[DL] A Survey of FPGA-based Neural Network Inference Accelerators
The DOI matches its Crossref record; 71 of the 71 references it cites were found in a registry or an index.
Abstract
Recent research on neural networks has shown a significant advantage in machine learning over traditional algorithms based on handcrafted features and models. Neural networks are now widely adopted in regions like image, speech, and video recognition. But the high computation and storage complexity of neural network inference poses great difficulty on its application. It is difficult for CPU platforms to offer enough computation capacity. GPU platforms are the first choice for neural network processes because of its high computation capacity and easy-to-use development frameworks. However, FPGA-based neural network inference accelerator is becoming a research topic. With specifically designed hardware, FPGA is the next possible solution to surpass GPU in speed and energy efficiency. Various FPGA-based accelerator designs have been proposed with software and hardware optimization techniques to achieve high speed and energy efficiency. In this article, we give an overview of previous work on neural network inference accelerators based on FPGA and summarize the main techniques used. An investigation from software to hardware, from circuit level to system level is carried out to complete analysis of FPGA-based neural network inference accelerator design and serves as a guide to future work.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“The research from Facebook shows the performance gain by porting DNN applications to specific hardware accelerators may not be able to compensate the significant engineering effort spent due to the poor ecosystems and program-ability [20].”
From Bringing ai to edge: from deep learning’s perspective (2022) · cites this paper as [20]
In the citing paper
“However, static DNN models are unable to achieve such guarantee under dynamic environment [20].”
From Bringing ai to edge: from deep learning’s perspective (2022) · cites this paper as [20]
In the citing paper
“Such variance may influence the quality of service (QoS) of applications without rigorously temporal requirement, like voice recognition, face recognition, machine translation, etc [20] and on the other hand may lead to catastrophic consequence for those with rigorously temporal requirement, (i.e., real-time requirement), like autonomous driving, UAV, etc.”
From Bringing ai to edge: from deep learning’s perspective (2022) · cites this paper as [20]
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 5×
“Besides CONV and FC layers, NN layers also have pooling, ReLU [28], concat [58], elementwise [22], and other types of layers.”
BackgroundMethodInfluentialVery Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148 · cited 6×
“For certain networks like VGG [56], only 3 × 3 convolution kernels are used.”
BackgroundMethodInfluentialImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 26×
“In Table 1, we list the number of operations, number of parameters (add or multiplication), and top-1 accuracy on the ImageNet dataset [50] of state-of-the-art CNN models.”
BackgroundMethodInfluentialGoing deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380 · cited 7×
“In Table 1, we list the number of operations, number of parameters (add or multiplication), and top-1 accuracy on the ImageNet dataset [50] of state-of-the-art CNN models.”
MethodInfluentialRich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.81 · Cited by 32,684
SSD: Single Shot MultiBox Detector
Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., & Berg, A. C. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46448-0_2 · Cited by 22,128 · cited 1×
“New features like depthwise convolution [24] and the complex branch in SSD [34] may brings more design opportunities.”
BackgroundMobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., & Adam, H. (2017) · arXiv · doi:10.48550/arxiv.1704.04861 · Cited by 19,015 · cited 4×
“AlexNet [28] VGG19 [56] ResNet152 [22] MobileNet [24] ShuffleNet [79] Year 2012 2014 2016 2017 2017 # Param 60M 144M 57M 4.”
BackgroundMethodInfluentialProceedings of IEEE Conference on Computer Vision and Pattern Recognition
(1993) · doi:10.1109/cvpr.1993 · Cited by 17,667
Caffe: Convolutional Architecture for Fast Feature Embedding
Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., & Darrell, T. (2014) · Proceedings of the 22nd ACM international conference on Multimedia · doi:10.1145/2647868.2654889 · Cited by 11,077 · cited 3×
“Development frameworks like Caffe [26] and Tensorflow [4] also offer easy-to-use interfaces, which makes GPU the first choice of neural network acceleration.”
Method
Research works printed but not linked: 14
- DeePhi Tech . 2017. DNNDK. Retrieved December 3, 2018 from http://www.deephi.com/technology/dnndk. DeePhi Tech. 2017. DNNDK. Retrieved December 3, 2018 from http://www.deephi.com/technology/dnndk.
- Martín Abadi , Ashish Agarwal , Paul Barham , Eugene Brevdo , Zhifeng Chen , Craig Citro , Greg S. Corrado , Andy Davis , Jeffrey Dean , Matthieu Devin , 2016 . Tensorflow: A system for large-scale machine learning . In Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI’16) . 265--283. Martín Abadi, Ashish Agarwal, Paul Barham, Eugene Brevdo, Zhifeng Chen, Craig Citro, Greg S. Corrado, Andy Davis, Jeffrey Dean, Matthieu Devin, et al. 2016. Tensorflow: A system for large-scale machine learning. In Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI’16). 265--283.
