论文标题
使用贵族演示BrainScales-2-2片间脉冲通信
Demonstrating BrainScaleS-2 Inter-Chip Pulse-Communication using EXTOLL
论文作者
论文摘要
Brainscales-2（BSS-2）神经形态计算系统当前由多个单芯片设置组成，这些设置通过Gigabit-Ethernet网络技术连接到计算群集。这对于小型实验很方便，其中神经网络适合单个芯片。当建模较大尺寸的网络时，必须在CHIP边界上连接神经元。我们使用Extroll网络技术对BSS-2实施这些连接。这提供了很高的带宽和低潜伏期，以及高信息率。在这里，我们描述了目标脉冲路由实现，并需要扩展到BSS-2软件堆栈。我们还使用缩放版本的版本在BSS-2上展示了馈入脉冲路由，而无需暂时合并。
The BrainScaleS-2 (BSS-2) Neuromorphic Computing System currently consists of multiple single-chip setups, which are connected to a compute cluster via Gigabit-Ethernet network technology. This is convenient for small experiments, where the neural networks fit into a single chip. When modeling networks of larger size, neurons have to be connected across chip boundaries. We implement these connections for BSS-2 using the EXTOLL networking technology. This provides high bandwidths and low latencies, as well as high message rates. Here, we describe the targeted pulse-routing implementation and required extensions to the BSS-2 software stack. We as well demonstrate feed-forward pulse-routing on BSS-2 using a scaled-down version without temporal merging.
