Difference between revisions of "FedCloudLOFAR"
Latest revision as of 16:32, 7 May 2015
|Overview||For users||For resource providers||Infrastructure status||Site-specific configuration||Architecture|
|Federated Cloud Communities menu:||Home •||Production use cases •||Under development use cases •||Closed use cases •||High level tools use cases|
- Status: Test & Integration
- Start Date: 06/10/2014
- End Date: -
- EGI.eu contact: Diego Scardaci / firstname.lastname@example.org, Enol Fernandez / email@example.com
- External contact: José Sabater Montez / firstname.lastname@example.org, Daniele Lezzi / email@example.com
This project aims to integrate calibration, analysis and modelling pipelines of radio-astronomy data into a cloud infrastructure. It is developed jointly by users of the [www.lofar.org LOFAR] radio-telescope and members of the AMIGA4GAS project.
A cloud infrastructure like the EGI Federated Cloud provides:
- flexibility to develop innovative processing pipelines;
- a powerful frame for parallel processing pipelines and workflows;
- the advantage of the elastic on-demand resource consumption.
Development of a calibration pipeline for LOFAR data. The calibration of data from the radio-interferometer LOFAR requires a high capacity of storage and parallel processing. The software -relatively difficult to install and under heavy development- will be first installed into a custom image. Several configurations of virtual clusters will be used to run and profile different calibration pipelines. LOFAR users would be able to use, at a later stage, the best configuration and pipeline for the calibration of the data.
The community would like to adopt the COMPSs high-level tool to port the application on the EGI Federated Cloud.
- Storage: about 3 TB for the tests.
- Memory: possibility to launch instances with as much memory as possible. The amount of available memory will limit the size and resolution of the final LOFAR images. A full resolution image of 20000x20000 pixels would require about 64 GB of memory.
- Number of instances: At least three instances, one control node and two working nodes.
- Number of CPUs: At least 2 per instance.