Abstract:
Various aspects of the present disclosure include methods, components and wireless devices configured to determine appropriate generalized system-wide thermal management policies and settings in wireless devices depending upon whether communication activities are driving or otherwise causing thermal conditions. In various aspects, a processor may determine workload characteristics and select and apply an appropriate thermal management policy/solution (or thermal configuration, settings etc.) based on the determine workload characteristics. The processor may determine workload characteristics based upon data from two or more temperature sensors within the wireless device. The processor may select a generalized system-wide thermal management policy suitable for operating when communication activities (e.g., 5G communication activities) are generating so much heat that CPU-centric thermal management policies are in appropriate.
Abstract:
Modem thermal management may include a state machine monitoring a temperature associated with a modem, setting a mode in response to detection of a change in the temperature with respect to a threshold, and applying a set of one or more thermal mitigation actions associated with a current state of the state machine. The state machine may set a timer in response to detection of the change in temperature and then transition from the current state to another state in response to expiration of the timer. The monitored temperature may be a junction temperature or a skin temperature.
Abstract:
Various embodiments of methods and systems for idle state optimization in a portable computing device (“PCD”) are disclosed. An exemplary method includes comparing an aggregate power consumption level for all processing cores in the PCD to a power budget and, if there is available headroom in the power budget, transitioning cores operating in a first idle state to a different idle state. In doing so, the latency value associated with bringing the transitioned cores out of an idle state and into an active state, should the need arise, may be reduced. The result is that user experience and QoS may be improved as an otherwise idle core in an idle state with a long latency time may be better positioned to quickly transition to an active state and process a workload.