DMA ST1 Seminar: Leverating the Jupyter ecosystem for cross-platform deployment of scientific applications

by Frank Schluenzen (IT (IT Benutzerservice))

Monday 26 Feb 2024, 11:00 → 12:00 Europe/Berlin

Meeting ID: 696 0421 6260 Magic word: 034898 (ZOOM)

The DMA ST1 seminar series features topics and tools around the full data lifecycle of the DMA communities.

The DMA ST1 seminar usually consists of a ~30 minute presentation, followed by a Q&A discussion session.

Attendance is open to all interested participants.

 

Leveraging the Jupyter ecosystem for cross-platform deployment of scientific applications.

Frank Schlünzen (DESY)

 

 

Abstract:  
Jupyter notebooks are great tools to mitigate the complexities of (heterogeneous) HPC systems, like the Maxwell HPC cluster at DESY. The Maxwell cluster serves the computational needs of all user facilities on campus, as well as a wide variety of applications ranging from plasma accelerators to quantum chemistry. Combining the Jupyter ecosystem with application frameworks like streamlit allows to provide application environments across computational platforms, tailored to the needs also of less experienced users. 
On this basis we have been implementing for example Jupyter-driven remote desktops, open data frontends, user-friendly dashboards to compose or monitor batch-jobs, and visualizations for data catalogues like SciCat. The implementations are accompanied by visual tools for resource utilization and CO2 footprints suitable both for users as well as admins.

maxwell-dma-st1-green.pdf