{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,19]],"date-time":"2026-10-19T15:13:18Z","timestamp":1792422798742,"version":"4.5.0"},"reference-count":63,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2023,3,11]],"date-time":"2023-03-11T00:00:00Z","timestamp":1678492800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-sa\/4.0\/"}],"funder":[{"name":"NSF\/Intel","award":["34627365, CCF-1723773 and 36888881"],"award-info":[{"award-number":["34627365, CCF-1723773 and 36888881"]}]},{"name":"NSF NeuroNex project","award":["DBI-1707408"],"award-info":[{"award-number":["DBI-1707408"]}]},{"name":"CRISP center under the JUMP program, and CDSC industrial partners"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Reconfigurable Technol. Syst."],"published-print":{"date-parts":[[2023,6,30]]},"abstract":"<jats:p>\n            With reduced data reuse and parallelism, recent convolutional neural networks (CNNs) create new challenges for FPGA acceleration. Systolic arrays (SAs) are efficient, scalable architectures for convolutional layers, but without proper optimizations, their efficiency drops dramatically for reasons: (1) the different dimensions within same-type layers, (2) the different convolution layers especially transposed and dilated convolutions, and (3) CNN\u2019s complex dataflow graph. Furthermore, significant overheads arise when integrating FPGAs into machine learning frameworks. Therefore, we present a flexible, composable architecture called FlexCNN, which delivers high computation efficiency by employing dynamic tiling, layer fusion, and data layout optimizations. Additionally, we implement a novel versatile SA to process normal, transposed, and dilated convolutions efficiently. FlexCNN also uses a fully pipelined software-hardware integration that alleviates the software overheads. Moreover, with an automated compilation flow, FlexCNN takes a CNN in the ONNX\n            <jats:xref ref-type=\"fn\">\n              <jats:sup>1<\/jats:sup>\n            <\/jats:xref>\n            representation, performs a design space exploration, and generates an FPGA accelerator. The framework is tested using three complex CNNs: OpenPose, U-Net, and E-Net. The architecture optimizations achieve 2.3\u00d7 performance improvement. Compared to a standard SA, the versatile SA achieves close-to-ideal speedups, with up to 5.98\u00d7 and 13.42\u00d7 for transposed and dilated convolutions, with a 6% average area overhead. The pipelined integration leads to a 5\u00d7 speedup for OpenPose.\n          <\/jats:p>","DOI":"10.1145\/3570928","type":"journal-article","created":{"date-parts":[[2022,12,20]],"date-time":"2022-12-20T12:50:46Z","timestamp":1671540646000},"page":"1-32","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":59,"title":["FlexCNN: An End-to-end Framework for Composing CNN Accelerators on FPGA"],"prefix":"10.1145","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8301-8411","authenticated-orcid":false,"given":"Suhail","family":"Basalama","sequence":"first","affiliation":[{"name":"University of California - Los Angeles, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1156-3306","authenticated-orcid":false,"given":"Atefeh","family":"Sohrabizadeh","sequence":"additional","affiliation":[{"name":"University of California - Los Angeles, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2133-7943","authenticated-orcid":false,"given":"Jie","family":"Wang","sequence":"additional","affiliation":[{"name":"University of California - Los Angeles, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0705-9510","authenticated-orcid":false,"given":"Licheng","family":"Guo","sequence":"additional","affiliation":[{"name":"University of California - Los Angeles, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2887-6963","authenticated-orcid":false,"given":"Jason","family":"Cong","sequence":"additional","affiliation":[{"name":"University of California - Los Angeles, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,3,11]]},"reference":[{"key":"e_1_3_2_2_2","unstructured":"DPUCAHX8H Resource Utilization. (n.d.). Retrieved from https:\/\/docs.xilinx.com\/r\/en-US\/pg367-dpucahx8h\/Resource-Utilization."