4.6 Article

Parallelization of Neural Processing on Neuromorphic Hardware

期刊

FRONTIERS IN NEUROSCIENCE
卷 16, 期 -, 页码 -

出版社

FRONTIERS MEDIA SA
DOI: 10.3389/fnins.2022.867027

关键词

neuromorphic computing; SpiNNaker; real-time; parallel programming; event-driven simulation; spiking neural networks

资金

  1. EPSRC (the UK Engineering and Physical Sciences Research Council) [EP/D07908X/1, EP/G015740/1]
  2. university of Southampton
  3. university of Cambridge
  4. university of Sheffield
  5. ARM Ltd.
  6. Silistix Ltd.
  7. Thales
  8. EU ICT Flagship Human Brain Project [H2020 785907, 945539]
  9. EPSRC DTA studentship in the Department of Computer Science

向作者/读者索取更多资源

This article presents novel multicore processing strategies on the SpiNNaker Neuromorphic hardware, which optimize the efficiency of Spiking Neural Network operations. By parameterizing load balancing between computational units, researchers are able to explore long-term learning and neural pathologies in real- or sub-realtime.
Learning and development in real brains typically happens over long timescales, making long-term exploration of these features a significant research challenge. One way to address this problem is to use computational models to explore the brain, with Spiking Neural Networks a popular choice to capture neuron and synapse dynamics. However, researchers require simulation tools and platforms to execute simulations in real- or sub-realtime, to enable exploration of features such as long-term learning and neural pathologies over meaningful periods. This article presents novel multicore processing strategies on the SpiNNaker Neuromorphic hardware, addressing parallelization of Spiking Neural Network operations through allocation of dedicated computational units to specific tasks (such as neural and synaptic processing) to optimize performance. The work advances previous real-time simulations of a cortical microcircuit model, parameterizing load balancing between computational units in order to explore trade-offs between computational complexity and speed, to provide the best fit for a given application. By exploiting the flexibility of the SpiNNaker Neuromorphic platform, up to 9x throughput of neural operations is demonstrated when running biologically representative Spiking Neural Networks.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.6
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据