摘要:
A method and apparatus includes a multi-processor apparatus including a plurality of integrated circuit processors having a shared thermal platform. Each processor has at least one subsystem operable at a plurality of different power settings, at least one internal thermal parameter detector providing power data related to the processor, and a power management unit. The method and apparatus illustratively shares power data from the at least one internal thermal parameter detector of each processor between the power management units of the plurality of processors; compares the shared power data from the plurality of processors to a thermal design power limit for the shared thermal platform; and controls a power setting of the at least one subsystem of the plurality of processors within the shared thermal platform based on the comparison of the shared power data to the thermal design power limit for the shared thermal platform.
摘要:
Power management for a processing system that has multiple processing units, (e.g., multiple graphics processing units (GPUs), is described herein. The processing system includes a power manager that obtains performance, power, operational or environmental data from a power management unit associated with each processor (e.g., GPU). The power manager determines, for example, an average value with respect to at least one of the performance, power, operational or environmental data. If the average value is below a predetermined threshold for a predetermined amount of time, then the power manager notifies a configuration manager to alter the number of active processors (e.g., GPUs), if possible. The power may then be distributed among the remaining GPUs or other processors, if beneficial for the operating and environmental conditions.
摘要:
A method and apparatus determines an activity history context for each of a plurality of virtual machines sharing use of a graphics processing core. Each activity history context provides information related to a power setting of at least one engine of the graphics processing core during at least one prior use of the graphics processing core by the corresponding virtual machine. The method and apparatus controls a power setting of the at least one engine of the graphics processing core based on the activity history context corresponding to an active virtual machine using the graphics processing core.
摘要:
A method of operating a device is provided. The method includes transitioning the GPU to a substantially disabled state in response to a first received signal, and generating, while the GPU is in the substantially disabled state, a response signal in response to a second received signal. The response signal is substantially similar to a second response signal that would be generated by the GPU in a powered state in response to the second received signal.
摘要:
An adaptive temperature dependent clock feedback control system and method for adaptively varying a frequency of a clock signal to a circuit such that the circuit may operate at a maximum safe operating clock frequency based on a circuit junction temperature. The clock control system includes a thermal sensor and a temperature dependent dynamic overclock generator circuit. The thermal sensor detects a junction temperature corresponding to at least a portion of the circuit on a semiconductor die. The temperature dependent dynamic overclock generator circuit varies the clock signal based on the semiconductor die junction temperature, such that the clock signal operates at the highest possible operating frequency associated with the detected junction temperature. The frequency of the clock signal is increased from a first frequency to at least a second frequency and a third frequency if the junction temperature is below a lower junction temperature threshold.
摘要:
A variable clock control information generator receives graphics engine activity data relating to the operating level of a graphics engine, and memory activity data relating to an activity level of memory. In response, the variable clock control information generator produces graphics engine clock control information and memory clock control information with respect to each other, such that a relative difference between the graphics engine activity data and the memory activity data is within balance threshold data. Accordingly, the variable clock control information generator adapts to the varying levels of graphics engine activity and memory activity and adjusts the frequency of the graphics engine clock signal and the frequency of the memory clock signal to achieve a balanced relative activity level.
摘要:
A method of power management is provided. The method includes detecting an event, assign a first responsibility to a first graphics processing unit (GPU) and a second responsibility to second GPU, and changing a power state of the first and second GPUs based on the first and second responsibilities, respectively. The first responsibility is different from the second responsibility.
摘要:
A method and apparatus includes a multi-processor apparatus including a plurality of integrated circuit processors having a shared thermal platform. Each processor has at least one subsystem operable at a plurality of different power settings, at least one internal thermal parameter detector providing power data related to the processor, and a power management unit. The method and apparatus illustratively shares power data from the at least one internal thermal parameter detector of each processor between the power management units of the plurality of processors; compares the shared power data from the plurality of processors to a thermal design power limit for the shared thermal platform; and controls a power setting of the at least one subsystem of the plurality of processors within the shared thermal platform based on the comparison of the shared power data to the thermal design power limit for the shared thermal platform.
摘要:
In devices in which display data is read from a memory for display, display underflow in a processing block is alleviated by controlling a clock frequency driving the processing block. Stages of the processing block send underflow detection signals to underflow prevention logic. The underflow prevention logic controls the frequencies of clock signals generated by a clock generator to alleviate the underflow condition.
摘要:
In a power management scheme, at least one indicator of at least one current device operating condition that affects an amount of power required to operate a device may be received. Based on the at least one indicator, a floor value for an operating parameter of the device (e.g. clock frequency or voltage) may be determined. At least one further indicator of at least one current device operating condition may further be received. Based on the at least one further indicator, a ceiling value for the operating parameter may be determined. Based on an indicator of current activity of the device, the operating parameter may be dynamically adjusted to a value between the floor value and the ceiling value, to control power consumption by the device. In some embodiments, the value may be adjusted to only the ceiling value or the floor value, e.g. by selectively applying a scaling ratio.