Memory hierarchy optimization of multimedia applications on programmable embedded cores

Data memory hierarchy optimization and partitioning for a widely used multimedia application kernel known as the hierarchical motion estimation algorithm is undertaken, with the use of global loop and data-reuse transformations for three different embedded processor architecture models. Exhaustive exploration of the obtained results clarifies the effect of the transformations on power, area, and performance and also indicates a relation between the complexity of the application and the power savings obtained by this strategy. Furthermore, the significant contribution of the instruction memory even after the application of performance optimizations to the total power budget becomes evident and a methodology is introduced in order to reduce this component.