- 10.5555/3195638.3195664 · doi:10.5555/3195638.3195664
- Wenlin Chen , James Wilson , Stephen Tyree , Kilian Weinberger , and Yixin Chen . 2015 . Compressing neural networks with the hashing trick . In Proceedings of the International Conference on Machine Learning. 2285--2294 . Wenlin Chen, James Wilson, Stephen Tyree, Kilian Weinberger, and Yixin Chen. 2015. Compressing neural networks with the hashing trick. In Proceedings of the International Conference on Machine Learning. 2285--2294.
- P. K. Gupta . 2016 . Accelerating datacenter workloads . In Proceedings of the 26th International Conference on Field Programmable Logic and Applications (FPL’16) . P. K. Gupta. 2016. Accelerating datacenter workloads. In Proceedings of the 26th International Conference on Field Programmable Logic and Applications (FPL’16).
- Awni Hannun Carl Case Jared Casper Bryan Catanzaro Greg Diamos Erich Elsen Ryan Prenger Sanjeev Satheesh Shubho Sengupta Adam Coates etal 2014. Deep speech: Scaling up end-to-end speech recognition. arXiv preprint arXiv:1412.5567 (2014). Awni Hannun Carl Case Jared Casper Bryan Catanzaro Greg Diamos Erich Elsen Ryan Prenger Sanjeev Satheesh Shubho Sengupta Adam Coates et al. 2014. Deep speech: Scaling up end-to-end speech recognition. arXiv preprint arXiv:1412.5567 (2014). · arXiv
- Fengfu Li , Bo Zhang , and Bin Liu . 2016. Ternary weight networks. arXiv preprint arXiv:1605.04711 ( 2016 ). Fengfu Li, Bo Zhang, and Bin Liu. 2016. Ternary weight networks. arXiv preprint arXiv:1605.04711 (2016). · arXiv
- 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 Proceedings of the 26th International Conference on Field Programmable Logic and Applications (FPL’16) . IEEE, 1--9. 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 Proceedings of the 26th International Conference on Field Programmable Logic and Applications (FPL’16). IEEE, 1--9.
- Huizi Mao , Song Han , Jeff Pool , Wenshuo Li , Xingyu Liu , Yu Wang , and William J. Dally . 2017. Exploring the granularity of sparsity in convolutional neural networks . In Proceedings of the Computer Vision and Pattern Recognition Workshops. 1927--1934 . Huizi Mao, Song Han, Jeff Pool, Wenshuo Li, Xingyu Liu, Yu Wang, and William J. Dally. 2017. Exploring the granularity of sparsity in convolutional neural networks. In Proceedings of the Computer Vision and Pattern Recognition Workshops. 1927--1934.
- Duncan J. M. Moss , Eriko Nurvitadhi , Jaewoong Sim , Asit Mishra , Debbie Marr , Suchit Subhaschandra , and Philip H. W. Leong . 2017. High performance binary neural networks on the Xeon+FPGA™ platform . In Proceedings of the 27th International Conference on Field Programmable Logic and Applications (FPL’17) . IEEE, 1--4. Duncan J. M. Moss, Eriko Nurvitadhi, Jaewoong Sim, Asit Mishra, Debbie Marr, Suchit Subhaschandra, and Philip H. W. Leong. 2017. High performance binary neural networks on the Xeon+FPGA™ platform. In Proceedings of the 27th International Conference on Field Programmable Logic and Applications (FPL’17). IEEE, 1--4.
- 10.5555/3130379.3130591 · doi:10.5555/3130379.3130591
- 10.5555/3195638.3195659 · doi:10.5555/3195638.3195659
- Stylianos I. Venieris and Christos-Savvas Bouganis. 2017. Latency-driven design for FPGA-based convolutional neural networks . In Proceedings of the 27th International Conference on Field Programmable Logic and Applications (FPL’17) . IEEE, 1--8. Stylianos I. Venieris and Christos-Savvas Bouganis. 2017. Latency-driven design for FPGA-based convolutional neural networks. In Proceedings of the 27th International Conference on Field Programmable Logic and Applications (FPL’17). IEEE, 1--8.
- Xin Wang , Fisher Yu , Zi-Yi Dou , and Joseph E . Gonzalez . 2017 . Skipnet : Learning dynamic routing in convolutional networks. arXiv preprint arXiv:1711.09485 (2017). Xin Wang, Fisher Yu, Zi-Yi Dou, and Joseph E. Gonzalez. 2017. Skipnet: Learning dynamic routing in convolutional networks. arXiv preprint arXiv:1711.09485 (2017). · arXiv
Cited by
Items 301–400 of 575
Optimizing CNN Accelerator With Improved Roofline Model
Fang, S., Zeng, S., & Wang, Y. (2020) · IEEE International System-on-Chip Conference (SOCC) · doi:10.1109/socc49529.2020.9524754 · Cited by 5
Self-citationSiddique, A., Iqbal, M. A., Aleem, M., & Islam, M. A. (2023) · Microprocessors and Microsystems · doi:10.1016/j.micpro.2023.104831 · Cited by 5
Smilodon: An Efficient Accelerator for Low Bit-Width CNNs with Task Partitioning
Chen, Q., Fu, Y., Cheng, K., Song, W., Lu, Z., Li, L., & Zhang, C. (2019) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas.2019.8702547 · Cited by 5
Mixture of Deterministic and Stochastic Quantization Schemes for Lightweight CNN
Kim, S.-R., & Kim, H. (2020) · International SoC Design Conference · doi:10.1109/isocc50952.2020.9332958 · Cited by 5
“To satisfy these requirements, various compression studies related to lightweight and low-power DL networks have been actively conducted [5]-[8].”
