Serpens for Kepler
Energy-efficient Scalable Algorithms for Weather Prediction at Exascale
The main objective of the ESCAPE project is to develop the next generation platform for numerical weather prediction. The ESCAPE aims at developing a holistic understating of energy-efficiency for extreme-scale applications using heterogeneous architectures, accelerators and special compute units. The three key reasons why this project will provide the necessary means to take a huge step forward in weather and climate modelling as well as interdisciplinary research on energy-efficient high-performance computing are:
- Defining and encapsulating the fundamental algorithmic building blocks ('Weather & Climate Dwarfs') underlying weather and climate services. This is the prerequisite for any subsequent co-design, optimization, and adaptation efforts,
- Combining ground-breaking frontier research on algorithm development for use in extreme-scale, high-performance computing applications, minimizing time- and cost-to-solution,
- Synthesizing the complementary skills of all project partners: leading European regional forecasting consortia, excellent university research and experienced high-performance computing centres, two world-leading hardware companies, and one European start-up SME, providing entirely new knowledge and technology to the field.
In the ESCAPE project PSNC is responsible for providing performance models of the weather and climate dwarfs, and performance simulator to predict extreme-scale applications efficiency and energy consumption.
Scheduled finish date: 2018-09-30
The EU H2020 ESCAPE project (www.hpc-escape.eu) 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.
From 18th to 20th October 2016 the 1st ESCAPE Dissemination and Training Workshop on “Towards Energy-efficient Scalable Algorithms for Weather- and Climate Prediction: Status and Prospects” took place at the Konventum Conference Centre (Elsinore/ Helsingor, Denmark). In total, around 50 researchers and students attended the event from universities, research institutions and companies giving 24 oral presentations.
The EU-funded project ESCAPE is looking at improving code efficiency for both weather and climate modelling. ESCAPE is organising its 1st Dissemination and Training workshop between the 18th and 20th October 2016 in Elsinore, Denmark.