In this paper we describe GPU and its computing. GPU (Graphics Processing Unit) is an extremely multi-threaded architecture and then is broadly used for graphical and now nongraphical computations. The main advantage of GPUs is their capability to perform significantly more floating point operations (FLOPs) per unit time than a CPU. GPU computing increases hardware capabilities and improves programmability. By giving a good price or performance benefit, core-GPU can be used as the best alternative and complementary solution to multi-core servers. In fact, to perform network coding simultaneously, multi core CPUs and many-core GPUs can be used. It is also used in media streaming servers where hundreds of peers are served concurrently. GPU computing is the use of a GPU (graphics processing unit) together with a CPU to accelerate generalpurpose scientific and engineering applications. GPU was first manufactured by NVIDIA. CPUs have few cores which is used for serial processing and GPUs have thousands of smaller cores which are more efficient, designed for parallel processing. So, CPU + GPU is a powerful combination. Whenever the code is run on the machine, CPU runs serial portion and GPU runs parallel portion. GPU is used for general purpose applications like arithmetic and it is also used for gaming.