Benchmarking and Characterization of event-based Neuromorphic Hardware

Ostrau C, Klarhorst C, Thies M, Rückert U (Accepted)
Presented at the FastPath 2019 - International Workshop on Performance Analysis of Machine Learning Systems, Madison, Wisconsin, USA.

Kurzbeitrag Konferenz / Poster | Angenommen | Englisch
 
Download
OA 143.29 KB
Abstract / Bemerkung
We present the modular framework SNABSuite (Spiking Neural Architecture Benchmark Suite) for black-box benchmarking of neuromorphic hardware systems and spiking neural network software simulators. The motivation for having a coherent collection of benchmarks is twofold: first, benchmarks evaluated on different platforms provide measures for direct comparison of performance indicators (e.g. resource efficiency, quality of the result, robustness). By using the platforms as they are provided for possible end-users and evaluating selected performance indicators, benchmarks support the decision for or against a system based on use-case requirements. Second, benchmarks may reveal opportunities for effective improvements of a system and can contribute to future development. Systems like the Heidelberg BrainScaleS project, IBM TrueNorth, the Manchester SpiNNaker project or the Intel Loihi platform drive the evolution of neuromorphic hardware implementations, while comparable benchmarks and corresponding measures are still rare. We show our methodology for comparing such diverse systems by applying a modular framework, with a user- centric view based on configurable spiking neural network descriptions.
Erscheinungsjahr
2019
Konferenz
FastPath 2019 - International Workshop on Performance Analysis of Machine Learning Systems
Konferenzort
Madison, Wisconsin, USA
Konferenzdatum
2019-03-24 – 2019-03-24
Page URI
https://pub.uni-bielefeld.de/record/2935328

Zitieren

Ostrau C, Klarhorst C, Thies M, Rückert U. Benchmarking and Characterization of event-based Neuromorphic Hardware. Presented at the FastPath 2019 - International Workshop on Performance Analysis of Machine Learning Systems, Madison, Wisconsin, USA.
Ostrau, C., Klarhorst, C., Thies, M., & Rückert, U. (Accepted). Benchmarking and Characterization of event-based Neuromorphic Hardware. Presented at the FastPath 2019 - International Workshop on Performance Analysis of Machine Learning Systems, Madison, Wisconsin, USA.
Ostrau, C., Klarhorst, C., Thies, M., and Rückert, U. (Accepted).“Benchmarking and Characterization of event-based Neuromorphic Hardware”. Presented at the FastPath 2019 - International Workshop on Performance Analysis of Machine Learning Systems, Madison, Wisconsin, USA.
Ostrau, C., et al., Accepted. Benchmarking and Characterization of event-based Neuromorphic Hardware. Presented at the FastPath 2019 - International Workshop on Performance Analysis of Machine Learning Systems, Madison, Wisconsin, USA.
C. Ostrau, et al., “Benchmarking and Characterization of event-based Neuromorphic Hardware”, Presented at the FastPath 2019 - International Workshop on Performance Analysis of Machine Learning Systems, Madison, Wisconsin, USA, Accepted.
Ostrau, C., Klarhorst, C., Thies, M., Rückert, U.: Benchmarking and Characterization of event-based Neuromorphic Hardware. Presented at the FastPath 2019 - International Workshop on Performance Analysis of Machine Learning Systems, Madison, Wisconsin, USA (Accepted).
Ostrau, Christoph, Klarhorst, Christian, Thies, Michael, and Rückert, Ulrich. “Benchmarking and Characterization of event-based Neuromorphic Hardware”. Presented at the FastPath 2019 - International Workshop on Performance Analysis of Machine Learning Systems, Madison, Wisconsin, USA, Accepted.
Alle Dateien verfügbar unter der/den folgenden Lizenz(en):
Copyright Statement:
This Item is protected by copyright and/or related rights. [...]
Volltext(e)
Name
143.29 KB
Access Level
OA Open Access
Zuletzt Hochgeladen
2019-04-24T12:25:47Z
MD5 Prüfsumme
6002145e19dd1be818351a1f2a69c71e

Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Suchen in

Google Scholar