JSSC 2020第8期Digital CircuitsNeural Network Accelerator

Tianjic A Unified and Scalable Chip Bridging Spike-Based and Continuous Neural C

Tianjic芯片提出统一架构，支持脉冲神经网络与深度学习模型的高效兼容运行。

未明确披露（提及支持动态生物神经网络与深度学习加速）

神经形态计算深度学习统一架构众核网络硬件兼容性

▸统一模型描述框架

▸支持多类神经网络（SNN/CNN/RNN等）

▸去中心化众核网络的同构/异构扩展能力

Abstract

Toward the long-standing dream of artiﬁcial intelligence, two successful solution paths have been paved: 1) neuromorphic computing and 2) deep learning. Recently, they tend to interact for simultaneously achieving biological plausibility and powerful accuracy. However, models from these two domains have to run on distinct substrates, i.e., neuromorphic platforms and deep learning accelerators, respectively. This architectural incompatibility greatly compromises the model- ing ﬂexibility and hind