Applying Periodic Thermal Management on Hard Real-Time Systems to Minimize Peak Temperature

Abstract

Due to growing power density, on-chip temperature increases rapidly, which has hampered the reliability and performance of modern real-time systems. This paper studies how to minimize the peak temperature of real-time systems under hard real-time constraints with periodic thermal management. A closed-form representation of the peak temperature for such a periodic scheme is derived to tackle this problem. Based on this closed form and the arrival curve model, one offline approach and one online approach are proposed to minimize the peak temperature for a given event stream. The offline one does thermal optimization in design phase and introduces negligible runtime overhead. The online one computes dynamic power-control schemes which are adaptive to actual event arrivals and execution states. We conduct experiments on a real single-core processor and compare our approaches to two existing works. The temperature results measured from a physical thermal sensor demonstrate that the achieved maximal and average temperature reductions are 5[Formula: see text]K and 2.6[Formula: see text]K, respectively.