Opencl based image processing library and kernel fusion on embedded systems

Embedded computing is an increasingly improving area. With every new generation, the computation capacity of the mobile devices is improving. Contemporary mobile devices include a graphical processing unit (GPU) in order to offer better use interface in terms of graphics. As mobile devices require more performance to cope with computation-intensive applications, such as image processing, recently some embedded GPUs also included the support for OpenCL that allows the use of computation capacity of embedded GPUs for general purpose computing. Exploiting GPGPU on embedded platforms is also more efficient in terms of energy efficiency. In this thesis, we present a new OpenCL-based image processing library, which is specifically designed to run on an embedded platform. Our results show that the functions of TRABZ-10 show 7x speedup on embedded platform over the functions of OpenCV on average.