SODECL An Open-Source Library for Calculating Multiple Orbits of a System of Stochastic Differential Equations in Parallel
SODECL An Open-Source Library for Calculating Multiple Orbits of a System of Stochastic Differential Equations in Parallel
复制标题
SODECL 一个用于并行计算随机微分方程组的多个轨道的开源库
DOI：
10.1145/3385076
复制
发表时间：
2020
影响因子：
2.7
通讯作者：
Avramidis E
中科院分区：
文献类型：
--
作者：
Avramidis E
随机微分方程组(SDE)被广泛用于模拟受随机过程影响的系统。通常，SDE模型的分析需要在多个参数组合上多次生成数值解。然而，这个过程通常需要相当多的计算资源才是可行的。由于任务的并行性令人尴尬，可以使用多核处理器和图形处理器(GPU)等设备进行加速。在此，我们提出了SODECL(https://github.com/avramidis/sodecl)，)软件库，它利用这些设备来计算SDE模型的多个轨道。为了评估SODECL提供的加速，我们比较了一个样本随机模型在使用一个CPU核时计算多个轨道所需的时间，以及使用所有CPU核或一个GPU时所需的时间。此外，为了评估可伸缩性，我们调查了模型大小对不同并行计算设备上的执行时间的影响。我们的结果表明，当使用高端高性能计算节点的所有32个中央处理器核时，与使用单个中央处理器核相比，任务加速高达≈6.7倍。在高端图形处理器上执行该任务，与单≈内核相比，可获得高达CPU4.5的加速。
Stochastic differential equations (SDEs) are widely used to model systems affected by random processes. In general, the analysis of an SDE model requires numerical solutions to be generated many times over multiple parameter combinations. However, this process often requires considerable computational resources to be practicable. Due to the embarrassingly parallel nature of the task, devices such as multi-core processors and graphics processing units (GPUs) can be employed for acceleration.Here, we present SODECL (https://github.com/avramidis/sodecl), a software library that utilizes such devices to calculate multiple orbits of an SDE model. To evaluate the acceleration provided by SODECL, we compared the time required to calculate multiple orbits of an exemplar stochastic model when one CPU core is used, to the time required when using all CPU cores or a GPU. In addition, to assess scalability, we investigated how model size affected execution time on different parallel compute devices.Our results show that when using all 32 CPU cores of a high-end high-performance computing node, the task is accelerated by a factor of up to ≈6.7, compared to when using a single CPU core. Executing the task on a high-end GPU yielded accelerations of up to ≈4.5, compared to a single CPU core.