[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 101–200 of 575
Xu, Y., Zhao, Z., Xiao, Y., Yu, T., Mulaosmanovic, H., Kleimaier, D. M., Duenkel, S., Beyer, S., Gong, X., Joshi, R., et al. (2024) · Science Advances · doi:10.1126/sciadv.adk1525 · Cited by 28
Euler, H.-C. R., Alegre-Ibarra, U., van de Ven, B., Broersma, H. J., Bobbert, P. A., & van der Wiel, W. G. (2021) · Neuromorphic Computing and Engineering · doi:10.1088/2634-4386/ac1a7f · Cited by 28
DNNARA: A Deep Neural Network Accelerator using Residue Arithmetic and Integrated Photonics
Peng, J., Alkabani, Y., Sun, S., Sorger, V. J., & El‐Ghazawi, T. (2020) · Proceedings of the International Conference on Parallel Processing · doi:10.1145/3404397.3404467 · Cited by 27
Choi, H. (2023) · Electronics · doi:10.3390/electronics12061398 · Cited by 27
Joint Task Offloading and Resource Allocation in Heterogeneous Edge Environments
Liu, Y., Mao, Y., Liu, Z., Ye, F., & Yang, Y. (2023) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom53939.2023.10229015 · Cited by 27
High-Performance Acceleration of 2-D and 3-D CNNs on FPGAs Using Static Block Floating Point
Fan, H., Liu, S., Que, Z., Niu, X., & Luk, W. W. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3116302 · Cited by 26
Leveraging Domain Information for the Efficient Automated Design of Deep Learning Accelerators
Sakhuja, C., Shi, Z., & Lin, C. (2023) · IEEE International Symposium on High-Performance Computer Architecture (HPCA) · doi:10.1109/hpca56546.2023.10071095 · Cited by 26
Modeling and Analysis of Bus Contention for Hardware Accelerators in FPGA SoCs
Restuccia, F., Pagani, M., Biondi, A., Marinoni, M., & Buttazzo, G. (2020) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.ecrts.2020.12 · Cited by 25
Efficient Visual Recognition: A Survey on Recent Advances and Brain-inspired Methodologies
Wu, Y., Wang, D., Lu, X., Yang, F., Yao, M., Dong, W., Shi, J., & Li, G. (2022) · Machine Intelligence Research · doi:10.1007/s11633-022-1340-5 · Cited by 25
“(2019) [15] covers all aspects of FPGA-based DNN acceleration, especially on hardware-oriented model compression and efficient architectures for hardware design.”
BackgroundMethodShears, O., Bai, K., Liu, L., & Yi, Y. (2021) · International Conference on Computer Aided Design · doi:10.1109/iccad51958.2021.9643536 · Cited by 25
Zang, Z., Xiao, D., Wang, Q., Jiao, Z., Chen, Y., & Li, D. (2023) · Methods and Applications in Fluorescence · doi:10.1088/2050-6120/acc0d9 · Cited by 25
Roofline-Model-Based Design Space Exploration for Dataflow Techniques of CNN Accelerators
Park, C., Park, S., & Park, C. S. (2020) · IEEE Access · doi:10.1109/access.2020.3025550 · Cited by 25
Unleashing the Low-Precision Computation Potential of Tensor Cores on GPUs
Li, G., Xue, J., Liu, L., Wang, X., Ma, X., Dong, X., Li, J., & Feng, X. (2021) · Proceedings of the CGO/Proceedings of the ... CGO · doi:10.1109/cgo51591.2021.9370335 · Cited by 25
Low-Precision Floating-Point Schemes for Neural Network TrainingPreprint
Ortiz, M., Cristal, A., Ayguadé, E., & Casas, M. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1804.05267 · Cited by 25
Embedded Deep Inference in Practice: Case for Model Partitioning
Dey, S., Mukherjee, A., Pal, A., & Balamuralidhar, P. (2019) · doi:10.1145/3362743.3362964 · Cited by 24
“For hardware acceleration of CNNs [18] on FPGA & ASIC, the inherent parallelism of convolutional algorithms, linear algebra operations and processor-memory dataflow, along with weight storage schemes are mapped to the architecture of underlying specialized hardware [5, 10, 12, 29, 32].”