BackgroundMaximal clique enumeration problem on graphs: status and challenges
许, 绍., 廖, 小., 邵, 志., 华, 强., & 金, 海. (2021) · Scientia Sinica Informationis · doi:10.1360/ssi-2021-0155 · Cited by 5
A Compilation Flow for the Generation of CNN Inference Accelerators on FPGAsPreprint
Chung, S.-H., & Abdelrahman, T. S. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2203.04015 · Cited by 5
CONVOLVE: Smart and seamless design of smart edge processorsPreprint
Gomony, M. D., de Putter, F. A. M., Gebregiorgis, A., Paulin, G., Mei, L., Jain, V., Hamdioui, S., Sanchez, V., Grosser, T., Geilen, M. C. W., et al. (2022) · Lirias · doi:10.48550/arxiv.2212.00873 · Cited by 5
EdgeSight: Enabling Modeless and Cost-Efficient Inference at the EdgePreprint
Lao, C., Gao, J., Ananthanarayanan, G., Akella, A., & Yu, M. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2405.19213 · Cited by 5
Towards Intelligent Data Acquisition Systems with Embedded Deep Learning on MPSoC
Wang, W. (2021) · Repository KITopen (Karlsruhe Institute of Technology) · doi:10.5445/ir/1000133898 · Cited by 5
Sparse Convolution FPGA Accelerator Based on Multi-Bank Hash Selection
Jia, X., Pu, H., & Wang, D. (2024) · Micromachines · doi:10.3390/mi16010022 · Cited by 4
Misbehavior Detection With Collective Perception in V2X Networks: A Survey
Yüce, M. F., Ertürk, M. A., & Aydın, M. A. (2025) · Transactions on Emerging Telecommunications Technologies · doi:10.1002/ett.70267 · Cited by 4
Decomposing highly multimode fibers using a physics-driven neural network
Zhang, Q., Sui, Y., Rothe, S., Sun, J., Pohle, D., Koukourakis, N., Situ, G., & Czarske, J. (2026) · Advanced Photonics Nexus · doi:10.1117/1.apn.5.3.036007 · Cited by 4
Wang, W. H., Zhou, D., Xie, W., & Zhang, W. (2026) · Electronics · doi:10.3390/electronics15112442 · Cited by 4
Real-time object detection using Xilinx Zynq FPGA and tensor flow framework
Mansouri, A. E., Youssef, H. B., & Saidi, L. (2024) · International Journal of Research in Circuits Devices and Systems · doi:10.22271/27084531.2024.v5.i2a.70 · Cited by 4
Pacini, T., Nannipieri, P., Moranti, S., & Fanucci, L. (2025) · IEEE Access · doi:10.1109/access.2025.3577908 · Cited by 4
“These specialized toolflows ease the complex process of mapping RNNs, and more in general Deep Neural Networks (DNNs), onto FPGA hardware, optimizing both the model architecture and hardware resources to achieve optimal performance [21], [22].”
A Component-Centric Perspective on Hardware Accelerators for LLMs
Jia, K., Wang, X., Chen, H., Wei, Z., Xinxiong, L., Zenan, F., & An, F. (2025) · IEEE Access · doi:10.1109/access.2025.3609769 · Cited by 4
Towards Highly Automated Machine-Learning-Empowered Monitoring of Motor Test Stands
Botache, D., Bethke, F., Hardieck, M., Bieshaar, M., Brabetz, L., Ayeb, M., Zipf, P., & Sick, B. (2021) · IEEE International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS) · doi:10.1109/acsos52086.2021.00031 · Cited by 4
Photonic-aware Neural Networks for Packet Classification in Beyond 5G Networks
Paolini, E., Civerchia, F., Marinis, L. D., Valcarenghi, L., Maggiani, L., & Andriolli, N. (2022) · International Conference on the Network of the Future (NOF) · doi:10.1109/nof55974.2022.9942486 · Cited by 4
Holmes: A Hardware-Oriented Optimizer Using Logarithms
Yamagishi, Y., Kaneko, T., Akai‐Kasaya, M., & Asai, T. (2022) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2022pap0001 · Cited by 4
Photonic Convolution Engine Based on Phase-Change Materials and Stochastic Computing
Cardoso, R., Zrounba, C., Abdalla, M., Jimenez, P., de Queiroz, M. G., Charbonnier, B., Pavanello, F., O’Connor, I., & Beux, S. L. (2023) · IEEE Computer Society Annual Symposium on VLSI · doi:10.1109/isvlsi59464.2023.10238608 · Cited by 4
Dadà, M., Zulberti, L., Nannipieri, P., Fanucci, L., & Moranti, S. (2023) · European Data Handling & Data Processing Conference (EDHPC) · doi:10.23919/edhpc59100.2023.10396304 · Cited by 4
“ Hardware Architecture : In accelerating CNN inference, two main architectures can be generated by corresponding toolflows [12].”
