A memory energy consumption analysis of Motion Estimation algorithms using data reuse in video coding systems

The number of accesses Motion Estimation requires to write and read large amount of data from external memory is the major issue in video coding systems, since, besides being the performance bottleneck of these systems, it impacts directly on the energy consumption. To attenuate this problem, there are solutions that involve data reuse strategies using on-chip SRAM memories. The main advantage of these solutions is the fact that they can achieve high external memory bandwidth reduction on reading operations. This paper presents an evaluation of the impact of the memory accesses and energy consumption considering a Level C+ data reuse scheme for four different fast algorithms and the Full Search algorithm. Our results show that the energy consumption for the traditional method, when no memory bandwidth reduction strategy is used, becomes impractical for most of the considered Motion Estimation algorithms. However, when the data reuse scheme Level C+ is used, the energy consumption related to the memory suffers a great reduction, making it possible for fast algorithms to be used in real-time video coding systems. The reduction reached is up to 97% when considering fast Motion Estimation algorithms.