Demonstrating BrainScaleS-2 Inter-Chip Pulse-Communication using EXTOLL

Autor:	Thommes, Tobias, Bordukat, Sven, Grübl, Andreas, Karasenko, Vitali, Müller, Eric, Schemmel, Johannes
Rok vydání:	2022
Předmět:	Computer Science - Hardware Architecture Computer Science - Neural and Evolutionary Computing Computer Science - Networking and Internet Architecture
Druh dokumentu:	Working Paper
DOI:	10.1145/3517343.3517376
Popis:	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. Comment: 3 pages, 2 figures, submitted to the Neuro Inspired Computational Elements 2022 (NICE'2022) conference, accepted and presented as a lightning-talk in March 2022; 1st replacement: version to be published in the conference proceedings
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2202.12122 Zobrazit plný text záznamu View this record from Arxiv