Ilin M. Information technology of ecological monitoring for high performance computing systems

In dissertation was developed information technology for monitoring of anomalous processes of atmosphere pollution by the groups of chemically-interacting pollutants. Information technology is based on hybrid high performance systems with Nvidia CUDA accelerators, and offers higher performance and less memory usage. Software complex “Monitoring” was developed based on proposed information technology. Method of parallel computing implementation of models that arise in the study of atmospheric pollution processes is developed. It allows effective application of hybrid computing systems based on Nvidia CUDA graphics accelerators and is based on the use of the modified D4 decomposition method, that uses 30% less random access memory. The method of parametric identification of the sources of pollution functions in models of abnormal atmospheric pollution processes based on the UNI-DEM model, taking into account abnormal self-cleaning processes, which is distinguished by high speed due to the use of developed direct and hybrid parallel methods of solving large-scale SLAE and allows shortening the simulation time in a 10- 12 times compared to the implementation without the use of GPGPU. The information technology of monitoring the abnormal processes of atmospheric pollution by chemically interacting impurities, based on Nvidia CUDA hybrid high performance computing systems, is developed, and is characterized by increased efficiency and lower requirements to RAM. The proposed information technology was used to solve practical problems of "Ukrekotekhinvest LLC" and in the educational process of the National Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute".