Efficient Implementation of Nested-Loop Multimedia Algorithms

Abstract

A novel dependence graph representation called the multiple-order dependence graph for nested-loop formulated multimedia signal processing algorithms is proposed. It allows a concise representation of an entire family of dependence graphs. This powerful representation facilitates the development of innovative implementation approach for nested-loop formulated multimedia algorithms such as motion estimation, matrix-matrix product, 2D linear transform, and others. In particular, algebraic linear mapping (assignment and scheduling) methodology can be applied to implement such algorithms on an array of simple-processing elements. The feasibility of this new approach is demonstrated in three major target architectures: application-specific integrated circuit (ASIC), field programmable gate array (FPGA), and a programmable clustered VLIW processor.