Following the Blind Seer - Creating Better Performance Models Using Less Information

Following the Blind Seer - Creating Better Performance Models Using Less Information
复制标题

跟随盲目的先知 - 使用更少的信息创建更好的性能模型

DOI:
10.1007/978-3-319-64203-1_8
复制
发表时间:
2017
期刊:
影响因子:
--
通讯作者:
Felix Wolf
Felix Wolf
中科院分区:
--
文献类型:
--
作者:
Patrick Reisert;Alexandru Calotoiu;Sergei Shudler;Felix Wolf

文献摘要

参考文献

被引文献

相似文献

性能模型提供了对更高规模的应用程序行为的洞察,对于发现性能错误和调优系统非常有用。Extra-P是一种自动化性能建模工具,它使用统计方法从少量的性能测量中自动生成模型,这些模型可用于在没有测量的情况下预测性能。然而,当前版本需要手动预配置搜索空间,这可能不适合手头的问题。此外,数据中的噪声通常会导致模型显示出比实际情况更差的行为。在本文中,我们提出了一种新的模型生成算法,解决了上述两个问题:搜索空间的建立和自动细化的需求,和一个规模无关的误差度量告诉何时停止细化过程,以及模型是否足够忠实地反映了数据表现出的行为。这使得Extra-P更易于使用,同时也使其能够产生更准确的结果。使用以前的案例研究的数据,我们表明,平均相对预测误差从46%下降到13%。
Offering insights into the behavior of applications at higher scale, performance models are useful for finding performance bugs and tuning the system. Extra-P, a tool for automated performance modeling, uses statistical methods to automatically generate, from a small number of performance measurements, models that can be used to predict performance where no measurements are available. However, the current version requires the manual pre-configuration of a search space, which might turn out to be unsuitable for the problem at hand. Furthermore, noise in the data often leads to models that indicate a worse behavior than there actually is. In this paper, we propose a new model-generation algorithm that solves both of the above problems: The search space is built and automatically refined on demand, and a scale-independent error metric tells both when to stop the refinement process and whether a model reflects faithfully enough the behavior the data exhibits. This makes Extra-P easier to use, while also allowing it to produce more accurate results. Using data from previous case studies, we show that the mean relative prediction error decreases from 46% to 13%.
使用自动化性能建模来查找复杂代码中的可扩展性错误
DOI: 10.1145/2503210.2503277
发表时间: 2013
期刊: 2013 SC - International Conference for High Performance Computing, Networking, Storage and Analysis (SC)
影响因子: --
作者:
Calotoiu;Hoefler
通讯作者: Hoefler
实践中的等效率:配置和了解基于任务的应用程序的性能
DOI: 10.1145/3018743.3018770
发表时间: 2017
期刊: Proceedings of the 22nd ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming
影响因子: --
作者:
Shudler;Sergei;Calotoiu;Alexandru;Hoefler;Torsten
通讯作者: Torsten
ESTIMA:推断内存应用程序的可扩展性
DOI: --
发表时间: 2016
期刊: ACM SIGPLAN Symposium on Principles & Practice of Parallel Programming
影响因子: --
作者:
Georgios Chatzopoulos;A. Dragojevic;R. Guerraoui
通讯作者: R. Guerraoui
MILC 晶格 QCD 应用的性能建模和比较分析 su3_rmd
DOI: 10.1109/ccgrid.2012.123
发表时间: 2012
期刊: 2012 12th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (ccgrid 2012)
影响因子: --
作者:
G. Bauer;S. Gottlieb;T. Hoefler
通讯作者: T. Hoefler
用于理解应用程序扩展问题的 MPI 实现的性能模型
DOI: 10.1007/978-3-642-15646-5_3
发表时间: 2010
影响因子: 7.2
作者:
T. Hoefler;W. Gropp;R. Thakur;J. Träff
通讯作者: J. Träff