Up-to-date graphical devices allow not only video games but may be used for scientific computations. They are heavily used in deep learning and artificial intelligence. With their superior performance it is not surprising that many of the fastest computers in the world contain these cards. This course offers basic knowledges on high performance computing on graphical devices. The course focuses on programming graphic cards with Compute Unified Device Architecture (CUDA) which is trained and deepened in examples and exercises.
- Comprehension in SIMD programming model (single instruction multiple data) and relation between hardware architecture and performance
- evaluation of parallel algorithms with regard to their performance
- theoretical and practical application of CUDA