Video processing applications and especially video compression algorithms are becoming more and more complex. The computation power required to simulate systems such as in MPEG 1-2 applications is much higher than the one available even on supercomputers, since it can easily exceed tens of giga operations per second.
The MOVIE approach is the result of a collaboration between the parallel VLSI architecture group at Irisa and the CCETT video architecture lab, aiming at the use of SIMD arrays of processing elements for rapid experimentation of video compression algorithms.
The solution is based on a building block approach, that is hardware and software elements tailored to real-time image coding application domain.