摘要:
A next idle state for a processor in a system may be determined based on a previous idle period and a previous idle state. The next idle state for the processor may also be determined based on times when interrupts are generated by devices in the system.
摘要:
A method and apparatus for intelligent power management for low power link states. Some embodiments include methods, apparatuses, and systems for a device coupled to a controller via a link; a link power management engine to alter a power state of the link based on a transaction and some knowledge of future transactions between the device and the controller; and a memory or logic to store the link power management engine. In some embodiments, the memory stores information about at least one of the following: the power state of the link, the device buffering, the controller or device state or a history of transactions. In some embodiments, the device is a peripheral of a computer system. In some embodiments, the method may include transitioning the device to various link states. Other embodiments are described.
摘要:
A method and system to perform a fast reset or restart of a platform by minimizing the hardware initialization of IO devices in the platform during a restart of the platform. The basic input/output system (BIOS) of the platform traps any software initiated reset request (SIRR) or warm reset. The BIOS restores the input/output (IO) devices coupled with the platform to their previous hardware state to avoid the full platform initialization when the SIRR is trapped. The restart of the platform can be performed in a fast manner as the full platform initialization is minimized.
摘要:
A method and device are provided to monitor clock control signals from a CPU core; and calculate a time period during a sampling interval that the CPU core was used to perform work based on the clock control signals.
摘要:
Various methods, apparatuses, and systems are described in which a chipset controller has circuitry to control communications with a peripheral device in a computing device. The chipset controller has logic configured 1) to detect a plug-in event when the peripheral device connects to the chipset controller and 2) to transition the chipset controller from a low power consumption state to a higher power consumption state based on the logic detecting the plug-in event.
摘要:
A demand-based method and system of a processor power management is described. A processor is caused to enter a particular performance mode based on a first and a second utilization threshold. The particular performance mode includes at least a first performance mode, a second performance mode, and a third performance mode. The processor is caused to operate with a clock frequency in the third performance mode that is lower than the clock frequency of the processor in the first and second performance modes.
摘要:
In some embodiments, an electronic apparatus comprises at least one processor, a plurality of components, and a policy engine comprising logic to receive latency data from one or more components in the electronic device, compute a minimum latency tolerance value from the latency data, and determine a power management policy from the minimum latency tolerance value.
摘要:
A power management system for a computing platform is described. In one embodiment, the power management system provides additional device states which the device controllers of the platform assume when the device controllers are operational but idle. These additional device states are states in which the device controller commits to certain types of inactivity. In another embodiment, the power management system provides additional platform modes which guarantee processor inactivity and/or deference of particular platform events while the mode is in effect.
摘要:
In some embodiments, the method and apparatus to provide for the detection of processor transition states is described. Some embodiments include at least two threads which provide detection for high and low priority states, which provide for power state transitions by the operating system: The low priority thread runs just prior to entry into an idle or low power state; the high priority thread runs when the idle state is ended or the highest power state is reached. In some embodiments, the use of these threads provides for the detection of processor state transitions and idle times independently of the operating system. Other embodiments are described.
摘要:
A power management technique uses system management interrupt (SMI) to manage performance states of logical processors in a physical processor. Each logical processor is associated with a virtual performance state and an actual performance state. A request to retrieve or to change the virtual performance state causes the SMI to be generated. The virtual performance state is a state known to an operating system (OS). The actual performance state is a state that the logical processor is operating at.