As a typical artificial intelligence algorithm, the convolutional neural network (CNN) is widely used in the Internet of Things (IoT) system. In order to improve the computing ability of an IoT CPU, this paper designs a reconfigurable CNN-accelerated coprocessor based on the RISC-V instruction set. The interconnection structure of the acceleration chain designed by the predecessors is optimized, and the accelerator is connected to the RISC-V CPU core in the form of a coprocessor. The corresponding instruction of the coprocessor is designed and the instruction compiling environment is established. Through the inline assembly in the C language, the coprocessor instructions are called, coprocessor acceleration library functions are established, and common algorithms in the IoT system are implemented on the coprocessor. Finally, resource consumption evaluation and performance analysis of the coprocessor are completed on a Xilinx FPGA. The evaluation results show that the reconfigurable CNN-accelerated coprocessor only consumes 8534 LUTS, accounting for 47.6% of the total SoC system. The number of instruction cycles required to implement functions such as convolution and pooling based on the designed coprocessor instructions is better than using the standard instruction set, and the acceleration ratio of convolution is 6.27 times that of the standard instruction set.
As a classical artificial intelligence algorithm, the convolutional neural network (CNN) algorithm plays an important role in image recognition and classification and is gradually being applied in the Internet of Things (IoT) system. A compact CNN accelerator for the IoT endpoint System-on-Chip (SoC) is proposed in this paper to meet the needs of CNN computations. Based on analysis of the CNN structure, basic functional modules of CNN such as convolution circuit and pooling circuit with a low data bandwidth and a smaller area are designed, and an accelerator is constructed in the form of four acceleration chains. After the acceleration unit design is completed, the Cortex-M3 is used to construct a verification SoC and the designed verification platform is implemented on the FPGA to evaluate the resource consumption and performance analysis of the CNN accelerator. The CNN accelerator achieved a throughput of 6.54 GOPS (giga operations per second) by consuming 4901 LUTs without using any hardware multipliers. The comparison shows that the compact accelerator proposed in this paper makes the CNN computational power of the SoC based on the Cortex-M3 kernel two times higher than the quad-core Cortex-A7 SoC and 67% of the computational power of eight-core Cortex-A53 SoC.
13 July 2019 in Journal of Electrical Engineering & Technology
More and more attention is being paid to the use of massive parallel computing performed on many-core Networks-on-Chip (NoC) in order to accelerate performance. Simultaneously deploying multiple applications on NoC is one feasible way to achieve this. In this paper, we propose a multi-phase-based multi-application mapping approach for NoC design. Our approach began with a rectangle analysis, which offered several potential regions for application. Then we mapped all tasks of the application into these potential regions using a genetic algorithm, and identified the one which exhibited the strongest performance. When the packeted regions for each application were identified, a B*Tree-based simulated annealing algorithm was used to generate the optimal placement for the multi-application mapping regions. The experiment results show that the proposed approach can achieve a considerable reduction in network power consumption (up to 23.45%) and latency (up to 24.42%) for a given set of applications.
1 January 2024 in IET Computers & Digital Techniques
The asynchronous advantage actor‐critic (A3C) algorithm is widely regarded as one of the most effective and powerful algorithms among various deep reinforcement learning algorithms. However, the distributed and asynchronous nature of the A3C algorithm brings increased algorithm complexity and computational requirements, which not only leads to an increased training cost but also amplifies the difficulty of deploying the algorithm on resource‐limited field programmable gate array (FPGA) platforms. In addition, the resource wastage problem caused by the distributed training characteristics of A3C algorithms and the resource allocation problem affected by the imbalance between the computational amount of inference and training need to be carefully considered when designing accelerators. In this paper, we introduce a deployment strategy designed for distributed algorithms aimed at enhancing the resource utilization of hardware devices. Subsequently, a FPGA architecture is constructed specifically for accelerating the inference and training processes of the A3C algorithm. The experimental results show that our proposed deployment strategy reduces resource consumption by 62.5% and decreases the number of agents waiting for training by 32.2%, and the proposed A3C accelerator achieves 1.83× and 2.39× improvements in speedup compared to CPU (Intel i9‐13900K) and GPU (NVIDIA RTX 4090) with less power consumption respectively. Furthermore, our design shows superior resource efficiency compared to existing works.