},{"key":"e_1_3_2_3_2","unstructured":"DPUCAHX8L Resource Utilization. (n.d.). Retrieved from https:\/\/docs.xilinx.com\/r\/en-US\/pg366-dpucahx8l\/Resource-Utilization."},{"key":"e_1_3_2_4_2","unstructured":"U280 Performance with 14E300 MHz DPUCAHX8H. (n.d.). Retrieved from https:\/\/docs.xilinx.com\/r\/1.4.1-English\/ug1354-xilinx-ai-sdk\/Alveo-U280-Data-Accelerator-Card."},{"key":"e_1_3_2_5_2","unstructured":"Vitis AI. (n.d.). Retrieved from https:\/\/www.xilinx.com\/products\/design-tools\/vitis\/vitis-ai.html."},{"key":"e_1_3_2_6_2","first-page":"265","volume-title":"12th USENIX Symposium on Operating Systems Design and Implementation (OSDI\u201916)","author":"Abadi Mart\u00edn","year":"2016","unstructured":"Mart\u00edn Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard et\u00a0al. 2016. Tensorflow: A system for large-scale machine learning. In 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI\u201916). 265\u2013283."},{"key":"e_1_3_2_7_2","first-page":"310","volume-title":"International Conference on Field-Programmable Technology (FPT\u201918)","author":"Akira Jinguji","year":"2018","unstructured":"Jinguji Akira, Tomoya Fujii, Shimpei Sato, and Hiroki Nakahara. 2018. An FPGA realization of OpenPose based on a sparse weight convolutional neural network. In International Conference on Field-Programmable Technology (FPT\u201918). IEEE, 310\u2013313."},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2018.2865896"},{"key":"e_1_3_2_9_2","first-page":"7291","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition","author":"Cao Zhe","year":"2017","unstructured":"Zhe Cao, Tomas Simon, Shih-En Wei, and Yaser Sheikh. 2017. Realtime multi-person 2D pose estimation using part affinity fields. In IEEE Conference on Computer Vision and Pattern Recognition. 7291\u20137299."},{"key":"e_1_3_2_10_2","first-page":"1","volume-title":"IEEE International Symposium on Circuits and Systems (ISCAS\u201920)","author":"Chang Kuo-Wei","year":"2020","unstructured":"Kuo-Wei Chang and Tian-Sheuan Chang. 2020. Efficient accelerator for dilated and transposed convolution with decomposition. In IEEE International Symposium on Circuits and Systems (ISCAS\u201920). IEEE, 1\u20135."},{"issue":"6","key":"e_1_3_2_11_2","first-page":"1540","article-title":"An efficient accelerator for multiple convolutions from the sparsity perspective","volume":"28","author":"Chen Qinyu","year":"2020","unstructured":"Qinyu Chen, Yan Huang, Rui Sun, Wenqing Song, Zhonghai Lu, Yuxiang Fu, and Li Li. 2020. An efficient accelerator for multiple convolutions from the sparsity perspective. IEEE Trans. Very Large Scale Integ. Syst. 28, 6 (2020), 1540\u20131544.","journal-title":"IEEE Trans. Very Large Scale Integ. Syst."},{"key":"e_1_3_2_12_2","first-page":"73","volume-title":"ACM\/SIGDA International Symposium on Field-programmable Gate Arrays","author":"Chen Yao","year":"2019","unstructured":"Yao Chen, Jiong He, Xiaofan Zhang, Cong Hao, and Deming Chen. 2019. Cloud-DNN: An open framework for mapping DNN models to cloud FPGAs. In ACM\/SIGDA International Symposium on Field-programmable Gate Arrays. 73\u201382."