Abstract: An interface to transfer data between a memory control hub and an input/output control hub of a chipset within a computer system. One embodiment of the interface includes a bi-directional data signal path and a pair of source synchronous strobe signals. The data signal path transmits data in packets via split transactions. In addition, the packets include a request packet and a completion packet, if necessary. Furthermore, in one embodiment, the request packets include a transaction descriptor.

Abstract: A method and apparatus of performing impedance compensation on signals on interfaces between chipset components is disclosed. In one embodiment, a present impedance adjustment value is generated, and a controlled impedance adjustment value is also established based on the present impedance adjustment value. Then a special cycle with a deterministic amount of time is generated to stabilize the interfaces. With the interfaces in a known state, the signals on the interfaces are updated with the controlled impedance adjustment value during the special cycle, where embodiment ensures the signals to be glitch-free.

Abstract: A configuration access request packet is transmitted from a first hub agent onto a hub interface. The configuration access request packet comprises an address formatted in accordance with a peripheral component interconnect (PCI) specification. The configuration access request packet is received from the hub interface by a second hub agent.

Abstract: A system is described for servicing a full cache line in response to a partial cache line request. The system includes a storage to store at least one cache line, a hit/miss detector, and a data mover. The hit/miss detector receives a partial cache line read request from a requesting agent and dispatches a fetch request to a memory device to fetch a full cache line data that contains data requested in the partial cache line read request from the requesting agent. The data mover loads the storage with the full cache line data returned from the memory device and forwards a portion of the full cache line data requested by the requesting agent. If data specified in a subsequent partial cache line request from the requesting agent is contained within the full cache line data specified in the previously dispatched fetch request, the hit/miss detector will send a command to the data mover to forward another portion of the full cache line data stored in the storage to the requesting agent.

Abstract: A first control hub component, within a computer system, having a first logic to synchronize an internal clock generator of the first control hub with an external clock generator in response to the external clock generator transitioning to a high power state. In response to the internal clock generator being synchronized with the external clock generator, the first logic initiates the first control hub to transmit a request packet to a second control hub via an interface. The first logic monitors the interface for receipt of a completion packet in reply to the request packet, wherein in response to the completion packet the first control hub is operable to continue communication with the second hub via the interface.

Abstract: According to one embodiment, a computer system includes a Central Processing Unit (CPU), a hub agent and a hub interface coupled to the first hub agent. The computer system transitions from a first power state to a second power state upon the CPU determining that no requests are pending to access the first hub interface.

Abstract: A system is described for servicing a full cache line in response to a partial cache line request. The system includes a storage to store at least one cache line, a hit/miss detector, and a data mover. The hit/miss detector receives a partial cache line read request from a requesting agent and dispatches a fetch request to a memory device to fetch a full cache line data that contains data requested in the partial cache line read request from the requesting agent. The data mover loads the storage with the full cache line data returned from the memory device and forwards a portion of the full cache line data requested by the requesting agent. If data specified in a subsequent partial cache line request from the requesting agent is contained within the full cache line data specified in the previously dispatched fetch request, the hit/miss detector will send a command to the data mover to forward another portion of the full cache line data stored in the storage to the requesting agent.

Abstract: A transaction rule is used to recognize a set of simulation signals obtained from a design simulation as a transaction. An action associated with the transaction rule is executed to produce an output identifying the transaction.

Abstract: According to one embodiment, a computer system includes a first hub agent and a hub interface coupled to the first hub agent. The first hub agent is adaptable to sample the hub interface in order to detect the presence of a second hub agent upon initiation of the computer system. In a further embodiment, the first hub agent comprises a presence detect module and control logic coupled to the presence detect module. The control logic responds to a central processing unit (CPU) poll request if the second hub agent is detected and does not respond to the CPU if the first device is not detected.

Abstract: According to one embodiment, a computer system comprises a central processing unit (CPU), a memory control hub (MCH) coupled to the CPU, a point to point interface coupled to the MCH; and an input/output control hub (ICH) coupled to the point to point interface. The MCH delays arbitration of a request to access the point to point interface until the access request is received at the ICH, and ICH delays arbitration of a request to access the point to point interface until the access request is received at the MCH.

