An ILP-based scheduling scheme for energy efficient high performance datapath synthesis

Abstract

In this paper, we describe an integer linear programming (ILP) based datapath scheduling algorithm which uses both multiple supply voltages and dynamic frequency clocking for power optimization. The scheduling technique assumes the number and type of different functional units as resource constraints and minimizes the energy delay product (EDP). The energy savings directly comes from the use of multiple supply voltages and the performance improvement from dynamic frequency clocking. The algorithm has been applied to various high level synthesis benchmark circuits under different resource constraints. The experimental results show that under various resource constraints using two supply voltage levels (5.0 V, 3.3 V), the average energy reduction is 55% and the average EDP reduction is 13%.