Mission
The implementation of some of the computational problems requires an architecture dependent algorithmic way of thinking. Our experience shows that the implementation of a given problem could be more efficient if not only one selected architecture was used, but more so called heterogeneous computational systems were applied simultaneously. Adequate partitioning and choosing the right architecture might be critical and non-trivial during the heterogeneous implementation of problem classes or an algorithm. Still, we believe that in future hardwares having more and more processors, the solution of these implementation problems will be needed for efficient algorithm development and their realization.
The direction of development is unequivocal. In the future, all the PCs will have many-thousand processor systems. For their development, there is a huge need to port earlier codes, today as well as in the forthcoming period. In the automation of software development, the new technology advocated by our company fundamentally changes the future of computer science. Our mission is summarized in the following items:
• To enable all existing softwares to use GPU in a simple way
• To make GPU programming as easy as possible for software developers
• To realize the automation of hybrid compiling, where the implementation would use the advantages of CPU and GPU simultaneously
• To make all this available free of charge for all developers on an efficient and widespread C++ development tool
• To give all possible help using the most modern online educational systems, whose cutting edge technology is being developed by the Pázmány Péter Catholic University which supporting our company
• To create a successful company that would be the most important connection between the software and hardware companies developing and manufacturing many-processor systems
This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 767912.