BackgroundOptimizing Neural Network Inference in Edge Robotics by Harnessing FPGA Hardware Acceleration
Rao, K. H. (2024) · Journal of Electrical Systems · doi:10.52783/jes.2529 · Cited by 4
“FPGA-based solutions offer tailored hardware designs optimized for specific neural network architectures, enabling efficient execution of inference algorithms with minimal latency [12].”
BackgroundHu, W., Li, H., Liu, F., & Zhong, Z. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-2387-4_22 · Cited by 4
Nakano, H., Błachut, K., Jeziorek, K., Wzorek, P., Dampfhoffer, M., Mesquida, T., Nishi, H., Kryjak, T., & Dalgaty, T. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-87995-1_4 · Cited by 4
“FPGAs (field programmable gate arrays) and custom integrated circuits offer a means of implementing architectures optimised to specific AI methods that are capable of meeting latency requirements while minimising power consumption [5,6,7].”
Minati, L., Movsisyan, V., McCormick, M. M., Gyozalyan, K., Papazyan, T., Makaryan, H., Aldrigo, S., Harutyunyan, T., Ghaltaghchyan, H., Mccormick, C., et al. (2019) · IEEE Access · doi:10.1109/access.2019.2934715 · Cited by 4
Deep Learning Framework with Arbitrary Numerical Precision
Kiyama, M., Amagasaki, M., & Iida, M. (2019) · IEEE International Symposium on Embedded Multicore/Many-core Systems-on-Chip (MCSoC) · doi:10.1109/mcsoc.2019.00019 · Cited by 4
MNN: A Solution to Implement Neural Networks into a Memory-based Reconfigurable Logic Device (MRLD)
Zhou, X., Wang, S., Higami, Y., Takahashi, H., Katsu, M., & Sekiguchi, S. (2021) · International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC) · doi:10.1109/itc-cscc52171.2021.9501454 · Cited by 4
Deep reinforcement learning‐based autonomous parking design with neural network compute accelerators
Özeloğlu, A., Gürbüz, İ. G., & San, İ. (2021) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.6670 · Cited by 4
Fast Learning Architecture for Neural Networks
Zhang, M. J., Garcia, S., & Terré, M. (2022) · European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco55093.2022.9909812 · Cited by 4
Acceleration of Deep Neural Network Training Using Field Programmable Gate Arrays
Tufa, G. T., Andargie, F. A., & Bijalwan, A. (2022) · Computational Intelligence and Neuroscience · doi:10.1155/2022/8387364 · Cited by 4
FPGA-accelerated deep neural network for real-time inversion of geosteering data
Jin, Y., Wan, Q., Wu, X., Fu, X., & Chen, J. (2023) · Geoenergy Science and Engineering · doi:10.1016/j.geoen.2023.211610 · Cited by 4
LUTNet: Learning FPGA Configurations for Highly Efficient Neural Network Inference
Wang, E. (2019) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.3517151 · Cited by 4
Convolution Processing Unit Featuring Adaptive Precision using Dynamic Reconfiguration
Cain, D., Eldash, O., Khalil, K., & Bayoumi, M. (2021) · IEEE World Forum on Internet of Things (WF-IoT) · doi:10.1109/wf-iot51360.2021.9595539 · Cited by 4
Reducing Down(stream)time: Pretraining Molecular GNNs using Heterogeneous AI AcceleratorsPreprint
Bilbrey, J. A., Herman, K. M., Sprueill, H. W., Xantheas, S. S., Das, P., Roldan, M. L., Kraus, M., Helal, H., & Choudhury, S. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2211.04598 · Cited by 4
vFPGA: Towards Sub-µs Reconfiguration via 3D FPGA and Packaging Co-Design
Cherukuri, N. K., Nag, S., Nalla, P. S., Kola, A. K., Gadireddi, C. S., Dai, K., Seo, J.-S., Fang, Z., Zhang, J. J., & Cao, Y. K. (2026) · ACM/SIGDA International Symposium on Field-Programmable Gate Arrays (FPGA) · doi:10.1145/3748173.3779206 · Cited by 3
“They have become a versatile computing platform across cloud infrastructure, embedded systems, networking, adaptive deep learning, and scientific computing [1, 5, 14, 29, 37, 43].”
