在微控制器上实现完整功能的神经形态脉冲网络模拟，低功耗边缘计算新方案
Full Feature Spiking Neural Network Simulation on Micro-Controllers for Neuromorphic Applications at the Edge
- 用16位浮点数压缩内存，让SNN仿真在8MB内存的MCU上运行
- 1200神经元的Synfire4基准准确率达97.5%，186神经元实时运行仅耗20mW
- 相比树莓派微型处理器能效提升5倍，系统级能效提升10倍
微控制器（MCU）相比传统计算机具有数量级更低的尺寸、重量和功耗（SWaP），适用于边缘应用。神经形态计算依赖脉冲神经网络（SNN）实现低功耗，但以往的SNN软件仿真需依赖GPU工作站、应用级处理器（如ARM Cortex-A53）或专用硬件（如Intel Loihi）。本文展示，通过使用IEEE 16位浮点数，可在配备8MB内存的RP2350 MCU上运行完整功能的CARLsim SNN仿真器。我们成功运行了包含1200个神经元的Synfire4基准测试，精度达97.5%（相较单精度浮点数）。此外，将该基准缩放至186个神经元后，可在MCU上实现实时运行，仅消耗20mW功耗。相比树莓派Pi Zero 2 W所用最小应用级ARM处理器，本方案对SNN本身能效提升5倍；若考虑完整SoC（MCU/CPU+主板），能效提升达一个数量级。
原文摘要 · Abstract (English)
Microcontroller units (MCU), which have an order of magnitude lower Size, Weight and Power (SWaP) than standard computers, makes them suitable for applications at the edge. Neuromorphic computing, which can realize low SWaP, relies on Spiking Neural Networks (SNNs). Until now, software based simulations of SNNs required GPU-based workstations, application classified core processors such as the ARM Cortex-A53, or specialized hardware like Intel's Loihi. In the present work, we demonstrate that the SNN simulator CARLsim can run its full feature set on a MCU RP2350 with 8 MB memory. We accomplished this by utilizing IEEE 16-bit float point numbers, which reduced memory requirements without loss of function. We were able to run the Synfire4 benchmark which comprises 1200 neurons. The accuracy was 97.5% compared to the standard single precision numbers. Furthermore, we show that CARLsim runs a Synfire4 benchmark scaled-down to 186 neurons on a MCU in real-time at only 20 mW. Compared to the smallest application class ARM processor used by Raspberry in their Pi Zero 2 W, our MCU implementation is five times more energy efficient for the SNN itself, and an order of magnitude better when compared to the complete SoC (MCU/CPU + Board).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。