Optimization of Finite-Differencing Kernels for Numerical Relativity Applications

Optimization of Finite-Differencing Kernels for Numerical Relativity Applications
复制标题

数值相对论应用的有限差分核优化

DOI:
--
复制
发表时间:
2018
期刊:
International Conference on Parallel Computing
影响因子:
--
通讯作者:
D. Radice
D. Radice
中科院分区:
--
文献类型:
--
作者:
R. Alfieri;S. Bernuzzi;A. Perego;D. Radice

文献摘要

参考文献

被引文献

相似文献

提出了一种简单的多核结构三维有限差分核计算优化策略。三维有限差分计算是逐方向分割的,并利用两个级别的并行性:核内矢量化和多线程共享内存并行化。该方法的主要应用是加速数值相对性代码的高阶模板计算。我们提出的方法在不同的处理器微架构(包括Intel Knight Landing)上提供了涉及张量收缩和3D模板计算的实质性加速。
A simple optimization strategy for the computation of 3D finite-differencing kernels on many-cores architectures is proposed. The 3D finite-differencing computation is split direction-by-direction and exploits two level of parallelism: in-core vectorization and multi-threads shared-memory parallelization. The main application of this method is to accelerate the high-order stencil computations in numerical relativity codes. Our proposed method provides substantial speedup in computations involving tensor contractions and 3D stencil calculations on different processor microarchitectures, including Intel Knight Landing.
DOI: 10.1137/17m1135578
发表时间: 2017-04
期刊: SIAM J. Sci. Comput.
影响因子: --
作者:
Jianyu Huang;D. Matthews;R. Geijn
通讯作者: Jianyu Huang;D. Matthews;R. Geijn
DOI: 10.1103/physrevd.77.024027
发表时间: 2006-10
期刊: Physical Review D
影响因子: 5
作者:
B. Bruegmann;José A. González;M. Hannam;S. Husa;U. Sperhake;W. Tichy
通讯作者: B. Bruegmann;José A. González;M. Hannam;S. Husa;U. Sperhake;W. Tichy
DOI: 10.1103/physrevlett.119.161101
发表时间: 2017-10-16
影响因子: 8.6
作者:
Abbott, B. P.;Abbott, R.;Zweizig, J.
通讯作者: Zweizig, J.