Performance Maximization via Frequency Oscillation on Temperature Constrained Multi-core Processors

Abstract

While multi-core architectures, by exploring the thread/process level parallelism, help to lower down the power/thermal barrier for single core architectures, power/thermal issues are still the primary limiting factors to achieve high computing performance. In this paper, we study the problem of how to maximize the computing performance of multi-core platforms without violating their peak temperature constraint. As different cores may exhibit different thermal behaviors, we propose to run each core with different working frequencies and develop a schedule based on two novel concepts, i.e. the step-up schedule and the m-Oscillating schedule, for multi-core platforms. We formally prove that the proposed schedule can guarantee the peak temperature constraint for a given multi-core platform. Compared with the traditional exhaustive search-based approach, our approach can reduce the computation time by orders of magnitude and improve the throughput up to 89%, with an average improvement of 11%.