Buchumschlag

BrainScaleS large scale spike communication using extoll

The BrainScaleS Neuromorphic Computing System is currently connected to a compute cluster via Gigabit-Ethernet network technology. This is convenient for the currently used experiment mode, where neuronal networks cover at most one wafer module. When modelling networks of larger size, as for example...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Thommes, Tobias (VerfasserIn) , Buwen, Niels (VerfasserIn) , Grübl, Andreas (VerfasserIn) , Müller, Eric (VerfasserIn) , Brüning, Ulrich (VerfasserIn) , Schemmel, Johannes (VerfasserIn)
Dokumenttyp: Article (Journal) Kapitel/Artikel
Sprache:Englisch
Veröffentlicht: 14 Dec 2021
Ausgabe:Version v2
In: Arxiv
Year: 2021, Pages: 1-3
DOI:10.48550/arXiv.2111.15296
Online-Zugang:Verlag, lizenzpflichtig, Volltext: https://doi.org/10.48550/arXiv.2111.15296
Verlag, lizenzpflichtig, Volltext: http://arxiv.org/abs/2111.15296
Volltext
Verfasserangaben:Tobias Thommes, Niels Buwen, Andreas Grübl, Eric Müller, Ulrich Brüning, and Johannes Schemmel
Beschreibung
Zusammenfassung:The BrainScaleS Neuromorphic Computing System is currently connected to a compute cluster via Gigabit-Ethernet network technology. This is convenient for the currently used experiment mode, where neuronal networks cover at most one wafer module. When modelling networks of larger size, as for example a full sized cortical microcircuit model, one has to think about connecting neurons across wafer modules to larger networks. This can be done, using the Extoll networking technology, which provides high bandwidth and low latencies, as well as a low overhead packet protocol format.
Beschreibung:Version 1 vom 30 November 2021, Version 2 vom 14 Dezember 2021
Gesehen am 10.10.2022
Beschreibung:Online Resource
DOI:10.48550/arXiv.2111.15296

Ähnliche Einträge