The EU H2020 ESCAPE project ( brings together numerical weather prediction (NWP), climate and high-performance computing (HPC) communities to develop world-class, extreme-scale computing capabilities for European operational NWP and future climate models. One of the challenges is to execute complex state-of-the-art models of the atmosphere within tight production schedules.

PSNC organises training to introduce young scientists into NWP relevant topics as well as modern computational physics and energy efficient computing. During this two-day training, undergraduates will get familiar with ESCAPE dwarfs – fundamental algorithmic building blocks – and recognise why HPC and energy-efficient computations are important. The presented material will be well balanced between theoretical introduction and practical exercises, given by professional NWP and HPC staff. For those unable to travel, remote and live access will be given. This training is a great opportunity to establish professional links with academic staff across Europe for future cooperation.


Initial agenda:

Monday, 27th February 2017 - NWP day
• Welcome, introduction to the ESCAPE
• Introduction to NWP - lectures
• Working on NWP dwarfs (MPDATA on unstructured grids with Atlas) - exercises


Tuesday, 28th February 2017 - HPC day

• Introduction to HPC, energy-efficiency, roofline model - lecture
• Working on NWP dwarfs (MPDATA on structured grids) - exercises

Location: PSNC, ul. Jana Pawłą II 10, Poznań
More info:

Agnieszka Musialska

Related projects: