A 2.56mm2 718GOPS configurable spiking convolutional sparse coding processor in 40nm CMOS

A 2.56mm2 718GOPS configurable spiking convolutional sparse coding processor in 40nm CMOS
复制标题

采用 40nm CMOS 的 2.56mm2 718GOPS 可配置尖峰卷积稀疏编码处理器

DOI:
--
复制
发表时间:
2017
期刊:
International Symposium on Security in Computing and Communications
影响因子:
--
通讯作者:
Zhengya Zhang
Zhengya Zhang
中科院分区:
--
文献类型:
--
作者:
Chester Liu;Sung;Zhengya Zhang

文献摘要

被引文献

相似文献

可配置的神经启发推理处理器被设计为神经元阵列,每个神经元在独立的时钟域中运行。该处理器使用有效的稀疏卷积和用于前馈操作的零补丁跳跃以及用于反馈操作的稀疏尖峰驱动重建来实现循环网络。全局异步本地同步结构可实现可扩展设计和负载平衡,从而实现 22% 的功耗降低。 2.56mm2 推理处理器采用 40nm CMOS 制造,集成了 48 个神经元、一个集线器和一个 OpenRISC 处理器。该芯片在380MHz下达到718GOPS,并演示了图像特征提取和立体图像深度提取的应用。
A configurable neuro-inspired inference processor is designed as an array of neurons each operating in an independent clock domain. The processor implements a recurrent network using efficient sparse convolutions with zero-patch skipping for feedforward operations, and sparse spike-driven reconstruction for feedback operations. A globally asynchronous locally synchronous structure enables scalable design and load balancing to achieve 22% reduction in power. Fabricated in 40nm CMOS, the 2.56mm2 inference processor integrates 48 neurons, a hub and an OpenRISC processor. The chip achieves 718GOPS at 380MHz, and demonstrates applications in feature extraction from images and depth extraction from stereo images.