Real-time cortical simulation on neuromorphic hardware
Real-time cortical simulation on neuromorphic hardware
复制标题
DOI：
10.1098/rsta.2019.0160
复制
发表时间：
2020-02-07
期刊：
影响因子：
5
通讯作者：
Furber, Steve B.
中科院分区：
文献类型：
--
作者：
Rhodes, Oliver;Peres, Luca;Furber, Steve B.
通过使用异构并行化方案和 SpiNNaker 神经形态硬件，提出了大规模生物代表性尖峰神经网络的实时模拟。已发布的皮质微电路模型用作基准测试用例，代表约 1 mm(2) 的早期感觉皮层，包含 77 k 个神经元和 3 亿个突触。这是该模型的第一次硬实时模拟，10 秒的生物模拟时间在 10 秒的挂钟时间内执行。这超过了在 HPC 神经模拟器（减速 3 倍）和运行优化的尖峰神经网络 (SNN) 库（减速 2 倍）的 GPU 上发表的最佳成果。此外，所提出的方法表明，随着 SNN 大小的增加，可以保持实时处理，打破了传统计算机器造成的通信障碍。将模型结果与已建立的 HPC 模拟器基线进行比较，以验证模拟的正确性，并与一系列统计指标进行良好比较。还报告了解决方案的能量和每个突触事件的能量，表明技术相对较低的 SpiNNaker 处理器相对于现代 HPC 系统实现了 10 倍的能耗降低，并且与现代 GPU 的能耗相当。最后，通过对皮质微电路进行多次 12 小时的模拟（每次模拟 12 小时的生物时间）来证明系统的鲁棒性，并展示了神经形态硬件作为神经科学研究工具在较长时间内研究复杂尖峰神经网络的潜力。本文是“协调能源自主计算与智能”主题的一部分。
Real-time simulation of a large-scale biologically representative spiking neural network is presented, through the use of a heterogeneous parallelization scheme and SpiNNaker neuromorphic hardware. A published cortical microcircuit model is used as a benchmark test case, representing approximate to 1 mm(2) of early sensory cortex, containing 77 k neurons and 0.3 billion synapses. This is the first hard real-time simulation of this model, with 10 s of biological simulation time executed in 10 s wall-clock time. This surpasses best-published efforts on HPC neural simulators (3 x slowdown) and GPUs running optimized spiking neural network (SNN) libraries (2 x slowdown). Furthermore, the presented approach indicates that real-time processing can be maintained with increasing SNN size, breaking the communication barrier incurred by traditional computing machinery. Model results are compared to an established HPC simulator baseline to verify simulation correctness, comparing well across a range of statistical measures. Energy to solution and energy per synaptic event are also reported, demonstrating that the relatively low-tech SpiNNaker processors achieve a 10 x reduction in energy relative to modern HPC systems, and comparable energy consumption to modern GPUs. Finally, system robustness is demonstrated through multiple 12 h simulations of the cortical microcircuit, each simulating 12 h of biological time, and demonstrating the potential of neuromorphic hardware as a neuroscience research tool for studying complex spiking neural networks over extended time periods. This article is part of the theme issue 'Harmonizing energy-autonomous computing and intelligence'.