FPGA-Enabled Deep Learning for Real-Time DC Series Arc Fault Detection
Li, Y., Mao, Y., Rothmann, M., Weiss, R. J., & Porrmann, M. (2026) · IEEE Open Journal of Industry Applications · doi:10.1109/ojia.2026.3671845 · Cited by 3
“Inthis work, the integration of field-programmable gate arrays (FPGAs) is evaluated as a solution to overcome this challenge [9], [10].”
Subramaniasiva, S. G., Kandar, D., & Das, S. (2026) · International Conference on Emerging Trends and Innovations in ICT (ICEI) · doi:10.1109/icei65890.2026.11447502 · Cited by 3
“…baseband processor is connected to the ML module with a wired connection implemented using either a Field-Programmable Gate Array (FPGA), System-on-Chip (SoC), Graphics Processing Unit (GPU), or Application-Specific Integrated Circuit (ASIC) depending on performance/power requirements [17] and [18].”
An Overview of Multilevel Co-Design for AI Accelerator: From Fundamentals to the Frontier
Thi, L.-T. N., Duong, P.-P., Mai, D.-T., Le, D.-H., & Pham, C. (2026) · IEEE Access · doi:10.1109/access.2026.3695927 · Cited by 3
Arockiaraj, J., Parikh, D., & Prasanna, V. K. (2026) · IEEE International Symposium on Field-Programmable Custom Computing Machines (FCCM) · doi:10.1109/fccm68464.2026.00041 · Cited by 3
Pure Frequency-Domain Deep Neural Network for IoT-Enabled Smart Cameras
Wu, B.-Y., & Lu, C.-H. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3163406 · Cited by 3
Design and Implementation of Lightweight Neural Network Inference Accelerator Based on FPGA
Wang, Y., Qian, Y., & He, X. H. (2024) · International Conference on Control, Electronic Engineering and Machine Learning (CEEML) · doi:10.1109/ceeml65709.2024.00021 · Cited by 3
Self-citationAnalysis of single layer artificial neural network neuromorphic hardware chip
Pant, A., Kumar, A., & Kuchhal, P. (2024) · IAES International Journal of Robotics and Automation (IJRA) · doi:10.11591/ijra.v13i4.pp495-505 · Cited by 3
“This data is distributed as an output that is applied as a non-linear function and calculated as the weighted total of the inputs [19].”
MethodNeggaz, M. A., Niar, S., & Kurdahi, F. J. (2018) · doi:10.1109/icm.2018.8704033 · Cited by 3
TileNET: Hardware accelerator for ternary Convolutional Neural Networks
Eetha, S., Sruthi, P. K., Pant, V., Vikram, S., Mody, M., & Purnaprajna, M. (2021) · Microprocessors and Microsystems · doi:10.1016/j.micpro.2021.104039 · Cited by 3
Power-Efficient Double-Cyclic Low-Precision Training for Convolutional Neural Networks
Kim, S.-R., & Kim, H. (2022) · IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS) · doi:10.1109/aicas54282.2022.9869948 · Cited by 3
Xiong, B., Fan, S., He, X., Zhou, Z., Yang, R., Li, S., Shen, R., & Chang, Y. (2023) · International Journal of Circuit Theory and Applications · doi:10.1002/cta.3834 · Cited by 3
Demo: Enabling DNN Inference in the Network Data Plane
Siddhartha, Tan, J., Bansal, R., Cheun, H. C., Tokusashi, Y., Kwan, C. Y., Javaid, H., & Baldi, M. (2023) · doi:10.1145/3630047.3630191 · Cited by 3
A Near-Memory Dynamically Programmable Many-Core Overlay
Elshimy, M. A., Iskandar, V., Göhringer, D., & Ghany, M. A. A. E. (2023) · IEEE International Symposium on Embedded Multicore/Many-core Systems-on-Chip (MCSoC) · doi:10.1109/mcsoc60832.2023.00047 · Cited by 3
“Additionally, interfacing multiples of such cores to a traditional DDR-based memory introduces a memory bottleneck [6].”
BackgroundSate, J., & Selavo, L. (2020) · Mediterranean Conference on Embedded Computing (MECO) · doi:10.1109/meco49872.2020.9134252 · Cited by 3
A Scalable Architecture for CNN Accelerators Leveraging High-Performance Memories
Hattink, M. H. N., Guglielmo, G. D., Carloni, L. P., & Bergman, K. (2020) · IEEE High Performance Extreme Computing Conference · doi:10.1109/hpec43674.2020.9286162 · Cited by 3
A design methodology for approximate multipliers in convolutional neural networks: A case of MNIST
Shirane, K., Yamamoto, T., & Tomiyama, H. (2021) · International Journal of Reconfigurable and Embedded Systems (IJRES) · doi:10.11591/ijres.v10.i1.pp1-10 · Cited by 3
Neural net implementation of steam properties on FPGA
Dutt, R. V. S. K., Ganesh, R., & Premchand, P. (2021) · International Journal of Reconfigurable and Embedded Systems (IJRES) · doi:10.11591/ijres.v10.i3.pp186-194 · Cited by 3
Real-Time Downhole Geosteering Data Processing Using Deep Neural Networks On FPGA
Wan, Q., Jin, Y., Wu, X., Chen, J., & Fu, X. (2021) · IEEE International Conference on Industry Applications · doi:10.1109/induscon51756.2021.9529474 · Cited by 3
A high-performance, hardware-based deep learning system for disease diagnosis
Siddique, A., Iqbal, M. A., Aleem, M., & Lin, J. C. (2022) · PeerJ Computer Science · doi:10.7717/peerj-cs.1034 · Cited by 3
“Deep learning is a subset of machine learning that does not involve much human effort and does not require handcrafting of features (Guo et al., 2019).”
