Intel Corporation

Ast Research, Inc.

Tuan M Quach

Bill Nale

Jun Zhu

Murugasamy K Nachimuthu

Kai Cheng

Lily Pao Looi

Subbarao S Vanka

John V Lovelace

Jonathan C Jasper

Kenneth C Haren

Reza E Daftari

Cuong D Dinh

Victor V Tran

Murugasamy M Nachimuthu

Provided are a method and apparatus for performing error handling operations using error signals A first error signal is asserted on an error pin on a bus to signal to a host memory controller that error handling operations are being performed by a memory module controller in response to detecting an error. Error handling operations are performed to return the bus to an initial state in response to detecting the error. A second error signal is asserted on the error pin on the bus to signal that error handling operations have completed and the bus is returned to the initial state.

Method and apparatus for performing error handling operations using error signals

Provided are a method and apparatus for providing a host memory controller write credits for write commands. A host memory controller coupled to a memory module over a bus determines whether a read data packet returned from the memory module indicates at least one write credit and increments a write credit counter in response to determining that the read data packet indicates at least one write credit.

Method and apparatus for providing a host memory controller write credits for write commands

Provided are a method and apparatus for using an error signal to indicate a write request error and write request acceptance performing error handling operations using error signals. A memory module controller detects a write error for a write request in a memory module and asserts an error signal on a bus to a host memory controller in response to detecting the write error.

Method and apparatus for using an error signal to indicate a write request error and write request acceptance

Provided are a method and apparatus for a memory module to accept a command in multiple parts. A first half of a command is placed on a bus for a memory module in a first clock cycle. A chip select signal is placed on the bus for the memory module for the first half of the command. A second half of the command is placed on the bus in a second clock cycle following the first clock cycle, wherein the memory module accepts the second half of the command a delay interval from accepting the first half of the command.

Method and apparatus for a memory module to accept a command in multiple parts

Provided is a device for use in a memory module coupled to a host memory controller over a bus, comprising memory module control logic to generate a request signal to a host memory controller having a pulse width greater than or equal to a minimum pulse width, wherein the minimum pulse width comprises a number of clock cycles needed to guarantee that the host memory controller detects the request signal, and wherein the pulse width of the request signal indicates at least one function in addition to the request signal to the host memory controller.

Memory system

Provided are a method and apparatus for method and apparatus for encoding registers in a memory module. A mode register command is sent to the memory module over a bus, initialization of the memory module before the bus to the memory module is trained for bus operations, to program one of a plurality of mode registers in the memory module, wherein the mode register command indicates one of the mode registers and includes data for the indicated mode register.

Method and apparatus for encoding registers in a memory module

Described herein are embodiments of selectively setting a memory command clock as a memory buffer reference clock. An apparatus configured for setting a memory command clock as a memory buffer reference clock may include a memory buffer configured to interface between a host and memory, and reference clock selection logic configured to selectively set a memory command clock as a memory buffer reference clock. Other embodiments may be described and/or claimed.

Apparatus and method for selectively using a memory command clock as a reference clock

Described herein are embodiments of dynamic command slot realignment after clock stop exit. An apparatus configured for dynamic command slot realignment after clock stop exit may include memory including a first memory module configured to receive commands over a first channel via a first command slot and a second memory module configured to receive commands over a second channel via a second command slot, and a memory buffer configured to receive a clock sync command targeting the first command slot, and perform a write pointer exchange in response to detecting the clock sync command in the second command slot to realign the first command slot and the second command slot. Other embodiments may be described and/or claimed.

Realignment of command slots after clock stop exit

In one embodiment, the present invention includes a method for receiving a snoop request, providing the snoop request to a coherency engine along a first path and providing the snoop request to a bypass logic along a bypass path, and generating a speculative invalid snoop response in the bypass logic and forwarding the speculative invalid snoop response to indicate that an address associated with the snoop response is not present in a cache memory. Other embodiments are described and claimed.

Reducing latency in responding to a snoop request

A system includes a scalability port switch (SPS) and a plurality of nodes. The SPS has a plurality of ports, each port coupled to a node. Each port is connected to a scalability port protocol distributed (SPPD). A snoop filter in the SPS tracks which nodes may be using various memory addresses. A scalability port protocol central (SPPC) is responsible for processing messages to support coherent and non-coherent transactions in the system.

Programmable protocol to support coherent and non-coherent transactions in a multinode system

A reordering priority to grant higher priority for a request over a response when a predetermined condition is detected for live-lock prevention is discussed. Specifically. A a circuit and flowchart for preventing a live lock situation is discussed without a need for a bus converter. In one example, a detection of a PRETRY response in a response queue is analyzed.

Method and apparatus for avoiding live-lock in a multinode system

An embodiment of the invention is directed to a method for accessing configuration registers. An indication that an attempt has been made to access a first register is received. This first register reflects an index variable that points to a configuration register. Next, an indication that an attempt has been made to access a second register is received. This second register reflects part of the contents of a configuration register to which the index variable points. Next, without waiting for another attempt to access the first register, the index variable is changed to point to another configuration register. Other embodiments are also described and claimed.

Accessing configuration registers by automatically changing an index

Machine-readable media, methods, and apparatus are described for processing coherent requests of a computing device comprising multiple cache nodes. In some embodiments, a coherent switch may receive from a requesting cache node a coherent request for a line of memory. The coherent switch may further issue snoop requests to one or more non-requesting cache nodes based upon whether a snoop filter bypass mode is enabled. In particular, the coherent switch when not in snoop filter bypass mode may obtain coherency data from a snoop filter and may issue snoop requests to zero or more non-requesting cache nodes based upon the coherency data obtained from the snoop filter. Further, the coherent switch when in snoop filter bypass mode may bypass the snoop filter and may issue snoop requests to all non-requesting cache agents.

Snoop filter bypass

An interrupt controller includes circuitry to process at least one end of interrupt (EOI) vector, the circuitry being capable of substantially simultaneously comparing the at least one EOI vector with a plurality of interrupts.

System for end of interrupt handling

An interrupt vector is issued by an interrupt controller in response to an interrupt request. A processor executes an interrupt service routine in response to receiving the interrupt vector. Upon the completion of the interrupt service routine, the processor issues an end of interrupt vector to the interrupt controller. The interrupt controller substantially simultaneously compares the end of interrupt vector with a plurality of stored interrupt vectors.

Growing community of inventors

Fullerton, CA, United States of America

Tuan M Quach