Early experiences in application level I/O tracing on blue gene systems
Early experiences in application level I/O tracing on blue gene systems
复制标题
蓝色基因系统应用程序级 I/O 跟踪的早期经验
DOI：
--
复制
发表时间：
2008
期刊：
影响因子：
--
通讯作者：
Hao Yu
中科院分区：
文献类型：
--
作者：
Seetharami R. Seelam;I. Chung;Ding;H. Wen;Hao Yu
在当今大规模并行处理（MPP）超级计算机上，了解应用程序的I/O性能既可以指导可扩展的应用程序开发并调整其性能，越来越重要。绩效分析工具通常可以启用这两个关键步骤，以获取MPP系统中数千个处理器的性能数据。为此，我们介绍了应用程序级别I/O跟踪库的设计，实现和早期体验，以及用于分析和优化蓝色基因（BG）MPP系统I/O性能的相应工具。这项工作是BG系统IBM UPC工具包的一部分。据我们所知，这是BG系统上可用的第一个全面的应用程序级I/O监视，播放和优化工具。对流行的NPB BTIO基准测试的初步实验表明，该工具对于促进详细的I/O性能分析非常有用。
On todays massively parallel processing (MPP) supercomputers, it is increasingly important to understand I/O performance of an application both to guide scalable application development and to tune its performance. These two critical steps are often enabled by performance analysis tools to obtain performance data on thousands of processors in an MPP system. To this end, we present the design, implementation, and early experiences of an application level I/O tracing library and the corresponding tool for analyzing and optimizing I/O performance on Blue Gene (BG) MPP systems. This effort was a part of IBM UPC Toolkit for BG systems. To our knowledge, this is the first comprehensive application-level I/O monitoring, playback, and optimizing tool available on BG systems. The preliminary experiments on popular NPB BTIO benchmark show that the tool is much useful on facilitating detailed I/O performance analysis.