Huiyong Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Huiyong Li has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Dongcheng Shi
School of Computer Science and Engineering, Beihang University
1 shared publication - Guocheng Zhao
School of Computer Science and Engineering, Beihang University
1 shared publication - Hongxu Jiang
Beihang University
1 shared publication - Qian Cao
School of Computer and Artificial Intelligence, Beijing Technology and Business University, Beijing 100048, China
1 shared publication Yifan Zhang
School of Computer Science and Engineering, Beihang University, Beijing 100191, China
1 shared publication- Yongxiang Cao
School of Computer Science and Engineering, Beihang University
1 shared publication
Latest Publications
- Open Access
- 26 September 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Embedded Computing Systems
- Vol. 24 (5s) , 1-27
HMSA: High-Performance Heterogeneous Mixed-Precision CNN Systolic Array Accelerator on FPGA
In power-constrained and real-time-demanding embedded scenarios, Field-Programmable Gate Arrays (FPGAs) emerge as ideal options for accelerating neural network inference, owing to the reconfigurability, high reliability, and flexibility of FPGAs. Mixed precision quantization technology significantly reduces computational complexity and bandwidth requirements while preserving model accuracy. However, existing FPGA accelerators fail to fully leverage the parallel advantages of mixed precision, which leads to the actual inference speedup being markedly lower than the theoretical prediction. Reviewing existing methods, we found three main drawbacks in enhancing practical computational performance. Firstly, FPGAs primarily rely on DSP slices to achieve high-performance parallel multiplication and accumulation (MAC) in neural network inference. However, the current DSP PE design and data packing methods are not compatible with mixed-precision models. Secondly, the remaining logic resources are not fully utilized to accelerate computations. Thirdly, the mixed-precision quantization bit-width selection method without hardware-guided guidance leads to additional model accuracy loss. To address these challenges, we propose a high-performance heterogeneous mixed-precision systolic array (SA) accelerator, HMSA. It aims to leverage mixed-precision quantization fully, enhancing the practical inference efficiency of neural networks on embedded FPGAs. We propose an optimized DSP data packing method guided by a resource-performance cost model, which enhances the parallel computing performance of accelerators. We propose a heterogeneous convolutional acceleration architecture based on SA architecture with high scalability, enabling efficient utilization of FPGA’s heterogeneous computing resources. In terms of the algorithm, we propose an optimization method for bit-width selection based on FPGA hardware architecture, aiming to avoid accuracy degradation without improving inference speed. Experiments confirm that HMSA on the Xilinx XC7VX690T FPGA reaches a peak throughput of 6.385 TOP/s at W1A8 precision. When inferring mixed precision neural networks, HMSA achieves 3.53×, 5.46×, and 1.58× improvements in actual throughput/DSP compared to state-of-the-art MPA, MSD, and MP-OPU. Compared with the state-of-the-art MBFQuant and Edge-MPQ mixed quantization algorithms, the proposed optimized bit-width selection method effectively reduces the model accuracy loss.
