Solving PDEs in space-time: 4D tree-based adaptivity, mesh-free and matrix-free approaches

Solving PDEs in space-time: 4D tree-based adaptivity, mesh-free and matrix-free approaches
复制标题

求解时空偏微分方程:基于 4D 树的自适应性、无网格和无矩阵方法

DOI:
10.1145/3295500.3356198
复制
发表时间:
2019
期刊:
Storage and Analysis
影响因子:
--
通讯作者:
Sundar, Hari
Sundar, Hari
中科院分区:
--
文献类型:
--
作者:
Ishii, Masado;Fernando, Milinda;Saurabh, Kumar;Khara, Biswajit;Ganapathysubramanian, Baskar;Sundar, Hari

文献摘要

参考文献

被引文献

相似文献

数值求解偏微分方程(PDE)仍然是超级计算资源的一个引人注目的应用。下一代计算资源-表现出更高的并行性和更深的内存层次-提供了重新思考如何解决偏微分方程组,特别是依赖时间的偏微分方程组的机会。在这里,我们把时间看作一个额外的维度,同时在大的时间块(即4D时空)中求解未知问题,而不是标准的顺序时间步长方法。我们使用一种无网格的Dtree结构来离散4D时空域,该结构能够实现良好的并行性能以及自适应4D网格的动态构建。为了更好地利用4D时空网格的自适应性,我们引用偏微分方程组分析中的概念来建立一般类型的偏微分方程组的严格的后验误差估计。我们在时空中求解典型的线性和非线性偏微分方程组(热扩散、对流扩散和Allen-Cahn),并说明了以下优点:(A)与顺序时间推进方法相比,在更大的处理器数量上持续的缩放行为,(B)使用自适应时空网格捕获空间和时间中的“局部化”行为的能力,以及(C)消除任何时间推进约束,如Courant-Friedrichs-Lewis(CFL)条件,以及利用空间变化的时间步长的能力。我们相信,算法和数学的发展以及在现代体系结构上的有效部署构成了朝着提高下一代超级计算机上的PDE解算器的可伸缩性迈出的重要一步。
Numerically solving partial differential equations (PDEs) remains a compelling application of supercomputing resources. The next generation of computing resources - exhibiting increased parallelism and deep memory hierarchies - provide an opportunity to rethink how to solve PDEs, especially time dependent PDEs. Here, we consider time as an additional dimension and simultaneously solve for the unknown in large blocks of time (i.e. in 4D space-time), instead of the standard approach of sequential time-stepping. We discretize the 4D space-time domain using a mesh-freekDtree construction that enables good parallel performance as well as on-the-fly construction of adaptive 4D meshes. To best use the 4D space-time mesh adaptivity, we invoke concepts from PDE analysis to establish rigorousa posteriorierror estimates for a general class of PDEs. We solve canonical linear as well as non-linear PDEs (heat diffusion, advection-diffusion, and Allen-Cahn) in space-time, and illustrate the following advantages: (a) sustained scaling behavior across a larger processor count compared to sequential time-stepping approaches, (b) the ability to capture "localized" behavior in space and time using the adaptive space-time mesh, and (c) removal of any time-stepping constraints like the Courant-Friedrichs-Lewy (CFL) condition, as well as the ability to utilizespatially varying time-steps.We believe that the algorithmic and mathematical developments along with efficient deployment on modern architectures shown in this work constitute an important step towards improving the scalability of PDE solvers on the next generation of supercomputers.
使用结构化和非结构化网格及时进行任意边界运动的保守非定常空气动力学模拟
DOI: --
发表时间: 2012
期刊:
影响因子: --
作者:
T. Rendall;C. Allen;Edward D. C. Power
通讯作者: Edward D. C. Power
DOI: --
发表时间: 2015
期刊:
影响因子: --
作者:
U. Langer;S. Moore;M. Neumüller
通讯作者: M. Neumüller
HykSort:分布式内存架构上超立方体快速排序的新变体
DOI: --
发表时间: 2013
期刊: International Conference on Supercomputing
影响因子: --
作者:
H. Sundar;D. Malhotra;G. Biros
通讯作者: G. Biros
DOI: --
发表时间: 2011
期刊:
影响因子: --
作者:
K. Mani;D. Mavriplis
通讯作者: D. Mavriplis
DOI: --
发表时间: 2005
期刊:
影响因子: --
作者:
B. Ganapathysubramanian;N. Zabaras
通讯作者: N. Zabaras