arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2007.03518physics.comp-ph
收藏

基于并行SFC的网格划分和负载均衡

Parallel SFC-based mesh partitioning and load balancing

Ricard Borrell, Guillermo Oyarzun, Damien Dosimont, Guillaume Houzeaux

摘要:

现代超级计算机允许以更高的精度模拟复杂现象。最终,这需要更精细的几何离散化与更大数量的网格元素。在这种情况下,外推到Exascale范式,网格化操作,如生成,自适应或分区,成为模拟工作流程中的一个关键瓶颈。在本文中,我们专注于网格划分。特别是,我们提出了一些改进的内部并行网格划分的基础上希尔伯特空间填充曲线。此外,利用其性能,我们提出了基于SFC的动态负载平衡分区的应用。该方法是基于在运行时的不平衡和随后的重新划分的网格的直接监测。使用考虑来自先前迭代的所有测量的最小二乘近似来评估优化分区的目标权重。以这种方式,最终分区对应于参与的计算设备的平均性能。

英文摘要:

Modern supercomputers allow the simulation of complex phenomena with increased accuracy. Eventually, this requires finer geometric discretizations with larger numbers of mesh elements. In this context, and extrapolating to the Exascale paradigm, meshing operations such as generation, adaptation or partition, become a critical bottleneck within the simulation workflow. In this paper, we focus on mesh partitioning. In particular, we present some improvements carried out on an in-house parallel mesh partitioner based on the Hilbert Space-Filling Curve. Additionally, taking advantage of its performance, we present the application of the SFC-based partitioning for dynamic load balancing. This method is based on the direct monitoring of the imbalance at runtime and the subsequent re-partitioning of the mesh. The target weights for the optimized partitions are evaluated using a least-squares approximation considering all measurements from previous iterations. In this way, the final partition corresponds to the average performance of the computing devices engaged.

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。

↑