Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe

T: Fachverband Teilchenphysik

T 44: Data, AI, Computing 4 (workflow)

T 44.2: Vortrag

Dienstag, 5. März 2024, 16:15–16:30, Geb. 30.34: LTI

Integration of the Goettingen HPC resources Emmy to the WLCG Tier-2 grid computing environment of GoeGrid and performance results of the ATLAS jobs — •Saidev Polisetty, Arnulf Quadt, Daniel Schindler, and Sebastian Wozniewski — II. Physikalisches Institut, Georg-August-Universitaet Goettingen

For the upcoming Run 4 of the LHC, there is a necessity to increase the computing resources for simulation, reconstruction and analysis in terms of storage and computing power. In this context, the German community is preparing to integrate the National High Performance Computing (NHR) resources and make them usable within the WLCG under the FIDIUM project.

At Goettingen campus, there is both, a WLCG Tier-2 site (GoeGrid) and a large HPC EMMY cluster by NHR and the North German Supercomputing Alliance (HLRN). In this project, the integration is done by virtually extending the GoeGrid batch system with containers turning the HPC nodes into virtual nodes with own partitionable job scheduling to run the ATLAS jobs. Their performance is studied for quantitative analysis and optimisation of the environment running the jobs. Results and the performance is discussed in this talk.

Keywords: HPC; WLCG; Grid; Computing