On the Role of Robust Staging Services for Extreme-Scale Workflows
DescriptionAs science applications target extreme scales (high-performance and distributed computing) environments systems, dramatically increasing data volumes and associated data management/IO costs are leading to in-situ approaches to coupling and data processing and analysis. The resulting staging-based in-situ workflows are increasingly leveraging data-staging services. As a result, robust and scalable staging services that target emerging architectures with deep and complex memory hierarchies have become essential. In this talk, I will present experiences with the design and implementation of such robust and scalable staging services for in-situ workflows as part of the DataSpaces project.
TimeMonday, June 2618:00 - 18:30 CEST
Computer Science, Machine Learning, and Applied Mathematics