An End-to-End DNN Inference Framework for the SpiNNaker2 Neuromorphic MPSoC
This work provides a domain-specific solution for deploying DNNs on neuromorphic hardware, which is incremental as it extends an existing scheduler for a specific platform.
The authors tackled the problem of executing large and complex DNNs, including transformers, on the SpiNNaker2 neuromorphic chip by developing an end-to-end inference framework with multi-layer scheduling, quantization, and lowering steps, enabling edge-based execution.
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.