hxtorch: PyTorch for BrainScaleS-2 -- Perceptrons on Analog Neuromorphic Hardware
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2020
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912458961059840 |
|---|---|
| author | Spilger, Philipp Müller, Eric Emmel, Arne Leibfried, Aron Mauch, Christian Pehle, Christian Weis, Johannes Breitwieser, Oliver Billaudelle, Sebastian Schmitt, Sebastian Wunderlich, Timo C. Stradmann, Yannik Schemmel, Johannes |
| author_facet | Spilger, Philipp Müller, Eric Emmel, Arne Leibfried, Aron Mauch, Christian Pehle, Christian Weis, Johannes Breitwieser, Oliver Billaudelle, Sebastian Schmitt, Sebastian Wunderlich, Timo C. Stradmann, Yannik Schemmel, Johannes |
| contents | We present software facilitating the usage of the BrainScaleS-2 analog neuromorphic hardware system as an inference accelerator for artificial neural networks. The accelerator hardware is transparently integrated into the PyTorch machine learning framework using its extension interface. In particular, we provide accelerator support for vector-matrix multiplications and convolutions; corresponding software-based autograd functionality is provided for hardware-in-the-loop training. Automatic partitioning of neural networks onto one or multiple accelerator chips is supported. We analyze implementation runtime overhead during training as well as inference, provide measurements for existing setups and evaluate the results in terms of the accelerator hardware design limitations. As an application of the introduced framework, we present a model that classifies activities of daily living with smartphone sensor data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2006_13138 |
| institution | arXiv |
| publishDate | 2020 |
| record_format | arxiv |
| spellingShingle | hxtorch: PyTorch for BrainScaleS-2 -- Perceptrons on Analog Neuromorphic Hardware Spilger, Philipp Müller, Eric Emmel, Arne Leibfried, Aron Mauch, Christian Pehle, Christian Weis, Johannes Breitwieser, Oliver Billaudelle, Sebastian Schmitt, Sebastian Wunderlich, Timo C. Stradmann, Yannik Schemmel, Johannes Neural and Evolutionary Computing We present software facilitating the usage of the BrainScaleS-2 analog neuromorphic hardware system as an inference accelerator for artificial neural networks. The accelerator hardware is transparently integrated into the PyTorch machine learning framework using its extension interface. In particular, we provide accelerator support for vector-matrix multiplications and convolutions; corresponding software-based autograd functionality is provided for hardware-in-the-loop training. Automatic partitioning of neural networks onto one or multiple accelerator chips is supported. We analyze implementation runtime overhead during training as well as inference, provide measurements for existing setups and evaluate the results in terms of the accelerator hardware design limitations. As an application of the introduced framework, we present a model that classifies activities of daily living with smartphone sensor data. |
| title | hxtorch: PyTorch for BrainScaleS-2 -- Perceptrons on Analog Neuromorphic Hardware |
| topic | Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2006.13138 |