MethodMultimodal Neural Network Acceleration on a Hybrid CPU-FPGA Architecture: A Case Study
Ajili, M. T., & Hara–Azumi, Y. (2022) · IEEE Access · doi:10.1109/access.2022.3144977 · Cited by 24
“To address the above issue and because field-programmable gate arrays (FPGAs) are promising competitors to graphics processing units (GPUs) in a way that can well balance speed and energy efficiency [11], we present a hybrid CPU-FPGA co-designed accelerationmodel for DeepSense.”
BackgroundFPGA based acceleration of game theory algorithm in edge computing for autonomous driving
Du, S., Huang, T., Hou, J., Song, S., & Song, Y. (2018) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2018.12.009 · Cited by 24
A Review of FPGA‐Based Custom Computing Architecture for Convolutional Neural Network Inference
Xiyuan, P., Yu, J., Yao, B., Liansheng, L., & Peng, Y. (2021) · Chinese Journal of Electronics · doi:10.1049/cje.2020.11.002 · Cited by 24
Self-citationRoukhami, M., Lazarescu, M. T., Gregoretti, F., Lahbib, Y., & Mami, A. (2019) · IEEE Access · doi:10.1109/access.2019.2931392 · Cited by 24
Gao, L. H., Luo, Z., & Wang, L. (2025) · Information · doi:10.3390/info16100914 · Cited by 23
Enabling Efficient and Flexible FPGA Virtualization for Deep Learning in the Cloud
Zeng, S., Dai, G., Sun, H., Zhong, K., Ge, G., Guo, K., Wang, Y., & Yang, H. (2020) · IEEE International Symposium on Field-Programmable Custom Computing Machines (FCCM) · doi:10.1109/fccm48280.2020.00023 · Cited by 23
Self-citationAccelerating DNNs from local to virtualized FPGA in the Cloud: A survey of trends
Wu, C., Fresse, V., Suffran, B., & Konik, H. (2021) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2021.102257 · Cited by 23
Wang, H., Chen, H., Wang, B., Jin, Y., Li, G., & Kan, Y. (2022) · Applied Energy · doi:10.1016/j.apenergy.2022.119203 · Cited by 23
Real-Time Embedded Vision System for Online Monitoring and Sorting of Citrus Fruits
Maganda, M. A. N., Davila-Rodriguez, I.-A., Mier, Y. H., Barrón-Zambrano, J. H., Elizondo-Leal, J. C., Diaz-Manríquez, A., & Martagón, S. P. (2023) · Electronics · doi:10.3390/electronics12183891 · Cited by 23
Graph-OPU: A Highly Integrated FPGA-Based Overlay Processor for Graph Neural Networks
Chen, R., Zhang, H., Li, S., Tang, E., Yu, J. W., & Wang, K. (2023) · International Conference on Field Programmable Logic and Applications (FPL) · doi:10.1109/fpl60245.2023.00039 · Cited by 23
“This substantial time investment is required when users need to adjust configuration parameters or switch models [20].”
BackgroundSelf-citationReconfigurable Architectures: The Shift from General Systems to Domain Specific Solutions
D’Arnese, E., Conficconi, D., Santambrogio, M. D., & Sciuto, D. (2022) · Computer architecture and design methodologies · doi:10.1007/978-981-16-7487-7_14 · Cited by 22
FPGA-Based Sparse Matrix Multiplication Accelerators: From State-of-the-Art to Future Opportunities
Liu, Y., Chen, R., Li, S., Yang, J. F., Li, S., & da Silva, B. (2024) · ACM Transactions on Reconfigurable Technology and Systems · doi:10.1145/3687480 · Cited by 22
“…architecture conferences (ISCA, MICRO, HPCA, ASPLOS), FPGA conferences (FPGA, FPL, FCCM, FPT), electronic design automation conferences (DAC, DATE, ICCAD, ASP-DAC), and high-impact journals (TC, TCAD, TRETS, TVLSI, and so on) because these publications represent the forefront of this field [19].”
