A 28-nm 25.1 TOPS/W Sparsity-Aware CNN-GCN Deep Learning SoC for Mobile Augmented Reality
Journal
Digest of Technical Papers - Symposium on VLSI Technology
Journal Volume
2022-June
ISBN
9781665497725
Date Issued
2022-01-01
Author(s)
Huang, Wen Cong
Lin, I. Ting
Chen, Wen Ching
Lin, Liang Yi
Chang, Nian Shyang
CHUN-PIN LIN
Chen, Chi Shi
Abstract
This work presents the first CNN-GCN SoC for diverse AI vision computations on mobile augmented reality (AR). A CNN engine utilizes the channel-wise feature sparsity with a specialized processing element to achieve an up to 8× higher throughput and 6.1× energy efficiency. A GCN engine is implemented for graph-based action recognition. The computational complexity and memory usage are minimized by lever-aging matrix and graph properties. The proposed SoC achieves 25.1 TOPS/W energy efficiency for CNN inference, outperforming prior designs by 2.0×. It delivers 72 action/s on action recognition, exceeding prior art by 18× in latency.
SDGs
Type
conference paper