Institution profile

Centre for Tactile Internet with Human-in-the-Loop

Academic institution
Official website
Research library1linked papers
Opportunities0open roles
Selected work

Representative Papers

An End-to-End DNN Inference Framework for the SpiNNaker2 Neuromorphic MPSoC

Jul 18, 2025

This work addresses the challenge of deploying large, complex deep neural networks (DNNs)—notably Transformers—on the SpiNNaker2 neuromorphic MPSoC for efficient inference. We present the first end-to-end PyTorch-to-SpiNNaker2 inference framework, built upon an extended OctopusScheduler that integrates multi-layer DNN scheduling, fine-grained model quantization, operator downgrading, and neuromorphic hardware mapping. Our framework enables full compilation and execution of PyTorch models directly onto a single SpiNNaker2 chip. To our knowledge, this is the first demonstration of end-to-end Transformer-scale DNN inference on SpiNNaker2, achieving high accuracy while significantly improving energy efficiency and throughput. The work overcomes a key bottleneck in neuromorphic hardware support for large-scale DNN inference and provides a scalable, system-level solution for deploying complex AI models at the edge.

0 citationsRead paper
Recent publications

Latest Papers

An End-to-End DNN Inference Framework for the SpiNNaker2 Neuromorphic MPSoC

Jul 18, 2025

This work addresses the challenge of deploying large, complex deep neural networks (DNNs)—notably Transformers—on the SpiNNaker2 neuromorphic MPSoC for efficient inference. We present the first end-to-end PyTorch-to-SpiNNaker2 inference framework, built upon an extended OctopusScheduler that integrates multi-layer DNN scheduling, fine-grained model quantization, operator downgrading, and neuromorphic hardware mapping. Our framework enables full compilation and execution of PyTorch models directly onto a single SpiNNaker2 chip. To our knowledge, this is the first demonstration of end-to-end Transformer-scale DNN inference on SpiNNaker2, achieving high accuracy while significantly improving energy efficiency and throughput. The work overcomes a key bottleneck in neuromorphic hardware support for large-scale DNN inference and provides a scalable, system-level solution for deploying complex AI models at the edge.

0 citationsRead paper