Yang Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Interests
Yang Liu has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Lan Chen
Institute of Microelectronics of the Chinese Academy of Sciences, Beijing 100029, China
1 shared publication - Mao Ni
Institute of Microelectronics of Chinese Academy of Sciences
1 shared publication - Ming Chen
Institute of Microelectronics of Chinese Academy of Sciences
1 shared publication - Rong Chen
EDA Center, Institute of Microelectronics of the Chinese Academy of Sciences, Beijing, China
1 shared publication - Xiaoran Hao
Institute of Microelectronics of the Chinese Academy of Sciences, Beijing 100029, China
1 shared publication - Yiheng Zhang
Institute of Microelectronics of Chinese Academy of Sciences
1 shared publication
Latest Publications
- Open Access
- 4 March 2024
- Published by MDPI AG in Electronics
- Vol. 13 (5) , 975
Design of a Convolutional Neural Network Accelerator Based on On-Chip Data Reordering
Convolutional neural networks have been widely applied in the field of computer vision. In convolutional neural networks, convolution operations account for more than 90% of the total computational workload. The current mainstream approach to achieving high energy-efficient convolution operations is through dedicated hardware accelerators. Convolution operations involve a significant amount of weights and input feature data. Due to limited on-chip cache space in accelerators, there is a significant amount of off-chip DRAM memory access involved in the computation process. The latency of DRAM access is 20 times higher than that of SRAM, and the energy consumption of DRAM access is 100 times higher than that of multiply–accumulate (MAC) units. It is evident that the “memory wall” and “power wall” issues in neural network computation remain challenging. This paper presents the design of a hardware accelerator for convolutional neural networks. It employs a dataflow optimization strategy based on on-chip data reordering. This strategy improves on-chip data utilization and reduces the frequency of data exchanges between on-chip cache and off-chip DRAM. The experimental results indicate that compared to the accelerator without this strategy, it can reduce data exchange frequency by up to 82.9%.
- 4 March 2024
- Published by MDPI AG in Electronics
- Vol. 13 (5) , 975
Open AccessDesign of a Convolutional Neural Network Accelerator Based on On-Chip Data Reordering
Convolutional neural networks have been widely applied in the field of computer vision. In convolutional neural networks, convolution operations account for more than 90% of the total computational workload. The current mainstream approach to achieving high energy-efficient convolution operations is through dedicated hardware accelerators. Convolution operations involve a significant amount of weights and input feature data. Due to limited on-chip cache space in accelerators, there is a significant amount of off-chip DRAM memory access involved in the computation process. The latency of DRAM access is 20 times higher than that of SRAM, and the energy consumption of DRAM access is 100 times higher than that of multiply–accumulate (MAC) units. It is evident that the “memory wall” and “power wall” issues in neural network computation remain challenging. This paper presents the design of a hardware accelerator for convolutional neural networks. It employs a dataflow optimization strategy based on on-chip data reordering. This strategy improves on-chip data utilization and reduces the frequency of data exchanges between on-chip cache and off-chip DRAM. The experimental results indicate that compared to the accelerator without this strategy, it can reduce data exchange frequency by up to 82.9%.