High-Performance Computing on Mathematical Coprocessors and Graphics Accelerators Using Python

This paper considers the use of Python modules for solving resource-intensive tasks on a high-performance computer cluster. It shows the application of the cluster for solving the most complex problems in the field of nuclear physics. It also demonstrates methods of high-performance computing based on mathematical coprocessors and graphics accelerators on the example of multiplication of real matrices. The use of the Python algorithmic language in high-performance computing in many cases significantly expands the convenience of creating, debugging and testing program code.