CUDA is a parallel computing platform API, which extended the usage of GPU (which was otherwise used only for graphics processing) for general purpose processing. But the scope is limited to CUDA-enabled GPUs manufactured by NVIDIA only and does not work on different GPUs by other manufacturers. CUDA platform is designed to work with C, C++ and Fortran programming languages hence easier to code straight to GPU. Compatible with most standard operating systems.
e.g. Identify hidden plaque in arteries, Analyze air traffic flow and Visualize molecules etc...
OpenGL is a graphics library, which provides set of API that makes use of GPU (hardware-accelerated) to render graphics faster - focus is specific to rendering on GPUs. Supported on essentially every GPU. Required advanced skills in graphics programming. It is language and platform independent.
e.g. CAD, Virtual reality, Flight simulation and Video games etc...
