An End-to-End DNN Inference Framework for the SpiNNaker2 Neuromorphic MPSoC
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911063547576320 |
|---|---|
| author | Jobst, Matthias Langer, Tim Liu, Chen Alici, Mehmet Gonzalez, Hector A. Mayr, Christian |
| author_facet | Jobst, Matthias Langer, Tim Liu, Chen Alici, Mehmet Gonzalez, Hector A. Mayr, Christian |
| contents | This work presents a multi-layer DNN scheduling framework as an extension of OctopuScheduler, providing an end-to-end flow from PyTorch models to inference on a single SpiNNaker2 chip. Together with a front-end comprised of quantization and lowering steps, the proposed framework enables the edge-based execution of large and complex DNNs up to transformer scale using the neuromorphic platform SpiNNaker2. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_13736 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | An End-to-End DNN Inference Framework for the SpiNNaker2 Neuromorphic MPSoC Jobst, Matthias Langer, Tim Liu, Chen Alici, Mehmet Gonzalez, Hector A. Mayr, Christian Machine Learning Hardware Architecture Distributed, Parallel, and Cluster Computing This work presents a multi-layer DNN scheduling framework as an extension of OctopuScheduler, providing an end-to-end flow from PyTorch models to inference on a single SpiNNaker2 chip. Together with a front-end comprised of quantization and lowering steps, the proposed framework enables the edge-based execution of large and complex DNNs up to transformer scale using the neuromorphic platform SpiNNaker2. |
| title | An End-to-End DNN Inference Framework for the SpiNNaker2 Neuromorphic MPSoC |
| topic | Machine Learning Hardware Architecture Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2507.13736 |