Patent application number | Description | Published |
20090037658 | Providing an inclusive shared cache among multiple core-cache clusters - In one embodiment, the present invention includes a method for receiving requested data from a system interconnect interface in a first scalability agent of a multi-core processor including a plurality of core-cache clusters, storing the requested data in a line of a local cache of a first core-cache cluster including a requester core, and updating a cluster field and a core field in a vector of a tag array for the line. Other embodiments are described and claimed. | 02-05-2009 |
20120254643 | Managing Power Consumption In A Multi-Core Processor - A processor may include a core and an uncore area. The power consumed by the core area may be controlled by controlling the Cdyn of the processor such that the Cdyn is within an allowable Cdyn value irrespective of the application being processed by the core area. The power management technique includes measuring digital activity factor (DAF), monitoring architectural and data activity levels, and controlling power consumption by throttling the instructions based on the activity levels. As a result of throttling the instructions, throttling may be implemented in 3 | 10-04-2012 |
20130080795 | Dynamically Adjusting Power Of Non-Core Processor Circuitry - In one embodiment, the present invention includes a multicore processor having a variable frequency domain including a plurality of cores and at least a portion of non-core circuitry of the processor. This non-core portion can include a cache memory, a cache controller, and an interconnect structure. In addition to this variable frequency domain, the processor can further have a fixed frequency domain including a power control unit (PCU). This unit may be configured to cause a frequency change to the variable frequency domain without draining the non-core portion of pending transactions. Other embodiments are described and claimed. | 03-28-2013 |
20130151569 | COMPUTING PLATFORM INTERFACE WITH MEMORY MANAGEMENT - In some embodiments, a PPM interface may be provided with functionality to facilitate to an OS memory power state management for one or more memory nodes, regardless of a particular platform hardware configuration, as long as the platform hardware is in conformance with the PPM interface. | 06-13-2013 |
20130179716 | Dynamically Adjusting Power Of Non-Core Processor Circuitry - In one embodiment, the present invention includes a multicore processor having a variable frequency domain including a plurality of cores and at least a portion of non-core circuitry of the processor. This non-core portion can include a cache memory, a cache controller, and an interconnect structure. In addition to this variable frequency domain, the processor can further have a fixed frequency domain including a power control unit (PCU). This unit may be configured to cause a frequency change to the variable frequency domain without draining the non-core portion of pending transactions. Other embodiments are described and claimed. | 07-11-2013 |
20130232368 | MANAGING POWER CONSUMPTION IN A MULTI-CORE PROCESSOR - A processor may include a core and an uncore area. The power consumed by the core area may be controlled by controlling the Cdyn of the processor such that the Cdyn is within an allowable Cdyn value irrespective of the application being processed by the core area. The power management technique includes measuring digital activity factor (DAF), monitoring architectural and data activity levels, and controlling power consumption by throttling the instructions based on the activity levels. As a result of throttling the instructions, throttling may be implemented in 3 | 09-05-2013 |
20130254572 | OPTIMIZING POWER USAGE BY FACTORING PROCESSOR ARCHITECTURAL EVENTS TO PMU - A method and apparatus to monitor architecture events is disclosed. The architecture events are linked together via a push bus mechanism with each architectural event having a designated time slot. There is at least one branch of the push bus in each core. Each branch of the push bus may monitor one core with all the architectural events. All the data collected from the events by the push bus is then sent to a power control unit. | 09-26-2013 |
20140095905 | Computing System and Processor With Fast Power Surge Detection And Instruction Throttle Down To Provide For Low Cost Power Supply Unit - A processor is described that includes a quick signal path from an input of the processor to logic circuitry within the processor. The input is to receive a fast throttle down signal. The logic circuitry is to throttle down a rate at which the processor issues instructions for execution in response to the fast throttle down signal. The quick signal path is to impose practicably minimal propagation delay of the fast throttle down signal within the processor. | 04-03-2014 |
20140157021 | ENFORCING A POWER CONSUMPTION DUTY CYCLE IN A PROCESSOR - In an embodiment, a processor includes a plurality of cores each to independently execute instructions, a plurality of graphics engines each to independently perform graphics operations; and, a power control unit coupled to the plurality of cores to control power consumption of the processor, where the power control unit includes a power excursion control logic to limit a power consumption level of the processor from being above a defined power limit for more than a duty cycle portion of an operating period. Other embodiments are described and claimed. | 06-05-2014 |
