On the field of parallel programing has seen arrive a new big player in the last 10 years. The GPU's has taken a relevant importance on scientific computing because offers high performance computing, low cost and simplicity of implementation. However one of the most important challenges it the program languages used for this devices. The effort for recoding algorithms designed for CPUs is an important problem. In this article we review three of principal frameworks for programming CUDA devices compared with the new directives introduced on the OpenMP 4 standard resolving the Jacobi iterative method