首页> 外文期刊>Journal of Computational Physics >GPU-accelerated Monte Carlo simulation of particle coagulation based on the inverse method
【24h】

GPU-accelerated Monte Carlo simulation of particle coagulation based on the inverse method

机译:基于逆方法的GPU加速蒙特卡罗模拟颗粒凝结

获取原文
获取原文并翻译 | 示例
获取外文期刊封面目录资料

摘要

Simulating particle coagulation using Monte Carlo methods is in general a challenging computational task due to its numerical complexity and the computing cost. Currently, the lowest computing costs are obtained when applying a graphic processing unit (GPU) originally developed for speeding up graphic processing in the consumer market. In this article we present an implementation of accelerating a Monte Carlo method based on the Inverse scheme for simulating particle coagulation on the GPU. The abundant data parallelism embedded within the Monte Carlo method is explained as it will allow an efficient parallelization of the MC code on the GPU. Furthermore, the computation accuracy of the MC on GPU was validated with a benchmark, a CPU-based discrete-sectional method. To evaluate the performance gains by using the GPU, the computing time on the GPU against its sequential counterpart on the CPU were compared. The measured speedups show that the GPU can accelerate the execution of the MC code by a factor 10-100, depending on the chosen particle number of simulation particles. The algorithm shows a linear dependence of computing time with the number of simulation particles, which is a remarkable result in view of the n~2 dependence of the coagulation.
机译:由于其数值复杂性和计算成本,使用蒙特卡洛方法模拟颗粒凝结通常是一项艰巨的计算任务。当前,当应用最初为加速消费市场中的图形处理而开发的图形处理单元(GPU)时,可获得最低的计算成本。在本文中,我们提出了一种基于反向方案的加速蒙特卡罗方法的实现方案,用于在GPU上模拟颗粒凝结。解释了嵌入在蒙特卡洛方法中的大量数据并行性,因为它将允许在GPU上对MC代码进行有效的并行化。此外,通过基准测试(基于CPU的离散截面方法)验证了MC在GPU上的计算精度。为了评估使用GPU的性能提升,比较了GPU上的计算时间与CPU上的顺序计算时间。测得的加速比表明,GPU可以将MC代码的执行速度提高10到100倍,具体取决于所选的模拟粒子数量。该算法显示了计算时间与模拟粒子数量之间的线性相关性,鉴于凝固的n〜2相关性,这是一个了不起的结果。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号