{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T09:23:59Z","timestamp":1775467439450,"version":"3.50.1"},"reference-count":24,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"7","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2023,7,1]]},"DOI":"10.1587\/transinf.2022edp7175","type":"journal-article","created":{"date-parts":[[2023,6,30]],"date-time":"2023-06-30T22:19:02Z","timestamp":1688163542000},"page":"1198-1208","source":"Crossref","is-referenced-by-count":9,"title":["Parallel Implementation of CNN on Multi-FPGA Cluster"],"prefix":"10.1587","volume":"E106.D","author":[{"given":"Yasuyu","family":"FUKUSHIMA","sequence":"first","affiliation":[{"name":"Dept. of Information and Computer Science, Keio University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kensuke","family":"IIZUKA","sequence":"additional","affiliation":[{"name":"Dept. of Information and Computer Science, Keio University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hideharu","family":"AMANO","sequence":"additional","affiliation":[{"name":"Dept. of Information and Computer Science, Keio University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"532","reference":[{"key":"1","unstructured":"[1] PALTEK, \u201cFPGA computing platform M-KUBOS,\u201d https:\/\/www.pal-tek.co.jp\/design\/original\/m-kubos\/ (accessed 2021-1-20)."},{"key":"2","doi-asserted-by":"crossref","unstructured":"[2] T. Inage, K. Hironaka, K. Iizuka, K. Ito, Y. Fukushima, M. Namiki, and H. Amano, \u201cM-KUBOS\/PYNQ cluster for multi-access edge computing,\u201d CANDAR2021, Nov. 2021. 10.1109\/CANDAR53791.2021.00020","DOI":"10.1109\/CANDAR53791.2021.00020"},{"key":"3","unstructured":"[3] Xilinx Inc, \u201cPYNQ-Python productivity for Zynq-Home,\u201d http:\/\/www.pynq.io\/ (accessed 2021-1-22), 2019."},{"key":"4","doi-asserted-by":"crossref","unstructured":"[4] K. Ito, K. Iizuka, K. Hironaka, Y. Hu, M. Koibuchi, and H. Amano, \u201cImplementing a multi-ejection switch and making the use of multiple Lanes in a circuit-switched multi-FPGA system,\u201d CANDAR20 Workshop, Nov. 2020. 10.1109\/CANDARW51189.2020.00049","DOI":"10.1109\/CANDARW51189.2020.00049"},{"key":"5","doi-asserted-by":"publisher","unstructured":"[5] K. Hironaka, K. Iizuka, M. Yamakura, A.B. Ahmed, and H. Amano, \u201cRemote dynamic reconfiguration of a multi-FPGA system FiC (Flow-in-Cloud),\u201d IEICE Trans. Inf. & Syst., vol.E104-D, no.8, pp.1321-1331, Aug. 2021. 10.1587\/transinf.2020EDP7165","DOI":"10.1587\/transinf.2020EDP7165"},{"key":"6","unstructured":"[6] \u201cSlurm Workload Manager.\u201d https:\/\/slurm.schedmd.com\/ (accessed 2021-12-01)."},{"key":"7","doi-asserted-by":"publisher","unstructured":"[7] M. Yamakura, R. Takano, A.B. Ahmed, M. Sugaya, and H. Amano, \u201cA multi-tenant resource management system for multi-FPGA systems,\u201d IEICE Trans. Inf. & Syst., vol.E104-D, no.12, pp.2078-2088, Dec. 2021. 10.1587\/transinf.2021PAP0005","DOI":"10.1587\/transinf.2021PAP0005"},{"key":"8","doi-asserted-by":"crossref","unstructured":"[8] K. He, X. Zhang, S. Ren, and J. Sun, \u201cDeep residual learning for image recognition,\u201d 2016 IEEE Conference on Comput. Vis. Pattern Recognit. (CVPR), pp.770-778, June 2016. 10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"9","unstructured":"[9] MLCommons, \u201cMLPerf,\u201d https:\/\/mlcommons.org\/ja\/ (accessed 2021-6-18)."},{"key":"10","unstructured":"[10] Microsoft Research, \u201cProject Brainwave,\u201d https:\/\/www.microsoft.c-om\/en-us\/research\/project\/project-brainwave\/ (accessed 2021-6-18)."},{"key":"11","doi-asserted-by":"crossref","unstructured":"[11] H. Sharma, J. Park, D. Mahajan, E. Amaro, J.K. Kim, C. Shao, A. Mishra, and H. Esmaeilzadeh, \u201cFrom high-level deep neural models to FPGAs,\u201d 2016 49th Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO), pp.1-12, 2016. 10.1109\/MICRO.2016.7783720","DOI":"10.1109\/MICRO.2016.7783720"},{"key":"12","doi-asserted-by":"crossref","unstructured":"[12] C. Zhang, P. Li, G. Sun, Y. Guan, B. Xiao, and J. Cong, \u201cOptimizing FPGA-based accelerator design for deep convolutional neural networks,\u201d Proc. 2015 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays, FPGA '15, New York, NY, USA, pp.161-170, ACM, Feb. 2015. 