> Details
Müller, Eric
[Author];
Arnold, Elias
[Author];
Breitwieser, Oliver
[Author];
Czierlinski, Milena
[Author];
Emmel, Arne
[Author];
Kaiser, Jakob
[Author];
Mauch, Christian
[Author];
Schmitt, Sebastian
[Author];
Spilger, Philipp
[Author];
Stock, Raphael
[Author];
Stradmann, Yannik
[Author];
Weis, Johannes
[Author];
Baumbach, Andreas
[Author];
Billaudelle, Sebastian
[Author];
Cramer, Benjamin
[Author];
Ebert, Falk
[Author];
Göltz, Julian
[Author];
Ilmberger, Joscha
[Author];
Karasenko, Vitali
[Author];
Kleider, Mitja
[Author];
Leibfried, Aron
[Author];
Pehle, Christian
[Author];
Schemmel, Johannes
[Author]
A scalable approach to modeling on accelerated neuromorphic hardware
Sharing
Reference
management
Direct link
Bookmarks
Remove from
bookmarks
Share this by email
Share this on Twitter
Share this on Facebook
Share this on Whatsapp
- Media type: E-Article
- Title: A scalable approach to modeling on accelerated neuromorphic hardware
- Contributor: Müller, Eric [VerfasserIn]; Arnold, Elias [VerfasserIn]; Breitwieser, Oliver [VerfasserIn]; Czierlinski, Milena [VerfasserIn]; Emmel, Arne [VerfasserIn]; Kaiser, Jakob [VerfasserIn]; Mauch, Christian [VerfasserIn]; Schmitt, Sebastian [VerfasserIn]; Spilger, Philipp [VerfasserIn]; Stock, Raphael [VerfasserIn]; Stradmann, Yannik [VerfasserIn]; Weis, Johannes [VerfasserIn]; Baumbach, Andreas [VerfasserIn]; Billaudelle, Sebastian [VerfasserIn]; Cramer, Benjamin [VerfasserIn]; Ebert, Falk [VerfasserIn]; Göltz, Julian [VerfasserIn]; Ilmberger, Joscha [VerfasserIn]; Karasenko, Vitali [VerfasserIn]; Kleider, Mitja [VerfasserIn]; Leibfried, Aron [VerfasserIn]; Pehle, Christian [VerfasserIn]; Schemmel, Johannes [VerfasserIn]
- Published: May 2022
- Published in: Frontiers in neuroscience ; 16(2022), Artikel-ID 884128, Seite 1-22
- Language: English
- DOI: 10.3389/fnins.2022.884128
- ISSN: 1662-453X
- Description: Neuromorphic systems open up opportunities to enlarge the explorative space for computational research. However, it is often challenging to unite efficiency and usability. This work presents the software aspects of this endeavor for the BrainScaleS-2 system, a hybrid accelerated neuromorphic hardware architecture based on physical modeling. We introduce key aspects of the BrainScaleS-2 Operating System: experiment workflow, API layering, software design, and platform operation. We present use cases to discuss and derive requirements for the software and showcase the implementation. The focus lies on novel system and software features such as multi-compartmental neurons, fast re-configuration for hardware-in-the-loop training, applications for the embedded processors, the non-spiking operation mode, interactive platform access, and sustainable hardware/software co-development. Finally, we discuss further developments in terms of hardware scale-up, system usability, and efficiency.
-
Footnote:
Published: 18 May 2022
- Provenance information:
- Access State: Open Access