Enabling future parallel applications
Our main objective is to enable the usage of this technology to optimize resources management by assigning adequate resources to the applications and dealing with non-functional aspects; facilitate access to resources, thanks to frontends which hide the complexity of HPC; create and adapt new tools able to use the parallel computation capabilities, especially in the field of parallel (real-time) data analytics; and research on new ways to perform parallel computation.
We are working towards the development of technologies of Exascale Computation for optimal resources management which enables the use of highly scalable applications avoiding bottlenecks while managing heterogeneous systems with accelerators; easing the use of HPC for different domains with tools for large and complex data analytics and parallelizing data processing to ease execution of experiments with a transparent access to HPC; and researching on future technologies such as New Quantum Computing and Future Neuromorphic Computing solutions.
We specialize in solving current issues when using HPC, and enabling the use of future exascale systems for smart orchestration of applications looking at several aspects (profiles, data movement, resources status, etc.), deriving some tasks to Cloud HPC resources whenever necessary; provision of front-ends for easy access and usage of HPC resources, integrating data management tools, experimentation tools, etc; and the development of the parallel Complex Event Processing engine for real-time data analysis, also available for low-power computing devices.