Abstract: One embodiment of an apparatus for communicating routing and attribute information for a transaction between hubs in a computer system is disclosed. The apparatus includes a data path input/output unit to output a packet header for a transaction. The packet header includes a transaction descriptor routing field to identify an initiating agent that initiated the transaction. The transaction descriptor routing field includes a hub identification portion and a pipe identification portion. The hub identification portion identifies a hub that contains the initiating agent. The pipe identification portion further identifies the initiating agent within the identified hub if the transaction has no ordering requirements with respect to a second agent in the identified hub.

Abstract: An apparatus for reusing arbitration signals to frame data transfers between hub agents is disclosed. The apparatus includes an arbitration signal output circuit to output a first request signal to indicate a data transfer. The apparatus further includes a data path input/output unit to output data to a data path during a period indicated by the arbitration signal.

Abstract: An apparatus for arbitrating ownership of an interface between two hub agents is described. The apparatus includes a data path input/output unit to communicate with a data path and an arbitration circuit. The arbitration unit includes a least recently serviced status tracking circuit to determine which of the data path input/output unit and a device that transmits the second request signal has been granted ownership of the data path least recently, an arbitration signal output circuit to output a first request signal, and an arbitration signal input circuit to receive a second request signal. The arbitration unit grants ownership of the data path to the data path input/output unit when the first request signal is asserted if the second request signal is not asserted.

Abstract: A method and apparatus for queuing commands. An apparatus of the present invention utilizes one or more token queues and a storage block to avoid maintaining multiple separate queues and/or to facilitate reordering of queued elements. The apparatus includes at least one token queue and a token assignment circuit which queues a selected token in a token queue. A storage block stores an element in a slot corresponding to the selected token. One system employing the present invention includes a processor, a bus agent, a memory controller, and a main memory. The memory controller queues tokens representing received commands into appropriate command queues.

Abstract: One embodiment of an apparatus for communicating transaction types between hubs in a computer system includes a data path input/output unit to output a packet header. The packet header includes a request/completion field to indicate whether the packet header is a request packet header or a completion packet header. The packet header also includes a read/write field to indicate whether the packet header is for a read packet or for a write packet. The read/write field further indicates whether a length of data is to follow the packet header. The packet header further includes a data length field to indicate the length of data.

Abstract: An interface to transfer data between a memory controller hub and an input/output (I/O) hub of a chipset within a computer system. One embodiment of the interface includes a bi-directional data signal path and a pair of source synchronous strobe signals. The data signal path transmits data in packets via split transactions. In addition, the packets include a request packet and a completion packet, if necessary. Furthermore, in one embodiment, the request packets include a transaction descriptor.

Abstract: A system and method is provided for enhancing the efficiency with which commands from and initiating device to a resource are processed by the resource. The system includes a command queue, a plurality of command reorder slots coupled to the command queue, and command selection logic coupled to the resource and the command reorder slots. Commands ready for processing are loaded into the command reorder slots, and the command selection logic applies an efficiency criterion to the loaded commands. A command meeting the efficiency criterion is transferred to the resource for processing. The system may also include response reordering logic, which is coupled to the command reorder logic. The response reorder logic returns to original command order data provided in response to reorder read commands.

Abstract: A method and apparatus for arbitrating between command streams. The method unblocks high priority commands which are blocked and then selects any remaining high priority commands. Normal priority commands are selected after the high priority commands. A memory controller described includes a command queue block having a plurality of command queues, each being coupled to receive a different type of command. The memory controller also includes arbitration logic which, among other things, selects high priority read commands before high priority write commands. Memory interface logic generates memory accesses performing commands selected by the arbitration logic.

Abstract: A method and apparatus for ordering memory access commands. A command ordering circuit which is described includes a plurality of command slots which receive memory access commands. A page register stores a value indicating a last page accessed by a prior memory access command. Comparators compare the value in the page register to values stored in the command slots, and an arbiter receives outputs from the comparators and selects a command from one of the slots. According to the method described, memory accesses are reordered depending on the portion of memory accessed. A first memory access command requesting access to a first portion of memory is issued. Additional memory access commands also referencing the first portion of memory are issued until a count is reached. After the count is reached, a second memory access command which references a second portion of memory is issued.

Abstract: A method and apparatus for fencing the execution of commands. A fence command and an executable command are received in succession. The executable command is enqueued in a first queue together with an indication that the executable command succeeded the fence command. A synchronization value is enqueued in a second queue. The executable command is then delayed from being dequeued from the first queue until the synchronization value is advanced to the head of the second queue.