Abstract: A method of thermal mitigation in a device having a plurality of non-real-time processing units (PUs) and a plurality of real-time PUs, including connecting each of the plurality of real-time PUs and the plurality of non-real-time PUs to a first power supply, and performing thermal mitigation. Performing thermal mitigation includes disconnecting each of the plurality of non-real-time PUs except one of the plurality of non-real-time PUs from the first power supply resulting in an active non-real-time PU, and connecting a second power supply that derives power from the first power supply to the active non-real-time PU, wherein a voltage supplied by the second power supply is less than a voltage supplied by the first power supply.

Abstract: A method of thermal mitigation in a device having a plurality of non-real-time processing units (PUs) and a plurality of real-time PUs, including connecting each of the plurality of real-time PUs and the plurality of non-real-time PUs to a first power supply, and performing thermal mitigation. Performing thermal mitigation includes disconnecting each of the plurality of non-real-time PUs except one of the plurality of non-real-time PUs from the first power supply resulting in an active non-real-time PU, and connecting a second power supply that derives power from the first power supply to the active non-real-time PU, wherein a voltage supplied by the second power supply is less than a voltage supplied by the first power supply.

Abstract: Systems and methods are disclosed for providing micro-idle memory power management. One embodiment of a method comprises receiving and storing an exit latency vote from each of a plurality of memory subsystems on a system on chip electrically coupled to a system memory. In response to a micro-idle memory state in which each of the memory subsystems are idle, a minimum exit latency value from the plurality of exit latency votes is determined. One of a plurality of system memory modes is selected which has a micro-idle sleep time that meets the minimum exit latency value while minimizing system memory power consumption. The selected system memory mode is initiated.

Abstract: A method of thermal mitigation in a device having a plurality of non-real-time processing units (PUs) and a plurality of real-time PUs, including connecting each of the plurality of real-time PUs and the plurality of non-real-time PUs to a first power supply, and performing thermal mitigation. Performing thermal mitigation includes disconnecting each of the plurality of non-real-time PUs except one of the plurality of non-real-time PUs from the first power supply resulting in an active non-real-time PU, and connecting a second power supply that derives power from the first power supply to the active non-real-time PU, wherein a voltage supplied by the second power supply is less than a voltage supplied by the first power supply.

Abstract: Methods, systems, and circuits for preserving state information during power saving operations are disclosed. One example embodiment includes a circuit having a processing core, where the processing core includes logic processing circuits as well as circuits (e.g., flip-flops registers) that are used to store state information in the processing core. The logic processing circuits have power connections to a power rail that are subject to a switch, which can disconnect the power connections from the power rail. The circuits that are used to store state information have different power connections that are subject to a different switch. Therefore, the logic processing circuits and the state information circuits can be separately power-collapsed.

Abstract: Methods, systems, and circuits for preserving state information during power saving operations are disclosed. One example embodiment includes a circuit having a processing core, where the processing core includes logic processing circuits as well as circuits (e.g., flip-flops registers) that are used to store state information in the processing core. The logic processing circuits have power connections to a power rail that are subject to a switch, which can disconnect the power connections from the power rail. The circuits that are used to store state information have different power connections that are subject to a different switch. Therefore, the logic processing circuits and the state information circuits can be separately power-collapsed.

Abstract: A method of thermal mitigation in a device having a plurality of non-real-time processing units (PUs) and a plurality of real-time PUs, including connecting each of the plurality of real-time PUs and the plurality of non-real-time PUs to a first power supply, and performing thermal mitigation. Performing thermal mitigation includes disconnecting each of the plurality of non-real-time PUs except one of the plurality of non-real-time PUs from the first power supply resulting in an active non-real-time PU, and connecting a second power supply that derives power from the first power supply to the active non-real-time PU, wherein a voltage supplied by the second power supply is less than a voltage supplied by the first power supply.