BackgroundHardware designs for convolutional neural networks: Memoryful, memoryless and cached
de Franca, A. B. Z., Oliveira, F. D. V. R., Gomes, J. G. R. C., & Nedjah, N. (2023) · Integration · doi:10.1016/j.vlsi.2023.102074 · Cited by 3
Foumani, S. N. A., Guo, C., & Luk, W. W. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.02784 · Cited by 3
A Very Compact Embedded CNN Processor Design Based on Logarithmic ComputingPreprint
Lu, T.-Y., Chin, H.-H., Wu, H., & Tsay, R. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.11686 · Cited by 3
“[24] reported severe model accuracy loss for bit-width less than 8.”
BackgroundMinimal Filtering Algorithms for Convolutional Neural NetworksPreprint
Cariow, A., & Cariowa, G. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.05607 · Cited by 3
HAPM -- Hardware Aware Pruning Method for CNN hardware accelerators in resource constrained devicesPreprint
Peccia, F. N., Ferreyro, L., & Furfaro, A. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2408.14055 · Cited by 3
Feasibility of Time-Domain DNN-Based Speech Enhancement on Embedded FPGA for Hearing AidsPreprint
Olalere, F., Altin, U., van der Heijden, K., & van Gerven, M. A. J. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.04221 · Cited by 3
“Reducing numerical precision is a common strategy for addressing this in resource-constrained FPGA deployments, with most accelerator studies targeting INT8 or lower precision combined with pruning and quantization-aware training [48].”
Implementing live object recognition on PYNQ-Z2 board
Shabarinath, B. B., Kiran, D. R., Prasad, S. D., & Preethika, S. (2025) · AIP conference proceedings · doi:10.1063/5.0241580 · Cited by 2
Efficient Implementation of a Lightweight AI Classification Model for Handwriting Detection on FPGA
Chavoshi, M., Lighvan, . Z., & Mohammadkhanli, L. (2024) · IEEE East-West Design & Test Symposium (EWDTS) · doi:10.1109/ewdts63723.2024.10873796 · Cited by 2
Kordi, F., Fortier, P., & Miled, A. (2025) · Electronics · doi:10.3390/electronics15010058 · Cited by 2
Distilling knowledge for low-energy AIoT
di Torrepadula, F. R., Maisto, V., Cilardo, A., & Mazzocca, N. (2026) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2026.103692 · Cited by 2
Ely, A. F., Veiga, V. K., Benevenuti, F., Beck, A. C. S., Azambuja, J. R., & Kastensmidt, F. L. (2026) · Journal of Integrated Circuits and Systems · doi:10.29292/jics.v21i1.1028 · Cited by 2
Meta-Optical Encoder for Image Segmentation
Choi, M., Xiang, J., Zhang, Y., Zhou, Z., Shlizerman, E., & Majumdar, A. (2026) · Nano Letters · doi:10.1021/acs.nanolett.6c02292 · Cited by 2
Jeziorek, K., Wzorek, P., Błachut, K., Nakano, H., Dampfhoffer, M., Mesquida, T., Nishi, H., Dalgaty, T., & Kryjak, T. (2026) · ACM Transactions on Reconfigurable Technology and Systems · doi:10.1145/3838800 · Cited by 2
“FPGAs (field-programmable gate arrays) and custom application-specific integrated circuits (ASICs) offer a third path – architectures tailored to a specific method that satisfies both latency and energy requirements simultaneously [2, 3, 26].”
