181","https://openalex.org/W3167919718","https://openalex.org/W4251718783","https://openalex.org/W4239447582","https://openalex.org/W1484403103","https://openalex.org/W2521947294","https://openalex.org/W2999668243"],"abstract_inverted_index":{"Convolutional":[0],"neural":[1],"network":[2],"(CNN)":[3],"accelerators":[4,214],"are":[5,82,147],"being":[6],"widely":[7],"used":[8],"for":[9,79],"their":[10],"efficiency,":[11],"but":[12],"they":[13],"require":[14],"a":[15,46,56,60,72,77,116,130,135,194,204],"large":[16],"amount":[17,41,67,92],"of":[18,24,48,55,68,85,93,103,111,138,143,152,168,231],"memory,":[19],"leading":[20],"to":[21,36,44,100,149,212],"the":[22,38,65,69,80,86,91,94,101,104,120,144,150,153,157,166,180,186,220],"use":[23],"slow":[25],"and":[26,42,76,122,234],"power":[27],"consuming":[28],"external":[29,209],"memories.":[30],"This":[31],"paper":[32],"exploits":[33],"two":[34],"schemes":[35],"reduce":[37,64],"required":[39],"memory":[40,54,66,97,182],"ultimately":[43],"implement":[45],"CNN":[47,198],"reasonable":[49],"performance":[50],"only":[51],"with":[52,119,215,227],"on-chip":[53],"practical":[57],"device":[58],"like":[59],"low-end":[61,205],"FPGA.":[62],"To":[63],"intermediate":[70,95,161],"data,":[71],"stream-based":[73],"line-buffer":[74],"architecture":[75,81,109,158],"dataflow":[78],"proposed":[83,221],"instead":[84],"conventional":[87],"frame-based":[88],"architecture,":[89],"where":[90],"data":[96,162],"is":[98,183],"proportional":[99,148],"square":[102],"input":[105,121,139,154,171],"image":[106],"size.":[107],"The":[108,141,189],"consists":[110],"layer-dedicated":[112],"blocks":[113],"operating":[114],"in":[115,165,173],"pipelined":[117],"way":[118],"output":[123],"streams.":[124],"Each":[125],"convolutional":[126],"layer":[127],"block":[128],"has":[129],"line":[131,145],"buffer":[132],"storing":[133],"just":[134],"few":[136],"rows":[137],"data.":[140],"sizes":[142],"buffers":[146],"width":[151],"image,":[155],"so":[156],"requires":[159],"less":[160,228],"storage,":[163],"especially":[164],"trend":[167],"getting":[169],"larger":[170],"size":[172],"modern":[174],"object":[175,196,217],"detection":[176,197,218],"CNNs.":[177],"In":[178],"addition,":[179],"weight":[181],"reduced":[184],"by":[185],"accelerator-aware":[187],"pruning.":[188],"experimental":[190],"results":[191],"show":[192],"that":[193],"whole":[195],"can":[199],"be":[200],"implemented":[201],"even":[202,226],"on":[203],"FPGA":[206,229],"without":[207],"an":[208],"memory.":[210],"Compared":[211],"previous":[213],"similar":[216],"accuracy,":[219],"accelerator":[222],"reaches":[223],"higher":[224,237],"throughput":[225],"resources":[230],"LUTs,":[232],"registers,":[233],"DSPs,":[235],"showing":[236],"efficiency.":[238]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}