This spring Météo-France, the national meteorological service for France and its overseas territories, turned on its ‘new’ supercomputer, a long planned upgrade delivered by Bull/Atos that doubled the performance of its predecessor (already on the Top500 list), significantly reduced power consumption, and is allowing Météo-France to increase the resolutions of its weather and climate models. It’s also one of the first such machines to use Intel’s new Xeon E5 v4 (Broadwell) processor according to Alain Beuraud, HPC Project Manager, Météo-France.
Not surprisingly, high performance computing (HPC) is a strategic element in Météo-France’s operations, critical to remaining on par with peers in the rest of Europe, the U.S., Canada, China, Korea, India, Japan, and Australia. “This is a 24/7 business,” said Beuraud, “We need reliability, accuracy and speed. There’s no room for delays in delivering our reports: after 15 minutes, the result is considered missing. Our work simply cannot be done without very high levels of computational power.”
By way of background, Météo-France provides meteorological solutions worldwide and its subsidiary MFI (Météo-France International) is recognized as a leading turnkey project integrator in the field of meteorology. Météo-France is an agency under the Ministry of Environment, Energy and Sea and has a budget of more than $480 million. It’s also a member of the European Centre for Medium-Range Weather Forecasts (ECMWF), Eumetsat, the operator of European weather satellites, and Eumetnet, the network of European meteorological services. Météo-France contributes to the World meteorological Organization (WMO) and the UN Intergovernmental Panel on Climate Change (IPCC).
In 2014, Météo-France installed two Bull systems with each containing 1008 Bull DLC B710 compute nodes, each equipped with two 12-core Intel Xeon processors E5-2600 v2 product family. “This [latest] extension of Météo-France’s supercomputer was planned from the start of the project, so that it took the Bull/Atos teams only a few weeks to replace the previous Bull blades – more than 500 of them – with new generation Bull B720 Direct Liquid Cooling blades, add several hundred blades to reach a total of 1800 compute nodes, and integrate the complete configuration within the FDR InfiniBand interconnect network,” said Damien Déclat, Head of HPC Global PreSales & Delivery at Bull/Atos.
“With the new Intel Xeon E5-2698 v4 processors, this configuration increases the available computing power by a factor of four with a sustained performance in excess of 2 PFLOPS. [Because it is] based on Bull’s energy-saving Direct Liquid Cooling technology, the FLOPS/Watt ratio is improved by a factor of 2.5. This early integration allowed Météo-France to (re)start its operations on the Bull Prolix supercomputer in early March, making it one of the first production sites worldwide equipped with Intel Xeon E5 v4 processors.”
The goal of weather and climate simulations, of course, is to provide accurate forecasts and early warning systems to aid in natural disaster prevention, better protection of property and well-being of citizens, as well as decision-making support for weather-sensitive sectors such as agriculture, marine, aviation, tourism, oil and gas, and other industries. Long-term weather analysis and climate models evaluate global climate changes to help adapt national development programs for the future.
Producing Météo-France’s weather forecasts and climate analysis is the responsibility of dozens of physicists, atmospheric chemists, hydrologists and oceanographers. Underpinning their research is a series of powerful, proprietary computer models fed by millions of data points around the world.
“Weather simulation is an extremely complex calculation that depends on numerous computer simulations of atmospheric conditions. Forecast quality depends on several factors including the number and quality of the observation points where data is collected, the methods for assimilating that data into models, the accuracy of the model itself, and the available computing power,” said Beuraud.
Météo-France’s supercomputers are used both for weather forecasting (around 80% of the resources) and the remainder for climate modeling. Noteably, the performance of supercomputers used by Météo-France from 1992 through 2016 grew from 2 GFLOPS to 5 PFLOPS. Indeed, more computational power is an ongoing need to produce ever more precise meteorological information for the French territory in Europe, not least because more precision requires increasing the number of data points to be analyzed.
With the new system, Beuraud expects to be able to extend use of Météo-France’s high-resolution model (AROME) to France’s our overseas territories. Until now, AROME 1.3 km mesh could only be run on France and Western Europe. “We will also install an “Ensemble AROME local-area forecast” to better anticipate severe events both in terms of location, and in terms of timing of the event.”
“In addition, we will also experiment with very high resolutions for the AROME model (less than 1 km) for some specific locations (around the largest French airports, for example),” stated Beuraud. For its operational and research model, the Météo-France team intensively uses many Intel tools, particularly the Fortran, C, C++ compilers, OpenMP, and Intel MPI libraries. Many developers use the Intel VTune Amplifier to optimize the performances of their application. The following figures show examples of weather modeling and precipitation mapping done using the AROME model running on the Bull supercomputer.
In the figure shown below: Example of improvement in precipitation forecast in the South of France, created using the AROME model (2.5 km mesh in 2014 -, 1.3 km mesh in 2015). Courtesy of Météo-France.
“As far as climate modeling is concerned,” said Beuraud, “we will run a new release of our climate model within the CMIP6 exercise (it will contribute to the sixth IPCC report, which should be published around 2020). The atmospheric part of the model – whose name is ARPEGE CLIMAT – will have a new physics, and will use higher horizontal (91 levels against 31 previously) and vertical (50 km against 150 previously) resolution. The resolution of the ocean model will also be improved (25 km instead of 100 in horizontal, 75 levels instead of 42 in vertical).”
“A very important part of our HPC developments rely on national or international cooperation. For example, our global model ARPEGE (used both for weather forecasting and climate modeling) is built in cooperation with ECMWF, this cooperation is more than 25 years old. The NEMO model that we use in our climate model comes from a large consortium, and has been developed with European cooperation between universities, research and meteorological centers.”
The adoption of the Bull/Atos supercomputers enabled Météo-France to move from vector to scalar technology and achieve much higher levels of parallel processing power for minimal total cost of ownership.
“Most importantly, the new configuration will enable us to enhance the AROME model in line with our government contract. We have moved our existing models across to the new configuration and can now develop them. But it is also helping us to deliver new and exciting services both to the French government and to our numerous clients. We are developing models for airports, for example, that will improve our ability to predict and provide useful analysis of fog conditions. It has opened up a whole new range of possibilities and cements our position at the heart of international weather and climate research,” said Beuraud.
“However, we continually need to improve the resolution of climate models and weather forecasts which requires increased computational power and supercomputers of the future will help us meet this need. As we continue our work, we need supercomputers that can allow us to process petabytes of data in an efficient manner. Météo-France will continue to utilize state-of-the-art hardware and find ways to optimize its code. We will also have to experiment with our code on new architecture, so we intend to make tests on Intel Xeon Phi coprocessors. We have our own development team and we dedicate more than 10 percent of our annual revenue to finance research and development programs to best meet our future needs.”
Linda Barney is the founder and owner of Barney and Associates, a technical/marketing writing, training and web design firm in Beaverton, OR.