Application description
RADICAL-Cybertools is an abstractions-based suite of well-defined capabilities that are architected for scalable, interoperable and sustainable approaches to support science on a range of high-performance and distributed computing systems.
It currently consists of three components:
RADICAL-SAGA: the infrastructure access layer of the RADICAL Cybertools stack. It provides a homogeneous programming interface to the majority of production HPC queuing systems, Grid- and Cloud-services. RADICAL-SAGA supports XSDE and OSG resources as well as academic and commercial cloud computing platforms.
RADICAL-Pilot: a tool that uses pilots in order to achieve the scalable execution of large numbers of tasks. A pilot is a job submitted to a machine in order to acquire exclusive use of a chunk of its resources. Once the pilot becomes active, it can execute the tasks specified by the user. Instead of having each task waiting on a machine to be executed, the user only has to wait once with a pilot! RADICAL-Pilot allows users to specify resources in the form of pilots and their tasks separately so the user can wait once and run everything;
Ensemble Toolkit: a toolkit which provides a simple way to develop applications comprised of multiple tasks and which adhere to pre-defined patterns. The tool comes predefined with common execution patterns so users can quickly adapt the toolkit to their needs; it is possible to define more complex execution patterns. By building upon RADICAL-Pilot, the Ensemble Toolkit can take advantage of flexible and scalable resource management techniques.
User Resources
Related articles
- Design and Performance Characterization of RADICAL-Pilot on Leadership-class Platforms. Andre Merzky, Matteo Turilli, Mikhail Titov, Aymen Al-Saadi, Shantenu Jha.
- IMPECCABLE: Integrated Modeling PipelinE for COVID Cure by Assessing Better LEads. Aymen AlSaadi, et al.
- High-throughput Binding Affinity Calculations at Extreme Scales. Jumana Dakka, Matteo Turilli, David W Wright, Stefan J Zasada, Vivek Balasubramanian, Shunzhou Wan, Peter V Coveney and Shantenu Jha. BMC Bioinformatics 2018 19(Suppl 18):482 and Computational Approaches for Cancer Workshop at SuperComputing (SC 2017).
- Concurrent and Adaptive Extreme Scale Binding Free Energy Calculations. Jumana Dakka, Kristof Farkas-Pall, Matteo Turilli, David W Wright, Peter V Coveney and Shantenu Jha. 2018 IEEE 14th International Conference on e-Science (e-Science).