Annu Int Conf IEEE Eng Med Biol Soc. 2017 Jul;2017:1010-1013. doi: 10.1109/EMBC.2017.8036997.
Microelectrode arrays with hundreds of channels have been widely used to acquire neuron population signals in neuroscience studies. Online spike sorting is becoming one of the most important challenges for high-throughput neural signal acquisition systems. Graphic processing unit (GPU) with high parallel computing capability might provide an alternative solution for increasing real-time computational demands on spike sorting. This study reported a method of real-time spike sorting through computing unified device architecture (CUDA) which was implemented on an embedded GPU (NVIDIA JETSON Tegra K1, TK1). The sorting approach is based on the principal component analysis (PCA) and K-means. By analyzing the parallelism of each process, the method was further optimized in the thread memory model of GPU. Our results showed that the GPU-based classifier on TK1 is 37.92 times faster than the MATLAB-based classifier on PC while their accuracies were the same with each other. The high-performance computing features of embedded GPU demonstrated in our studies suggested that the embedded GPU provide a promising platform for the real-time neural signal processing.
具有数百个通道的微电极阵列已被广泛用于神经科学研究中获取神经元群体信号。在线尖峰分类正成为高通量神经信号采集系统面临的最重要挑战之一。具有高并行计算能力的图形处理单元（GPU）可能为满足尖峰分类不断增长的实时计算需求提供替代解决方案。本研究报告了一种通过计算统一设备架构（CUDA）进行实时尖峰分类的方法，该方法在嵌入式GPU（NVIDIA JETSON Tegra K1，TK1）上实现。分类方法基于主成分分析（PCA）和K均值。通过分析每个过程的并行性，该方法在GPU的线程内存模型中进一步优化。我们的结果表明，TK1上基于GPU的分类器比PC上基于MATLAB的分类器快37.92倍，而它们的准确率相同。我们研究中展示的嵌入式GPU的高性能计算特性表明，嵌入式GPU为实时神经信号处理提供了一个有前景的平台。