},{"key":"e_1_3_2_13_2","volume-title":"8th USENIX Workshop on Hot Topics in Cloud Computing (HotCloud\u201916)","author":"Chen Yu-Ting","year":"2016","unstructured":"Yu-Ting Chen, Jason Cong, Zhenman Fang, Jie Lei, and Peng Wei. 2016. When Spark meets FPGAs: A case study for next-generation DNA sequencing acceleration. In 8th USENIX Workshop on Hot Topics in Cloud Computing (HotCloud\u201916)."},{"key":"e_1_3_2_14_2","article-title":"cuDNN: Efficient primitives for deep learning","author":"Chetlur Sharan","year":"2014","unstructured":"Sharan Chetlur, Cliff Woolley, Philippe Vandermersch, Jonathan Cohen, John Tran, Bryan Catanzaro, and Evan Shelhamer. 2014. cuDNN: Efficient primitives for deep learning. arXiv preprint arXiv:1410.0759 (2014).","journal-title":"arXiv preprint arXiv:1410.0759"},{"key":"e_1_3_2_15_2","first-page":"1","volume-title":"IEEE\/ACM International Conference on Computer-Aided Design (ICCAD\u201918)","author":"Chi Yuze","year":"2018","unstructured":"Yuze Chi, Jason Cong, Peng Wei, and Peipei Zhou. 2018. SODA: Stencil with optimized dataflow architecture. In IEEE\/ACM International Conference on Computer-Aided Design (ICCAD\u201918). IEEE, 1\u20138."},{"key":"e_1_3_2_16_2","first-page":"204","volume-title":"IEEE 29th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM\u201921)","author":"Chi Yuze","year":"2021","unstructured":"Yuze Chi, Licheng Guo, Jason Lau, Young-kyu Choi, Jie Wang, and Jason Cong. 2021. Extending high-level synthesis for task-parallel programs. In IEEE 29th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM\u201921). IEEE, 204\u2013213."},{"key":"e_1_3_2_17_2","first-page":"1","volume-title":"IEEE\/ACM International Conference on Computer-Aided Design (ICCAD\u201918)","author":"Cong Jason","year":"2018","unstructured":"Jason Cong and Jie Wang. 2018. PolySA: Polyhedral-based systolic array auto-compilation. In IEEE\/ACM International Conference on Computer-Aided Design (ICCAD\u201918). IEEE, 1\u20138."},{"key":"e_1_3_2_18_2","volume-title":"10th USENIX Workshop on Hot Topics in Cloud Computing (HotCloud\u201918)","author":"Cong Jason","year":"2018","unstructured":"Jason Cong, Peng Wei, and Cody Hao Yu. 2018. From JVM to FPGA: Bridging abstraction hierarchy via optimized deep pipelining. In 10th USENIX Workshop on Hot Topics in Cloud Computing (HotCloud\u201918)."},{"key":"e_1_3_2_19_2","first-page":"181","volume-title":"IEEE 29th Annual International Symposium on Field-programmable Custom Computing Machines (FCCM\u201921)","author":"Deng Huipeng","year":"2021","unstructured":"Huipeng Deng, Jian Wang, Huafeng Ye, Shanlin Xiao, Xiangyu Meng, and Zhiyi Yu. 2021. 3D-VNPU: A flexible accelerator for 2D\/3D CNNs on FPGA. In IEEE 29th Annual International Symposium on Field-programmable Custom Computing Machines (FCCM\u201921). IEEE, 181\u2013185."},{"issue":"2","key":"e_1_3_2_20_2","doi-asserted-by":"crossref","first-page":"286","DOI":"10.3390\/electronics9020286","article-title":"Exploring efficient acceleration architecture for winograd-transformed transposed convolution of GANs on FPGAs","volume":"9","author":"Di Xinkai","year":"2020","unstructured":"Xinkai Di, Hai-Gang Yang, Yiping Jia, Zhihong Huang, and Ning Mao. 2020. Exploring efficient acceleration architecture for winograd-transformed transposed convolution of GANs on FPGAs. Electronics 9, 2 (2020), 286.","journal-title":"Electronics"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_25"},{"key":"e_1_3_2_22_2","article-title":"A guide to convolution arithmetic for deep learning","author":"Dumoulin Vincent","year":"2016","unstructured":"Vincent Dumoulin and Francesco Visin. 