Optimizing OpenCL Kernels and Runtime for DNN Inference on FPGAs
Chung, S., & Abdelrahman, T. S. (2020) · IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum · doi:10.1109/ipdpsw50202.2020.00034 · Cited by 2
Reliability Analysis of Compressed CNNs
Ribes, S., Malek, A., Trancoso, P., & Sourdis, I. (2021) · Chalmers Research (Chalmers University of Technology) · Cited by 2
Reconfigurable Multi-algorithm Neural Network Accelerator Based on Target Detection
Han, W., Wu, N., Zhou, F., & Ge, F. (2022) · IEEE International Conference on Communication Technology (ICCT) · doi:10.1109/icct56141.2022.10072633 · Cited by 2
Jun, Z., & Terré, M. (2023) · International Conference on Signal-Image Technology & Internet-Based Systems (SITIS) · doi:10.1109/sitis61268.2023.00080 · Cited by 2
FPGA based Flexible Implementation of Light Weight Inference on Deep Convolutional Neural Networks
Dawwd, S. A. (2024) · The International Arab Journal of Information Technology · doi:10.34028/iajit/21/3/5 · Cited by 2
DCNN For Cataract Disease Detection Based on Model Parallelism
Thanoon, M. A. J., & Dawwd, S. A. (2024) · Maǧallaẗ al-handasaẗ al-rāfidayn · doi:10.33899/arej.2024.147115.1338 · Cited by 2
Acceleration of Neural Network Training on Hardware via HLS for an Edge-AI Device
Özeloğlu, A., & San, İ. (2020) · Innovations in Intelligent Systems and Applications Conference (ASYU) · doi:10.1109/asyu50717.2020.9259845 · Cited by 2
“Fakat FPGA tabanlı yapay sinir a˘gı özel donanım tasarımları hem enerji tüketimi hem de hız performansı bakımından GPU tabanlı çözümlerden 10 kat daha verimli olabildikleri literatürde gös-terilmi¸stir [1].”
Efficient Hardware Optimization for CNN
Aydın, S. G., & Bılge, H. Ş. (2022) · International Journal of Multidisciplinary Studies and Innovative Technologies · doi:10.36287/ijmsit.6.1.38 · Cited by 2
A Resource-Limited FPGA-based MobileNetV3 Accelerator
Jewajinda, Y., & Thongkum, T. (2022) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.23919/apsipaasc55919.2022.9980265 · Cited by 2
Acceleration of Neural Network training algorithms via FPGA devices
Zoltán-Valentin, G.-N. (2023) · Procedia Computer Science · doi:10.1016/j.procs.2023.10.259 · Cited by 2
FPGA-Based Acceleration of the Self-Organizing Map (SOM) Algorithm using High-Level Synthesis
Oninda, M. A. M. (2019) · Scholarship at UWindsor (University of Windsor) · Cited by 2
FFCNN: Fast FPGA based Acceleration for Convolution neural network inferencePreprint
Keddous, F. E., Nguyen, H.-N., & Nakib, A. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2208.13250 · Cited by 2
Pixel Embedding: Fully Quantized Convolutional Neural Network with Differentiable Lookup TablePreprint
Tokunaga, H., Nicholls, J., Vazhenina, D., & Kanemura, A. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2407.16174 · Cited by 2
Ultra low latency deep neural network inference for gravitational waves interferometer: *
de Rooij, M. (. (2021) · Research Repository (Delft University of Technology) · Cited by 2
Space Use-Case: Onboard Satellite Image Classification
Lemaire, E., Millet, P., Miramond, B., Bilavarn, S., Saoud, H., & Naik, A. S. (2020) · Springer eBooks · doi:10.1007/978-3-030-53532-2_12 · Cited by 1
Abbasi, M., Cardoso, F., da Silva, J. P. L. R., & Martins, P. (2023) · Advances in intelligent systems and computing · doi:10.1007/978-3-031-38344-1_9 · Cited by 1
Bailey, D. G. (2023) · Wiley eBooks · doi:10.1002/9781119819820.ch14 · Cited by 1
Dynamic Hardware Accelerator Selection Achieving Optimal Utilization of Resources
Toyoshima, Y., Hatano, T., Shimada, T., & Yoshida, T. (2024) · IEICE Communications Express · doi:10.23919/comex.2024xbl0152 · Cited by 1
Pape, G., Wintermann, B., Jungemann, L., Lass, M., Meyer, M., Riebler, H., & Plessl, C. (2025) · International Symposium on Highly Efficient Accelerators and Reconfigurable Technologies (HEART) · doi:10.1145/3728179.3728190 · Cited by 1
FPGA-Friendly Architecture of Processing Elements for Efficient and Accurate Quantized CNNs
Xiong, B., Zhang, S., Shao, X., He, X., & Chang, Y. (2025) · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · doi:10.1109/tcad.2025.3591734 · Cited by 1
High-Performance FPGA-Based CNN Acceleration for Real-Time DC Arc Fault Detection
Li, Y., Mao, Y., Weiss, R. J., & Porrmann, M. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-02725-2_15 · Cited by 1
FPGA-Based Hardware Accelerator with RISC-V Processor for Real-Time CNN Inference on ECG Signals
Kulkarni, P. R., Manjunath, M., Dhotar, P. R., Mishra, U., Bandikatte, S. A., Ramavenkateswaran, N., & Purohit, M. V. (2025) · International Conference on Computation System and Information Technology for Sustainable Solutions (CSITSS) · doi:10.1109/csitss67709.2025.11294741 · Cited by 1
Tsmots, I., & Shtohrinets, B. (2025) · Vìsnik Nacìonalʹnogo unìversitetu Lʹvìvsʹka polìtehnìka Serìâ Ìnformacìjnì sistemi ta merežì · doi:10.23939/sisn2025.18.1.190 · Cited by 1
Small-Area CNN Inference Architecture with Bit-Serial Pipeline Datapath and Zero Skipping
HATTORI, S., & Hiroyuki, O. C. H. I. (2025) · IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences · doi:10.1587/transfun.2025vlp0007 · Cited by 1
Edge Detection on a 2D-Mesh NoC with Systolic Arrays: From FPGA Validation to GDSII Proof-of-Concept
Mascorro-Guardado, E., Cisneros, S. O., Ibarra-Villegas, F. J., Rivera, J., Zapata, H. E. M., & Baungarten-Leon, E. I. (2026) · Applied Sciences · doi:10.3390/app16020702 · Cited by 1
Design of a High-Performance Transformer Accelerator Based on FPGA
Zhao, W., Ren, Z., Yan, M., Su, T., & Gao, J. (2025) · International Conference on Digital Society and Intelligent Systems (DSInS) · doi:10.1109/dsins68311.2025.11329897 · Cited by 1
Nie, Z., Wang, H., Chronopoulos, A. T., Tang, Z., Li, K., Liu, C., & Xiao, Z. (2026) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2026.3667207 · Cited by 1
“For example, vision tasks rely on convolutional layers, while speech tasks use LSTM layers [22].”