Evaluating Built-In ECC of FPGA On-Chip Memories for the Mitigation of Undervolting Faults
Salami, B., Ünsal, O., & Kestelman, A. C. (2019) · Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP) · doi:10.1109/empdp.2019.8671543 · Cited by 22
FPGA based neural network accelerators
Kim, J.-Y. (2020) · Advances in computers · doi:10.1016/bs.adcom.2020.11.002 · Cited by 22
Enhancing the Scalability of Multi-FPGA Stencil Computations via Highly Optimized HDL Components
Reggiani, E., Sozzo, E. D., Conficconi, D., Natale, G., Moroni, C., & Santambrogio, M. D. (2021) · ACM Transactions on Reconfigurable Technology and Systems · doi:10.1145/3461478 · Cited by 22
An OpenCL-Based FPGA Accelerator for Faster R-CNN
An, J., Zhang, D., Xu, K., & Wang, D. (2022) · Entropy · doi:10.3390/e24101346 · Cited by 22
“Recent studies have shown [9] that the computing capacity of a typical CPU can only reach 10–100 Giga Floating-point Operations Per Second (GFLOPS), and the energy consumption efficiency is normally below 1 Giga Operation Per Joule (GOP/J).”
Design Space Exploration of FPGA-Based System With Multiple DNN Accelerators
Kedia, R., Goel, S., Balakrishnan, S., Paul, K., & Sen, R. (2020) · IEEE Embedded Systems Letters · doi:10.1109/les.2020.3017455 · Cited by 22
“Xilinx’s DPU (Deep Learning Processor Unit) [3], [4] is a generic DNN accelerator which can be used for any DNN topology (unlike others that are specific to particular DNN [1], [2]).”
BackgroundLearning on Hardware: A Tutorial on Neural Network Accelerators and Co-ProcessorsPreprint
Baischer, L., Wess, M., & TaheriNejad, N. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.09252 · Cited by 22
MAGPIE: Machine Automated General Performance Improvement via Evolution of SoftwarePreprint
Blot, A., & Petke, J. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2208.02811 · Cited by 22
Hardware Resource and Computational Density Efficient CNN Accelerator Design Based on FPGA
Chen, X. '., Li, J., & Zhao, Y. B. (2021) · IEEE International Conference on Integrated Circuits, Technologies and Applications (ICTA) · doi:10.1109/icta53157.2021.9661886 · Cited by 21
An Area-Efficient FPGA Implementation of a Real-Time Multi-Class Classifier for Binary Images
Attarmoghaddam, N., & Li, K. F. (2022) · IEEE Transactions on Circuits & Systems II Express Briefs · doi:10.1109/tcsii.2022.3148228 · Cited by 21
Algorithm/Accelerator Co-Design and Co-Search for Edge AI
Zhang, X., Li, Y., Pan, J., & Chen, D. (2022) · IEEE Transactions on Circuits & Systems II Express Briefs · doi:10.1109/tcsii.2022.3179229 · Cited by 21
Hardware Acceleration for Real-Time Wildfire Detection Onboard Drone Networks
Briley, A. A., & Afghah, F. (2024) · IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS) · doi:10.1109/infocomwkshps61880.2024.10620877 · Cited by 21
“Several recent works have been developed addressing inference acceleration on FPGAs [11].”
BackgroundCheshfar, M., Maghami, M. H., Amiri, P., Garakani, H. G., & Lavagno, L. (2024) · IEEE Access · doi:10.1109/access.2024.3510677 · Cited by 21
“Comparison of hardware accelerators for deep learning, the data presented in this table has been interpreted and synthesized from the following references: [19], [32], [42], [43].”
InfluentialAlphaGo Policy Network: A DCNN Accelerator on FPGA
Li, Z., Zhu, C., Gao, Y., Wang, Z.-K., & Wang, J. (2020) · IEEE Access · doi:10.1109/access.2020.3023739 · Cited by 21
FTT-NAS: Discovering Fault-tolerant Convolutional Neural Architecture
Ning, X., Ge, G., Li, W., Zhu, Z., Zheng, Y., Chen, X., Gao, Z., Wang, Y., & Yang, H. (2021) · ACM Transactions on Design Automation of Electronic Systems · doi:10.1145/3460288 · Cited by 20
“With dedicated data flow design for efficient neural network processing, FPGA-based NN accelerators could achieve at least 10 × better energy efficiency than GPUs [11, 37].”
