Event-Based Triggering and Management of Scientific Workflow Ensembles

Event-Based Triggering and Management of Scientific Workflow Ensembles
复制标题

科学工作流程集成的基于事件的触发和管理

DOI:
--
复制
发表时间:
2018
期刊:
影响因子:
--
通讯作者:
E. Deelman
E. Deelman
中科院分区:
--
文献类型:
--
作者:
Suraj Pandey;K. Vahi;Rafael Ferreira da Silva;E. Deelman

文献摘要

被引文献

相似文献

随着科学界为极端规模计算做准备,大数据分析正在成为科学过程的重要组成部分,从而实现新的见解和发现。这张海报描述了我们如何利用工作流集成来建模下一代计算工作流,其中长时间运行的模拟作业定期生成需要在高性能计算资源上并行分析的数据。在这项工作中,我们开发了对开源Pegasus Ensemble Manager服务的扩展,以支持基于事件的触发,可用于将工作流添加到现有的运行集合中。
As the scientific community prepares for extreme-scale computing, Big Data analytics are becoming an essential part of the scientific process enabling new insights and discoveries. This poster describes how we utilized workflow ensembles to model the next generation of computational workflows, where a long-running simulation job periodically generates data that needs to be analyzed concurrently on high-performance computing resources. In this work, we developed extensions to the open source Pegasus Ensemble Manager service to enable support for event-based triggering that can be used to add workflows to an existing running ensemble.