基于大规模并行计算的2D/1D耦合三维全堆输运程序Tiger-3D

Tiger-3D: 2D/1D Coupled Whole-Core Transport Code Based on Large-Scale Parallel Computation

2D/1D耦合方法求解三维输运方程具有快速、精确的优点;通常的2D/1D耦合方法利用轴向和角度方面的并行度,不能进行大规模并行计算。本研究在三维粗网有限差分(CMFD)框架下,径向采用区域分解并行的矩阵特征线方法(MOC),轴向采用扩散有限差分,综合利用2D/1D耦合方法径向和轴向的并行度,基于消息传递接口(MPI)实现大规模的并行计算,编写了Tiger-3D程序。数值验证表明,Tiger-3D程序具有良好的计算精度和较高的计算效率。

2D/1D coupled method can obtain good accuracy and efficiency for 3D transport equation. Generally, parallel features of axial planes and MOC angles are adopted in many codes. However, large-scale parallel computation is not realized. In this paper, 2D/1D coupled whole-core transport method was studied within the framework of 3D CMFD, in which spacial domain-decomposed matrix MOC was radially adopted while finite difference diffusion was axially adopted. By combining the parallel features of both directions of the 2D/1D coupled method, the code Tiger-3D with large-scale parallel computation was developed based on MPI. Numerical results demonstrated that Tiger-3D has good accuracy and high efficiency.