Using Directed Variance to Identify Meaningful Views in Call-Path Performance Profiles

Tom Vierjahn, Marc-André Hermanns, B. Mohr, Matthias S. Müller, T. Kuhlen, B. Hentschel
{"title":"Using Directed Variance to Identify Meaningful Views in Call-Path Performance Profiles","authors":"Tom Vierjahn, Marc-André Hermanns, B. Mohr, Matthias S. Müller, T. Kuhlen, B. Hentschel","doi":"10.1109/VPA.2016.7","DOIUrl":null,"url":null,"abstract":"Understanding the performance behaviour of massively parallel high-performance computing (HPC) applications based on call-path performance profiles is a time-consuming task. In this paper, we introduce the concept of directed variance in order to help analysts find performance bottlenecks in massive performance data and in the end optimize the application. According to HPC experts' requirements, our technique automatically detects severe parts in the data that expose large variation in an application's performance behaviour across system resources. Previously known variations are effectively filtered out. Analysts are thus guided through a reduced search space towards regions of interest for detailed examination in a 3D visualization. We demonstrate the effectiveness of our approach using performance data of common benchmark codes as well as from actively developed production codes.","PeriodicalId":166523,"journal":{"name":"2016 Third Workshop on Visual Performance Analysis (VPA)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2016-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2016 Third Workshop on Visual Performance Analysis (VPA)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/VPA.2016.7","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2

Abstract

Understanding the performance behaviour of massively parallel high-performance computing (HPC) applications based on call-path performance profiles is a time-consuming task. In this paper, we introduce the concept of directed variance in order to help analysts find performance bottlenecks in massive performance data and in the end optimize the application. According to HPC experts' requirements, our technique automatically detects severe parts in the data that expose large variation in an application's performance behaviour across system resources. Previously known variations are effectively filtered out. Analysts are thus guided through a reduced search space towards regions of interest for detailed examination in a 3D visualization. We demonstrate the effectiveness of our approach using performance data of common benchmark codes as well as from actively developed production codes.
使用有向方差来识别调用路径性能配置文件中有意义的视图
理解基于调用路径性能概要的大规模并行高性能计算(HPC)应用程序的性能行为是一项耗时的任务。在本文中,我们引入了有向方差的概念,以帮助分析人员在大量性能数据中找到性能瓶颈,并最终优化应用程序。根据高性能计算专家的要求,我们的技术自动检测数据中的严重部分,这些部分暴露了应用程序跨系统资源的性能行为的巨大变化。以前已知的变化被有效地过滤掉。因此,分析人员可以通过减少的搜索空间,在3D可视化中对感兴趣的区域进行详细检查。我们使用通用基准代码的性能数据以及积极开发的生产代码来演示我们方法的有效性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信