BackgroundMethodSelf-citationReal-Time CLAHE Algorithm Implementation in SoC FPGA Device for 4K UHD Video Stream
Kryjak, T., Błachut, K., Szolc, H., & Wąsala, M. (2022) · Electronics · doi:10.3390/electronics11142248 · Cited by 20
On the Resilience of Deep Learning for Reduced-voltage FPGAs
Givaki, K., Salami, B., Hojabr, R., Tayaranian, S. M. R., Khonsari, A., Rahmati, D., Gorgin, S., Cristal, A., & Ünsal, O. (2020) · Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP) · doi:10.1109/pdp50117.2020.00023 · Cited by 20
INFER: INterFerence-aware Estimation of Runtime for Concurrent CNN Execution on DPUs
Goel, S., Kedia, R., Balakrishnan, S., & Sen, R. (2020) · International Conference on Field-Programmable Technology (FPT) · doi:10.1109/icfpt51103.2020.00018 · Cited by 20
Kreß, F., Sidorenko, V., Schmidt, P., Hoefer, J., Hotfilter, T., Walter, I., Harbaum, T., & Becker, J. (2023) · Computer Networks · doi:10.1016/j.comnet.2023.109759 · Cited by 19
Fast and Scalable Multicore YOLOv3-Tiny Accelerator Using Input Stationary Systolic Architecture
Adiono, T., Ramadhan, R. M., Sutisna, N., Syafalni, I., Mulyawan, R., & Lin, C. H. (2023) · IEEE Transactions on Very Large Scale Integration (VLSI) Systems · doi:10.1109/tvlsi.2023.3305937 · Cited by 19
RCT: Resource Constrained Training for Edge AI
Huang, T., Luo, T., Yan, M., Zhou, J. T., & Goh, R. S. M. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3190451 · Cited by 19
B 2 N 2 : Resource efficient Bayesian neural network accelerator using Bernoulli sampler on FPGA
Awano, H., & Hashimoto, M. (2022) · Integration · doi:10.1016/j.vlsi.2022.11.005 · Cited by 19
Li, J., Liang, Y., Yang, Z.-H., & Li, X. (2025) · Electronics · doi:10.3390/electronics14061182 · Cited by 18
Mukhopadhyay, A. K., Majumder, S., & Chakrabarti, I. (2021) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2021.107628 · Cited by 18
Comparison of Artificial Neural Networks for Low-Power ECG-Classification System
Rana, A., & Kim, K. K. (2020) · Journal of Sensor Science and Technology · doi:10.5369/jsst.2019.29.1.19 · Cited by 17
Electronic Nose Pattern Recognition Engine: Design, Build, and Deployment
Sun, F., Wu, B., Jia, Y., Duan, S., & Hu, X. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3225535 · Cited by 17
Evolving Multi-Resolution Pooling CNN for Monaural Singing Voice Separation
Yuan, W., Dong, B., Wang, S., Unoki, M., & Wang, W. (2021) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2021.3051331 · Cited by 17
“Since the model complexity is an important factor for limited memory applications [19], the multi-objective scheme is designed to balance two objectives, i.”
BackgroundA Marr's Three‐Level Analytical Framework for Neuromorphic Electronic Systems
Guo, Y., Zou, X., Hu, Y., Yang, Y., Wang, X., He, Y., Kong, R., Guo, Y., Li, G., Zhang, W., et al. (2021) · Advanced Intelligent Systems · doi:10.1002/aisy.202100054 · Cited by 16
Automated CNN back-propagation pipeline generation for FPGA online training
Mazouz, A., & Bridges, C. (2021) · Journal of Real-Time Image Processing · doi:10.1007/s11554-021-01147-2 · Cited by 16
Analyzing the Single Event Upset Vulnerability of Binarized Neural Networks on SRAM FPGAs
Souvatzoglou, I., Papadimitriou, A., Sari, A., Vlagkoulis, V., & Psarakis, M. (2021) · Proceedings · doi:10.1109/dft52944.2021.9568280 · Cited by 16
A Non-Linear Convolution Network for Image Processing
Marsi, S., Bhattacharya, J., Molina, R., & Ramponi, G. (2021) · Electronics · doi:10.3390/electronics10020201 · Cited by 16
Accelerating DNN Inference with Heterogeneous Multi-DPU Engines
Du, Z., Zhang, W., Zhou, Z., Shao, Z., & Ju, L. (2023) · ACM/IEEE Design Automation Conference (DAC) · doi:10.1109/dac56929.2023.10247793 · Cited by 15
“Over the last decade, numerous FPGA-based neural network accelerator designs have been proposed [4], [5].”
