通过冯·诺伊曼瓶颈路由大脑流量:在通用计算机上脉冲神经网络模拟代码中高效使用缓存
Routing brain traffic through the von Neumann bottleneck: Efficient cache usage in spiking neural network simulation code on general purpose computers
摘要:
在研究复杂动态系统如生物神经网络中,仿真是实验和理论之后的第三大支柱。当代的大脑规模网络对应于几百万个节点的有向图,每个节点具有几千条边的入度和出度,其中节点和边分别对应于基本的生物单元、神经元和突触。当考虑随机图时,每个节点的边分布在数千个并行进程中。神经元网络中的活动也是稀疏的。每个神经元偶尔会通过其传出突触向相应的目标神经元发送一个简短的信号,称为尖峰。这种空间和时间的稀疏性代表了传统计算机上模拟的固有瓶颈:从根本上讲,不规则的内存访问模式会导致缓存利用率低下。使用已建立的神经网络模拟代码作为参考实现,我们研究如何常见的技术来恢复缓存性能,如软件诱导的预取和软件流水线可以受益于现实世界的应用程序。算法的变化减少了高达50%的模拟时间。该研究证实了具有内在并行计算问题的众核系统可以克服传统计算机体系结构的冯·诺依曼瓶颈。
英文摘要:
Simulation is a third pillar next to experiment and theory in the study of complex dynamic systems such as biological neural networks. Contemporary brain-scale networks correspond to directed graphs of a few million nodes, each with an in-degree and out-degree of several thousands of edges, where nodes and edges correspond to the fundamental biological units, neurons and synapses, respectively. When considering a random graph, each node's edges are distributed across thousands of parallel processes. The activity in neuronal networks is also sparse. Each neuron occasionally transmits a brief signal, called spike, via its outgoing synapses to the corresponding target neurons. This spatial and temporal sparsity represents an inherent bottleneck for simulations on conventional computers: Fundamentally irregular memory-access patterns cause poor cache utilization. Using an established neuronal network simulation code as a reference implementation, we investigate how common techniques to recover cache performance such as software-induced prefetching and software pipelining can benefit a real-world application. The algorithmic changes reduce simulation time by up to 50%. The study exemplifies that many-core systems assigned with an intrinsically parallel computational problem can overcome the von Neumann bottleneck of conventional computer architectures.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。