Memory energy consumption analyzer for video encoder hardware architectures

Abstract

The motion estimation stage requires high number of memory accesses, causing high-energy consumption in the video coding process. This results in lower battery lifetime on mobile devices. Thus, solutions to reduce the external memory bandwidth in video coding systems must be used. This work proposes a memory energy consumption analyzer, which estimates the energy consumption related to memory accesses of video encoder systems. This analyzer enables the evaluation of different schemes with data reuse, reference frame compression and memory hierarchy, which are the most used techniques for memory bandwidth reduction and its associated energy consumption. This analyzer is implemented in SystemC, which allows system modeling in a simple and fast way. As a case study of the tool, the developed analyzer was used to evaluate a solution joining a reference frame compressor and a Level C data reuse scheme. The energy consumption results of the evaluated scheme present reduction on both write and read memory operations, reaching a total memory energy consumption reduction of 97.91% when compared to original video encoder without any technique for memory access reduction.