20140164799 | OPTIMIZING POWER USAGE BY FACTORING PROCESSOR ARCHITECTURAL EVENTS TO PMU - A method and apparatus to monitor architecture events is disclosed. The architecture events are linked together via a push bus mechanism with each architectural event having a designated time slot. There is at least one branch of the push bus in each core. Each branch of the push bus may monitor one core with all the architectural events. All the data collected from the events by the push bus is then sent to a power control unit. | 06-12-2014 |
20140337646 | Adaptively Limiting A Maximum Operating Frequency In A Multicore Processor - In an embodiment, a processor includes a plurality of cores each to independently execute instructions, and a power control unit coupled to the plurality of cores to control power consumption of the processor, where the power control unit includes a control logic to reduce a maximum operating frequency of the processor if a first number of forced performance state transitions occurs in a first time period or a second number of forced performance state transitions occurs in a second time period. Other embodiments are described and claimed. | 11-13-2014 |
Patent application number | Description | Published |
20080244193 | ADAPTIVE RANGE SNOOP FILTERING METHODS AND APPARATUSES - Snoop filtering methods and apparatuses for systems utilizing memory are contemplated. Method embodiments comprise receiving a request for contents of a memory line by a home agent, comparing an address of the memory line to a range in a set of adaptive ranges, and snooping an I/O agent for the contents upon a match of the address with the range. Apparatus embodiments comprise a range table, a table updater, a receiver module, and a range comparator. The range tables allow for the tracking of memory addresses as I/O agents assert ownership of the addresses. | 10-02-2008 |
20080244195 | METHODS AND APPARATUSES TO SUPPORT MEMORY TRANSACTIONS USING PARTIAL PHYSICAL ADDRESSES - Methods and apparatuses to support memory transactions using partial physical addresses are disclosed. Method embodiments generally comprise home agents monitoring multiple responses to multiple memory requests, wherein at least one of the responses has a partial address for a memory line, resolving conflicts for the memory requ'fvests, and suspending conflict resolution for the memory requests which match partial address responses until determining the full address. Apparatus embodiments generally comprise a home agent having a response monitor and a conflict resolver. The response monitor may observe a snoop response of a memory agent, wherein the snoop response only has a partial address and is for a memory line of a memory agent. The conflict resolver may suspend conflict resolution for memory transactions which match the partial address of the memory line until the conflict resolver receives a full address for the memory line. | 10-02-2008 |
20090006871 | METHOD, SYSTEM, AND APPARATUS FOR A CORE ACTIVITY DETECTOR TO FACILITATE DYNAMIC POWER MANAGEMENT IN A DISTRIBUTED SYSTEM - A system and method to provide source controlled dynamic power management. An activity detector in a source determines expected future resource usage. Based on that expected usage, the source generates a power management command and sends that command to a destination. The destination then adjusts the power level of the resource based in the command. | 01-01-2009 |
20100274975 | Forming Multiprocessor Systems Using Dual Processors - In one embodiment, link logic of a multi-chip processor (MCP) formed using multiple processors may interface with a first point-to-point (PtP) link coupled between the MCP and an off-package agent and another PtP link coupled between first and second processors of the MCP, where the on-package PtP link operates at a greater bandwidth than the first PtP link. Other embodiments are described and claimed. | 10-28-2010 |
20110296116 | System and Method for Aggregating Core-Cache Clusters in Order to Produce Multi-Core Processors - According to one embodiment of the invention, a processor comprises a memory, a plurality of core-cache clusters and a scalability agent unit that operates as an interface between an on-die interconnect and multiple core-cache clusters. The scalability agent operates in accordance with a protocol to ensure that the plurality of core-cache clusters appear as a single caching agent. | 12-01-2011 |
20120089850 | Optimizing Power Usage By Factoring Processor Architectural Events To PMU - A method and apparatus to monitor architecture events is disclosed. The architecture events are linked together via a push bus mechanism with each architectural event having a designated time slot. There is at least one branch of the push bus in each core. Each branch of the push bus may monitor one core with all the architectural events. All the data collected from the events by the push bus is then sent to a power control unit. | 04-12-2012 |
20120179878 | Forming Multiprocessor Systems Using Dual Processors - In one embodiment, link logic of a multi-chip processor (MCP) formed using multiple processors may interface with a first point-to-point (PtP) link coupled between the MCP and an off-package agent and another PtP link coupled between first and second processors of the MCP, where the on-package PtP link operates at a greater bandwidth than the first PtP link. Other embodiments are described and claimed. | 07-12-2012 |
Patent application number | Description | Published |
20120144217 | Dynamically Modifying A Power/Performance Tradeoff Based On Processor Utilization - In one embodiment, the present invention includes a multicore processor having a power controller with logic to dynamically switch a power management policy from a power biased policy to a performance biased policy when a utilization of the processor exceeds a threshold level. Thus at low utilizations, reduced power consumption can be realized, while at higher utilizations, greater performance can be realized. Other embodiments are described and claimed. | 06-07-2012 |