2016. A guide to convolution arithmetic for deep learning. arXiv preprint arXiv:1603.07285 (2016).","journal-title":"arXiv preprint arXiv:1603.07285"},{"key":"e_1_3_2_23_2","first-page":"152","volume-title":"IEEE 25th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM\u201917)","author":"Guan Yijin","year":"2017","unstructured":"Yijin Guan, Hao Liang, Ningyi Xu, Wenqiang Wang, Shaoshuai Shi, Xi Chen, Guangyu Sun, Wei Zhang, and Jason Cong. 2017. FP-DNN: An automated framework for mapping deep neural networks onto FPGAs with RTL-HLS hybrid templates. In IEEE 25th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM\u201917). IEEE, 152\u2013159."},{"key":"e_1_3_2_24_2","first-page":"24","volume-title":"IEEE Computer Society Annual Symposium on VLSI (ISVLSI\u201916)","author":"Guo Kaiyuan","year":"2016","unstructured":"Kaiyuan Guo, Lingzhi Sui, Jiantao Qiu, Song Yao, Song Han, Yu Wang, and Huazhong Yang. 2016. Angel-Eye: A complete design flow for mapping cnn onto customized hardware. In IEEE Computer Society Annual Symposium on VLSI (ISVLSI\u201916). IEEE, 24\u201329."},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2017.2705069"},{"key":"e_1_3_2_26_2","first-page":"81","volume-title":"ACM\/SIGDA International Symposium on Field-programmable Gate Arrays","author":"Guo Licheng","year":"2021","unstructured":"Licheng Guo, Yuze Chi, Jie Wang, Jason Lau, Weikang Qiao, Ecenur Ustun, Zhiru Zhang, and Jason Cong. 2021. AutoBridge: Coupling coarse-grained floorplanning and pipelining for high-frequency HLS design on multi-die FPGAs. In ACM\/SIGDA International Symposium on Field-programmable Gate Arrays. 81\u201392."},{"key":"e_1_3_2_27_2","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard Andrew G.","year":"2017","unstructured":"Andrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam. 2017. MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017).","journal-title":"arXiv preprint arXiv:1704.04861"},{"key":"e_1_3_2_28_2","first-page":"0","volume-title":"European Conference on Computer Vision (ECCV\u201918)","author":"Ignatov Andrey","year":"2018","unstructured":"Andrey Ignatov, Radu Timofte, William Chou, Ke Wang, Max Wu, Tim Hartley, and Luc Van Gool. 2018. AI benchmark: Running deep neural networks on android smartphones. In European Conference on Computer Vision (ECCV\u201918). 0\u20130."},{"key":"e_1_3_2_29_2","first-page":"1","volume-title":"IEEE International Symposium on Circuits and Systems (ISCAS\u201919)","author":"Im Dongseok","year":"2019","unstructured":"Dongseok Im, Donghyeon Han, Sungpill Choi, Sanghoon Kang, and Hoi-Jun Yoo. 2019. DT-CNN: Dilated and transposed convolution neural network accelerator for real-time image segmentation on mobile devices. In IEEE International Symposium on Circuits and Systems (ISCAS\u201919). IEEE, 1\u20135."},{"key":"e_1_3_2_30_2","unstructured":"Ildoo Kim. 2018. tf-pose-estimation. Retrieved from https:\/\/github.com\/ildoonet\/tf-pose-estimation."},{"key":"e_1_3_2_31_2","first-page":"1857","volume-title":"International Conference on Machine Learning","author":"Kim Taeksoo","year":"2017","unstructured":"Taeksoo Kim, Moonsu Cha, Hyunsoo Kim, Jung Kwon Lee, and Jiwon Kim. 2017. Learning to discover cross-domain relations with generative adversarial networks. In International Conference on Machine Learning. PMLR, 1857\u20131865."},{"key":"e_1_3_2_32_2","first-page":"1","volume-title":"26th International Conference on Field Programmable Logic and Applications (FPL\u201916)","author":"Li Huimin","year":"2016","unstructured":"Huimin Li, Xitian Fan, Li Jiao, Wei Cao, Xuegong Zhou, and Lingli Wang. 2016. A high performance FPGA-based accelerator for large-scale convolutional neural networks. In 26th International Conference on Field Programmable Logic and Applications (FPL\u201916). IEEE, 1\u20139."