Block-Circulant Neural Network Accelerator Featuring Fine-Grained Frequency-Domain Quantization and Reconfigurable FFT Modules
Autor: | Yifan He, Huazhong Yang, Yongpan Liu, Jinshan Yue |
---|---|
Rok vydání: | 2021 |
Předmět: |
010302 applied physics
Artificial neural network Computer science Fast Fourier transform 02 engineering and technology Parallel computing 01 natural sciences 020202 computer hardware & architecture Frequency domain Compression (functional analysis) 0103 physical sciences 0202 electrical engineering electronic engineering information engineering Quantization (image processing) Circulant matrix Efficient energy use Block (data storage) |
Zdroj: | ASP-DAC |
Popis: | Block-circulant based compression is a popular technique to accelerate neural network inference. Though storage and computing costs can be reduced by transforming weights into block-circulant matrices, this method incurs uneven data distribution in the frequency domain and imbalanced workload. In this paper, we propose RAB: a Reconfigurable Architecture Block-Circulant Neural Network Accelerator to solve the problems via two techniques. First, a fine-grained frequency-domain quantization is proposed to accelerate MAC operations. Second, a reconfigurable architecture is designed to transform FFT/IFFT modules into MAC modules, which alleviates the imbalanced workload and further improves efficiency. Experimental results show that RAB can achieve 1.9x/1.8x area/energy efficiency improvement compared with the state-of-the-art block-circulant compression based accelerator. |
Databáze: | OpenAIRE |
Externí odkaz: |