20120185706 | METHOD, APPARATUS, AND SYSTEM FOR ENERGY EFFICIENCY AND ENERGY CONSERVATION INCLUDING DYNAMIC CONTROL OF ENERGY CONSUMPTION IN POWER DOMAINS - An apparatus, method and system is described herein for dynamic power control of a power domain. A power limit over a time window is provided. And over a control loop period a power interface determines energy consumption of the power domain, intelligently budgets power among devices within the power domain based on the energy consumption, converts those budgets to performance maximums for the power domain, and limits performance of devices in the power domain to the performance maximums utilizing a running average power limit. | 07-19-2012 |
20120204042 | User Level Control Of Power Management Policies - In one embodiment, the present invention includes a processor having a core and a power controller to control power management features of the processor. The power controller can receive an energy performance bias (EPB) value from the core and access a power-performance tuning table based on the value. Using information from the table, at least one setting of a power management feature can be updated. Other embodiments are described and claimed. | 08-09-2012 |
20130179706 | User Level Control Of Power Management Policies - In one embodiment, the present invention includes a processor having a core and a power controller to control power management features of the processor. The power controller can receive an energy performance bias (EPB) value from the core and access a power-performance tuning table based on the value. Using information from the table, at least one setting of a power management feature can be updated. Other embodiments are described and claimed. | 07-11-2013 |
20130275737 | COLLABORATIVE PROCESSOR AND SYSTEM PERFORMANCE AND POWER MANAGEMENT - The present invention relates to a platform power management scheme. In some embodiments, a platform provides a relative performance scale using one or more parameters to be requested by an OSPM system. | 10-17-2013 |
20130275796 | COLLABORATIVE PROCESSOR AND SYSTEM PERFORMANCE AND POWER MANAGEMENT - The present invention relates to a platform power management scheme. In some embodiments, a platform provides a relative performance scale using one or more parameters to be requested by an OSPM system. | 10-17-2013 |
20130332753 | DYNAMIC POWER LIMIT SHARING IN A PLATFORM - A method and apparatus for dynamic power limit sharing among the modules in the platform. In one embodiment of the invention, the platform comprises a processor and memory modules. By expanding the power domain to include the processor and the memory modules, dynamic sharing of the power budget of the platform between the processor and the memory modules is enabled. For low-bandwidth workloads, the dynamic sharing of the power budget offers significant opportunity for the processor to increase its frequency by using the headroom in the memory power and vice versa. This enables higher peak performance for the same total platform power budget in one embodiment of the invention. | 12-12-2013 |
20140006673 | UTILIZATION-AWARE LOW-OVERHEAD LINK-WIDTH MODULATION FOR POWER REDUCTION IN INTERCONNECTS | 01-02-2014 |
20140006761 | MECHANISM TO PROVIDE WORKLOAD AND CONFIGURATION-AWARE DETERMINISTIC PERFORMANCE FOR MICROPROCESSORS | 01-02-2014 |
20140129858 | METHOD AND APPARATUS FOR SETTING AN I/O BANDWIDTH-BASED PROCESSOR FREQUENCY FLOOR - An apparatus and method for managing a frequency of a computer processor. The apparatus includes a power control unit (PCU) to manage power in a computer processor. The | 05-08-2014 |
20140173248 | Performing Frequency Coordination In A Multiprocessor System Based On Response Timing Optimization - In an embodiment, a processor includes a core to execute instructions and a logic to receive memory access requests from the core and to route the memory access requests to a local memory and to route snoop requests corresponding to the memory access requests to a remote processor. The logic is configured to maintain latency information regarding a difference between receipt of responses to the snoop requests from the remote processor and receipt of responses to the memory access requests from the local memory. Other embodiments are described and claimed. | 06-19-2014 |
20140173297 | Performing Frequency Coordination In A Multiprocessor System - In an embodiment, a processor includes a core to execute instructions, uncore logic coupled to the core, and a power controller to control a power consumption level. The power controller is configured to determine an activity level of the processor and responsive to this level, to generate a request for communication to a second processor coupled to the processor to request frequency coordination between the processors. Other embodiments are described and claimed. | 06-19-2014 |
20140176581 | CONTROLLING CONFIGURABLE PEAK PERFORMANCE LIMITS OF A PROCESSOR - In one embodiment, the present invention includes a processor having a plurality of cores each to execute instructions, a non-volatile storage to store maximum peak operating frequency values each a function of a given number of active cores, a configuration storage to store frequency limits each corresponding to one of the maximum peak operating frequency values or a configurable clip frequency value less than the maximum peak operating frequency value. In turn, a power controller is configured to limit operating frequency of the cores to a corresponding frequency limit obtained from the configuration storage. Other embodiments are described and claimed. | 06-26-2014 |
