Abstract
Scheduling is one of the most important tasks in high-level and system synthesis. Traditional time-constrained scheduling algorithms try to meet performance target while minimizing hardware cost and energy consumption rate assuming that power supply is unlimited. As energy-efficiency is getting important, we should consider using the concept of energy harvesting for portable applications. We propose a timeconstrained task scheduling algorithm for portable system synthesis. The targeted system is powered by an energy harvesting device together with a rechargeable battery. We show that there exists trade-off among hardware computational resource, energy harvester, and battery. We formulate the problem as an integer linear programming (ILP) one. Experimental results show that it can find optimal solutions for practical-sized problem instances. With battery, we can minimize the total hardware cost more than that without battery.