Response-time minimization in soft real-time systems with temperature-affected reliability constraint

With the continuous shrinking of technology size, chip temperature, and consequently the temperature-affected error vulnerability have been increased. To control these issues, some temperature and reliability constraints have been added, which has led to confined performance. This paper proposes a proactive approach using thermal throttling to guarantee the failure rate of running tasks while minimizing the corresponding response-times. The task's jobs are executed according to the as soon as possible (ASAP) policy and the temperature of the processor is controlled based on the vulnerability factor of the running task. The optimality of the method in the case of first-come first-served (FCFS) task scheduling policy has also been proven. Simulation results reveal that the proposed method can reduce the job miss ratio and response-times, respectively, for at least 17% and 16% on the average.