非结构网格下稀疏下三角方程求解器众核优化技术研究  

Many-core Optimization for Sparse Triangular Solver Under Unstructured Grids

作　　者：倪鸿 刘鑫 NI Hong;LIU Xin(National Research Centre of Parallel Computer Engineering and Technology,Beijing 100086,China)

机构地区：[1]国家并行计算机工程技术研究中心

出　　处：《计算机科学》2019年第B06期518-522,共5页Computer Science

基　　金：“全球变化和应对”专项(2016YFA0602200)资助

摘　　要：稀疏下三角方程求解器(SpTRSV)作为基础线性代数库中一个重要的算法,在大规模科学计算中有着广泛应用。在非结构网格中,由于非结构网格具有数据存储无序性、数据强相关性以及频繁地离散访存等特点,该算法在众核架构上难以实现有效的并行。文中基于国产异构众核处理器SW26010体系结构的特点,针对非结构网格计算,提出了一种基于流水线串行-局部并行思想的通用众核优化方法。该方法能够有效减少非结构网格计算中的随机访存,提高计算效率,并且具有很好的扩展性。基于该算法对多个实际应用算例进行众核优化,实验结果表明:该方法能够实现单核组3倍以上的加速,显著降低了运行时间。Sparse Triangular Solver(SpTRSV),as an important algorithm in basic linear algebraic library,has been widely used in large-scale scientific computing.In unstructured-grids,because unstructured grid have the characte-ristics of data storage disorder,data depth correlation and frequent discrete-time memory access,this algorithm is difficult to achieve effective parallelism in the many-core architecture.In this paper,based on the architecture of the domestic heterogeneous multiprocessor SW26010 architecture,a general kernel optimization method based on pipelined serial and local parallel was proposed for unstructured grid computing.This method can effectively reduce random access in unstructured grid computing,improve the computing efficiency,and have the good scalability.Based on this algorithm,multiple kernel optimization is carried out for several practical applications.The experimental results show that the method can achieve more than 3 times acceleration of the single core group and significantly reduce the running time.

关 键 词：稀疏下三角方程求解器 非结构网格 SW26010 异构众核优化 并行算法 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]