SRNPU: An Energy-Efficient CNN-Based Super-Resolution Processor With Tile-Based Selective Super-Resolution in Mobile Devices
Juhyoung Lee, Jinsu Lee, Hoi‐Jun Yoo
Abstract
In this article, we propose an energy-efficient convolutional neural network (CNN) based super-resolution (SR) processor, super-resolution neural processing unit (SRNPU), for mobile applications. Traditionally, it is hard to realize real-time CNN-based SR on resource-limited platforms like mobile devices due to its massive amount of computation workload and communication bandwidth with external memory. The SRNPU can support the tile-based selective super-resolution (TSSR) which dynamically selects the proper sized CNN in a tile-by-tile manner. The TSSR reduces the computational workload of CNN-based SR by 31.1 % while maintaining image restoration performance. Moreover, a proposed selective caching based convolutional layer fusion (SC <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> LF) can reduce 78.8 % of external memory bandwidth with 93.2 % smaller on-chip memory footprint compared with previous layer fusion methods, by only caching short reuse distance intermediate feature maps. Additionally, reconfigurable cyclic ring architecture in the SRNPU enables maintaining high PE utilization by amortizing the reloading process caused by SC <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> LF operation under various convolutional layer configurations. The SRNPU is fabricated in 65 nm CMOS technology and occupies 4×4 mm <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> die area. The SRNPU has a peak power efficiency of 1.9 TOPS/W at 0.75 V, 50 MHz. The SRNPU achieves 31.8 fps ×2 scale Full-HD generation and 88.3 fps ×4 scale Full-HD generation with higher restoration performance and power efficiency than previous SR hardware implementations. To the best of our knowledge, the SRNPU is the first ASIC implementation of the CNN-based SR algorithm which supports real-time Full-HD up-scaling.