},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00120"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3268344"},{"key":"e_1_3_2_35_2","first-page":"187","volume-title":"29th International Conference on Field Programmable Logic and Applications (FPL\u201919)","author":"Liu Shuanglong","year":"2019","unstructured":"Shuanglong Liu and Wayne Luk. 2019. Towards an efficient accelerator for DNN-based remote sensing image segmentation on FPGAs. In 29th International Conference on Field Programmable Logic and Applications (FPL\u201919). IEEE, 187\u2013193."},{"key":"e_1_3_2_36_2","first-page":"1","volume-title":"IEEE International Symposium on Circuits and Systems (ISCAS\u201919)","author":"Liu Wenjian","year":"2019","unstructured":"Wenjian Liu, Jun Lin, and Zhongfeng Wang. 2019. USCA: A unified systolic convolution array architecture for accelerating sparse neural network. In IEEE International Symposium on Circuits and Systems (ISCAS\u201919). IEEE, 1\u20135."},{"issue":"1","key":"e_1_3_2_37_2","first-page":"1299","article-title":"GPflow: A Gaussian process library using TensorFlow","volume":"18","author":"Matthews De G.","year":"2017","unstructured":"De G. Matthews, G. Alexander, Mark Van Der Wilk, Tom Nickson, Keisuke Fujii, Alexis Boukouvalas, Pablo Le\u00f3n-Villagr\u00e1, Zoubin Ghahramani, and James Hensman. 2017. GPflow: A Gaussian process library using TensorFlow. J. Mach. Learn. Res. 18, 1 (2017), 1299\u20131304.","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_2_38_2","first-page":"1","volume-title":"5th International Workshop on FPGAs for Software Programmers","author":"Noronha Daniel H.","year":"2018","unstructured":"Daniel H. Noronha, Bahar Salehpour, and Steven J. E. Wilton. 2018. LeFlow: Enabling flexible FPGA high-level synthesis of TensorFlow deep neural networks. In 5th International Workshop on FPGAs for Software Programmers. VDE, 1\u20138."},{"key":"e_1_3_2_39_2","article-title":"ENet: A deep neural network architecture for real-time semantic segmentation","author":"Paszke Adam","year":"2016","unstructured":"Adam Paszke, Abhishek Chaurasia, Sangpil Kim, and Eugenio Culurciello. 2016. ENet: A deep neural network architecture for real-time semantic segmentation. arXiv preprint arXiv:1606.02147 (2016).","journal-title":"arXiv preprint arXiv:1606.02147"},{"key":"e_1_3_2_40_2","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","author":"Radford Alec","year":"2015","unstructured":"Alec Radford, Luke Metz, and Soumith Chintala. 2015. Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434 (2015).","journal-title":"arXiv preprint arXiv:1511.06434"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_3_2_43_2","first-page":"1","volume-title":"49th Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO\u201916)","author":"Sharma Hardik","year":"2016","unstructured":"Hardik Sharma, Jongse Park, Divya Mahajan, Emmanuel Amaro, Joon Kyung Kim, Chenkai Shao, Asit Mishra, and Hadi Esmaeilzadeh. 2016. From high-level deep neural models to FPGAs. In 49th Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO\u201916). IEEE, 1\u201312."},{"key":"e_1_3_2_44_2","first-page":"97","volume-title":"ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays","author":"Shen Junzhong","year":"2018","unstructured":"Junzhong Shen, You Huang, Zelong Wang, Yuran Qiao, Mei Wen, and Chunyuan Zhang. 2018. Towards a uniform template-based architecture for accelerating 2D and 3D CNNs on FPGA. In ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays. 97\u2013106."},{"key":"e_1_3_2_45_2","first-page":"535","volume-title":"ACM\/IEEE 44th Annual International Symposium on Computer Architecture (ISCA\u201917)","author":"Shen Yongming","year":"2017","unstructured":"Yongming Shen, Michael Ferdman, and Peter Milder. 2017. Maximizing CNN accelerator efficiency through resource partitioning. In ACM\/IEEE 44th Annual International Symposium on Computer Architecture (ISCA\u201917). IEEE, 535\u2013547."