Logo image
CINE: A 4K-UHD Energy-Efficient Computational Imaging Neural Engine With Overlapped Stripe Inference and Structure-Sparse Kernel
期刊文章

CINE: A 4K-UHD Energy-Efficient Computational Imaging Neural Engine With Overlapped Stripe Inference and Structure-Sparse Kernel

Kai-Ping Lin, Yu-Chun Ding, Chun-Yeh Lin, Yong-Tai ChenChao-Tsung Huang
IEEE Solid-State Circuits Letters, 卷.7, 頁碼.26-29
12/2023

摘要

computational imaging;Convolution;Convolutional neural network;Engines;external memory access;Kernel;Open systems;overlapped stripe inference;Random access memory;Resource management;structural sparsity;System-on-chip;weight-rotated allocation Electrical and Electronic Engineering

Recently, convolutional neural networks have achieved great success in high-resolution computational imaging applications such as super-resolution, image denoising, and image style transfer. However, it demands an enormous number of external memory access, i.e. DRAM bandwidth, and intensive computation while inferencing deeper models for high-quality images. In this letter, an energy-efficient computational imaging neural engine, CINE, is proposed with three key features: 1) overlapped stripe inference flow; 2) structure-sparse convolution kernel; 3) weight-rotated allocation unit. As a result, CINE can provide 4.6-8.3 TOP/W of energy efficiency for high-quality computational imaging applications.

相關連結

指標

1 檢視次數

詳細資料

Logo image