BackgroundSharma, P. K., Abraham, A., & Rajendiran, V. N. (2021) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2021.3134158 · Cited by 15
Towards An FPGA-targeted Hardware/Software Co-design Framework for CNN-based Edge Computing
Pham‐Quoc, C., Nguyen, X.-Q., & Thinh, T. N. (2022) · Mobile Networks and Applications · doi:10.1007/s11036-022-01985-9 · Cited by 15
“Surveys in [7–9] have analyzed these techniques in detail.”
MethodWho is the Winner? Memristive-CMOS Hybrid Modules: CNN-LSTM Versus HTM
Smagulova, K., Krestinskaya, O., & James, A. P. (2019) · IEEE Transactions on Biomedical Circuits and Systems · doi:10.1109/tbcas.2019.2956435 · Cited by 15
A design of EEGNet‐based inference processor for pattern recognition of EEG using FPGA
Tsukahara, A., Anzai, Y., Tanaka, K., & Uchikawa, Y. (2020) · Electronics and Communications in Japan · doi:10.1002/ecj.12280 · Cited by 15
Bipolar Morphological Neural Networks: Gate-Efficient Architecture for Computer Vision
Limonova, E. E., Alfonso, D. M., Nikolaev, D., & Arlazarov, V. V. (2021) · IEEE Access · doi:10.1109/access.2021.3094484 · Cited by 15
Zhang, Z., He, H., Deng, X., Xie, J., & Luo, Y. (2022) · IEEE Transactions on Circuits and Systems I Regular Papers · doi:10.1109/tcsi.2022.3153560 · Cited by 15
Bouazzaoui, A. E., Hadjoudja, A., Mouhib, O., & Cherkaoui, N. (2024) · Array · doi:10.1016/j.array.2024.100337 · Cited by 14
FPGA-accelerated mode decomposition for multimode fiber-based communication
Zhang, Q., Zhang, Y., & Czarske, J. (2025) · Light Advanced Manufacturing · doi:10.37188/lam.2025.031 · Cited by 14
Famous: Flexible Accelerator for the Attention Mechanism of Transformer on Ultrascale+ FPGAs
Kabir, E., Kabir, M. A., Downey, A. R. J., Bakos, J. D., Andrews, D., & Huang, M. (2024) · International Conference on Field-Programmable Technology (FPT) · doi:10.1109/icfpt64416.2024.11113430 · Cited by 14
“In contrast, FPGAs have gained widespread use for accelerating DNNs due to their high level of parallelism and low latency [15], [16].”
Deep Learning on RISC-V Platforms at the Edge: A Perspective on the Hardware and Software Support
Agosta, G., Galimberti, A., & Zoni, D. (2025) · ACM Computing Surveys · doi:10.1145/3772277 · Cited by 15
“Third, a significant number of surveys analyze hardware accelerators for DL, including FPGA-and ASIC-based implementations [64, 120], CNN-oriented accelerators [23, 145, 164], precision-scalable and systolic-array designs [21, 183], and accelerators for heterogeneous high-performance Deep Learning…”
Agile Autotuning of a Transprecision Tensor Accelerator Overlay for TVM Compiler Stack
Diamantopoulos, D., Ringlein, B., Purandare, M., Singh, G., & Hagleitner, C. (2020) · International Conference on Field Programmable Logic and Applications (FPL) · doi:10.1109/fpl50879.2020.00058 · Cited by 14
“Apart from TVM’s auto-tuning, which we used in our analysis, and was used with FPGAs [17], as well as GPUs and embedded devices [15], numerous DL works employ optimizers for parameter tuning.”
BackgroundSurvey of Deep Learning Neural Networks Implementation on FPGAs
Tourad, E. H. C., & Eleuldj, M. (2020) · International Conference on Cloud Computing Technologies and Applications (CloudTech) · doi:10.1109/cloudtech49835.2020.9365911 · Cited by 14
Learning ultrasound rendering from cross-sectional model slices for simulated training
Zhang, L., Portenier, T., & Göksel, O. (2021) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-021-02349-6 · Cited by 14
A New Hardware Architecture for FPGA Implementation of Feed Forward Neural Networks
Sumayyabeevi, V. A., Poovely, J. J., Aswathy, N., & Chinnu, S. (2021) · International Conference on Advances in Computing, Communication, Embedded and Secure Systems (ACCESS) · doi:10.1109/access51619.2021.9563342 · Cited by 14
A Deep Neural Network Accelerator using Residue Arithmetic in a Hybrid Optoelectronic System
Peng, J., Alkabani, Y., Puri, K., Ma, X., Sorger, V. J., & El‐Ghazawi, T. (2022) · ACM Journal on Emerging Technologies in Computing Systems · doi:10.1145/3550273 · Cited by 14
Deep Learning Architecture Improvement Based on Dynamic Pruning and Layer Fusion
Li, Q., Li, H., & Meng, L. (2023) · Electronics · doi:10.3390/electronics12051208 · Cited by 14
“In addition, the pruned model is intact in parallelism, which contributes to the efficient utilization of hardware resources [26].”
