{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,19]],"date-time":"2026-10-19T16:15:24Z","timestamp":1792426524467,"version":"4.5.0"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2022,5,14]],"date-time":"2022-05-14T00:00:00Z","timestamp":1652486400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,5,14]],"date-time":"2022-05-14T00:00:00Z","timestamp":1652486400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100010712","name":"Viet Nam National University Ho Chi Minh City","doi-asserted-by":"publisher","award":["B2021-20-02"],"award-info":[{"award-number":["B2021-20-02"]}],"id":[{"id":"10.13039\/501100010712","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mobile Netw Appl"],"published-print":{"date-parts":[[2022,10]]},"DOI":"10.1007\/s11036-022-01985-9","type":"journal-article","created":{"date-parts":[[2022,5,14]],"date-time":"2022-05-14T01:04:02Z","timestamp":1652490242000},"page":"2024-2035","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Towards An FPGA-targeted Hardware\/Software Co-design Framework for CNN-based Edge Computing"],"prefix":"10.1007","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2917-1244","authenticated-orcid":false,"given":"Cuong","family":"Pham-Quoc","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuan-Quang","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tran Ngoc","family":"Thinh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,5,14]]},"reference":[{"issue":"8","key":"1985_CR1","doi-asserted-by":"publisher","first-page":"5455","DOI":"10.1007\/s10462-020-09825-6","volume":"53","author":"A Khan","year":"2020","unstructured":"Khan A, Sohail A, Zahoora U, Qureshi AS (2020) A survey of the recent architectures of deep convolutional neural networks. Artif Intell Rev 53(8):5455\u20135516","journal-title":"Artif Intell Rev"},{"key":"1985_CR2","doi-asserted-by":"crossref","unstructured":"Strigl D, Kofler K, Podlipnig S (2010) Performance and scalability of gpu-based convolutional neural networks. In: 2010 18Th Euromicro conference on parallel, distributed and network-based processing, pp 317\u2013324","DOI":"10.1109\/PDP.2010.43"},{"key":"1985_CR3","unstructured":"Lacey G, Taylor GW, Areibi S (2016) Deep learning on fpgas: Past, present, and future. arxiv:1602.04283"},{"key":"1985_CR4","unstructured":"Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. arxiv:1409.1556"},{"key":"1985_CR5","doi-asserted-by":"publisher","unstructured":"Wu R, Guo X, Du J, Li J (2021) Accelerating neural network inference on fpga-based platforms\u2014a survey. Electronics 10(9). https:\/\/doi.org\/10.3390\/electronics10091025","DOI":"10.3390\/electronics10091025"},{"issue":"02","key":"1985_CR6","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1109\/MCSE.2017.31","volume":"19","author":"R Williams","year":"2017","unstructured":"Williams R (2017) What\u2019s next? [the end of moore\u2019s law]. Comput Sci Eng 19(02):7\u201313","journal-title":"Comput Sci Eng"},{"key":"1985_CR7","doi-asserted-by":"crossref","unstructured":"Guo K, Zeng S, Yu J, Wang Y, Yang H (2019) [dl] a survey of fpga-based neural network inference accelerators. ACM Trans. Reconfigurable Technol. Syst 12(1)","DOI":"10.1145\/3289185"},{"issue":"4","key":"1985_CR8","doi-asserted-by":"publisher","first-page":"1109","DOI":"10.1007\/s00521-018-3761-1","volume":"32","author":"S Mittal","year":"2020","unstructured":"Mittal S (2020) A survey of fpga-based accelerators for convolutional neural networks. Neural Comput Applic 32(4):1109\u20131139","journal-title":"Neural Comput Applic"},{"key":"1985_CR9","doi-asserted-by":"crossref","unstructured":"Wu R, Guo X, Du J, Li J (2021) Accelerating neural network inference on fpga-based platforms\u2014a survey. Electronics 