arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.04092cs.NEcs.AIcs.DCcs.LGcs.PF
收藏

使用Lazy+事件驱动可塑性和共享原子实现更快的SNN仿真

Even Faster SNN Simulation with Lazy+Event-driven Plasticity and Shared Atomics

FORTH(希腊研究与技术基金会);UOC(克里特大学)

Dennis Bautembach, Iason Oikonomidis, Antonis Argyros

摘要:

我们提出了两个新的优化,加速基于时钟的脉冲神经网络(SNN)模拟器。第一个目标是尖峰时间依赖可塑性(STDP)。它结合了懒惰与事件驱动的可塑性,并有效地促进了使用位域和整数intrinsic的突触前和突触后尖峰的计算。它提供了比单独的事件驱动可塑性更高的带宽,并实现了比我们最接近的竞争对手快1.5 - 2倍的速度。第二个优化目标是尖峰输送。我们以一种方式划分我们的图表示,该方式限制了在任何给定时间需要更新的神经元的数量,这允许我们在共享内存而不是全局内存中执行所述更新。这比我们最接近的竞争对手快2 - 2.5倍。这两种优化都代表了STDP上多年迭代的最后进化阶段,并在我们最先进的SNN模拟器“Spice”(/spaIk/)内提供峰值。所提出的优化不限于我们的图形表示或管道,但适用于众多的模拟器设计。我们评估我们的表现,三个完善的模型,并比较自己对其他三个国家的最先进的模拟器。

英文摘要:

We present two novel optimizations that accelerate clock-based spiking neural network (SNN) simulators. The first one targets spike timing dependent plasticity (STDP). It combines lazy- with event-driven plasticity and efficiently facilitates the computation of pre- and post-synaptic spikes using bitfields and integer intrinsics. It offers higher bandwidth than event-driven plasticity alone and achieves a 1.5x-2x speedup over our closest competitor. The second optimization targets spike delivery. We partition our graph representation in a way that bounds the number of neurons that need be updated at any given time which allows us to perform said update in shared memory instead of global memory. This is 2x-2.5x faster than our closest competitor. Both optimizations represent the final evolutionary stages of years of iteration on STDP and spike delivery inside "Spice" (/spaIk/), our state of the art SNN simulator. The proposed optimizations are not exclusive to our graph representation or pipeline but are applicable to a multitude of simulator designs. We evaluate our performance on three well-established models and compare ourselves against three other state of the art simulators.

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。

↑