20140181538 | Controlling Configurable Peak Performance Limits Of A Processor - In one embodiment, the present invention includes a processor having a plurality of cores each to execute instructions, a non-volatile storage to store maximum peak operating frequency values each a function of a given number of active cores, a configuration storage to store frequency limits each corresponding to one of the maximum peak operating frequency values or a configurable clip frequency value less than the maximum peak operating frequency value. In turn, a power controller is configured to limit operating frequency of the cores to a corresponding frequency limit obtained from the configuration storage. Other embodiments are described and claimed. | 06-26-2014 |
20140181596 | WEAR-OUT EQUALIZATION TECHNIQUES FOR MULTIPLE FUNCTIONAL UNITS - Wear-out equalization techniques for multiple functional hardware units are disclosed. An integrated circuit includes a power control unit (PCU) configured to monitor indicators of wear-out incurred by multiple functional hardware units of the integrated circuit. The PCU calculates cumulative wear-out metrics of the functional hardware units based on the monitored indicators and performs an equalization action to equalize the cumulative wear-out metrics of the functional hardware units. | 06-26-2014 |
20140189694 | MANAGING PERFORMANCE POLICIES BASED ON WORKLOAD SCALABILITY - Methods and systems may provide for identifying a workload associated with a platform and determining a scalability of the workload. Additionally, a performance policy of the platform may be managed based at least in part on the scalability of the workload. In one example, determining the scalability includes determining a ratio of productive cycles to actual cycles. | 07-03-2014 |
20140195828 | DYNAMICALLY MEASURING POWER CONSUMPTION IN A PROCESSOR - In one embodiment, the present invention includes a processor having multiple cores to independently execute instructions, a first sensor to measure a first power consumption level of the processor based at least in part on events occurring on the cores, and a hybrid logic to combine the first power consumption level and a second power consumption level. Other embodiments are described and claimed. | 07-10-2014 |
20140281445 | PROCESSOR HAVING FREQUENCY OF OPERATION INFORMATION FOR GUARANTEED OPERATION UNDER HIGH TEMPERATURE EVENTS - A processor is described having a semiconductor chip having non volatile storage circuitry. The non volatile storage circuitry has information identifying a maximum operational frequency of the processor at which the processor's operation is guaranteed for an ambient temperature that corresponds to an extreme thermal event. | 09-18-2014 |
20140281612 | MEASUREMENT OF PERFORMANCE SCALABILITY IN A MICROPROCESSOR - A scalability algorithm causes a processor to initialize a performance indicator counter, operate at an initial frequency of the first clock signal for a first duration, and determine, based on the performance indicator counter, an initial performance of the first processing core. The algorithm may then cause the processor to operate at a second frequency of the first clock signal for a second duration and determine, based on the performance indicator counter, a second performance of the first processing core. A performance scalability of the first processing core may be determined based on the initial performance and the second performance and an operational parameter, such as one or more clock frequencies and/or supply voltage(s), may be changed based on the determined scalability. | 09-18-2014 |
20150058650 | Forcing Core Low Power States In A Processor - In an embodiment, a processor includes a plurality of cores each to independently execute instructions, a power delivery logic coupled to the plurality of cores, and a power controller including a first logic to cause a first core to enter into a first low power state of an operating system power management scheme independently of the OS, during execution of at least one thread on the first core. Other embodiments are described and claimed. | 02-26-2015 |
20150067361 | Adaptively Controlling Low Power Mode Operation For A Cache Memory - In an embodiment, a processor includes a plurality of cores each to independently execute instructions, a cache memory including a plurality of portions distributed across a die of the processor, a plurality of sleep circuits each coupled to one of the portions of the cache memory, and at least one sleep control logic coupled to the cache memory portions to dynamically determine a sleep setting independently for each of the sleep circuits and to enable the corresponding sleep circuit to maintain the corresponding cache memory portion at a retention voltage. Other embodiments are described and claimed. | 03-05-2015 |
20150089287 | EVENT-TRIGGERED STORAGE OF DATA TO NON-VOLATILE MEMORY - An event management resource monitors a processor environment. In response to detecting occurrence of a trigger event in the processor environment, the event management resource initiates a transfer of processor cache data from volatile storage in the processor environment to non-volatile memory. The event management resource can be configured to produce status information associated with the transfer of cache data to a respective non-volatile memory resource. The event management resource stores the status information in a non-volatile storage resource for later retrieval. Accordingly, status information associated with the event causing the transfer is available for analysis on subsequent power up or reboot of a respective computer system. | 03-26-2015 |