Skip to Main Content
Integrating multiple cores into a processor increases the heat density significantly, which often constrains the maximum performance of such a processor. There have been many techniques using dynamic voltage and frequency scaling (DVFS) and thread migration to manipulate heat dissipation in thermally-constrained multi-core processors. However, most of them were analyzed and applied individually for optimizing the performance of the multi-core processors while their computational cost for the optimization was not studied well. In this paper, we argue that a coherent organization of two techniques can maximize the performance of the multi-core processors with the least performance overheads associated with the thermal management techniques. Furthermore, we also propose an efficient method to optimize the performance of thermal-constrained multi-core processors. According to our experiment, we achieved 5% throughput improvement with negligible computation cost.
Date of Conference: 22-24 March 2010