摘要:
A system and method for reduced power consumption communications over a physical interconnect is described. In an embodiment, an input/output circuit includes a port to receive a transmission unit via an interconnect, a combining module coupled to the port to append at least one of a first and a second indicator to the transmission unit, a first adder module to generate the first indicator, indicating that the transmission unit is a starting transmission unit of a set of related transmission units, a second adder module to generate the second indicator, indicating that the starting transmission unit of the set of related transmission units has already been received, and logic to determine at least one of the start and end boundaries of the set of related transmission units.
摘要:
In a cache coherency protocol multiple conflict phases may be utilized to resolve a data request conflict condition. The multiple conflict phases may avoid buffering or stalling conflict resolution, which may reduce system inefficiencies.
摘要:
An apparatus is described that routes packets to, from, and within a socket. The apparatus includes routing components that provide different functionality based upon which socket component they are connected to. One routing component is connected to an interface that communicates with the processor core of the socket.
摘要:
Systems and methods of managing a link provide for receiving a remote width capability during a link initialization, the remote width capability corresponding to a remote port. A link between a local port and the remote port is operated at a plurality of link widths in accordance with the remote width capability.
摘要:
Embodiments of the invention provide an algorithm for dividing a link into one or more reduced-width links. For one embodiment of the invention, a multiplexing scheme is employed to effect a bit transmission order required by a particular cyclic redundancy check. The multiplexed output bits are then swizzled on-chip to reduce on-board routing congestion.
摘要:
In one embodiment of the present invention, a method includes identifying a transaction from a first processor to a second processor of a system with a transaction identifier. The transaction identifier may have a value that is less than or equal to a maximum number of outstanding transactions between the two processors. In such manner, a transaction field for the transaction identifier may be limited to n bits, where the maximum number of outstanding transactions is less than or equal to 2n. In various embodiments, such a transaction identifier combined with a source identifier and a home node identifier may form a globally unique transaction identifier.
摘要:
In one embodiment, the present invention includes a method for receiving a first portion of a first packet at a first agent and determining whether the first portion is an interleaved portion based on a value of an interleave indicator. The interleave indicator may be sent as part of the first portion. In such manner, interleaved packets may be sent within transmission of another packet, such as a lengthy data packet, providing improved processing capabilities. Other embodiments are described and claimed.
摘要:
In one embodiment of the present invention, a method may include separating incoming transactions to an agent of a coherent system into at least a first channel, a second channel, and a third channel, based upon a type of the incoming transactions. The incoming transactions may be sent by a peer device coupled to the coherent system. By separating the transactions based on type, deadlocks may be avoided.
摘要:
A predetermined network packet is utilized for power reduction in either or both of a transmitter and receiver when information is not needed. Upon detection of the predetermined network packet type, various portions of the transmitter and/or receiver may be clock gated or powered down.
摘要:
Systems and methods of processing write transactions provide for combining write transactions on an input/output (I/O) hub according to a protocol between the I/O hub and a processor. Data associated with the write transactions can be flushed to an I/O device without the need for proprietary software and specialized registers within the I/O device.