摘要:
A method and system for managing requests to resources among processors of a portable computing device (“PCD”) includes each master processor identifying a plurality of resources of the PCD in a storage device, such as a message RAM. This message RAM is part of the PCD. A master processor may identify desired states for the plurality of resources in the message RAM. Then, the master processor may generate an alert that the plurality of resources and desired states for resources have been set in the message RAM. After receiving the alert, a controller may determine if one or more previous requests have been processed to completion. If so, then the controller may review the contents of the message RAM to identify the plurality of resources and to identify the desired states of the resources. If appropriate, the controller may pass the desired states to the plurality of resources.
摘要:
A method and system for managing sleep states of a portable computing device are described. They include maintaining a sleep set of resource states and an active set of resource states in memory. A request may be issued for a processor to enter into a sleep state. This causes a controller to review a trigger set to determine if a shut down condition for the processor matches one or more conditions listed in the trigger set. Each trigger set may comprise a “trigger event” that may allow a controller to select a specific resource set which is desired by a particular processor based on a trigger event detected by a system power manager. If a trigger set matches a shut down condition, then switching states of one or more resources in accordance with the sleep set may be made by the controller without using a software handshake.
摘要:
A method and system for managing sleep states of one or more interrupt controllers of processors contained within a portable computing device are described. The method includes a processor defining wake-up interrupt settings in a storage device contained within the portable computing device. This storage device may comprise message random access memory (“RAM”). After wake-up settings have been established in message RAM, a processor may generate an alert that the wake-up settings in the message RAM have been defined. Next, a controller reviews the wake-up interrupt settings in the message RAM for a plurality of interrupt controllers that correspond with a plurality of processors contained within the portable computing device. The controller merges the wake-up settings in the message RAM and then sends the merged wake-up settings to an always-on power manager (“APM”). The APM is responsible for issuing signals to place interrupt controllers of processors into a sleep state.
摘要:
A start time to begin transitioning resources to states indicated in the second resource state set is scheduled based upon an estimated amount of processing time to complete transitioning the resources. At a scheduled start time, a process starts in which the states of one or more resources are switched from states indicated by the first resource state set to states indicated by the second resource state set. Scheduling the process of transitioning resource states to begin at a time that allows the process to be completed just in time for the resource states to be immediately available to the processor upon entering the second application state helps minimize adverse effects of resource latency. This calculation for the time that the process should be completed just in time may be enhanced when system states and transitions between states are measured accurately and stored in memory of the portable computing device.
摘要:
A method and system for managing requests among resources within a portable computing device include a scheduler receiving data from a client for scheduling a plurality of requests. Each request identifies at least one resource and a requested deadline. Next, data from the client is stored by the scheduler in a database. The scheduler then determines times and a sequence for processing the requests based on requested deadlines in the requests and based on current states of resources within the portable computing device. The scheduler then communicates the requests to the resources at the determined times and according to the determined sequence. The scheduler, at its discretion, may schedule a request after its requested deadline in response to receiving a new request command from a client. The scheduler may allow a sleep set corresponding to a sleep processor state to power off a processor.
摘要:
Resource state sets corresponding to the application states are maintained in memory. A request may be issued for a processor operating in a first application state corresponding to the first resource state set to transition to a second application state corresponding to the second resource state set. A start time to begin transitioning resources to states indicated in the second resource state set is scheduled based upon an estimated amount of processing time to complete transitioning. A process is begun by which the states of resources are switched from states indicated by the first resource state set to states indicated by the second resource state set. Scheduling the process to begin at a time that allows the process to be completed just in time for the resource states to be immediately available to the processor upon entering the second application state helps minimize adverse effects of resource latency.
摘要:
A start time to begin transitioning resources to states indicated in the second resource state set is scheduled based upon an estimated amount of processing time to complete transitioning the resources. At a scheduled start time, a process starts in which the states of one or more resources are switched from states indicated by the first resource state set to states indicated by the second resource state set. Scheduling the process of transitioning resource states to begin at a time that allows the process to be completed just in time for the resource states to be immediately available to the processor upon entering the second application state helps minimize adverse effects of resource latency. This calculation for the time that the process should be completed just in time may be enhanced when system states and transitions between states are measured accurately and stored in memory of the portable computing device.
摘要:
Resource state sets corresponding to the application states are maintained in memory. A request may be issued for a processor operating in a first application state corresponding to the first resource state set to transition to a second application state corresponding to the second resource state set. A start time to begin transitioning resources to states indicated in the second resource state set is scheduled based upon an estimated amount of processing time to complete transitioning. A process is begun by which the states of resources are switched from states indicated by the first resource state set to states indicated by the second resource state set. Scheduling the process to begin at a time that allows the process to be completed just in time for the resource states to be immediately available to the processor upon entering the second application state helps minimize adverse effects of resource latency.
摘要:
A method and system for managing requests among resources within a portable computing device include a scheduler receiving data from a client for scheduling a plurality of requests. Each request identifies at least one resource and a requested deadline. Next, data from the client is stored by the scheduler in a database. The scheduler then determines times and a sequence for processing the requests based on requested deadlines in the requests and based on current states of resources within the portable computing device. The scheduler then communicates the requests to the resources at the determined times and according to the determined sequence. The scheduler, at its discretion, may schedule a request after its requested deadline in response to receiving a new request command from a client. The scheduler may allow a sleep set corresponding to a sleep processor state to power off a processor.
摘要:
Resource state sets of a portable computing device are managed. A sleep set of resource states, an active set of resource states and a next-active set of resource states are maintained in memory. A request may be issued for a processor to enter into a sleep state or otherwise change from one application state corresponding to one resource state set to another application state corresponding to another application state set. This causes a controller to review a trigger set to determine if a shut down condition for the processor matches one or more conditions listed in the trigger set. If a trigger set matches a shut down condition, then switching states of one or more resources in accordance with the sleep set may be made by the controller. Providing a next-awake set of resource states that is immediately available to the processor upon a wake-up event helps minimize resource latency.