{"id":"https://openalex.org/W4294032011","doi":"https://doi.org/10.1145/3561053","title":"An <i>Intermediate-Centric</i> Dataflow for Transposed Convolution Acceleration on FPGA","display_name":"An <i>Intermediate-Centric</i> Dataflow for Transposed Convolution Acceleration on FPGA","publication_year":2022,"publication_date":"2022-09-01","ids":{"openalex":"https://openalex.org/W4294032011","doi":"https://doi.org/10.1145/3561053"},"language":"en","primary_location":{"id":"doi:10.1145/3561053","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3561053","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3561053","source":{"id":"https://openalex.org/S136160450","display_name":"ACM Transactions on Embedded Computing Systems","issn_l":"1539-9087","issn":["1539-9087","1558-3465"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Embedded Computing Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3561053","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054412582","display_name":"Zhengzheng Ma","orcid":"https://orcid.org/0000-0002-6764-7437"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengzheng Ma","raw_affiliation_strings":["School of Computer Science, Center for Energy-efficient Computing and Applications, Peking University"],"raw_orcid":"https://orcid.org/0000-0002-6764-7437","affiliations":[{"raw_affiliation_string":"School of Computer Science, Center for Energy-efficient Computing and Applications, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049858651","display_name":"Tuo Dai","orcid":"https://orcid.org/0000-0003-0684-7299"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tuo Dai","raw_affiliation_strings":["School of Computer Science, Center for Energy-efficient Computing and Applications, Peking University"],"raw_orcid":"https://orcid.org/0000-0003-0684-7299","affiliations":[{"raw_affiliation_string":"School of Computer Science, Center for Energy-efficient Computing and Applications, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102904614","display_name":"Xuechao Wei","orcid":"https://orcid.org/0000-0002-0996-2260"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuechao Wei","raw_affiliation_strings":["School of Computer Science, Center for Energy-efficient Computing and Applications, Peking University"],"raw_orcid":"https://orcid.org/0000-0002-0996-2260","affiliations":[{"raw_affiliation_string":"School of Computer Science, Center for Energy-efficient Computing and Applications, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023468643","display_name":"Guojie Luo","orcid":"https://orcid.org/0000-0003-4932-3655"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guojie Luo","raw_affiliation_strings":["School of Computer Science, Center for Energy-efficient Computing and Applications, Peking University"],"raw_orcid":"https://orcid.org/0000-0003-4932-3655","affiliations":[{"raw_affiliation_string":"School of Computer Science, Center for Energy-efficient Computing and Applications, Peking University","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.2936,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.52758404,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"22","issue":"6","first_page":"1","last_page":"22"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9994000196456909,"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":0.9994000196456909,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9991000294685364,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9945999979972839,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.8793623447418213},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8216649293899536},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.7515254616737366},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7194303870201111},{"id":"https://openalex.org/keywords/stencil","display_name":"Stencil","score":0.658571720123291},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6005560159683228},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5591048002243042},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5517532229423523},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.46206673979759216},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4418971538543701},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.4285229742527008},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4151188135147095},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.2745600938796997},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22175267338752747},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.15784713625907898},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08575031161308289}],"concepts":[{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.8793623447418213},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8216649293899536},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.7515254616737366},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7194303870201111},{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.658571720123291},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6005560159683228},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5591048002243042},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5517532229423523},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.46206673979759216},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4418971538543701},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.4285229742527008},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4151188135147095},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.2745600938796997},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22175267338752747},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.15784713625907898},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08575031161308289},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3561053","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3561053","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3561053","source":{"id":"https://openalex.org/S136160450","display_name":"ACM