Abstract: Methods, apparatus and systems for facilitating one-way ordering of otherwise independent message classes. A one-way message ordering mechanism facilitates one-way ordering of messages of different message classes sent between interconnects employing independent pathways for the message classes. In one aspect, messages of a second message class may not pass messages of a first message class. Moreover, when messages of the first and second classes are received in sequence, the ordering mechanism ensures that messages of the first class are forwarded to, and received at, a next hop prior to forwarding messages of the second class.

Abstract: 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 requests, 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 that match the partial address of the memory line until the conflict resolver receives a full address for the memory line.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: In various embodiments, hardware, software and firmware or combinations thereof may be used to prevent cache conflicts within microprocessors and/or computer systems. More particularly, embodiments of the invention relate to a technique to prevent cache conflicts within a processor and/or computer system in which a number of accesses may be made to a particular cache or group of caches.

Abstract: According to one embodiment of the invention, an activity detector comprises a resource partitioned into a plurality of chunks, a power controller and an activity detection unit. In communication with the activity detector and the resource, the power controller, based on measured activity by the activity detector, activates an additional chunk of the plurality of chunks and assigned the additional chunk to a specified agent or deactivates at least one chunk of the plurality of chunks.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: The present invention presents an efficient way to implement global ordering between a system interconnect and internal core interfaces in a MCMP system. In particular, snooping transactions on the system interconnect, processor requests, and processor request completions may trigger corresponding snooping transactions and request completions to the cores. The order in which the transactions are observed on the system interconnect may impose the order in which the transaction triggered to the core are generated. Since this ordering is between multiple interfaces this is referred to as global ordering.

Abstract: Methods and apparatus to manage credits in a computing system with multiple banks of shared cache are described. In one embodiment, a credit request from a processor core is translated into a physical credit that corresponds to one of the multiple banks of shared cache.

Abstract: 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.

Abstract: According to one embodiment of the invention, an activity detector comprises a resource partitioned into a plurality of chunks, a power controller and an activity detection unit. In communication with the activity detector and the resource, the power controller, based on measured activity by the activity detector, activates an additional chunk of the plurality of chunks and assigned the additional chunk to a specified agent or deactivates at least one chunk of the plurality of chunks.

Abstract: Methods and apparatus to manage credits in a computing system with multiple banks of shared cache are described. In one embodiment, a credit request from a processor core is translated into a physical credit that corresponds to one of the multiple banks of shared cache.

Abstract: A method and apparatus for improving snooping performance is disclosed. One embodiment provides mechanisms for processing multi-core evictions in a multi-core inclusive shared cache processor. By using parallel eviction state machine, the latency of eviction processing is minimized. Another embodiment provides mechanisms for processing multi-core evictions in a multi-core inclusive shared cache processor in the presence of external conflicts.

Abstract: A method and apparatus for cache coherency sequencing implementation and an adaptive LLC access priority control is disclosed. One embodiment provides mechanisms to resolve last level cache access priority among multiple internal CMP cores, internal snoops and external snoops. Another embodiment provides mechanisms for implementing cache coherency in multi-core CMP system.

Abstract: A method and apparatus for improving snooping performance is disclosed. In one embodiment, one or more content addressable matches are used to determine where and when an address conflict occurs. Depending upon the timing, a read request or a snoop request may be set for retry. In another embodiment, an age order matrix may be used to determine when several core snoop requests may be issued during a same time period, so that the snoops may be processed during this time period.

Abstract: Preventing cache conflicts within microprocessors and/or computer systems. More particularly, embodiments of the invention relate to a technique to prevent cache conflicts within a processor and/or computer system in which a number of accesses may be made to a particular cache or group of caches.

Abstract: Preventing request conflicts within microprocessors and/or computer systems. More particularly, embodiments of the invention relate to a technique to manage request conflicts within a processor and/or computer system in which a number of accesses may be made to a particular cache or group of caches shared amongst a set of cores or processors or agents.