摘要:
A mechanism is provided for estimating energy/power consumption of a fixed-frequency operating mode while system is running in dynamic power management mode. For each time interval in a plurality of time intervals within a time period: a first processor identifies a modeled total nominal power value for at least one second processor during a current time interval, stores the modeled total nominal power value for the current time interval in a storage, identifies a dynamic power management mode power value for the at least one second processor in the data processing system during the current interval, and stores the dynamic power management mode power value for the current time interval in the storage. Responsive to the time period expiring, a comparison is produced of a plurality of modeled total nominal power values and a plurality of dynamic power management mode power values over the time period.
摘要:
A method for increasing a capacity of a memory is provided in the illustrative embodiments. Using an application executing using a processor wherein the memory includes a set of ranks, the memory is configured to form a cold tier and a hot tier, the cold tier including a first subset of ranks from the set of ranks in the memory, and the hot tier including a second subset of ranks from the set of ranks in the memory. A determination is made whether a page to which a memory access request is directed is located in the cold tier in the memory. In response to the page being located in the cold tier of the memory, the processing of the memory access request is throttled by processing the memory access request with a delay.
摘要:
According to one aspect of the present disclosure a method and technique for monitoring memory access is disclosed. The method includes monitoring, by a plurality of memory controllers, access to a memory unit, wherein each memory controller is associated with a different range of memory addresses of the memory unit, and wherein each memory controller monitors access for its associated range of memory addresses. The method also includes updating an incrementor with access data corresponding to accesses to the memory unit, wherein each memory controller updates the access data based on access of its associated range of memory addresses. The method further includes storing, by each respective memory controller, the updated access data in a cache corresponding to the respective range of memory addresses and, responsive to the updated access data for a respective range of memory addresses exceeding a threshold, storing the access data for the respective range of memory addresses in memory unit.
摘要:
A mechanism is provided for directed resource folding for power management. The mechanism receives a set of static platform characteristics and a set of dynamic platform characteristics for a set of resources associated with the data processing system thereby forming characteristic information. The mechanism determines whether one or more conditions have been met for each resource in the set of resources using the characteristic information. Responsive to the one or more conditions being met, the mechanism performs a resource optimization to determine at least one of a first subset of resources in the set of resources to keep active and a second subset of resources in the set of resources to dynamically fold. Based on the resource optimization, the mechanism performs either a virtual resource optimization to optimally schedule the first subset of resources or a physical resource optimization to dynamically fold the second subset of resources.
摘要:
A mechanism is provided for oversubscribing branch circuits. An active energy management mechanism determines a cumulative wattage rating using power consumption information for a powered element, the power consumption information is for a primary and a redundant portion of the powered element. The active energy management mechanism determines a power reduction power cap to be used by the powered element in the event of a loss of either a primary or a redundant power source supplied to the powered element using the cumulative wattage rating, a branch circuit rating, and a circuit breaker rating for the powered element. The active energy management mechanism sends the power reduction power cap to the powered element in order that the powered element reduces power to the power reduction power cap in the event of the loss of either the primary power source or the redundant power source supplied to the powered element.
摘要:
A mechanism is provided for oversubscribing branch circuits. An active energy management mechanism determines a cumulative wattage rating using power consumption information for a powered element, the power consumption information is for a primary and a redundant portion of the powered element. The active energy management mechanism determines a power reduction power cap to be used by the powered element in the event of a loss of either a primary or a redundant power source supplied to the powered element using the cumulative wattage rating, a branch circuit rating, and a circuit breaker rating for the powered element. The active energy management mechanism sends the power reduction power cap to the powered element in order that the powered element reduces power to the power reduction power cap in the event of the loss of either the primary power source or the redundant power source supplied to the powered element.
摘要:
Mechanisms are provided for inhibiting precharging of memory cells of a dynamic random access memory (DRAM) structure. The mechanisms receive a command for accessing memory cells of the DRAM structure. The mechanisms further determine, based on the command, if precharging the memory cells following accessing the memory cells is to be inhibited. Moreover, the mechanisms send, in response to the determination indicating that precharging the memory cells is to be inhibited, a command to blocking logic of the DRAM structure to block precharging of the memory cells following accessing the memory cells.
摘要:
A modular processing module is provided. The modular processing module comprises a set of processing module sides. Each processing module side comprises a circuit board, a plurality of connectors coupled to the circuit board, and a plurality of processing nodes coupled to the circuit board. Each processing module side in the set of processing module sides couples to another processing module side using at least one connector in the plurality of connectors such that, when all of the set of processing module sides are coupled together, the modular processing module is formed. The modular processing module comprises an exterior connection to a power source and a communication system.
摘要:
A mechanism is provided for dynamically power capping one or more units. A power capping mechanism sets a counter value corresponding to an initial energy budget assigned to a unit for a given interval. Responsive to the unit receiving an operation to perform during the given interval, the power capping mechanism decrements the counter value by a decrement value. Responsive to the given interval expiring, the power capping mechanism sends the counter value to a power control loop in the data processing system, receives a new energy budget from the power control loop, and resets the counter value to a value corresponding to the new energy budget assigned to the unit for a next interval.
摘要:
A mechanism is provided for controlling operational parameters associated with a plurality of processors. A control system in the data processing system determines a utilization slack value of the data processing system. The utilization slack value is determined using one or more active core count values and one or more slack core count values. The control system computes a new utilization metric to be a difference between a full utilization value and the utilization slack value. The control system determines whether the new utilization metric is below a predetermined utilization threshold. Responsive to the new utilization metric being below the predetermined utilization threshold, the control system decreases a frequency of the plurality of processors.