Optimizing Performance of Stencil Code with SPL Conqueror

Optimizing Performance of Stencil Code with SPL Conqueror
复制标题

使用 SPL Conqueror 优化模板代码的性能

DOI:
--
复制
发表时间:
2014
期刊:
影响因子:
--
通讯作者:
H. Köstler
H. Köstler
中科院分区:
--
文献类型:
--
作者:
A. Grebhahn;Norbert Siegmund;S. Apel;S. Kuckuk;Christian Schmitt;H. Köstler

文献摘要

参考文献

被引文献

相似文献

在结构网格上数值求解椭圆型偏微分方程组的一种标准技术是通过Nite差分离散,然后应用一种特殊的几何多重网格求解器。不幸的是,多网格组件和参数的最佳选择是具有挑战性和平台依赖性的,尤其是在领域知识不完整的情况下。自动调优是一种可行的选择,但面临着大的拥塞空间和功能交互的问题。为了改善这一现状,我们探索了最近关于生产线充分性优化的工作是否可以应用到模板代码领域。特别是,我们在一系列实验中扩展和使用了与域无关的工具SPL征服器来预测两种几何多重网格码的性能最优凝聚:一个使用HIPA cc框架的程序和一个称为HSMGP的评估原型。对于HIPA CC,当测量57.5%的聚集时,我们可以预测所有聚集的性能,平均准确率为98%,
A standard technique to numerically solve elliptic partial differential equations on structured grids is to discretize them via nite dierences and then to apply an ecient geometric multi-grid solver. Unfortunately, nding the optimal choice of multi-grid components and parameters is challenging and platform dependent, especially, in cases where domain knowledge is incomplete. Auto-tuning is a viable alternative, but faces the problem of large conguration spaces and feature interactions. To improve the state of the art, we explore whether recent work on conguration optimization in product lines can be applied to the stencil-code domain. In particular, we extend and use the domain-independent tool SPL Conqueror in a series of experiments to predict the performance-optimal congurations of two geometric multigrid codes: a program using the HIPA cc framework and an evaluation prototype called HSMGP. For HIPA cc , we can predict the performance of all congurations with an accuracy of 98 %, on average, when measuring 57.5 % of the congurations,
DOI: 10.1109/icse.2012.6227196
发表时间: 2012-06
期刊: 2012 34th International Conference on Software Engineering (ICSE)
影响因子: --
作者:
Norbert Siegmund;Sergiy S. Kolesnikov;Christian Kästner;S. Apel;D. Batory;Marko Rosenmüller;G. Saake
通讯作者: Norbert Siegmund;Sergiy S. Kolesnikov;Christian Kästner;S. Apel;D. Batory;Marko Rosenmüller;G. Saake
可变性感知性能预测:一种统计学习方法
DOI: 10.1109/ase.2013.6693089
发表时间: 2013
期刊: 2013 28th IEEE/ACM International Conference on Automated Software Engineering (ASE)
影响因子: --
作者:
J. Guo;K. Czarnecki;S. Apel;N. Siegmund;A. Wasowski
通讯作者: A. Wasowski