This paper describes the impact of our system level data transfer and storage exploration methodology -- as proposed in our mboxATOMIUM approach -- in a software development context on embedded processors. The effectiveness of this methodology on power reduction is demonstrated by optimizing a public domain MPEG-2 video decoder program for an embedded processor. The result is an average factor 3.7 gained on simulated power reduction for the memory transfers. These transfers represent the dominant power consumption source. The presented optimizations can also improve the overall performance of the MPEG-2 algorithm due to the better data caching behaviour. For MPEG-2 additional code transformations were performed to reduce the cycle overhead initially induced by the optimization. 1 Introduction Nowadays, people see the need for a portable multimedia device capable of handling complex and advanced data communication. Text and speech services are already available. But extensions towards ...