Abstract:
Various embodiments of methods and systems for adaptive thermal management techniques implemented in a portable computing device (“PCD”) are disclosed. Notably, in many PCDs, temperature thresholds associated with various components in the PCD such as, but not limited to, die junction temperatures, package on package (“PoP”) memory temperatures and the “touch temperature” of the external surfaces of the device itself limits the extent to which the performance capabilities of the PCD can be exploited. It is an advantage of the various embodiments of methods and systems for adaptive thermal management that, when a temperature threshold is violated, the performance of the PCD is sacrificed only as much and for as long as necessary to clear the violation before authorizing the thermally aggressive processing component(s) to return to a maximum operating power.
Abstract:
Thermal management in a portable computing device differentiates between a temperature increase caused by a steady workload and a temperature increase caused by an instantaneous workload. If it is determined that a detected temperature increase is caused by a steady workload, then a configuration of thermal parameters is applied that optimizes thermal performance for a steady workload. If it is determined that a temperature increase is caused by an instantaneous workload increase, then a configuration of thermal parameters is applied that optimizes thermal performance for an instantaneous workload.
Abstract:
A method and system for adjusting bandwidth within a portable computing device based on danger signals monitored from one on more elements of the portable computing device are disclosed. A danger level of an unacceptable deadline miss (“UDM”) element of the portable computing device may be determined with a danger level sensor within the UDM element. Next, a quality of service (“QoS”) controller may adjust a magnitude for one or more danger levels received based on the UDM element type that generated the danger level and based on a potential fault condition type associated with the particular danger level. The danger levels received from one UDM element may be mapped to at least one of another UDM element and a non-UDM element. A quality of service policy for each UDM element and non-UDM element may be mapped in accordance with the danger levels.