基于ARM SVE的光滑粒子流体动力学SIMD加速方法  

SIMD optimization of smoothed particle hydrodynamics based on ARM SVE

作　　者：范小康[1] 夏泽宇 龙思凡 杨灿群[1] FAN Xiao-kang;XIA Ze-yu;LONG Si-fan;YANG Can-qun(College of Computer Science and Technology,National University of Defense Technology,Changsha 410073,China)

机构地区：[1]国防科技大学计算机学院,湖南长沙410073

出　　处：《计算机工程与科学》2021年第6期989-996,共8页Computer Engineering & Science

基　　金：国家重点研发计划(2018YFB0204301)。

摘　　要：光滑粒子流体动力学(SPH)是近年来兴起的一种无网格的粒子方法,SPH在处理大变形、运动物质表面以及自由表面等问题时优势明显,在数值模拟领域得到了非常广泛的应用,是一种典型的科学计算应用。作为一种显式的粒子方法,SPH在每一个迭代步都需要计算大量的粒子间相互作用,计算量非常大,如何提高SPH的计算效率成为研究热点。可伸缩矢量扩展(SVE)是ARM针对高性能计算推出的下一代SIMD指令集,基于SVE研究了SPH方法的SIMD加速方法,取得了显著的加速效果。Smoothed Particle Hydrodynamics(SPH)is a meshless particle method that has emerged in recent years.SPH has obvious advantages in dealing with large deformations,moving material surfaces,and free surfaces.In recent years,it has been widely used in the field of numerical simulation,and it is a typical application of scientific computing.As an explicit particle method,SPH needs to calculate a large number of particle interactions in each iteration step,and the amount of calculation is very large.How to improve the calculation efficiency of SPH has become a research hotspot.Scalable Vector Extension(SVE)is the next generation SIMD extension proposed by ARM.This paper proposes a SIMD optimization method for SPH based on SVE,and achieves a good speedup.

关 键 词：可伸缩矢量扩展 光滑粒子流体动力学 向量化 

分 类 号：O351.2[理学—流体力学]