Computation and Complexity-Aware DNN Accelerators: Architectures, Dataflows, and Design Trade-Offs
Vishwakarma, S., Khan, Z., & Lehtomäki, J. J. (2026) · IEEE Access · doi:10.1109/access.2026.3700058 · Cited by 1
“A lot of research works have been developed for hardware optimization strategies that reduce memory bottlenecks and frequent impediments that slow data flow between memory and the central processing unit (CPU) by the architecture of the computational unit [38], [39].”
DPUConfig: Optimizing ML Inference in FPGAs Using Reinforcement Learning
Patras, A., Lalis, S., Antonopoulos, C. D., & Bellas, N. (2026) · Design, Automation, and Test in Europe · doi:10.23919/date69613.2026.11539418 · Cited by 1
“Many works propose efficient CNN accelerators for FPGAs [35]–[37].”
Buccellato, F., Mannini, L., & Sio, C. D. (2026) · ACM International Conference on Computing Frontiers: Workshops and Special Sessions (CF Companion) · doi:10.1145/3801488.3808246 · Cited by 1
“Several studies have demonstrated that FPGA architectures, thanks to their high degree of parallelism and hardware specialization, represent a valid alternative to CPUs and GPUs for the efficient execution of deep learning models [8].”
Hardware-Aware Runtime Detection of Soft-Error Anomalies in DPU-Accelerated Neural Networks
Buccellato, F., Sio, C. D., Azimi, S., & Sterpone, L. (2026) · IEEE International On-Line Testing Symposium (IOLTS) · doi:10.1109/iolts69666.2026.11633646 · Cited by 1
“Among these, Deep Learning Processing Units (DPUs) are widely adopted for high-performance inference on FPGA platforms, thanks to their efficiency and seamless integration with both hardware and software components [6].”
Zarrouk, Y., Bourhaleb, M., Rahmoun, M., Hamdaoui, H., & Hachami, K. (2026) · Array · doi:10.1016/j.array.2026.101069 · Cited by 1
Analysis of Research Progress on Deployment Methods for Deep Learning Models on FPGAs
Wang, S., Chen, L., Tian, C., Zhou, J., Zhang, Y., & Cao, Y. (2026) · Electronics · doi:10.3390/electronics15163536 · Cited by 1
Metadata
- Authors
- Guo, K., Zeng, S., Yu, J., Wang, Y., & Yang, H.
- Affiliations
- Tsinghua University (CN)
- Venue
- ACM Transactions on Reconfigurable Technology and Systems
- Published
- 2019-03-28
- Volume
- 12
- Issue
- 1
- Pages
- 1-26
- ISSN
- 1936-7406 (ISSN-L)
- 1936-7414
- OpenAlex
- W2997106510
- Cited by
- 292
- References
- 65
- Citations by year
- 2026: 43 · 2025: 37 · 2024: 29 · 2023: 44 · 2022: 42 · 2021: 54 · 2020: 34 · 2019: 9
- FWCI
- 35.21
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- ACM Transactions on Reconfigurable Technology and Systems (publishedVersion)
- Funders
- National Key R&D Program of China (2018YFB0105005, 2017YFA0207600)
- National Natural Science Foundation of China (61622403, 61621091)
- Topics
- Physical Sciences › Computer Science › Hardware and Architecture › Embedded Systems Design Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Engineering › Electrical and Electronic Engineering › VLSI and FPGA Design Techniques
- Keywords
- FPGA, neural network inference, hardware acceleration, energy efficiency, program optimization, hardware optimization, GPU comparison, machine learning hardware
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.