},{"key":"e_1_3_2_46_2","article-title":"Rigid-motion scattering for image classification","author":"Sifre Laurent","year":"2014","unstructured":"Laurent Sifre and St\u00e9phane Mallat. 2014. Rigid-motion scattering for image classification. \u00c9cole Normale Sup\u00e9rieure, D\u00e9partement d\u2019Informatique, Ph.D. Dissertation.","journal-title":"Ph.D. Dissertation"},{"key":"e_1_3_2_47_2","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014).","journal-title":"arXiv preprint arXiv:1409.1556"},{"key":"e_1_3_2_48_2","first-page":"133","volume-title":"ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays","author":"Sohrabizadeh Atefeh","year":"2020","unstructured":"Atefeh Sohrabizadeh, Jie Wang, and Jason Cong. 2020. End-to-end optimization of deep learning applications. In ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays. 133\u2013139."},{"key":"e_1_3_2_49_2","first-page":"16","volume-title":"ACM\/SIGDA International Symposium on Field-programmable Gate Arrays","author":"Suda Naveen","year":"2016","unstructured":"Naveen Suda, Vikas Chandra, Ganesh Dasika, Abinash Mohanty, Yufei Ma, Sarma Vrudhula, Jae-sun Seo, and Yu Cao. 2016. Throughput-optimized OpenCL-based FPGA accelerator for large-scale convolutional neural networks. In ACM\/SIGDA International Symposium on Field-programmable Gate Arrays. ACM, 16\u201325."},{"key":"e_1_3_2_50_2","first-page":"3760","volume-title":"IEEE International Conference on Image Processing (ICIP\u201917)","author":"Tan Wei Ren","year":"2017","unstructured":"Wei Ren Tan, Chee Seng Chan, Hern\u00e1n E. Aguirre, and Kiyoshi Tanaka. 2017. ArtGAN: Artwork synthesis with conditional categorical GANs. In IEEE International Conference on Image Processing (ICIP\u201917). IEEE, 3760\u20133764."},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2844093"},{"key":"e_1_3_2_52_2","first-page":"1","volume-title":"IEEE\/ACM International Conference on Computer-Aided Design (ICCAD\u201918)","author":"Wei Xuechao","year":"2018","unstructured":"Xuechao Wei, Yun Liang, Xiuhong Li, Cody Hao Yu, Peng Zhang, and Jason Cong. 2018. TGPA: Tile-grained pipeline architecture for low latency CNN inference. In IEEE\/ACM International Conference on Computer-Aided Design (ICCAD\u201918). IEEE, 1\u20138."},{"key":"e_1_3_2_53_2","first-page":"29","volume-title":"54th Annual Design Automation Conference","author":"Wei Xuechao","year":"2017","unstructured":"Xuechao Wei, Cody Hao Yu, Peng Zhang, Youxiang Chen, Yuxin Wang, Han Hu, Yun Liang, and Jason Cong. 2017. Automated systolic array architecture synthesis for high throughput CNN inference on FPGAs. In 54th Annual Design Automation Conference. ACM, 29."},{"key":"e_1_3_2_54_2","unstructured":"Xilinx. 2018. Vivado design suite user guide - high-level synthesis (UG902). https:\/\/docs.xilinx.com\/v\/u\/2018.2-English\/ug902-vivado-high-level-synthesis."},{"issue":"10","key":"e_1_3_2_55_2","doi-asserted-by":"crossref","first-page":"2668","DOI":"10.1109\/TCAD.2019.2930577","article-title":"DNNVM: End-to-end compiler leveraging heterogeneous optimizations on FPGA-based CNN accelerators","volume":"39","author":"Xing Yu","year":"2019","unstructured":"Yu Xing, Shuang Liang, Lingzhi Sui, Xijie Jia, Jiantao Qiu, Xin Liu, Yushun Wang, Yi Shan, and Yu Wang. 2019. DNNVM: End-to-end compiler leveraging heterogeneous optimizations on FPGA-based CNN accelerators. IEEE Trans. Comput.-Aid. Des. Integ. Circ. Syst. 39, 10 (2019), 2668\u20132681.","journal-title":"IEEE Trans. Comput.-Aid. Des. Integ. Circ. Syst."