Skip to Main Content
A distributed embedded system consists of different processing elements (PEs) communicating via communication links. PEs have various power characteristics and in turn, have different thermal profiles. With new technologies, processor power density is dramatically increased which results in high temperature. This alarming trend underscores the importance of temperature management methods in system design. The majority of proposed techniques to address thermal issues, impose severe penalties on performance and reliability. We present Schedule Swapping, a technique for reducing peak temperature in distributed embedded systems while satisfying real-time constraints. Contrary to many other approaches, our proposed technique does not use slack time for reducing power dissipation but leaves it to be used by recovery mechanisms (rollback re-execution). The more slack time, the more the number of possible recoveries and the more reliability. We also introduce a simple yet effective scheme to ensure that all the deadlines will be met if our technique is used. This scheme also determines the order in which tasks should transmit their data in Schedule Swapping. Our experimental results show up to 18.1°C reduction in peak temperature. On average, Schedule Swapping achieves the peak temperature reduction of 11.13°C.
Date of Conference: 11-13 Dec. 2010