Operational Numerical Weather Prediction systems based on Linux cluster architectures

The progress in weather forecast and atmospheric science has been always closely linked to the improvement of computing technology. In order to have more accurate weather forecasts and climate predictions, more powerful computing resources are needed, in addition to more complex and better-performing numerical models. To overcome such a large computing request, powerful workstations or massive parallel systems have been used. In the last few years, parallel architectures, based on the Linux operating system, have been introduced and became popular, representing real"high performance-low cost" systems. In this work the Linux cluster experience achieved at the Laboratory for Meteorology and Environmental Analysis (LaMMA-CNR-IBIMET) is described and tips and performances analysed.