Accelerating High-Dimensional Integration Using Lattice Rules on GPUs

Accelerating High-Dimensional Integration Using Lattice Rules on GPUs
复制标题

在 GPU 上使用格子规则加速高维集成

DOI:
10.1109/csci.2017.276
复制
发表时间:
2017
期刊:
2017 International Conference on Computational Science and Computational Intelligence (CSCI)
影响因子:
--
通讯作者:
E. Doncker
E. Doncker
中科院分区:
--
文献类型:
--
作者:
Ahmed H. Almulihi;E. Doncker

文献摘要

参考文献

被引文献

相似文献

多重积分的格型规则产生了一个强大的方法来近似各种函数类的高维积分。使用从格规则的快速逐分量(CBC)构造获得的生成器向量,我们将秩1格用于GPU加速器上的数值积分。我们展示了一些多元积分的准确性和效率的结果,并与Monte Carlo积分相同的功能也在GPU上获得的结果进行比较。格规则实现了高精度和出色的加速比。
Lattice rules for multiple integration yield a powerful method to approximate high-dimensional integrals for various function classes. Using generator vectors obtained from the fast component-by-component (CBC) construction of lattice rules, we incorporated rank-1 lattices for numerical integration on GPU accelerators. We show accuracy and efficiency results for a number of multivariate integrals, and compare with results obtained by Monte Carlo integration for the same functions also on GPU. The lattice rules achieve high accuracy and excellent speedups.
DOI: 10.12694/scpe.v11i4.663
发表时间: 2010
期刊: Scalable Comput. Pract. Exp.
影响因子: --
作者:
Jie Cheng
通讯作者: Jie Cheng