},{"key":"e_1_3_2_56_2","article-title":"DNN dataflow choice is overrated","author":"Yang Xuan","year":"2018","unstructured":"Xuan Yang, Mingyu Gao, Jing Pu, Ankita Nayak, Qiaoyi Liu, Steven Emberton Bell, Jeff Ou Setter, Kaidi Cao, Heonjae Ha, Christos Kozyrakis et\u00a0al. 2018. DNN dataflow choice is overrated. arXiv preprint arXiv:1809.04070 (2018).","journal-title":"arXiv preprint arXiv:1809.04070"},{"key":"e_1_3_2_57_2","first-page":"65","volume-title":"IEEE 26th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM\u201918)","author":"Yazdanbakhsh Amir","year":"2018","unstructured":"Amir Yazdanbakhsh, Michael Brzozowski, Behnam Khaleghi, Soroush Ghodrati, Kambiz Samadi, Nam Sung Kim, and Hadi Esmaeilzadeh. 2018. FlexiGAN: An end-to-end solution for FPGA acceleration of generative adversarial networks. In IEEE 26th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM\u201918). IEEE, 65\u201372."},{"key":"e_1_3_2_58_2","article-title":"Multi-scale context aggregation by dilated convolutions","author":"Yu Fisher","year":"2015","unstructured":"Fisher Yu and Vladlen Koltun. 2015. Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122 (2015).","journal-title":"arXiv preprint arXiv:1511.07122"},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2020.2995741"},{"key":"e_1_3_2_60_2","first-page":"161","volume-title":"ACM\/SIGDA International Symposium on Field-programmable Gate Arrays","author":"Zhang Chen","year":"2015","unstructured":"Chen Zhang, Peng Li, Guangyu Sun, Yijin Guan, Bingjun Xiao, and Jason Cong. 2015. Optimizing FPGA-based accelerator design for deep convolutional neural networks. In ACM\/SIGDA International Symposium on Field-programmable Gate Arrays. ACM, 161\u2013170."},{"key":"e_1_3_2_61_2","article-title":"Caffeine: Towards uniformed representation and acceleration for deep convolutional neural networks","author":"Zhang Chen","year":"2018","unstructured":"Chen Zhang, Guangyu Sun, Zhenman Fang, Peipei Zhou, Peichen Pan, and Jason Cong. 2018. Caffeine: Towards uniformed representation and acceleration for deep convolutional neural networks. IEEE Trans. Comput.-Aid. Des. Integ. Circ. Syst. 38, 11 (2018), 2072\u20132085.","journal-title":"IEEE Trans. Comput.-Aid. Des. Integ. Circ. Syst."},{"issue":"3","key":"e_1_3_2_62_2","doi-asserted-by":"crossref","first-page":"282","DOI":"10.3390\/electronics10030282","article-title":"FPGA implementation for CNN-based optical remote sensing object detection","volume":"10","author":"Zhang Ning","year":"2021","unstructured":"Ning Zhang, Xin Wei, He Chen, and Wenchao Liu. 2021. FPGA implementation for CNN-based optical remote sensing object detection. Electronics 10, 3 (2021), 282.","journal-title":"Electronics"},{"key":"e_1_3_2_63_2","doi-asserted-by":"publisher","DOI":"10.1145\/3240765.3240801"},{"key":"e_1_3_2_64_2","doi-asserted-by":"publisher","DOI":"10.1145\/3400302.3415609"}],"container-title":["ACM Transactions on Reconfigurable Technology and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3570928","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3570928","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:49:12Z","timestamp":1750182552000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3570928"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,11]]},"references-count":63,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2023,6,30]]}},"alternative-id":["10.1145\/3570928"],"URL":"https:\/\/doi.org\/10.1145\/3570928","relation":{},"ISSN":["1936-7406","1936-7414"],"issn-type":[{"value":"1936-7406","type":"print"},{"value":"1936-7414","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3,11]]},"assertion":[{"value":"2022-06-25","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-10-19","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-03-11","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}