webinars

Eviden Center for Excellence in Performance Programming (CEPP)The rise of exascale, LLM and machine learning poses challenges in terms of managing large datasets, hardware evolution and power consumption. Optimizing code for diverse systems and recruiting AI data...

Beyond Speed: Integrating Energy Considerations into I/O Performance Analysis for SKA CodesAstronomical data processing codes for the analysis of massive observations are inherently demanding in terms of computational resources and input/output (I/O) operations. The...

Accelerating Baseline-Dependent Averaging in Gridding with GPUsThe new-generation radio telescope SKA will be the most sensitive ever built, allowing surveys over larger fields of view and producing petabytes of data daily. Since not all the generated data can be...

Towards efficient, RFI-robust interferometric imaging: dynamic antenna switching, EM models and algorithmsModern radio telescopes like the Square Kilometre Array (SKA) offer exceptional sensitivity, but this comes with major challenges in terms of processing massive...

Prototyping the SKA pipeline with Karabo, from raw data generation to final data products.In the context of the development of the SKA radio telescope, it is becoming essential to have robust and modular pipelines capable of simulating, calibrating and imaging radio...

Towards better I/O resource usage in HPCIn HPC systems, I/O resources are not traditionally arbitrated in the same way as compute resources (nodes, CPUs, etc). However, I/O resources have an important impact on performance, and this impact depends on application...