A 5-mm2, 4.7-μ W Convolutional Neural Network Layer Accelerator for Miniature Systems
IEEE Transactions on Very Large Scale Integration (VLSI) Systems(2023)
摘要
This brief presents an energy-efficient accelerator for convolutional neural network (CNN) layer computations in a compact system. The accelerator replaces traditional data shift registers with a multiplexer-based barrel shifter, offering greater flexibility for supporting various models and reducing power consumption by 56.2% compared to flip-flop-based shifters. The prototype, fabricated using a 180-nm CMOS process, accelerates CIFAR-10 dataset CNN computations by 8.5 times compared to a system without the accelerator. It achieves this speedup while consuming only
$4.7 ~\mu \text{W}$
of power and
$9.53 ~\mu \text{J}$
for each inference task.
更多查看译文
关键词
Convolutional neural network,hardware accelerator,low power,miniature system
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要