10(9)","DOI":"10.3390\/electronics10091025"},{"key":"1985_CR10","unstructured":"Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Andreetto M, Adam H (2017) Mobilenets: Efficient convolutional neural networks for mobile vision applications. arxiv:1704.04861"},{"key":"1985_CR11","doi-asserted-by":"publisher","unstructured":"Pham-Quoc C, Al-Ars Z, Bertels K (2012) A heuristic-based communication-aware hardware optimization approach in heterogeneous multicore systems. In: 2012 International conference on reconfigurable computing and FPGAs, pp 1\u20136. https:\/\/doi.org\/10.1109\/ReConFig.2012.6416720","DOI":"10.1109\/ReConFig.2012.6416720"},{"key":"1985_CR12","doi-asserted-by":"crossref","unstructured":"DeMicheli G, Sami M (1996) Hardware\/software co-design. Nato Science Series E. Springer Netherlands.\u00a0https:\/\/www.springer.com\/gp\/book\/9780792338833.\u00a0Accessed 1 Nov 2021","DOI":"10.1007\/978-94-009-0187-2"},{"key":"1985_CR13","doi-asserted-by":"crossref","unstructured":"Pham-Quoc C, Nguyen XQ, Thinh TN (2021) Hardware\/software co-design for convolutional neural networks acceleration: a survey and open issues. In: 2021 10Th EAI International conference on context-aware systems and applications, pp 1\u201315","DOI":"10.1007\/978-3-030-93179-7_13"},{"issue":"2","key":"1985_CR14","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1109\/MM.2017.39","volume":"37","author":"K Guo","year":"2017","unstructured":"Guo K, Han S, Yao S, Wang Y, Xie Y, Yang H (2017) Software-hardware codesign for efficient neural network acceleration. IEEE Micro 37(2):18\u201325","journal-title":"IEEE Micro"},{"key":"1985_CR15","unstructured":"Li H, Fan X, Jiao L, Cao W, Zhou X, Wang L (2016) A high performance fpga-based accelerator for large-scale convolutional neural networks. In: 2016 26Th International conference on field programmable logic and applications (FPL), pp 1\u20139"},{"key":"1985_CR16","doi-asserted-by":"crossref","unstructured":"Lin X, Yin S, Tu F, Liu L, Li X, Wei S (2018) Lcp: a layer clusters paralleling mapping method for accelerating inception and residual networks on fpga. In: 2018 55Th ACM\/ESDA\/IEEE design automation conference (DAC), pp 1\u20136","DOI":"10.1109\/DAC.2018.8465777"},{"key":"1985_CR17","unstructured":"Liu Z, Dou Y, Jiang J, Xu J (2016) Automatic code generation of convolutional neural networks in fpga implementation. In: 2016 International conference on field-programmable technology (FPT), pp 61\u201368"},{"key":"1985_CR18","doi-asserted-by":"crossref","unstructured":"Ma Y, Cao Y, Vrudhula S, Seo JS (2017) Optimizing loop operation and dataflow in fpga acceleration of deep convolutional neural networks. In: Proceedings of the 2017 ACM\/SIGDA international symposium on field-programmable gate arrays, FPGA \u201917, pp 45\u201354. ACM, New York, NY, USA","DOI":"10.1145\/3020078.3021736"},{"key":"1985_CR19","doi-asserted-by":"crossref","unstructured":"Yang L, He Z, Fan D (2018) A fully onchip binarized convolutional neural network fpga impelmentation with accurate inference. In: Proceedings of the international symposium on low power electronics and design, ISLPED \u201918. ACM, New York, NY, USA","DOI":"10.1145\/3218603.3218615"},{"key":"1985_CR20","doi-asserted-by":"crossref","unstructured":"Zhang X, Wang J, Zhu C, Lin Y, Xiong J, Hwu WM, Chen D (2018) Dnnbuilder: An automated tool for building high-performance dnn hardware accelerators for fpgas. In: Proceedings of the international conference on computer-aided design, ICCAD \u201918. ACM, New York, NY, USA","DOI":"10.1145\/3240765.3240801"},{"key":"1985_CR21","doi-asserted-by":"crossref","unstructured":"Podili A, Zhang C, Prasanna V (2017) Fast and efficient implementation of convolutional neural networks on fpga. In: 