10.1145\/2684746.2689060","DOI":"10.1145\/2684746.2689060"},{"key":"13","doi-asserted-by":"crossref","unstructured":"[13] X. Zhang, J. Wang, C. Zhu, Y. Lin, J. Xiong, W. Hwu, and D. Chen, \u201cDNNBuilder: an automated tool for building high-performance DNN hardware accelerators for FPGAs,\u201d 2018 IEEE\/ACM International Conference on Computer-Aided Design (ICCAD), pp.1-8, Nov. 2018. 10.1145\/3240765.3240801","DOI":"10.1145\/3240765.3240801"},{"key":"14","doi-asserted-by":"crossref","unstructured":"[14] C. Zhang, D. Wu, J. Sun, G. Sun, G. Luo, and J. Cong, \u201cEnergy-efficient CNN implementation on a deeply pipelined FPGA cluster,\u201d Proc. 2016 International Symposium on Low Power Electronics and Design, ISLPED '16, New York, NY, USA, pp.326-331, Association for Computing Machinery, Aug. 2016. 10.1145\/2934583.2934644","DOI":"10.1145\/2934583.2934644"},{"key":"15","doi-asserted-by":"crossref","unstructured":"[15] W. Zhang, J. Zhang, M. Shen, G. Luo, and N. Xiao, \u201cAn efficient mapping approach to large-scale DNNs on multi-FPGA architectures,\u201d 2019 Design, Automation Test in Europe Conference Exhibition (DATE), pp.1241-1244, March 2019. 10.23919\/DATE.2019.8715174","DOI":"10.23919\/DATE.2019.8715174"},{"key":"16","doi-asserted-by":"crossref","unstructured":"[16] T. Geng, T. Wang, A. Sanaullah, C. Yang, R. Patel, and M. Herbordt, \u201cA framework for acceleration of CNN training on deeply-pipelined FPGA clusters with work and weight load balancing,\u201d 2018 28th International Conference on Field Programmable Logic and Applications (FPL), pp.394-398, 2018. 10.1109\/FPL.2018.00074","DOI":"10.1109\/FPL.2018.00074"},{"key":"17","doi-asserted-by":"crossref","unstructured":"[17] Y. Fukushima, K. Iizuka, and H. Amano, \u201cParallel implementation of CNN on multi-FPGA cluster,\u201d MCSoC-2021, Dec. 2021. 10.1109\/MCSoC51149.2021.00019","DOI":"10.1109\/MCSoC51149.2021.00019"},{"key":"18","unstructured":"[18] PyTorch, \u201cQuantization \u2014 PyTorch 1.9.0 documentation,\u201d https:\/\/pytorch.org\/docs\/stable\/quantization.html (accessed 2021-6-18)."},{"key":"19","doi-asserted-by":"crossref","unstructured":"[19] D. Nguyen, D. Kim, and J. Lee, \u201cDouble MAC: Doubling the performance of convolutional neural networks on modern FPGAs,\u201d Design, Automation & Test in Europe Conference Exhibition (DATE), 2017, pp.890-893, 2017. 10.23919\/DATE.2017.7927113","DOI":"10.23919\/DATE.2017.7927113"},{"key":"20","unstructured":"[20] NVIDIA Developer, \u201cTwo Days to a Demo,\u201d https:\/\/developer.nvi-dia.com\/embedded\/twodaystoademo (accessed 2022-12-26)."},{"key":"21","unstructured":"[21] Xilinx, \u201cAI-Model-Zoo,\u201d https:\/\/github.com\/Xilinx\/Vitis-AI\/tree\/m-aster\/model_zoo (accessed 2022-12-26)."},{"key":"22","doi-asserted-by":"publisher","unstructured":"[22] Y. Liang, L. Lu, Q. Xiao, and S. Yan, \u201cEvaluating fast algorithms for convolutional neural networks on FPGAs,\u201d IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst., vol.39, no.4, pp.857-870, April 2020. 10.1109\/TCAD.2019.2897701","DOI":"10.1109\/TCAD.2019.2897701"},{"key":"23","doi-asserted-by":"crossref","unstructured":"[23] C. Zhuge, X. Liu, X. Zhang, S. Gummadi, J. Xiong, and D. Chen, \u201cFace recognition with hybrid efficient convolution algorithms on FPGAs,\u201d Proc. 2018 on Great Lakes Symposium on VLSI, GLSVLSI '18, pp.123-128, New York, NY, USA, Association for Computing Machinery, May 2018. 10.1145\/3194554.3194597","DOI":"10.1145\/3194554.3194597"},{"key":"24","doi-asserted-by":"crossref","unstructured":"[24] L. Lu, J. Xie, R. Huang, J. Zhang, W. Lin, and Y. Liang, \u201cAn efficient hardware accelerator for sparse convolutional neural networks on fpgas,\u201d 2019 IEEE 27th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM), pp.17-25, 2019. 10.1109\/FCCM.2019.00013","DOI":"10.1109\/FCCM.2019.00013"}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E106.D\/7\/E106.D_2022EDP7175\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T04:22:20Z","timestamp":1688185340000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E106.D\/7\/E106.D_2022EDP7175\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,1]]},"references-count":24,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2023]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2022edp7175","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"value":"0916-8532","type":"print"},{"value":"1745-1361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,1]]},"article-number":"2022EDP7175"}}