MethodProcessing Systems for Deep Learning Inference on Edge Devices
Véstias, M. P. (2020) · Internet of things · doi:10.1007/978-3-030-44907-0_9 · Cited by 14
Deep Image Translation for Enhancing Simulated Ultrasound Images
Zhang, L., Portenier, T., Paulus, C. J., & Göksel, O. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-60334-2_9 · Cited by 14
Odetola, T. A., & Hasan, S. R. (2021) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas51556.2021.9401166 · Cited by 14
Fast Reactive Grasping with In-Finger Vision and In-Hand FPGA-accelerated CNNs
Hundhausen, F., Grimm, R., Stieber, L., & Asfour, T. (2021) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros51168.2021.9636043 · Cited by 14
A Survey of Deep Neural Networks: Deployment Location and Underlying Hardware
Kotlar, M., Bojić, D. M., Punt, M., & Milutinović, V. M. (2018) · Symposium on Neural Networks and Applications (NEUREL) · doi:10.1109/neurel.2018.8587006 · Cited by 13
Rodríguez, I., Campos, C., & Fdez‐Riverola, F. (2021) · Applied Sciences · doi:10.3390/app11199173 · Cited by 13
Kim, H., Park, J., Lee, H., Won, D., & Han, M. (2024) · Electronics · doi:10.3390/electronics13122280 · Cited by 13
Li, S., Tao, Y., Tang, E., Xie, T., & Chen, R. (2022) · PeerJ Computer Science · doi:10.7717/peerj-cs.1166 · Cited by 13
“It is worthwhile to mention that we focused on the FPGA-based designs published in the top FPGA conferences (FPGA, FCCM, FPL, FPT), EDA conferences (DAC, ASP-DAC, DATE, ICCAD), and architecture conferences (MICRO, HPCA, ISCA, ASPLOS) since 2019 (Guo et al., 2019).”
BackgroundToken-based Approach for Real-time Plagiarism Detection in Digital Designs
Wan, H., Liu, K., & Gao, X. (2018) · IEEE Frontiers in Education Conference (FIE) · doi:10.1109/fie.2018.8658531 · Cited by 13
An overview of sound source localization based condition monitoring robots
Lv, D., Tang, W., Feng, G., Zhen, D., Gu, F., & Ball, A. D. (2024) · ISA Transactions · doi:10.1016/j.isatra.2024.12.046 · Cited by 12
ProTEA: Programmable Transformer Encoder Acceleration on FPGA
Kabir, E., Bakos, J. D., Andrews, D. A., & Huang, M. (2024) · International Conference for High Performance Computing, Networking, Storage and Analysis (SC) · doi:10.1109/scw63240.2024.00074 · Cited by 12
“In addition to GPUs, FPGAs have become popular commercial off the shelf components used to accelerate DNNs. FPGAs offer the ability to exploit high level of parallelism to provide low run time inference latencies with efficient power consumption [12], [13].”
Reconfigurable Framework for Resilient Semantic Segmentation for Space Applications
Sabogal, S., George, A. D., & Crum, G. (2021) · ACM Transactions on Reconfigurable Technology and Systems · doi:10.1145/3472770 · Cited by 12
Fast Inner-Product Algorithms and Architectures for Deep Neural Network Accelerators
Pogue, T. E., & Nicolici, N. (2023) · IEEE Transactions on Computers · doi:10.1109/tc.2023.3334140 · Cited by 12
“However, as expected from our theoretical analysis, the FIP architecture provides the much more significant near 2 × reduction in DSP units , which are hard logic resources used to implement MAC units in FPGAs since that operation cannot be mapped efficiently onto the soft logic resources [15].”
