Sie verwenden einen Browser, in dem JavaScript deaktiviert ist. Dadurch wird verhindert, dass Sie die volle Funktionalität dieser Webseite nutzen können. Zur Navigation müssen Sie daher die Sitemap nutzen.

You are currently using a browser with deactivated JavaScript. There you can't use all the features of this website. In order to navigate the site, please use the Sitemap .

Analyzing Performance Variation of Task Schedulers with TaskInsight

Authors:: Ceballos, G. , Grass, T. , Hugo, A. , Black-Schaffer, D.
Journal:: Parallel Computing
Date:: 2018
DOI:: 10.1016/j.parco.2018.02.003
hsb:: RWTH-2021-00686
Language:: English
Abstract:: Recent scheduling heuristics for task-based applications have managed to improve performance by taking into account memory-related properties such as data locality and cache sharing. However, there is still a general lack of tools that can provide insights into why, and where, different schedulers result in different memory behavior, and how this is related to the applications’ performance.

To address this we present TaskInsight, a technique to characterize the memory behavior of different task schedulers through the analysis of data reuse across tasks. TaskInsight provides high-level, quantitative information that can be correlated with tasks’ performance variation over time to understand data reuse through the caches due to scheduling choices. TaskInsight is useful to diagnose and identify which scheduling decisions affected performance, when were they taken, and why the performance changed, both in single and multi-threaded executions.

We demonstrate how TaskInsight can diagnose cases where poor scheduling caused over 40% difference on average (and up to 7x slowdowns) across the Montblanc benchmarks due to changes in the tasks’ data reuse through the private and shared caches. This flexible insight is key for optimization in many contexts, including data locality, throughput, memory footprint or even energy efficiency.
Download:: BibTeX