hxtorch: PyTorch for BrainScaleS-2 (original) (raw)

Abstract

We present software facilitating the usage of the BrainScaleS-2 analog neuromorphic hardware system as an inference accelerator for artificial neural networks. The hardware is transparently integrated into the PyTorch machine learning framework. In particular, we support vector-matrix multiplications and convolutions; corresponding software-based autograd functionality is provided for hardware-in-the-loop training. The software provides support for automatic partitioning and scheduling of neural networks onto one or multiple chips. We discuss the implementation including optimizations, analyze runtime overhead, measure performance and evaluate the results in terms of the hardware design limitations. As an application of the introduced framework, we present a model that classifies activities of daily living with smartphone sensor data.

P. Spilger and E. Müller—Contributed equally.

Similar content being viewed by others

References

  1. He, H.: The State of Machine Learning Frameworks in 2019. The Gradient (2019)
    Google Scholar
  2. Weis, J., et al.: Inference with artificial neural networks on analog neuromorphic hardware. In: Gama, J., et al. (eds.) ITEM 2020/IoT Streams 2020. CCIS, vol. 1325, pp. 201–212. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-66770-2_15
  3. Wunderlich, T., et al.: Demonstrating advantages of neuromorphic computation: a pilot study. Front. Neurosci. 13, 260 (2019). https://doi.org/10.3389/fnins.2019.00260
    Article Google Scholar
  4. Schemmel, J., Billaudelle, S., Dauer, P., Weis, J.: Accelerated analog neuromorphic computing. arXiv preprint (2020). arXiv: 2003.11996 [cs.NE]
  5. Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. In: Wallach, H., Larochelle, H., Beygelzimer, A., d’Alché-Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 32 (2019)
    Google Scholar
  6. Müller, E., et al.: The operating system of the neuromorphic BrainScaleS-1 system. arXiv preprint (2020). arXiv: 2003.13749 [cs.NE]
  7. Müller, E., et al.: Extending BrainScaleS OS for BrainScaleS-2. arXiv preprint (2020). arXiv: 2003.13750 [cs.NE]
  8. Schmitt, S., et al.: Classification With deep neural networks on an accelerated analog neuromorphic system. In: Proceedings of the 2017 IEEE International Joint Conference on Neural Networks (2017). https://doi.org/10.1109/IJCNN.2017.7966125
  9. Cramer, B., et al.: Training spiking multi-layer networks with surrogate gradients on an analog neuromorphic substrate. arXiv preprint (2020). arXiv: 2006.07239 [cs.NE]
  10. Anguita, D., Ghio, A., Oneto, L., Parra, X., Reyes-Ortiz, J.L.: A public domain dataset for human activity recognition using smartphones. In: Esann (2013)
    Google Scholar
  11. Ronao, C.A., Cho, S.-B.: Human activity recognition with smartphone sensors using deep learning neural networks. Expert Syst. Appl. 59, 235–244 (2016)
    Article Google Scholar
  12. Le Gallo, M., et al.: Mixed-precision in-memory computing. Nat. Electron. 1(4), 246–253 (2018). https://doi.org/10.1038/s41928-018-0054-8
    Article Google Scholar

Download references

Author information

Authors and Affiliations

  1. Kirchhoff-Institute for Physics, Ruprecht-Karls-Universität Heidelberg, Heidelberg, Germany
    Philipp Spilger, Eric Müller, Arne Emmel, Aron Leibfried, Christian Mauch, Christian Pehle, Johannes Weis, Oliver Breitwieser, Sebastian Billaudelle, Sebastian Schmitt, Timo C. Wunderlich, Yannik Stradmann & Johannes Schemmel

Authors

  1. Philipp Spilger
  2. Eric Müller
  3. Arne Emmel
  4. Aron Leibfried
  5. Christian Mauch
  6. Christian Pehle
  7. Johannes Weis
  8. Oliver Breitwieser
  9. Sebastian Billaudelle
  10. Sebastian Schmitt
  11. Timo C. Wunderlich
  12. Yannik Stradmann
  13. Johannes Schemmel

Corresponding author

Correspondence toPhilipp Spilger .

Editor information

Editors and Affiliations

  1. University of Porto, Porto, Portugal
    Joao Gama
  2. Halmstad University, Halmstad, Sweden
    Sepideh Pashami
  3. Waikato University, Hamilton, New Zealand
    Albert Bifet
  4. University of Lille, Lille, France
    Moamar Sayed-Mouchawe
  5. Heidelberg University, Heidelberg, Germany
    Holger Fröning
  6. Graz University of Technology, Graz, Austria
    Franz Pernkopf
  7. University of Duisburg-Essen, Essen, Germany
    Gregor Schiele
  8. XILINX Research, Dublin, Ireland
    Michaela Blott

Rights and permissions

© 2020 Springer Nature Switzerland AG

About this paper

Cite this paper

Spilger, P. et al. (2020). hxtorch: PyTorch for BrainScaleS-2. In: Gama, J., et al. IoT Streams for Data-Driven Predictive Maintenance and IoT, Edge, and Mobile for Embedded Machine Learning. ITEM IoT Streams 2020 2020. Communications in Computer and Information Science, vol 1325. Springer, Cham. https://doi.org/10.1007/978-3-030-66770-2\_14

Download citation

Keywords

Publish with us