BackgroundMethodInfluentialPotential of edge machine learning for instrumentation
Therrien, A. C., Gouin-Ferland, B., & Rahimifar, M. M. (2022) · Applied Optics · doi:10.1364/ao.445798 · Cited by 12
End-to-End Synthesis of Dynamically Controlled Machine Learning Accelerators
Curzel, S., Agostini, N. B., Castellana, V. G., Minutoli, M., Limaye, A., Manzano, J., Zhang, J. J., Brooks, D. M., Wei, G.-Y., Ferrandi, F., et al. (2022) · IEEE Transactions on Computers · doi:10.1109/tc.2022.3211430 · Cited by 12
“Research and industry also proposed many FPGA-based accelerators for ML inference [10], [11], often supporting specialized numeric formats to”
BackgroundClPy: A NumPy-Compatible Library Accelerated with OpenCL
Higuchi, T., Yoshifuji, N., Sakai, T., Kitta, Y., Takano, R., Ikegami, T., & Taura, K. (2019) · IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum · doi:10.1109/ipdpsw.2019.00159 · Cited by 12
XDN: Towards Efficient Inference of Residual Neural Networks on Cambricon Chips
Li, G., Wang, X., Ma, X., Liu, L., & Feng, X. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-49556-5_4 · Cited by 11
Post-configuration Activation of Hardware Trojans in FPGAs
Ahmed, Q. A., Wiersema, T., & Platzner, M. (2024) · Journal of Hardware and Systems Security · doi:10.1007/s41635-024-00147-5 · Cited by 11
Elastic Significant Bit Quantization and Acceleration for Deep Neural Networks
Gong, C., Lu, Y., Xie, K., Jin, Z., Li, T., & Wang, Y. (2021) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2021.3129615 · Cited by 11
“Energy efficiency is a critical criterion for evaluating a computing system, which is defined as the number of operations that can be completed within a unit of energy (J) [42].”
BackgroundSelf-citationA Unified FPGA Virtualization Framework for General-Purpose Deep Neural Networks in the Cloud
Zeng, S., Dai, G., Sun, H., Liu, J., Li, S., Ge, G., Zhong, K., Guo, K., Wang, Y., & Yang, H. (2021) · ACM Transactions on Reconfigurable Technology and Systems · doi:10.1145/3480170 · Cited by 11
Self-citationDynamically reconfigurable variable-precision sparse-dense matrix acceleration in Tensorflow Lite
Nunez-Yanez, J. L., Otero, A., & de la Torre, E. (2023) · Microprocessors and Microsystems · doi:10.1016/j.micpro.2023.104801 · Cited by 11
Reduced-Parameter YOLO-like Object Detector Oriented to Resource-Constrained Platform
Zheng, X., & He, T. (2023) · Sensors · doi:10.3390/s23073510 · Cited by 11
“Prior to this, there have been many studies on the practical application of neural network accelerators [12–15] and the design of neural network accelerators [16–18].”
BackgroundQuantization-Based Optimization Algorithm for Hardware Implementation of Convolution Neural Networks
Mohd, B. J., Yousef, K. M. A., AlMajali, A., & Hayajneh, T. S. (2024) · Electronics · doi:10.3390/electronics13091727 · Cited by 11
Using hls4ml to Map Convolutional Neural Networks on Interconnected FPGA Devices
Mageiropoulos, E., Chrysos, N. I., Dimou, N., & Katevenis, M. G. H. (2021) · IEEE International Symposium on Field-Programmable Custom Computing Machines (FCCM) · doi:10.1109/fccm51124.2021.00062 · Cited by 11
“The dominant implementation of CNN accelerators on FPGAs relies on a generic hardware unit that is time shared among the different layers of the CNN [1]; in this paradigm, each layer typically fetches the parameters (weights and biases) from DRAM, in order to compute its output.”
MethodBaroni, A., Glukhov, A., Pérez, E., Wenger, C., Calore, E., Schifano, S. F., Olivo, P., Ielmini, D., & Zambelli, C. (2022) · Frontiers in Neuroscience · doi:10.3389/fnins.2022.932270 · Cited by 11
“We used values retrieved from different FPGA platforms obtained by a literature survey (Guo et al., 2019).”
MethodBounding Memory Access Times in Multi-Accelerator Architectures on FPGA SoCs
Restuccia, F., Pagani, M., Biondi, A., Marinoni, M., & Buttazzo, G. (2022) · IEEE Transactions on Computers · doi:10.1109/tc.2022.3214117 · Cited by 11
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.