Transactions on Embedded Computing Systems","issn_l":"1539-9087","issn":["1539-9087","1558-3465"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Embedded Computing Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3561053","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3561053","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3561053","source":{"id":"https://openalex.org/S136160450","display_name":"ACM Transactions on Embedded Computing Systems","issn_l":"1539-9087","issn":["1539-9087","1558-3465"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Embedded Computing Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1720568649","display_name":null,"funder_award_id":"62090021","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6438779272","display_name":null,"funder_award_id":"M-0187","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8996992023","display_name":null,"funder_award_id":"M-0187","funder_id":"https://openalex.org/F4320326177","funder_display_name":"Chinesisch-Deutsche Zentrum f\u00fcr Wissenschaftsf\u00f6rderung"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320326177","display_name":"Chinesisch-Deutsche Zentrum f\u00fcr Wissenschaftsf\u00f6rderung","ror":"https://ror.org/03ny8r668"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4294032011.pdf","grobid_xml":"https://content.openalex.org/works/W4294032011.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W1903029394","https://openalex.org/W2047920195","https://openalex.org/W2076517649","https://openalex.org/W2094756095","https://openalex.org/W2331128040","https://openalex.org/W2503339013","https://openalex.org/W2535919346","https://openalex.org/W2600578627","https://openalex.org/W2603178913","https://openalex.org/W2606722458","https://openalex.org/W2798838583","https://openalex.org/W2895738878","https://openalex.org/W2899824860","https://openalex.org/W2899915146","https://openalex.org/W2906403229","https://openalex.org/W3034100311","https://openalex.org/W3040533934","https://openalex.org/W3137762252","https://openalex.org/W4206010581","https://openalex.org/W4238913942"],"related_works":["https://openalex.org/W3105129168","https://openalex.org/W2804920739","https://openalex.org/W2998381397","https://openalex.org/W4236419692","https://openalex.org/W4316371992","https://openalex.org/W2999668243","https://openalex.org/W2807127337","https://openalex.org/W2177020196","https://openalex.org/W1429949169","https://openalex.org/W3139770841"],"abstract_inverted_index":{"Transposed":[0],"convolution":[1,83,130],"has":[2],"been":[3],"prevailing":[4],"in":[5,14,60,64,102,145],"convolutional":[6,205,215],"neural":[7],"networks":[8],"(CNNs),":[9],"playing":[10],"an":[11,98,187],"important":[12],"role":[13],"multiple":[15],"scenarios":[16],"such":[17],"as":[18,88],"image":[19],"segmentation":[20],"and":[21,55,140,155,195,207,220,237,246],"back-propagation":[22],"process":[23],"of":[24,81,93,108,159,181,228,241],"training":[25],"CNNs.":[26],"This":[27],"mainly":[28],"benefits":[29],"from":[30,43,112,217],"the":[31,35,44,49,67,71,79,89,106,109,120,128,136,142,168,173,178,192,198,212,224,232,239],"ability":[32],"to":[33,66,190],"up-sample":[34],"input":[36,45,137,160],"feature":[37,46,138,161],"maps":[38,139],"by":[39],"interpolating":[40],"new":[41],"information":[42],"pixels.":[47],"However,":[48],"backward-stencil":[50,121,143],"computation":[51,122,144,153],"constrains":[52,177],"its":[53,57,113],"performance":[54,240],"hindered":[56],"wide":[58],"application":[59],"diverse":[61],"platforms.":[62,209],"Moreover,":[63],"contrast":[65],"efforts":[68],"on":[69,78,231],"accelerating":[70],"convolution,":[72,95],"there":[73],"is":[74,85],"a":[75,146],"rare":[76],"investigation":[77],"acceleration":[80,92],"transposed":[82,94,129,182,204,214],"that":[84],"identically":[86],"compute-intensive":[87],"former.":[90],"For":[91],"we":[96,104,164,185,222],"propose":[97],"intermediate-centric":[99,125,229],"dataflow":[100,126,230],"scheme,":[101],"which":[103,176],"decouple":[105],"generation":[107],"intermediate":[110],"patch":[111],"further":[114],"process,":[115],"aim":[116],"at":[117],"efficiently":[118],"performing":[119,141],".":[123],"The":[124],"breaks":[127],"into":[131],"several":[132],"phases/stages,":[133],"achieving":[134],"feeding":[135],"pipelining":[147],"manner.":[148],"It":[149],"also":[150,165],"provides":[151],"four-degree":[152],"parallelism":[154],"efficient":[156],"data":[157,170],"reuse":[158],"maps/weights.":[162],"Furthermore,":[163],"theoretically":[166],"analyze":[167],"irregular":[169],"dependence":[171],"leveraging":[172],"polyhedral":[174],"model,":[175],"parallel":[179],"computing":[180],"convolution.":[183],"Additionally,":[184],"devise":[186],"optimization":[188],"problem":[189],"explore":[191],"design":[193,200],"space":[194],"automatically":[196],"generate":[197,223],"optimal":[199],"configurations":[201],"for":[202],"different":[203],"layers":[206,216],"hardware":[208],"By":[210],"selecting":[211],"representative":[213],"DCGAN,":[218],"FSRCNN,":[219],"FCN,":[221],"corresponding":[225],"accelerator":[226],"arrays":[227],"Xilinx":[233],"Alveo":[234],"U200":[235],"platform":[236],"reach":[238],"3.92":[242],"TOPS,":[243,245,248],"2.72":[244],"4.76":[247],"respectively.":[249]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}