基于JASMIN的地下水流大规模并行数值模拟

针对具有精细网格剖分、长时间跨度特征的地下水流模拟中计算时间长、存储开销大等瓶颈问题,基于MODFLOW三维非稳定流计算方法,提出基于网格片的核心算法以及基于影像区的通信机制,并在JASMIN框架上研制了大规模地下水流并行数值模拟程序JOGFLOW.通过河南郑州市中牟县雁鸣湖水源地地下水流的模拟,对程序正确性和性能进行了验证;通过建立一个具有精细网格剖分的假想地下水概念模型对可扩展性进行测试.相对于32核的并行程序,在512以及1 024个处理机上的并行效率分别可达77.2%和67.5%.数值模拟结果表明,JOGFLOW具有较好的计算性能与可扩展性,能够有效使用数百上千计算核心,支持千万量级以上网格剖分的地下水流模型的大规模并行计算.

JASMIN-based Massive Parallel Computing of Large Scale Groundwater Flow

To overcome prohibitive cost in computational time and memory requirement in simulating groundwater flow models with detailed spatial discretization and long time period,we present an efficient massive parallel-computing program JOGFLOW for large scale groundwater flow simulation.In the program,groundwater flow process in MODFLOW is re-implemented on JASMIN by designing patch-based algorithms as well as using communication method based on adding ghost cells to each patch.Accuracy and efficiency of JOGFLOW are demonstrated in modeling a field flow located at Yanming Lake in Zhengzhou of Henan province.Parallel scalability is measured by simulating a hypothetic groundwater flow problem with much detailed spatial discretization.Compared to 32 cores,the parallel efficiency reaches 77.2% and 67.5% on 512 and 1 024 processors,respectively.Numerical modeling demonstrates good performance and scalability of JOGFLOW,which enables to support groundwater flow simulation with tens of millions of computational cells through massive parallel computing on hundreds or thousands of CPU cores.