Date Added: Oct 2010
In this paper, the authors present a new technique for reducing the energy consumption of a multi-task system by sharing its Scratch-Pad Memory (SPM) space among the tasks. With this technique, tasks can interfere by using common areas of the SPM. However, this paper requires to update these areas during context switches, which involves considerable overheads. Hence, an integer linear programming formulation is used at compile time for finding the best assignment of memory objects to the SPM and their respective locations inside it. Experiments show that the technique achieves up to 85% energy reduction with 8Kb of SPM and surpasses other sharing approaches.