Transactions on Computational Collective Intelligence X

Transactions on Computational Collective Intelligence X
复制标题

计算集体智能 X 汇刊

DOI:
10.1007/978-3-642-38496-7_10
复制
发表时间:
2013
期刊:
--
影响因子:
--
通讯作者:
Garba M
Garba M
中科院分区:
--
文献类型:
--
作者:
Garba M

文献摘要

被引文献

相似文献

作为数值分析和计算科学中的一个经常性问题,特征向量和特征值的确定通常使用高性能的线性代数库。本文探讨了在图形处理器(GPU)上实现多个大型厄米特特征向量和特征值系统的高性能例程。我们报告的性能提高了两个数量级以上的originalroutines与NVIDIA Tesla C2050 GPU,提供了一个有效的数量级增加的单位细胞大小或模拟分辨率的非弹性中子散射(INS)建模从原子模拟。
As a recurrent problem in numerical analysis and computational science, eigenvector and eigenvalue determination usually employs high-performance linear algebra libraries. This paper explores the implementation of high-performance routines for the solution of multiple large Hermitian eigenvector and eigenvalue systems on a Graphics Processing Unit (GPU). We report a performance increase of up to two orders of magnitude over the originalroutines with a NVIDIA Tesla C2050 GPU, providing an effective order of magnitude increase in unit cell size or simulated resolution for Inelastic Neutron Scattering (INS) modelling from atomistic simulations.