← 返回 JSSC 论文列表JSSC 2009第1期Digital Circuits0.13μm 8-metal CMOS
A 125 GOPS 583 mW Network-on-Chip Based Parallel Processor With Bio-Inspired Vis
一款基于NoC的并行处理器，用于生物启发式实时物体识别，具有视觉注意力算法。
125 GOPS, 583 mW, 22 frames/sec, 1.2 V
网络芯片(NoC)并行处理器物体识别视觉注意力引擎ARM10兼容处理器
▸网络芯片(NoC)并行处理器
▸视觉注意力引擎(V AE)
▸双通道自适应切换和基于数据包的功耗管理
Abstract
IEEE , Seungjin Lee , Student Member , IEEE ,
Joo-Young Kim, Student Member , IEEE, Minsu Kim , Student Member , IEEE, and Hoi-Jun Yoo , Fellow, IEEE
Abstract—A network-on-chip (NoC) based parallel processor is
presented for bio-inspired real-time object recognition with visual
attention algorithm. It contains an ARM10-compatible 32-bit main
processor, 8 single-instruction multiple-data (SIMD) clusters with
8 processing elements in each cluster , a cellular neural network
based visual attention