Automatic detection of parallel applications computation phases
Automatic detection of parallel applications computation phases
复制标题
自动检测并行应用程序计算阶段
DOI：
--
复制
发表时间：
2009
期刊：
影响因子：
--
通讯作者：
Jesús Labarta
中科院分区：
文献类型：
--
作者：
Juan Gonzalez;Judit Giménez;Jesús Labarta
分析并行程序已经变得越来越困难，由于大量的信息收集在大型系统上。已经提出使用聚类技术来分析应用程序。然而，虽然以前的作品的目标是集中在识别具有相似特征的进程组，我们的目标是在应用程序的行为更细的粒度。在本文中，我们提出了一个工具，自动表征不同的计算区域之间的通信原语在消息传递应用程序。这项研究表明，一些聚类算法，这可能是适用于粗粒度不再是足够的，在这个级别。基于密度的聚类算法应用于现代处理器提供的性能计数器在这种情况下更合适。该工具自动生成应用程序结构的准确显示以及检测到的每个区域的广泛指标的详细报告。
Analyzing parallel programs has become increasingly difficult due to the immense amount of information collected on large systems. The use of clustering techniques has been proposed to analyze applications. However, while the objective of previous works is focused on identifying groups of processes with similar characteristics, we target a much finer granularity in the application behavior. In this paper, we present a tool that automatically characterizes the different computation regions between communication primitives in message-passing applications. This study shows how some of the clustering algorithms which may be applicable at a coarse grain are no longer adequate at this level. Density-based clustering algorithms applied to the performance counters offered by modern processors are more appropriate in this context. This tool automatically generates accurate displays of the structure of the application as well as detailed reports on a broad range of metrics for each individual region detected.