Corpus ID: 207880671

SpiNNaker 2: A 10 Million Core Processor System for Brain Simulation and Machine Learning

@article{Mayr2019SpiNNaker2A,
  title={SpiNNaker 2: A 10 Million Core Processor System for Brain Simulation and Machine Learning},
  author={Christian Mayr and Sebastian H{\"o}ppner and S. Furber},
  journal={ArXiv},
  year={2019},
  volume={abs/1911.02385}
}
  • Christian Mayr, Sebastian Höppner, S. Furber
  • Published 2019
  • Computer Science
  • ArXiv
  • SpiNNaker is an ARM-based processor platform optimized for the simulation of spiking neural networks. This brief describes the roadmap in going from the current SPINNaker1 system, a 1 Million core machine in 130nm CMOS, to SpiNNaker2, a 10 Million core machine in 22nm FDSOI. Apart from pure scaling, we will take advantage of specific technology features, such as runtime adaptive body biasing, to deliver cutting-edge power consumption. Power management of the cores allows a wide range of… CONTINUE READING
    10 Citations
    Mapping Deep Neural Networks on SpiNNaker2
    Event-Driven Signal Processing with Neuromorphic Computing Systems
    • Peter Blouw, C. Eliasmith
    • Computer Science
    • ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
    • 2020
    • 3
    Provable neuromorphic advantages for constrained shortest paths
      • PDF
      Benchmarking of Neuromorphic Hardware Systems
      • 2
      • Highly Influenced
      • PDF
      Adaptive Extreme Edge Computing for Wearable Devices
      • PDF
      Evolving to learn: discovering interpretable plasticity rules for spiking networks
      • 2
      • PDF

      References

      SHOWING 1-10 OF 11 REFERENCES
      Overview of the SpiNNaker System Architecture
      • 457
      • PDF
      A fixed point exponential function accelerator for a neuromorphic many-core system
      • 18
      • PDF
      A million spiking-neuron integrated circuit with a scalable communication network and interface
      • 1,916
      • PDF
      Dynamic voltage and frequency scaling for neuromorphic many-core systems
      • 14
      Pattern representation and recognition with accelerated analog neuromorphic systems
      • 13
      • PDF
      Memory-Efficient Deep Learning on a SpiNNaker 2 Prototype
      • 28
      • PDF
      BioSpaun: A large-scale behaving brain model with complex neurons
      • 14
      • PDF
      True random number generation from bang-bang ADPLL jitter
      • 5
      Spinnaker2-towards extremely efficient digital neuromorphics and multi-scale brain emulation
      • Neuro Inspired Computational Elements (NICE
      • 2018