Computational reproducibility of scientific workflows at extreme scales
Computational reproducibility of scientific workflows at extreme scales
复制标题
极端规模的科学工作流程的计算再现性
DOI：
10.1177/1094342019839124
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
K. K. van Dam
中科院分区：
文献类型：
--
作者：
Line C. Pouchard;Sterling Baldwin;Todd O. Elsethagen;S. Jha;B. Raju;E. Stephan;L. Tang;K. K. van Dam
我们提出一种提高重现性的方法，该方法包括获取并关联起源特征和性能指标。我们讨论了两个用例：能源百亿亿次地球系统模型（E3SM——先前为ACME）中结果的科学重现性以及高性能计算平台上分子动力学工作流的性能重现性。为了获取并持久保存这些工作流的起源和性能数据，我们设计并开发了Chimbuko和ProvEn框架。Chimbuko获取起源信息，并能够进行详细的单一工作流性能分析。ProvEn是一个混合的、可查询的系统，用于在工作流性能分析活动中存储和分析多次运行的起源和性能指标。从Chimbuko输出的工作流起源和性能数据可以在一个动态的、多层可视化中呈现，为感兴趣的区域提供概览和放大功能。摄入到ProvEn中的起源和相关性能数据是可查询的，并可用于重现运行。我们基于起源的方法凸显了在提取信息方面的挑战以及所收集信息中的差距。它对所获取的起源数据类型没有特定要求，因此我们的工具可用于探索科学结果的重现性以及性能的重现性。
We propose an approach for improved reproducibility that includes capturing and relating provenance characteristics and performance metrics. We discuss two use cases: scientific reproducibility of results in the Energy Exascale Earth System Model (E3SM—previously ACME) and performance reproducibility in molecular dynamics workflows on HPC platforms. To capture and persist the provenance and performance data of these workflows, we have designed and developed the Chimbuko and ProvEn frameworks. Chimbuko captures provenance and enables detailed single workflow performance analysis. ProvEn is a hybrid, queryable system for storing and analyzing the provenance and performance metrics of multiple runs in workflow performance analysis campaigns. Workflow provenance and performance data output from Chimbuko can be visualized in a dynamic, multilevel visualization providing overview and zoom-in capabilities for areas of interest. Provenance and related performance data ingested into ProvEn is queryable and can be used to reproduce runs. Our provenance-based approach highlights challenges in extracting information and gaps in the information collected. It is agnostic to the type of provenance data it captures so that both the reproducibility of scientific results and that of performance can be explored with our tools.