A Combination of Evolutionary Algorithm and Mathematical Programming for the 3D Thermal-Aware Floorplanning Problem

(1)Heat removal and power density distribution delivery have become two major reliability concerns in 3D stacked technology. Additionally, the placement of Through-Silicon-Vias (TSVs) for connecting different layers is one of the key issues in 3D technology. Although a few recent works have considered thermal-aware placement of cores in chip multiprocessor architectures, the concepts of 3D and TSVs have not been conveniently incorporated. Therefore, new suitable exploration methods for the 3D thermal-aware floorplaning problem need to be developed. In this paper we analyze the benefits of two different exploration techniques for the floorplanning problem: Multi-Objective Genetic Algorithm (MOGA) and a Mixed Integer Linear Program (MILP). We present a novel algorithm that uses MILP to minimize average temperature in the 3D chip, whereas uses MOGA to insert TSVs, connecting the layers while the total wire length is minimized. Our experiments with two different 3D chips show that our algorithm achieves 10% reduction in the maximum temperature and thermal gradient.