2017 IEEE 28Th international conference on application-specific systems, architectures and processors (ASAP), pp 11\u201318","DOI":"10.1109\/ASAP.2017.7995253"},{"key":"1985_CR22","doi-asserted-by":"crossref","unstructured":"Motamedi M, Gysel P, Akella V, Ghiasi S (2016) Design space exploration of fpga-based deep convolutional neural networks. In: 2016 21St Asia and south pacific design automation conference (ASP-DAC), pp 575\u2013580","DOI":"10.1109\/ASPDAC.2016.7428073"},{"key":"1985_CR23","doi-asserted-by":"crossref","unstructured":"Yang Y, Huang Q, Wu B, Zhang T, Ma L, Gambardella G, Blott M, Lavagno L, Vissers K, Wawrzynek J, Keutzer K (2019) Synetgy: Algorithm-hardware co-design for convnet accelerators on embedded fpgas. In: Proceedings of the 2019 ACM\/SIGDA international symposium on field-programmable gate arrays, FPGA \u201919, pp 23\u201332. ACM, New York, NY, USA","DOI":"10.1145\/3289602.3293902"},{"key":"1985_CR24","doi-asserted-by":"crossref","unstructured":"Ghasemzadeh M, Samragh M, Koushanfar F (2018) Rebnet: Residual binarized neural network. In: IEEE 26th Annual international symposium on field-programmable custom computing machines (FCCM), pp 57\u201364. IEEE Computer Society, Los Alamitos, CA, USA","DOI":"10.1109\/FCCM.2018.00018"},{"key":"1985_CR25","doi-asserted-by":"crossref","unstructured":"Jiao L, Luo C, Cao W, Zhou X, Wang L (2017) Accelerating low bit-width convolutional neural networks with embedded fpga. In: 2017 27Th International conference on field programmable logic and applications (FPL), pp 1\u20134","DOI":"10.23919\/FPL.2017.8056820"},{"key":"1985_CR26","doi-asserted-by":"crossref","unstructured":"Moss DJM, Nurvitadhi E, Sim J, Mishra A, Marr D, Subhaschandra S, Leong PHW (2017) High performance binary neural networks on the xeon+fpga\u2122platform. In: 2017 27Th International conference on field programmable logic and applications (FPL), pp 1\u20134","DOI":"10.23919\/FPL.2017.8056823"},{"key":"1985_CR27","doi-asserted-by":"crossref","unstructured":"Nakahara H, Fujii T, Sato S (2017) A fully connected layer elimination for a binarizec convolutional neural network on an fpga. In: 2017 27Th international conference on field programmable logic and applications (FPL), pp 1\u20134","DOI":"10.23919\/FPL.2017.8056771"},{"key":"1985_CR28","doi-asserted-by":"crossref","unstructured":"Nurvitadhi E, Sheffield D, Sim J, Mishra A, Venkatesh G, Marr D (2016) Accelerating binarized neural networks: Comparison of fpga, cpu, gpu, and asic. In: 2016 International conference on field-programmable technology (FPT), pp 77\u201384","DOI":"10.1109\/FPT.2016.7929192"},{"key":"1985_CR29","doi-asserted-by":"crossref","unstructured":"Prost-Boucle A, Bourge A, P\u00e9trot F., Alemdar H, Caldwell N, Leroy V (2017) Scalable high-performance architecture for convolutional ternary neural networks on fpga. In: 2017 27Th International conference on field programmable logic and applications (FPL), pp 1\u20137","DOI":"10.23919\/FPL.2017.8056850"},{"key":"1985_CR30","doi-asserted-by":"crossref","unstructured":"Umuroglu Y, Fraser NJ, Gambardella G, Blott M, Leong P, Jahre M, Vissers K (2017) Finn: a framework for fast, scalable binarized neural network inference. In: Proceedings of the 2017 ACM\/SIGDA international symposium on field-programmable gate arrays, FPGA \u201917, pp 65\u201374. ACM, New York, NY, USA","DOI":"10.1145\/3020078.3021744"},{"key":"1985_CR31","doi-asserted-by":"publisher","first-page":"1072","DOI":"10.1016\/j.neucom.2017.09.046","volume":"275","author":"S Liang","year":"2018","unstructured":"Liang S, Yin S, Liu L, Luk W, Wei S (2018) Fp-bnn: Binarized neural network on fpga. Neurocomputing 275:1072\u20131086","journal-title":"Neurocomputing"},{"key":"1985_CR32","doi-asserted-by":"crossref","unstructured":"Cao