← 返回 JSSC 论文列表JSSC 2021第7期Digital CircuitsNeural Network Accelerator
COMPAC Compressed Time-Domain Pooling-Aware Convolution CNN Engine With Reduced
提出一种压缩时域池化感知卷积CNN引擎，用于高效边缘AI计算。
AlexNet CNN在1000张ImageNet图像上的测试结果
时域计算卷积神经网络边缘计算能效优化脉冲宽度编码
▸压缩时域(CTD)方法提高输入激活的时间编码吞吐量
▸改进的内存延迟线(MDL)支持时域多比特输入和权重的有符号累加
▸池化感知卷积(PAC)技术减少冗余MAC计算
Abstract
In this work, we demonstrate a compressed
time-domain, pooling-aware convolution (COMPAC) convolu-
tional neural network (CNN) engine for energy-efficient edge AI
computing by performing multi-bit input and multi-bit weight
multiply-and-accumulate (MAC) o perations in the time domain.
The multi-bit inputs are compactly represented as a single
pulsewidth encoded input. This translates into reduced switching
capacitance (C
DYN), compared with the baseline digital implemen-
tation, and can enable lo