IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · 2020 · 48 citations · 25 references
EngineeringComputer EngineeringComputer ScienceComputer ArchitectureDesign OptimizationField-programmable Gate ArraysAccelerator ArchitectureDeep LearningField-programmable Gate Array ArchitectureFpga ArchitectureHardware AccelerationReconfigurable AcceleratorsAccelerator MicroarchitectureAcceleratorsConvolutional Neural NetworksDomain-specific Accelerator DesignField-programmable Gate Array AcceleratorsSparse Computation AccelerationSparse LearningWeight Sparsity
In recent years, a variety of accelerators on FPGAs have been proposed to speed up the convolutional neural network (CNN) in many domain-specific application fields. Besides, some optimization algorithms, such as fast algorithms and network sparsity, have greatly reduced the theoretical computational workload of CNN inference. There are currently a few accelerators on FPGAs that support both the fast Winograd algorithm (WinoA) and network sparsity to minimize the amount of computation. However, on the one hand, these architectures feed data into processing elements (PEs) in units of blocks, some boundary losses caused by sparse irregularities cannot be avoided. On the other hand, these works have not discussed the design space exploration under the sparse condition. In this article, we propose a novel accelerator called WINONN. We fully discuss the challenges faced by supporting WinoA, weight sparsity, and activation sparsity simultaneously. To minimize the online encoding overhead caused by activation sparsity, an efficient encoding format called multibit mask (MBM) is proposed. To handle the irregularities of sparse data, we proposed a novel Scatter-Compute-Gather method in hardware design, combined with a freely sliding buffer to achieve fine-grained data loading to minimize the boundary waste. Finally, we combine a theoretical analysis and experimental method to explore the design space, allowing WINONN to get the best performance on a specific FPGA. Our high scalability design enables us to deploy sparse Winograd accelerators on very small embedded FPGAs, which is not supported in previous works. The experimental results on VGG16 show that we achieve the highest digital signal processing unit (DSP) efficiency and highest energy efficiency compared with the state-of-the-art sparse architectures.
25
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2016 · 222.1K citations · Full text
Going deeper with convolutions
Christian Szegedy, Wei Liu, Yangqing Jia et al. · 2015 · 46.8K citations
DaDianNao: A Machine-Learning Supercomputer
Yunji Chen, Tao Luo, Shaoli Liu et al. · 2014 · 1.5K citations