CATWALK - A Quick Development Path for Performance Models

CATWALK - 性能模型的快速开发路径

• 批准号: 230954187
• 负责人: Professor Dr. Christian Bischof
• 金额: --
• 依托单位: Departement Informatik
• 依托单位国家: 德国
• 项目类别: Priority Programmes
• 财政年份: 2012
• 资助国家: 德国
• 起止时间: 2011-12-31 至 2015-12-31
• 项目状态: 已结题
• 来源: https://gepris.dfg.de/gepris/projekt/230954187?language=en
• 关键词: CATWALK; Quick; Development; Path; Performance

The cost of running applications at exascale will be tremendous. Reducing runtime and energy consumption of a code to a minimum is therefore crucial. Moreover, many existing applications suffer from inherent scalability limitations that will prevent them from running at exascale in the first place. Current tuning practices, which rely on diagnostic experiments, are insufficient because (i) they detect scalability problems too late in the development process when major effort has already been invested into an inadequate solution and (ii) they incur the extra cost of potentially numerous full-scale experiments. Analytical performance models, in contrast, allow application developers to address performance issues already during the design or prototyping phase. Unfortunately, the difficulties of creating such models combined with the lack of appropriate tool support still render performance modeling an esoteric discipline mastered only by a relatively small community of experts. The objective of this project is therefore to provide a flexible set of tools to support key activities of the performance modeling process, making this powerful methodology accessible to a wider audience of HPC application developers. The tool suite will be used to study and help improve the scalability of applications from life sciences, fluid dynamics, and particle physics.

以亿级运行应用程序的成本将是巨大的。因此，将代码的运行时间和能耗降至最低至关重要。此外，许多现有的应用程序都受到固有的可伸缩性限制，这将阻止它们首先在exascale上运行。目前的调优实践，依赖于诊断实验，是不够的，因为（i）他们发现可扩展性问题太晚，在开发过程中，当主要的努力已经投入到一个不充分的解决方案，（ii）他们招致潜在的许多全面的实验的额外成本。相比之下，分析性能模型允许应用程序开发人员在设计或原型设计阶段就解决性能问题。不幸的是，创建这种模型的困难加上缺乏适当的工具支持，仍然使性能建模成为一门深奥的学科，只有相对较小的专家群体才能掌握。因此，本项目的目标是提供一套灵活的工具，以支持性能建模过程的关键活动，使这种强大的方法可供更广泛的HPC应用程序开发人员使用。该工具套件将用于研究并帮助提高生命科学、流体动力学和粒子物理学应用的可扩展性。