Abstract: A dynamic power management system includes an operating system (OS) that causes a processor to operate in one of multiple run states that have different performance and/or power dissipation levels. The OS selects the run state in response to processor information (e.g., processor load) being monitored by the OS. The OS can predict future states of the processor information based on sampled processor information. The OS can take an average of the predicted and actual samples for comparison with a threshold to select a run state. The OS can track the number of consecutive saturated samples that occur during a selected window of samples. The OS can predict future processor information samples based on the number of consecutive saturated samples.

Abstract: Methods and apparatuses to manage working states of a data processing system. At least one embodiment of the present invention includes a data processing system with one or more sensors (e.g., physical sensors such as tachometer and thermistors, and logical sensors such as CPU load) for fine grain control of one or more components (e.g., processor, fan, hard drive, optical drive) of the system for working conditions that balance various goals (e.g., user preferences, performance, power consumption, thermal constraints, acoustic noise). In one example, the clock frequency and core voltage for a processor are actively managed to balance performance and power consumption (heat generation) without a significant latency. In one example, the speed of a cooling fan is actively managed to balance cooling effort and noise (and/or power consumption).