S, Zhang C, Yao Z, Xiao W, Nie L, Zhan D, Liu Y, Wu M, Zhang L (2019) Efficient and effective sparse lstm on fpga with bank-balanced sparsity. In: Proceedings of the 2019 ACM\/SIGDA international symposium on field-programmable gate arrays, FPGA \u201919, pp 63\u201372. Association for Computing Machinery","DOI":"10.1145\/3289602.3293898"},{"issue":"12","key":"1985_CR33","doi-asserted-by":"publisher","first-page":"2816","DOI":"10.1109\/TVLSI.2019.2941250","volume":"27","author":"S Kala","year":"2019","unstructured":"Kala S, Jose BR, Mathew J, Nalesh S (2019) High-performance cnn accelerator on fpga using unified winograd-gemm architecture. IEEE Trans Very Large Scale Integration (VLSI) Systems 27 (12):2816\u20132828. https:\/\/doi.org\/10.1109\/TVLSI.2019.2941250","journal-title":"IEEE Trans Very Large Scale Integration (VLSI) Systems"},{"key":"1985_CR34","doi-asserted-by":"publisher","unstructured":"Wang J, Lou Q, Zhang X, Zhu C, Lin Y, Chen D (2018) Design flow of accelerating hybrid extremely low bit-width neural network in embedded fpga. In: 2018 28Th International conference on field programmable logic and applications (FPL), pp 163\u20131636. https:\/\/doi.org\/10.1109\/FPL.2018.00035","DOI":"10.1109\/FPL.2018.00035"},{"key":"1985_CR35","doi-asserted-by":"publisher","unstructured":"Ding C, Wang S, Liu N, Xu K, Wang Y, Liang Y (2019) Req-yolo: a resource-aware, efficient quantization framework for object detection on fpgas. In: Proceedings of the 2019 ACM\/SIGDA international symposium on field-programmable gate arrays, FPGA \u201919, pp 33\u201342. Association for Computing Machinery, New York, NY, USA. https:\/\/doi.org\/10.1145\/3289602.3293904","DOI":"10.1145\/3289602.3293904"},{"key":"1985_CR36","doi-asserted-by":"crossref","unstructured":"Pham-Quoc C, Al-Ars Z, Bertels K (2013) Heterogeneous hardware accelerators interconnect: an overview. In: 2013 NASA\/ESA Conference on adaptive hardware and systems (AHS-2013), pp 189\u2013197","DOI":"10.1109\/AHS.2013.6604245"},{"issue":"6","key":"1985_CR37","first-page":"1941","volume":"65","author":"J Wang","year":"2018","unstructured":"Wang J, Lin J, Wang Z (2018) Efficient hardware architectures for deep convolutional neural network. IEEE Trans Circ Syst I: Regular Papers 65(6):1941\u20131953","journal-title":"IEEE Trans Circ Syst I: Regular Papers"},{"key":"1985_CR38","doi-asserted-by":"crossref","unstructured":"Lu L, Liang Y, Xiao Q, Yan S (2017) Evaluating fast algorithms for convolutional neural networks on fpgas. In: 2017 IEEE 25Th annual international symposium on field-programmable custom computing machines (FCCM), pp 101\u2013108","DOI":"10.1109\/FCCM.2017.64"},{"key":"1985_CR39","doi-asserted-by":"crossref","unstructured":"Guan Y, Liang H, Xu N, Wang W, Shi S, Chen X, Sun G, Zhang W, Cong J (2017) Fp-dnn: an automated framework for mapping deep neural networks onto fpgas with rtl-hls hybrid templates. In: 2017 IEEE 25Th Annual international symposium on field-programmable custom computing machines (FCCM), pp 152\u2013159","DOI":"10.1109\/FCCM.2017.25"},{"key":"1985_CR40","doi-asserted-by":"crossref","unstructured":"Qiu J, Wang J, Yao S, Guo K, Li B, Zhou E, Yu J, Tang T, Xu N, Song S, Wang Y, Yang H (2016) Going deeper with embedded fpga platform for convolutional neural network. In: Proceedings of the 2016 ACM\/SIGDA international symposium on field-programmable gate arrays, FPGA \u201916, pp 26\u201335. ACM, New York, NY, USA","DOI":"10.1145\/2847263.2847265"},{"key":"1985_CR41","doi-asserted-by":"crossref","unstructured":"Wei X, Yu CH, Zhang P, Chen Y, Wang Y, Hu H, Liang Y, Cong J (2017) Automated systolic array architecture synthesis for high throughput cnn inference on fpgas. In: 