Predict and act: dynamic thermal management for multi-core processors

In this paper, we propose a proactive dynamic thermal management scheme for chip multiprocessors that run multi-threaded workloads. We introduce a new predictor that utilizes the band-limited property of the temperature frequency spectrum. A big advantage of our predictor is that it does not require the costly training phase like ARMA [7]. Our thermal management scheme incorporates tem-perature prediction information and runtime workload characteri-zation to perform efficient thermally aware scheduling. Our results show that applying our algorithm considerably improves the aver-age system temperature, hottest core temperature, product MTTF and performance by 6 oC, 8 oC, 41 % and 72 % respectively