Abstract: Systems and methods of overheat detection provide for generating a control signal on a die containing a processor based on an internal temperature of the processor and a control temperature threshold. It can be determined whether to generate a warning temperature event on the die based on a behavior of the control signal. In one embodiment, the warning temperature event provides for initiation of an automated data saving process, which reduces the abruptness of conventional warning temperature shutdowns. Other embodiments provide the user the option of saving his or her work before a shutdown temperature threshold is reached.

Abstract: Methods, apparatuses, and systems for managing power of a processing unit are described herein. Some embodiments include determining a voltage variation of a subset of current components of a current consumed by a processing unit. Other embodiments include detecting architectural events on a processing core of the processing unit and instituting various actions to reduce an input rate of instructions to the core. Other embodiments may be described and claimed.

Abstract: Techniques to manage operational parameters for a processor are described. For instance, a method includes monitoring performance values representing physical characteristics for multiple components of a computing platform, and managing a performance level for a processor based on the performance values and one or more operational parameters for the processor. The operational parameters may include one or more transitory operational parameters that cause the processor to temporarily exceed operational parameters set by a thermal design power limit. Other embodiments are described and claimed.

Abstract: Systems and methods of overheat detection provide for generating a control signal on a die containing a processor based on an internal temperature of the processor and a control temperature threshold. It can be determined whether to generate a warning temperature event on the die based on a behavior of the control signal. In one embodiment, the warning temperature event provides for initiation of an automated data saving process, which reduces the abruptness of conventional warning temperature shutdowns. Other embodiments provide the user the option of saving his or her work before a shutdown temperature threshold is reached.

Abstract: Provided is an approach to saving active power through lowering a supply voltage when operating temperature goes up, while substantially maintaining operating performance.

Abstract: Systems and methods of power management provide for issuing a power saving message from a processor toward a controller and using the controller to conduct a power saving activity in response to the power saving message. In one embodiment, the power saving message is issued by de-asserting a bus arbitration signal and the power saving activity can include disabling one or more input buffers of the controller.

Abstract: For some embodiments, skin temperature of a computer system may be determined by using a network of thermistors and conductors. A thermistor may be positioned at an intersection of two conductors. Current may be supplied to a first conductor. Voltage may be measured at a second conductor. Resistance information associated with the thermistor may be determined. Skin temperature may be determined from the resistance information.

Abstract: Systems and methods of managing operating points provide for determining the number of active cores in a plurality of processor cores. A maximum operating point is selected for at least one of the active cores based on the number of active cores. In one embodiment, the number of active cores is determined by monitoring an ACPI processor power state signal of each of the plurality of cores.

Abstract: Systems and methods of power management provide for issuing a power saving message from a processor toward a controller and using the controller to conduct a power saving activity in response to the power saving message. In one embodiment, the power saving message is issued by de-asserting a bus arbitration signal and the power saving activity can include disabling one or more input buffers of the controller.

Abstract: A technique to dynamically maintain the thermal levels of a plurality of cores of a processing system by interleave core hopping with throttling techniques. The interleaving logic may transfer execution of threads from a hot core to a cold if core hopping is applicable. Core hopping may be applicable if there exist a cold core to which the execution of threads can be assigned to from a hot core and if the rate of occurrence of core hopping is within an allowable rate value. The interleaving logic may apply throttling techniques if core hopping is not applicable. The throttling techniques may throttle the throttling parameters, which may comprise voltage, frequency, and micro-architecture throttling parameters provided to the hot core if the core hopping is not applicable.

Abstract: A package includes a thermal solution to thermal couple to a semiconductor device to remove heat generated by the semiconductor device, and a device to electrically isolate at least a portion of the thermal solution from the semiconductor device. The package also includes a biasing device to apply a voltage to a body of the semiconductor device.

Abstract: Systems and methods of managing operating points provide for determining the number of active cores in a plurality of processor cores. A maximum operating point is selected for at least one of the active cores based on the number of active cores. In one embodiment, the number of active cores is determined by monitoring an ACPI processor power state signal of each of the plurality of cores.

Abstract: Systems and methods of thermal management provide for dynamically the upper and lower operating points of a throttled device such as a processor. In one embodiment, it is determined that the temperature of the processor is below a threshold and moving the upper operating point and the lower operating point toward one another.

Abstract: Briefly, some embodiments of the invention may provide devices, systems and methods for thermal control. For example, a method in accordance with an embodiment of the invention may include modifying an operational parameter of a processor based on a temperature of a heat sink associated with the processor.

Abstract: Briefly, a processor and a method to control a power consumption of the processor are presented. The method may include: counting a micro-architecture event of a component of the processor, estimating the power consumption value of the processor based on a weighted value of the counted micro-architecture event and filtering the weighted value of the counted micro-architecture event.

Abstract: Systems and methods of managing power provide for applying a voltage from a voltage regulator to a component of a computing system and reducing the voltage based on a power saving parameter that is dedicated to the component. The reduction can be in conjunction with the entry of the component into a low power state such as a standby state or an off state, where the power saving parameter defines a voltage such as a minimum operating voltage or minimum sustainable voltage for the component, respectively. In one embodiment, the component is a central processing unit.

Abstract: Briefly, a processor and a method of estimating an active energy consumption of two or more cores of a processor based on dispatching micro operations to one or more execution units of the processor.

Abstract: Briefly, a processor and a method of setting a performance state of a turbo mode enabled processor. The method includes determining an effective performance state over a predetermined time period, calculating a target performance state based on core utilization and the effective performance state over the predetermined time period and setting the turbo mode enabled processor to a turbo mode performance state.

Abstract: Briefly, a method to control a temperature of a processor and a processor that includes a thermal controller to control a temperature. The thermal controller may decrease the power level of the processor to a first power level for a first predetermined time period and may vary the power of the processor to a second power level for a second predetermined time period.

Abstract: For some embodiments, skin temperature of a computer system may be determined by using a network of thermistors and conductors. A thermistor may be positioned at an intersection of two conductors. Current may be supplied to a first conductor. Voltage may be measured at a second conductor. Resistance information associated with the thermistor may be determined. Skin temperature may be determined from the resistance information.