- 26 September 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Embedded Computing Systems
- Vol. 24 (5s) , 1-27
Open AccessHMSA: High-Performance Heterogeneous Mixed-Precision CNN Systolic Array Accelerator on FPGA
In power-constrained and real-time-demanding embedded scenarios, Field-Programmable Gate Arrays (FPGAs) emerge as ideal options for accelerating neural network inference, owing to the reconfigurability, high reliability, and flexibility of FPGAs. Mixed precision quantization technology significantly reduces computational complexity and bandwidth requirements while preserving model accuracy. However, existing FPGA accelerators fail to fully leverage the parallel advantages of mixed precision, which leads to the actual inference speedup being markedly lower than the theoretical prediction. Reviewing existing methods, we found three main drawbacks in enhancing practical computational performance. Firstly, FPGAs primarily rely on DSP slices to achieve high-performance parallel multiplication and accumulation (MAC) in neural network inference. However, the current DSP PE design and data packing methods are not compatible with mixed-precision models. Secondly, the remaining logic resources are not fully utilized to accelerate computations. Thirdly, the mixed-precision quantization bit-width selection method without hardware-guided guidance leads to additional model accuracy loss. To address these challenges, we propose a high-performance heterogeneous mixed-precision systolic array (SA) accelerator, HMSA. It aims to leverage mixed-precision quantization fully, enhancing the practical inference efficiency of neural networks on embedded FPGAs. We propose an optimized DSP data packing method guided by a resource-performance cost model, which enhances the parallel computing performance of accelerators. We propose a heterogeneous convolutional acceleration architecture based on SA architecture with high scalability, enabling efficient utilization of FPGA’s heterogeneous computing resources. In terms of the algorithm, we propose an optimization method for bit-width selection based on FPGA hardware architecture, aiming to avoid accuracy degradation without improving inference speed. Experiments confirm that HMSA on the Xilinx XC7VX690T FPGA reaches a peak throughput of 6.385 TOP/s at W1A8 precision. When inferring mixed precision neural networks, HMSA achieves 3.53×, 5.46×, and 1.58× improvements in actual throughput/DSP compared to state-of-the-art MPA, MSD, and MP-OPU. Compared with the state-of-the-art MBFQuant and Edge-MPQ mixed quantization algorithms, the proposed optimized bit-width selection method effectively reduces the model accuracy loss.
- Open Access
- 25 March 2022
- Published by Wiley in Wireless Communications and Mobile Computing
- Vol. 2022, 1-17
MyoTac: Real-Time Recognition of Tactical Sign Language Based on Lightweight Deep Neural Network
Real-time tactical sign language recognition enables communication in a silent environment and outside the visual range, and human-computer interaction (HCI) can also be realized. Although the existing methods have high accuracy, they cannot be conveniently implemented in a portable system due to the complexity of their models. In this paper, we present MyoTac, a user-independent real-time tactical sign language classification system that makes the network lightweight through knowledge distillation, so as to balance between high accuracy and execution efficiency. We design tactical convolutional neural networks (TCNN) and bidirectional long short-term memory (B-LSTM) to capture the spatial and temporal features of the signals, respectively, and extract the soft target with knowledge distillation to compress the scale of the neural network by nearly four times without affecting the accuracy. We evaluate MyoTac on 30 tactical sign language (TSL) words based on data from 38 volunteers, including 25 volunteers collecting offline data and 13 volunteers conducting online tests. When dealing with new users, MyoTac achieves an average accuracy of 92.67% and the average recognition time is 2.81 ms. The obtained results show that our approach outperforms other algorithms proposed in the literature, reducing the real-time recognition time by 84.4% with higher accuracy.
- 25 March 2022
- Published by Wiley in Wireless Communications and Mobile Computing
- Vol. 2022, 1-17
Open AccessMyoTac: Real-Time Recognition of Tactical Sign Language Based on Lightweight Deep Neural Network
Real-time tactical sign language recognition enables communication in a silent environment and outside the visual range, and human-computer interaction (HCI) can also be realized. Although the existing methods have high accuracy, they cannot be conveniently implemented in a portable system due to the complexity of their models. In this paper, we present MyoTac, a user-independent real-time tactical sign language classification system that makes the network lightweight through knowledge distillation, so as to balance between high accuracy and execution efficiency. We design tactical convolutional neural networks (TCNN) and bidirectional long short-term memory (B-LSTM) to capture the spatial and temporal features of the signals, respectively, and extract the soft target with knowledge distillation to compress the scale of the neural network by nearly four times without affecting the accuracy. We evaluate MyoTac on 30 tactical sign language (TSL) words based on data from 38 volunteers, including 25 volunteers collecting offline data and 13 volunteers conducting online tests. When dealing with new users, MyoTac achieves an average accuracy of 92.67% and the average recognition time is 2.81 ms. The obtained results show that our approach outperforms other algorithms proposed in the literature, reducing the real-time recognition time by 84.4% with higher accuracy.