Inter-Pixel Filtrering of Digital Images with CUDA from NVIDIA

The process of filtering digital images represented by complex Cartesian allows to use the available onedimensional (1D) elements (interpixel); however, having those additional 1D elements increases both the volume of data and the time for processing them. The time reduction strategy based on a parallel computing scheme on the number of available central processing units (CPUs) does not consider additional computing resources such as those offered by general purpose graphics processing units (GPUs) of NVIDIA. Parallel computing possibilities provided by the NVIDIA GPUs were explored and, based on them, a computational scheme for the digital image Cartesian complexes filtering task was proposed using the application program interface Open Computing Language (OpenCL) provided for NVIDIA corporation GPUs. The results assessment was established by comparing the response times of the proposed solution compared to those obtained using only CPU resources. The obtained implementation is an alternative to parallelization of the filtering task, which provides response times up to 14 times faster than those obtained with the implementation that uses only the CPU resource. The NVIDIA multicore GPU significantly improves the parallelism, which can be used in conjunction with the available multicore CPU computing capacity, balancing the workload between these two computing powers using both simultaneously.