H.264/AVC inter prediction for heterogeneous computing systems

Abstract

H.264/AVC is the latest standard for video compression and is a significant advance, but at the expense of increasing computing needs. Recently, the progress of GPUs has attracted considerable attention because they are able to offer practical and acceptable solutions for speeding up graphic and non-graphic applications. In this paper, we present an implementation of H.264/AVC Motion Estimation running on an NVIDIA GTX285 using CUDA. The algorithm is divided into three steps, all of which need to be executed sequentially but each one is exploited following a highly parallel procedure by using the GPU. The execution time of the proposed motion estimation algorithm is 53 times faster and it reduces the energy consumption by a factor of 9 compared with the JM reference encoder using a single CPU core.