2017 54Th ACM\/EDAC\/IEEE design automation conference (DAC), pp 1\u20136","DOI":"10.1145\/3061639.3062207"},{"key":"1985_CR42","doi-asserted-by":"crossref","unstructured":"Shen Y, Ferdman M, Milder P (2017) Escher: a cnn accelerator with flexible buffering to minimize off-chip transfer. In: 2017 IEEE 25Th annual international symposium on field-programmable custom computing machines (FCCM), pp 93\u2013100","DOI":"10.1109\/FCCM.2017.47"},{"issue":"1","key":"1985_CR43","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1109\/TCAD.2017.2705069","volume":"37","author":"K Guo","year":"2018","unstructured":"Guo K, Sui L, Qiu J, Yu J, Wang J, Yao S, Han S, Wang Y, Yang H (2018) Angel-eye: a complete design flow for mapping cnn onto embedded fpga. IEEE Trans Comput-Aided Des Integr Circuits Syst 37(1):35\u201347","journal-title":"IEEE Trans Comput-Aided Des Integr Circuits Syst"},{"issue":"July-Dec","key":"1985_CR44","first-page":"1","volume":"11","author":"XQ Nguyen","year":"2021","unstructured":"Nguyen XQ, Pham-Quoc C (2021) An fpga-based convolution ip core for deep neural networks acceleration. REV J Electron Commun 11(July-Dec):1\u20138","journal-title":"REV J Electron Commun"},{"issue":"1","key":"1985_CR45","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1109\/TVLSI.2019.2935251","volume":"28","author":"J Sim","year":"2020","unstructured":"Sim J, Lee S, Kim LS (2020) An energy-efficient deep convolutional neural network inference processor with enhanced output stationary dataflow in 65-nm cmos. IEEE Trans Very Large Scale Integration (VLSI) Syst 28(1):87\u2013100. https:\/\/doi.org\/10.1109\/TVLSI.2019.2935251","journal-title":"IEEE Trans Very Large Scale Integration (VLSI) Syst"},{"key":"1985_CR46","unstructured":"Avnet (2021) Ultra96-v2 board - arm-based, xilinx zynq ultrascale+ mpsoc development board based on the linaro 96boards consumer edition specification.\u00a0https:\/\/www.avnet.com\/wps\/portal\/us\/products\/new-product-introductions\/npi\/aes-ultra96-v2\/.\u00a0Accessed 10 Oct 2021"},{"key":"1985_CR47","unstructured":"Xilinx (2021) Zynq ultrascale+ mpsoc.\u00a0https:\/\/www.xilinx.com\/products\/silicon-devices\/soc\/zynq-ultrascale-mpsoc.html.\u00a0Accessed 10 Oct 2021"},{"key":"1985_CR48","doi-asserted-by":"crossref","unstructured":"Pham-Quoc C, Heisswolf J, Werner S, Al-Ars Z, Becker J, Bertels K (2013) Hybrid interconnect design for heterogeneous hardware accelerators. In: Proceedings of the Conference on Design, Automation and Test in Europe, DATE \u201913, pp 843\u2013846. EDA Consortium, San Jose, CA, USA","DOI":"10.7873\/DATE.2013.178"}],"container-title":["Mobile Networks and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11036-022-01985-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11036-022-01985-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11036-022-01985-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,24]],"date-time":"2022-10-24T09:23:00Z","timestamp":1666603380000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11036-022-01985-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,14]]},"references-count":48,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2022,10]]}},"alternative-id":["1985"],"URL":"https:\/\/doi.org\/10.1007\/s11036-022-01985-9","relation":{},"ISSN":["1383-469X","1572-8153"],"issn-type":[{"value":"1383-469X","type":"print"},{"value":"1572-8153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,5,14]]},"assertion":[{"value":"4 April 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 May 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that there are no conflicts of interest regarding the publication of this paper","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Conflict of Interests"}}]}}