← 返回 JSSC 论文列表JSSC 2021第6期Digital Circuits65nm
24 STICKER-T An Energy-Efficient Neural Network Processor Using Block-Circulant
STICKER-T是一款采用块循环神经网络算法的高效能统一神经网络处理器。
65nm CMOS, 0.54–1.15 V, 25–200 MHz, 13.3–339-mW, 140.3 TOPS/W
神经网络处理器块循环神经网络频域加速能量效率统一工作流
▸支持统一CNN/FC/RNN工作流程的块循环加速芯片架构
▸高效高吞吐量的多比特8-128点全局并行局部位串行FFT模块
▸利用6T分层位线切换转置SRAM实现二维数据重用的多比特频域MAC阵列
Abstract
The emerging edge intelligence requires low-cost
energy-efficient neural network (NN) processors. Supporting
various types of edge NN models leads to extra circuit over-
head. Designing a unified NN processor with high energy/area
efficiency is challenging. This work presents a frequency-
domain-accelerated unified NN processor, named STICKER-T.
It combines algorithm, architecture, and circuit-level optimiza-
tion to achieve high energy/area efficiency. By utilizing the
block-circulant NN (CirCNN) al